A Cytology Dataset for Early Detection of Oral Squamous Cell Carcinoma
Listen
Radio episode about this paper
Transcript
Introduction to the show: ident: Electrical Engineering. The day in electrical engineering: signals, systems and the hardware that carries them.
Rosa: I'm Rosa.
Dev: And I'm Dev, here with Taro.
Rosa: We're looking at the paper: "A Cytology Dataset for Early Detection of Oral Squamous Cell Carcinoma".
Dev: Here's the gist of the paper. Oral squamous cell carcinoma is a major global health burden where early detection dramatically improves outcomes <ref:2506.09661#pg2>.
Rosa: The authors introduce the first large and multi-center oral cytology dataset, comprising annotated slides stained with Papanicolaou(PAP) and May-Grünwald-Giemsa(MGG) protocols, collected from ten tertiary medical centers in India <ref:2506.09661#pg4>.
Dev: This resource aims to enhance automated detection, reduce diagnostic errors, and improve early OSCC diagnosis in resource-constrained settings <ref:2506.09661#pg5>.
Rosa: Oral squamous cell carcinoma is the most common head and neck malignancy and the sixth most common tumor worldwide.
Title and authors: Rosa: Let's talk about who wrote this: Garima Jain, Sanghamitra Pati, Mona Duggal, Amit Sethi, Abhijeet Patil, Gururaj Malekar, Nilesh Kowe, Jitender Kumar, Jatin Kashyap, Divyajeet Rout. They’re all from various institutions in India and they are the ones who put this whole dataset together.
Dev: It's a large collaboration because it spans multiple medical centers—ten of them specifically—which is important because it shows they aren't just looking at one small clinic's data. That multi-center aspect helps with how robust the resulting AI model will be later on.
Taro: The authors mentioned that they had to deal with privacy regulations when sharing data between those institutions, which is a huge hurdle in medical imaging research right now. It shows that getting access to diverse, high-quality data is a major logistical headache.
Rosa: Right. And what this paper really sets up is using this collection of annotated slides as the foundation to train some pretty powerful segmentation models for oral cytology. We're moving from just having data to actually building something functional with it.
Dev: It’s about establishing a standard for how we can use these cytological images for medical diagnosis, which is what they are doing by providing this organized resource. This moves the whole field forward because it gives researchers something concrete to build upon instead of just theorizing about what could work.
The paper's summary: Rosa: So, the summary of this paper boils down to them creating this first large and multi-center oral cytology dataset. They took slides stained with Papanicolaou and May-Grünwald-Giemsa protocols from over two hundred patients across ten institutions.
Dev: And they didn't just collect the images; they annotated them themselves using expert pathologists, then used a tool called QuPath24 to perform nucleus segmentation. This is the crucial part because it means we know exactly where the cancer cells are supposed to be in those slides.
Taro: That annotation process sounds intensive, and I wonder how consistent that labeling was across all those different pathologists at different centers; that inconsistency would be a big issue for any machine learning model trying to learn from it.
Rosa: They addressed that by having multiple experts label the data, which helps create a more reliable ground truth. But they also noted some challenges in building these datasets in general, like the difficulty of getting diverse data and the time it takes to annotate medical images.
Dev: And they pointed out that oral cytology has historically been neglected in data collection compared to other areas of medical imaging, so this effort is filling a real gap where we needed more variety and quantity.
The paper's improvements: Rosa: Now, the authors didn't just stop at collecting the data; they actually proposed some improvements for how these models can be trained to get better performance. They focused on using large, multi-source datasets to train high-capacity models that handle different staining protocols well.
Dev: That addresses the domain shift issue we talked about—making sure the AI isn't just good at one type of slide but can generalize across different stains like Pap and MGG. That’s a key improvement for real clinical deployment.
Taro: And they also mentioned that using dual resolution Whole Slide Images, which means having both high-resolution detail and broader tissue context, helps the AI capture both fine-grained features and the larger environment at once for better nucleus segmentation.
Rosa: That dual view is smart because it gives the model richer input, which should lead to much more accurate results when it comes to finding those malignant regions. They also discussed how they handled class imbalance in their training data, specifically noting that categories three and four had lower scores because of not enough examples for those types of cancer.
Dev: So they looked at balancing the data so the AI doesn't just ignore the rare but dangerous cases, which is a major concern when you’re building systems for high-risk medical screening.
Conclusion: Rosa: So to wrap up, this paper about "A Cytology Dataset for Early Detection of Oral Squamous Cell Carcinoma" presents a large, multi-center dataset built from over two hundred patients using both Pap and MGG stains across ten Indian institutions. It's designed to tackle the difficulty of early diagnosis by providing high-quality annotated images for training better AI models.
