Differential Diagnosis of Frontotemporal Dementia and Alzheimer's Disease using Generative Adversarial Network
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: "Differential Diagnosis of Frontotemporal Dementia and Alzheimer's Disease using Generative Adversarial Network".
Dev: Here's the gist of the paper. Differential Diagnosis of Frontotemporal Dementia and Alzheimer’s Disease using Generative Adversarial Network is a study proposing a novel framework combining multiscale structural features from MRI scans with Generative Adversarial Networks to distinguish between Frontotemporal Dementia (FTD), Alzheimer’s disease (AD), and normal controls, which is crucial for determining disease-specific interventions <ref:2109.05627#pg2> The proposed framework achieved 87.80% accuracy through 10 fold cross validation experiment <ref:2109.05627#pg4> Frontotemporal dementia (FTD) and Alzheimer’s disease (AD) share similar clinical symptoms, leading to common misdiagnoses between the two forms <ref:2109.05627#pg2> The specificity in the distinguishing of AD from FTD is still low even with significant expertise from clinicians <ref:2109.05627#pg2> Volumetric structural change measured by T1-weighted MRI is an effective biomarker for differential diagnosis <ref:2109.05627#pg3> Most previous dementia classification studies focused on binary classification, such as normal control (NC) vs.
Rosa: FTD or NC vs.
Dev: AD <ref:2109.05627#pg3> To the best of our knowledge, no deep learning based approach has been applied to the differential diagnosis of AD and FTD <ref:2109.05627#pg4> Data Preparation and Feature Extraction A total of 1954 Structural MRI were used for the preparation of this article <ref:2109.05627#pg4> Only images from subject with stable diagnosis during the longitudinal follow up were included to eliminate potential uncertainty <ref:2109.05627#pg4> Image preprocessing involved several steps to reduce the dimension of input data by extracting preliminary features <ref:2109.05627#pg4> 1) We first segmented the gray matter of each T1 structural MRI image into 87 anatomical structures (FreeSurfer 5.3
4: ) <ref:2109.05627#pg4> 2) Each structures were regarded as a regions of interest (ROI) and were further parcellated into smaller subregions, which we termed as "patches" <ref:2109.05627#pg4> 3) Volume size and cortical thickness for each patch was extracted as features for downstream classification <ref:2109.05627#pg4> The features were extracted at three different scales, i.e., 500, 1000 and 2000 voxels per patch because the discriminate information among each class could exist in different scale of images The resulted subparcellation of the structural ROIs resulted a total of 1488, 705 and 343 patches across the entire brain, respectively <ref:2109.05627#pg4> Model Architecture and Training A Generative Adversarial Network (GAN) was trained with the patch-wise features extracted at multiscales from MRI to augment data samples <ref:2109.05627#pg5> The GAN consisted of a generator (G) and a discriminator (D), where G aimed to find a mapping from random variables to the distribution of the actual data, while D aimed to distinguish the candidates synthesized by the generator, denoted here as "fake", from the samples belong to true classes <ref:2109.05627#pg5> A Multiscale Deep Neural Network (MDNN) was applied as the discriminator to learn latent pattern from the feature space and perform multi-class classification <ref:2109.05627#pg5> The MDNN consisted of a cascade of four four-layer Multilayer Perceptrons (MLPs) <ref:2109.05627#pg5> Experimental Validation and Results Ten fold cross validation was performed on the 1954 T1 MRI images to validate the discriminant ability of the proposed framework <ref:2109.05627#pg4> Five deep learning based experiments were performed, including MLP with single scale feature extracted at 500, 1000, and 2000 voxels per patch, MDNN with multiscale features, and GAN with multiscale features The overall classification accuracy of the GAN approach was 87.80% The network performances well for the task of distinguishing between AD and FTD, while the discrimination between NC and FTD showed least accurate performance The cross validation experiments proved that the MDNN could learn the latent representation among features extracted at different structural scales from MRI scans <ref:2109.05627#pg5> Further improvement on discriminant ability can be achieved by leveraging the GAN for data augmentation <ref:2109.05627#pg5> The combination of multiscale structural features and synthetic data augmentation based on generative adversarial network can improve the performance of challenging tasks such as differentiating Dementia sub-types <ref:2109.05627#pg2> The final classification result of testing set were obtained through majority voting of the 10 networks References Alladi, S., Xuereb, J., Bak, T., Nestor, P., Knibb, J., Patterson, K., Hodges, J.: Focal cortical presentations of