Dev: They showed that using this kind of large, multi-source data helps build models that generalize better across different staining methods and helps improve detection accuracy for those harder categories like malignancy three and four. It sets a much more concrete benchmark for how we should approach cytology in these settings.
Taro: From my side, the improvement with dual resolution images sounds promising because it lets the model see both the tiny details of a nucleus and where that nucleus sits in the larger tissue structure, which is crucial for accurate localization.
Rosa: That's right. For someone just listening to this, what this paper means is that we are finally getting a solid foundation—a massive, reliable set of data—to start building AI tools that can help doctors make faster and more accurate decisions about oral cancer in resource-constrained environments.
Indian Council of Medical Research-National Institute for Research in Digital Health & Data Science · Department of Electrical Engineering IIT Bombay · Koita Centre of Digital Health IIT Bombay · Indian Council of Medical Research-New Delhi · Division of Non Communicable Diseases, Indian Council of Medical Research-110029 · Department of Pathology, Regional Institute of Medical Sciences, Imphal · Department of Biochemistry, Pt BD Sharma PGIMS Rohtak · Institute of Pathology Madras Medical College Chennai · Department of Pathology SMS Medical College Jaipur · Department of Otorhinolaryngology SMS Medical College Jaipur · Department of Pathology Government Medical College and Hospital Chandigarh · Government Institute of Medical Sciences Greater Noida · Department of Pathology Chengalpattu Medical College Chengalpattu · Department of Pathology Coimbatore medical College Civil aerodrome post Coimbatore · Department of Pathology RIMS Ranchi Jharkhand · Gandhi Medical College Hyderabad Telangana
eess.IV, cs.CV, q-bio.TO
Submitted: 2025-06-11
Updated: 2026-11-06
Comments: We have performed detailed experiments and found few bugs in our script. This resulted in major differences in metrics mentioned in the manuscript and results we got through our recent runs. Metrics mentioned in this paper may mislead the reader, hence withdrawing
License: http://creativecommons.org/licenses/by/4.0/
Importance score: 72/100
The gist: Oral squamous cell carcinoma is a major global health burden where early detection dramatically improves outcomes <ref:2506.09661#pg2>.
Key concepts
- Oral Squamous Cell Carcinoma (OSCC)
- This is the most common type of cancer affecting the head and neck area. Early detection is crucial because almost half of cases are diagnosed at advanced stages, making it a major global health concern.
- Oral Cytology
- This involves examining cells collected from brush biopsies taken from the oral mucosa. It serves as a simpler, less invasive screening tool compared to traditional surgical biopsy and is useful for large-scale screening in high-risk groups.
- Whole Slide Images (WSIs)
- These are high-resolution digital scans of entire tissue slides. Using WSIs allows AI models to capture both fine details and the broader tissue context, which improves the accuracy of identifying specific cell structures like nuclei.
Terminology
Summary
Oral squamous cell carcinoma is a major global health burden where early detection dramatically improves outcomes <ref:2506. p. 0 com
ABSTRACT
Oral squamous cell carcinoma (OSCC) is a major global health burden, particularly in several regions across Asia, Africa,
and South America, where it accounts for a significant proportion of cancer cases. Early detection dramatically improves
outcomes, with stage I cancers achieving up to 90% survival. Development and validation of robust AI solutions requires access to large, labeled, and multi-source datasets to train
high-capacity models that generalize across domain shifts. We introduce the first large and multi-center oral cytology dataset,
comprising annotated slides stained with Papanicolaou(PAP) and May-Grünwald-Giemsa(MGG) protocols, collected from ten
tertiary medical centers in India. The dataset is labeled and annotated by expert pathologists for cellular anomaly classification
and detection, is designed to advance AI-driven diagnostic methods. By filling the gap in publicly available oral cytology
datasets, this resource aims to enhance automated detection, reduce diagnostic errors, and improve early OSCC diagnosis in
resource-constrained settings, ultimately contributing to reduced mortality and better patient outcomes worldwide.Where the paper says it
Where the paper says it
Where the paper says it
Background of the Problem
Oral squamous cell carcinoma is the most common head and neck malignancy and the sixth most common tumor worldwide. Overall mortality continues to be high because almost half of OSCC cases are diagnosed in advanced stages. p. 0 It is the most common head and neck
malignancy and the sixth most common tumor worldwide1
. Despite advances in therapies, overall mortality continues to be
high and has remained unchanged during the past decades because almost half of OSCC cases are diagnosed in advanced stages 2 On the contrary, survival rates of stage I cancer are up to 90%. Thus, early
diagnosis and referral are the cornerstone for reducing cancer-related mortality. 3, 4 Most often the delay is due to the time gap
(which is avoidable) between patient’s initial contact with a healthcare provider and obtaining a referral for specialist care and