Alzheimer’s disease <ref:2109.05627#pg2> Arjovsky, M., Bottou, L.: Towards principled methods for training generative adversarial networks <ref:2109.05627#pg5> Beg, M.F., Miller, M.I., Trouvé, A., Younes, L.: Computing large deformation metric mappings via geodesic flows of diffeomorphisms <ref:2109.05627#pg5> Dale AM, Fischl B, S.M.: Cortical surface-based analysis <ref:2109.05627#pg5> Davatzikos, C., Resnick, S.M., Wu, X., Parmpi, P., Clark, C.M.: Individual patient diagnosis of AD and FTD via high-dimensional pattern classification of MRI <ref:2109.05627#pg5> Du, A.T., Schuff, N., Kramer, J.H., Rosen, H.J., Gorno-Tempini, M.L., Rankin, K., Miller, B.L., Weiner, M.W.: Different regional patterns of cortical thinning in Alzheimer’s disease and frontotemporal dementia <ref:2109.05627#pg5> Neary, D., Snowden, J., Mann, D.: Frontotemporal dementia <ref:2109.05627#pg2> Neary, D., Snowden, J.S., Gustafson, L., Passant, U., Stuss, D., Black, S., Freedman, M., Kertesz, A., Robert, P., Albert, M.: Frontotemporal lobar degeneration A consensus on clinical diagnostic criteria <ref:2109.05627#pg2> Pasquier, F.: Telling the difference between frontotemporal dementia and Alzheimer’s disease <ref:2109.05627#pg2> Raamana, P.R., Rosen, H., Miller, B., Weiner, M.W., Wang, L., Beg, M.F.: Threeclass differential diagnosis among Alzheimer disease, frontotemporal dementia, and controls <ref:2109.05627#pg2> Raamana, P.R., Weiner, M.W., Wang, L., Beg, M.F., Initiative, A.D.N., et al.: Thickness network features for prognostic applications in dementia <ref:2109.05627#pg5> Rabinovici, G., Seeley, W., Kim, E., Gorno-Tempini, M., Rascovsky, K., Pagliaro, T., Allison, S., Halabi, C., Kramer, J., Johnson, J.: Distinct MRI atrophy patterns in autopsy-proven Alzheimer’s disease and frontotemporal lobar degeneration <ref:2109.05627#pg5> Lu, D., Popuri, K., Ding, G.W., Balachandar, R., Beg, M.F.: Multiscale deep neural network based analysis of FDG-PET images for the early diagnosis of Alzheimer’s disease <ref:2109.05627#pg5> Ma, D., Popuri, K., Bhalla, M., Sangha, O., Lu, D., Cao, J., Jacova, C., Wang, L., Beg, M.F.: Quantitative assessment of field strength <ref:2109.05627#pg5> Neary, D., Snowden, J.S.: Evaluation of the NINCDS-ADRDA criteria in the differentiation of Alzheimer’s disease and frontotemporal dementia <ref:2109.05627#pg2> Page 1 --- Differential Diagnosis of Frontotemporal Dementia and Alzheimer’s Disease using Generative Adversarial Network Da Ma, Donghuan Lu, Karteek Popuri, and Mirza Faisal Beg Simon Fraser University, School of Engineering Science, Burnaby, V5A 1S6, Canada Tencent, Jarvis Lab <ref:2109.05627#pg2> Abstract.
Rosa: Frontotemporal dementia and Alzheimer’s disease are two common forms of dementia and are easily misdiagnosed as each other due to their similar pattern of clinical symptoms <ref:2109.05627#pg2> Differentiating between the two dementia types is crucial for determining disease-specific intervention and treatment <ref:2109.05627#pg2> Recent development of Deep-learning-based approaches in the field of medical image computing are delivering some of the best performance for many binary classification tasks, although its application in differential diagnosis, such as neuroimage-based differentiation for multiple types of dementia, has not been explored <ref:2109.05627#pg2> In this study, a novel framework was proposed by using the Generative Adversarial Network technique to distinguish FTD, AD and normal control subjects, using volumetric features extracted at coarse-to-fine structural scales from Magnetic Resonance Imaging scans <ref:2109.05627#pg2> Experiments of 10-folds cross validation on 1,954 images achieved high accuracy <ref:2109.05627#pg4> With the proposed framework, we have demonstrated that the combination of multiscale structural features and synthetic data augmentation based on generative adversarial network can improve the performance of challenging tasks such as differentiating Dementia sub-types <ref:2109.05627#pg2> Keywords: Differential Diagnosis, Magnetic Resonance Imaging, Generative Adversarial Network <ref:2109.05627#pg2> Page 3 --- Structural magnetic Resonance Imaging (MRI) is commonly used to detect pathological atrophic changes in the brain for diagnosis of neurodegenerative diseases such as AD and FTD <ref:2109.05627#pg4> The atrophy patterns of these two types of dementia differs in terms of affected regions and rate of change, and the volumetric structural change measured by T1-weighted MRI is an effective biomarker for differential diagnosis
5: <ref:2109.05627#pg4> Example of volumetric-based features includes gray matter (GM) volume loss
16: , cortical thinning
6: , High-dimensional features based on GM and white matter (WM) volumes distribution of whole brain
5: , as well as atrophy and shape deformity of individual structures
8: <ref:2109.05627#pg4> Most previous dementia classification studies focused on binary classification, e.g., normal control (NC) vs.