treatment. 5 Histopathological analysis of tissue obtained through surgical biopsy is considered the gold standard for diagnosing
oral lesions. The absence of trained pathologists at the primary care level and the lack of essential resources for the processing
of the biopsy, such as paramedical staff and equipment (e. , automatic tissue processor), collectively hinder timely diagnosis,
particularly in low-income countries.Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Cytology as an Alternative
Cytology of brush biopsy is a simpler, safer, and less invasive alternative to histopathology of surgical biopsy. Tissue samples from the oral mucosa are collected for morphological evaluation using a firm brush on the mucosal surface with sufficient pressure to cause pinpoint bleeding. p. 1 5, 6
Cytology of brush biopsy is a simpler, safer, and less invasive alternative to histopathology of surgical biopsy, which can be
equally reliable for early detection of oral malignancies. 7
In brush biopsy, tissue samples from the oral mucosa are collected
for morphological evaluation using a firm brush on the mucosal surface with sufficient pressure to cause pinpoint bleeding
to ensure the collection of a full-thickness or transepithelial sample. Using exfoliative cytology can help reduce
the risk of false negative biopsies and eliminate the risk of postbiopsy complications9
. Oral cytology is recognized as a valuable
tool for large-scale screening in high-risk populations. Oral cytology is recognized as a valuable
tool for large-scale screening in high-risk populations. 10
While oral cytology demonstrates significant potential for identifying dysplastic and cancerous lesions, its clinical utility
has been hindered by inconsistent false-positive and false-negative rates.Where the paper says it
Where the paper says it
Where the paper says it
Dataset Construction Details
The dataset comprises over 200 patients, two stain types (Pap and MGG), multi-category benign controls and confirmed malignancies, and 10 institutions. The sample collection involved prospective multicentric cohort study conducted at 10 tertiary medical colleges in India between May 2023 and September 2024. p. 2 Dataset key statistics
Attribute Key statistics
Number of Patients 234
Number of WSIs 368
Stain types PAP – 184, MGG – 184
Age
Range – 18 to 70 years
Mean – 44 years
Median – 45 years
Gender Male – 194, Female – 40
Diagnosis Non Cancerous – 197 (306)
Cancerous – 42 (74)
Category
Category I – 162 (244)
Category II – 35 (62)
Category III – 24 (47)
Category IV – 18 (27)
Hospital centers
Maulana Azad Medical College, New Delhi – 59 (105)
Sawai Man Singh Medical College, Jaipur – 65 (99)
Rajendra Institute of Medical Sciences, Ranchi – 40 (75)
Regional Institute of Medical Sciences, Imphal – 19 (29)
Government Institute of Medical Sciences, Noida – 16 (20)
Tirunelveli Medical College, Tamil Nadu – 16(18)
Government Medical College and Hospital, Chandigarh – 8 (10)
Pandit Bhagwat Dayal Sharma Post Graduate Institute of Medical Sciences, Rohtak – 7 (8)
Coimbatore Medical College, Coimbatore – 3 (3)
Gandhi Medical College, Secunderabad – 1 (1)
Methods
We now describe sample collection, digitization, and annotation methods. Prospective multicentric cohort study was conducted
at 10 tertiary medical colleges and associated hospitals in India. Standard operating protocols were prepared and shared with all the respective centers to
maintain uniformity. Digitization
A total of 368 cytopathological slides were digitized using high-resolution 3DHISTECH whole slide scanners with a magnification of 40×, ensuring detailed visualization of cellular structures for downstream analysis. On an average, five such regions are annotated
per slide, providing a robust representation of the tissue sample. Following the identification of viable regions, each region
undergoes a detailed annotation process for nucleus segmentation, facilitated by QuPath24, an open-source software designed
for digital pathology.Where the paper says it
Where the paper says it
Where the paper says it
Model Performance Metrics
Model performance was evaluated using three key metrics: dice score, aggregated Jaccard index, and panoptic quality. Baseline models included UNet25, UNet++26, StarDist28, and HoverNet27 trained to perform nucleus segmentation. p. 4 This center-based splitting strategy ensures robust
evaluation by testing the models on data from centers unseen during training. The baseline models include UNet25, UNet++26
,
StarDist28, and HoverNet27, each of which was trained to perform nucleus segmentation on the dataset. Summary statistics of the dataset used, showing the number of whole slide images (WSIs), extracted patches, and
annotated nuclei across four categories (I–IV). I II III IV Total
# of WSIs 97 14 26 25 162
# of patches 523 92 140 112 867
# of nuclei 19888 6175 6022 7161 39246
Technical Validation
Baseline segmentation models were developed using the annotated dataset. The table reports overall segmentation
metrics as well as class-wise performance across four categories. Notably, categories 3 and 4 exhibit lower scores, likely due to
class imbalance and their under-representation in the training data compared to categories 1 and 2.Where the paper says it
Where the paper says it
Where the paper says it
Code Availability