Title and authors: Rosa: So what exactly is the main goal here, beyond just trying to separate the diagnoses? What’s the actual mechanism they’re proposing?
Dev: They are using a novel framework that combines multiscale structural information from MRI scans with a Generative Adversarial Network to distinguish FTD, AD, and normal control subjects.
Rosa: It sounds complicated because of those "multiscale structural features" they mention. Can you explain that simply for someone who isn't an image processing expert?
Dev: They take the T1-weighted MRI images and first segment them into eighty-seven anatomical structures, then they further break those structures down into smaller patches. They extract features like volume size and cortical thickness for each patch at three different sizes: five hundred, one thousand and two thousand voxels per patch.
Rosa: So they’re looking at the brain from a big view down to really fine details in those patches?
Dev: Precisely. They say that discriminating information among each class could exist at different scales of images, so they are testing features across these different levels. They end up with a total of one thousand four hundred eighty-eight seven hundred five, and three hundred forty-three patches across the whole brain depending on the scale used.
Taro: From my side, I’m wondering about how much noise those smaller patch sizes introduce when you're trying to find a pattern in real tissue atrophy.
Rosa: That’s a good point Taro. But they argue that this multiscale approach is necessary because the distinguishing information might be hidden at different structural levels in the scans.
The paper's summary: Dev: So, what do we actually get from putting all those features—the multiscale patches—into a model? What’s the overall finding they report on this study?
Rosa: The main result they report is that when they use this proposed framework, combining the multiscale structural features and synthetic data augmentation based on the Generative Adversarial Network, they achieved an accuracy of eighty-seven point eight zero percent through ten fold cross validation.
Dev: That eighty-seven point eight zero percent is a solid number for a multi-class classification task involving these complex brain diseases. It shows that this combination of methods works quite well for the task of differentiating between AD and FTD.
Rosa: The paper specifically points out that while the GAN helps improve performance, there’s a specific nuance in how it performs the discrimination between normal controls and Frontotemporal Dementia subjects; that distinction showed less accurate performance.
Dev: That tells us something important about where the current framework is strongest and weakest, even with all those advanced techniques applied. They also note that the Multiscale Deep Neural Network was successful in learning a latent pattern from the feature space using those features extracted at different scales.
Taro: It seems like they’ve built a robust system for general differentiation, but maybe the subtlety between the most similar group, AD and FTD, is still a challenge for this specific setup.
The paper's improvements: Rosa: So we’re talking about what makes this framework better than just using a single scale of features or just a standard deep learning model? What are the key improvements they suggest?
Dev: The paper suggests two main things that help push the performance up. First, using the multiscale features helps keep as much information as possible during feature dimension reduction, which lets them capture discriminating information across different structural levels in the scans.
Rosa: And second, they use the Generative Adversarial Network for data augmentation. They train a generator and a discriminator to synthesize new MRI samples based on the patch-wise features extracted at multiscale.
Dev: That augmentation is meant to address the limited number of available MRI scans in this study, which is a real constraint when you’re training deep learning models for rare conditions. They found that this combination of multiscale structural features and synthetic data augmentation can improve performance on challenging tasks like differentiating dementia subtypes by about twenty percent.
Taro: So, the augmentation isn't just padding the dataset; it's actually helping the discriminator learn a better representation of what true data looks like across those various scales. That sounds more useful than just adding random noise.
Rosa: It really does sound like they’re trying to make the model more resilient to variations in how these diseases manifest structurally, which is important when you’re moving from a lab setting to real-world trials.
Conclusion: Dev: So, wrapping this up, what’s the big picture for clinicians or researchers looking at this paper on "Differential Diagnosis of Frontotemporal Dementia and Alzheimer's Disease using Generative Adversarial Network"?
Rosa: Basically, they show that combining multiscale structural features with synthetic data augmentation via a GAN can improve the performance of challenging tasks like differentiating dementia subtypes. It suggests this integrated approach is useful for moving beyond the binary classification studies that have dominated the field so far.
Dev: They proved that this combination helps learn latent representations across different structural scales from MRI scans, and they used an ensemble classification framework by training ten networks with independently separated splits to get a final result through majority voting.
Taro: I just want to say that while eighty-seven point eight zero percent is good, the paper also flags a limitation: the discrimination between normal controls and Frontotemporal Dementia showed least accurate performance. That means we still need better tools for those specific comparisons.
Rosa: True, so this framework is strong for AD versus FTD, but they admit it’s not perfect when trying to pin down the normal control group specifically. It opens the door for future work focusing on improving that specific separation.
Dev: Exactly. So we’ve seen how they used multiscale features and GAN augmentation to boost accuracy, and while it’s a solid result for dementia sub-type differentiation, the next step is definitely refining those comparisons where it falls short.
Simon Fraser University · Tencent
eess.IV, cs.CV, cs.LG, q-bio.NC
Submitted: 2021-09-12
Updated: 2021-09-29
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
Importance score: 95/100
The gist: Differential Diagnosis of Frontotemporal Dementia and Alzheimer’s Disease using Generative Adversarial Network is a study proposing a novel framework combining multiscale structural features from…
Key concepts
- Multiscale Structural Features
- The researchers analyzed brain MRI scans by dividing them into patches of different sizes (500, 1000, and 2000 voxels). Extracting features at these different scales helps capture distinguishing information that might be present in both very small and very large structural changes within the brain tissue.
- Generative Adversarial Network (GAN)
- A GAN consists of two parts: a generator that creates synthetic data and a discriminator that tries to tell real data from fake data. In this study, the generator was trained on MRI patches to create realistic samples for AD, FTD, and normal controls. This synthetic data helps improve the model's performance when the original MRI dataset is limited.
- Multiscale Deep Neural Network (MDNN)
- The MDNN acts as a sophisticated discriminator in the GAN setup. It is designed to learn complex latent patterns from the features extracted at various structural scales. By using this network, the system can better understand and classify brain structures based on these multi-scale representations, leading to more accurate multi-class differentiation.
- Ensemble Classification Framework
- To ensure robust results and prevent overfitting with limited data, the study trained ten separate classification networks. The final diagnosis is determined by taking the majority vote among these ten models. This ensemble approach provides a more stable and reliable classification performance for distinguishing between AD, FTD, and normal controls.
Terminology
Summary
Differential Diagnosis of Frontotemporal Dementia and Alzheimer’s Disease using Generative Adversarial Network is a study proposing a novel framework combining multiscale structural features from MRI scans with Generative Adversarial Networks to distinguish between Frontotemporal Dementia (FTD), Alzheimer’s disease (AD), and normal controls, which is crucial for determining disease-specific interventions <ref:2109. p. 0 Recent development of Deep-learning-based
approaches in the field of medical image computing are delivering some
of the best performance for many binary classification tasks, although
its application in differential diagnosis, such as neuroimage-based differentiation for multiple types of dementia, has not been explored. In this
study, a novel framework was proposed by using the Generative Adversarial Network technique to distinguish FTD, AD and normal control
subjects, using volumetric features extracted at coarse-to-fine structural
scales from Magnetic Resonance Imaging scans. In this
study, a novel framework was proposed by using the Generative Adversarial Network technique to distinguish FTD, AD and normal control
subjects, using volumetric features extracted at coarse-to-fine structural
scales from Magnetic Resonance Imaging scans. Experiments of 10-folds
cross-validation on 1,954 images achieved high accuracy. The proposed framework achieved 87. 80% accuracy through 10
fold cross validation experiment.Where the paper says it
Where the paper says it
Where the paper says it
Background and Motivation
Frontotemporal dementia (FTD) and Alzheimer’s disease (AD) share similar clinical symptoms, leading to common misdiagnoses between the two forms <ref:2109.05627#pg2> The specificity in the distinguishing of AD from FTD is still low even with significant expertise from clinicians <ref:2109. p. 0 Keywords: Differential Diagnosis, Magnetic Resonance Imaging, Generative Adversarial Network
1 Introduction
Frontotemporal dementia (FTD) and Alzheimer’s disease (AD) are two common forms of dementia sharing similar clinical symptoms, such as brain atrophy,
progressive alterations in language ability, behavior and personality, and brain
atrophy [11], leading to the common misdiagnoses as each other [1]. Although
sophisticated clinical guidelines have been established for their corresponding
diagnosis, such as the the NINCDS-ADRDA criteria [12], while the specificity
in the distinguishing of AD from FTD is still low even with significant expertise from clinicians (23% as reported from [19]). 2 Da Ma, Donghuan Lu, Karteek Popuri, Mirza Faisal Beg