Codes to train segmentation models using images and GeoJson annotations are available publicly on GitHub. The comprehensive organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the community. p. 3 To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community. Digitization and annotation process is shown in Figure 1 and
annotated dataset is summarized in Table 2. Data Records
The dataset, containing annotated whole slide image (WSIs), patches with nucleus annotations, is publicly available on various
platforms, such as Kaggle , and Google Drive. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. These patches are accompanied by detailed nucleus annotations provided
in QuPath-compatible GeoJSON format, enabling precise cell segmentation. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. To streamline processing and integration into
machine learning pipelines, sample code is available on GitHub to convert the GeoJSON nucleus annotations into binary
masks or instance segmentation masks, supporting both semantic segmentation and instance-level analysis. The comprehensive
organization and multi-platform availability of this dataset aim to facilitate collaborative research and reproducibility across the
community.Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Green — the paper says it, and the page is printed. Red — no passage carries it, so treat that sentence as unverified. The same check runs on your own text: check a summary against its source, $5.
Improvements for AI systems
-
Large multi-center dataset creation allows for training high-capacity models that generalize across domain shifts, as stated in
Development and validation of robust AI solutions requires access to large, labeled, and multi-source datasets to train high-capacity models that generalize across domain shifts.
This enables AI systems to perform accurate classification of cellular anomalies across different staining protocols like Papanicolaou and May-Grünwald-Giemsa. -
Integration of dual resolution Whole Slide Images (WSIs) allows for capturing both
fine-grained and broader tissue contexts, enhancing the robustness of morphological studies
during digitization. This helps AI systems perform more accurate nucleus segmentation by providing both high-resolution detail and wider tissue context for better feature extraction. -
Automated annotation using QuPath24 facilitates a rigorous process where
each nucleus within the segmented regions is assigned a label ranging from one to four, based on established cytological criteria.
This allows AI systems to learn nuanced classification boundaries, improving the distinction between benign categories (Category I) and malignant categories (Category III and IV). -
Training models on data with class imbalance addresses the issue where
categories 3 and 4 exhibit lower scores, likely due to class imbalance and their under-representation in the training data compared to categories 1 and 2.
Improved AI systems can be specifically tuned or utilize techniques like synthetic data generation to enhance detection accuracy for rare, high-risk malignant categories. -
Using a center-based splitting strategy ensures that
the models are tested on data from centers unseen during training,
leading to more robust evaluation. This methodology prevents overfitting and provides reliable performance metrics for the AI systems when deployed in new clinical settings.
Abstract
Oral squamous cell carcinoma OSCC is a major global health burden, particularly in several regions across Asia, Africa, and South America, where it accounts for a significant proportion of cancer cases. Early detection dramatically improves outcomes, with stage I cancers achieving up to 90 percent survival. However, traditional diagnosis based on histopathology has limited accessibility in low-resource settings because it is invasive, resource-intensive, and reliant on expert pathologists. On the other hand, oral cytology of brush biopsy offers a minimally invasive and lower cost alternative, provided that the remaining challenges, inter observer variability and unavailability of expert pathologists can be addressed using artificial intelligence. Development and validation of robust AI solutions requires access to large, labeled, and multi-source datasets to train high capacity models that generalize across domain shifts. We introduce the first large and multicenter oral cytology dataset, comprising annotated slides stained with Papanicolaou(PAP) and May-Grunwald-Giemsa(MGG) protocols, collected from ten tertiary medical centers in India. The dataset is labeled and annotated by expert pathologists for cellular anomaly classification and detection, is designed to advance AI driven diagnostic methods. By filling the gap in publicly available oral cytology datasets, this resource aims to enhance automated detection, reduce diagnostic errors, and improve early OSCC diagnosis in resource-constrained settings, ultimately contributing to reduced mortality and better patient outcomes worldwide.
Related papers
- HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging
- Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction
- FDIR: Fidelity-Anchored Decompressed Image Restoration for Human and Machine Perception
- A Disease-Centric Vision-Language Foundation Model for Precision Oncology in Kidney Cancer
- CADS: A Comprehensive Anatomical Dataset and Segmentation for Whole-Body Anatomy in Computed Tomography
- Task-Aware Bitrate Thresholds for Codec-Robust Ultrasound Segmentation