Structural magnetic Resonance Imaging (MRI) is commonly used to detect
pathological atrophic changes in the brain for diagnosis of neurodegenerative
diseases such as AD and FTD. The atrophy patterns of these two types of dementia differs in terms of affected regions and rate of change, and the volumetric
structural change measured by T1-weighted MRI is an effective biomarker for
differential diagnosis [5]. Most previous dementia classification studies focused on binary classification,
e. , normal control (NC) vs. p. 0 Recent development of Deep-learning-based
approaches in the field of medical image computing are delivering some
of the best performance for many binary classification tasks, although
its application in differential diagnosis, such as neuroimage-based differentiation for multiple types of dementia, has not been explored. In this
study, a novel framework was proposed by using the Generative Adversarial Network technique to distinguish FTD, AD and normal control
subjects, using volumetric features extracted at coarse-to-fine structural
scales from Magnetic Resonance Imaging scans. Recent development of Deep-learning-based
approaches in the field of medical image computing are delivering some
of the best performance for many binary classification tasks, although
its application in differential diagnosis, such as neuroimage-based differentiation for multiple types of dementia, has not been explored. In this
study, a novel framework was proposed by using the Generative Adversarial Network technique to distinguish FTD, AD and normal control
subjects, using volumetric features extracted at coarse-to-fine structural
scales from Magnetic Resonance Imaging scans. It is therefore essential to develop a computer-aided diagnosis system with improved accuracy for
differential diagnosis. arXiv:2109. It is therefore essential to develop a computer-aided diagnosis system with improved accuracy for
differential diagnosis. arXiv:2109. has built a random undersampling boosting classifier for a five-class differential
diagnostics of neurodegenerative diseases using csf, age, volume and grading
features of whole brain as features [18]. To the best of our knowledge, no deep
learning based approach has been applied to the differential diagnosis of AD and
FTD.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
Data Preparation and Feature Extraction
A total of 1954 Structural MRI were used for the preparation of this article <ref:2109.05627#pg4> Only images from subject with stable diagnosis during the longitudinal follow up were included to eliminate potential uncertainty <ref:2109. p. 2 A total of 1954 Structural MRI were used. To eliminate potential uncertanly
coming from the clinical diagnosis, only images from subject with stable diagnosis during the the longitudinal follow up were included. The data included in this study contains a relatively large number of labeled data compared to most of other neuroimaging studies, although
is still relatively small in the context of deep learning study in general. To reduce the size of network and improve the classification performance, following
preprocessing steps were applied to reduce the dimension of input data by extracting preliminary features: 1) We first segmented the gray matter of each
T1 structural MRI image into 87 anatomical structures (FreeSurfer 5.Where the paper says it
Where the paper says it
-
We first segmented the gray matter of each T1 structural MRI image into 87 anatomical structures (FreeSurfer 5.3 [4]) <ref:2109. p. 0
05627#pg4>Where the paper says it
It is therefore essential to develop a computer-aided diagnosis system with improved accuracy for differential diagnosis. arXiv:2109.
-
Each structures were regarded as a regions of interest (ROI) and were further parcellated into smaller subregions, which we termed as
patches
<ref:2109.05627#pg4> -
Volume size and cortical thickness for each patch was extracted as features for downstream classification <ref:2109.05627#pg4>
The features were extracted at three different scales, i.e., 500, 1000 and 2000 voxels per patch because the discriminate information among each class could exist in different scale of images The resulted subparcellation of the structural ROIs resulted a total of 1488, 705 and 343 patches across the entire brain, respectively <ref:2109. p. 3 The number of voxels in each
patch was predefined to balance between preserving the information embedded
in the raw data and preventing overfitting due to oversized feature dimension
comparing to the relatively small number of data samples. The resulted subparcellation of the structural ROIs resulted a total of 1488, 705 and 343 patches
across the entire brain, respectively.Where the paper says it
Model Architecture and Training
A Generative Adversarial Network (GAN) was trained with the patch-wise features extracted at multiscales from MRI to augment data samples <ref:2109.05627#pg5> The GAN consisted of a generator (G) and a discriminator (D), where G aimed to find a mapping from random variables to the distribution of the actual data, while D aimed to distinguish the candidates synthesized by the generator, denoted here as The activation function for the first layer was rectified linear
unit (ReLU) while the one of the second layer was tanh function to squash the
synthesized data into (-1,1) to ensure the symetry of the output distribution [17]. A Multiscale Deep Neural Network (MDNN) [9] With the feature extracted
at different scales was applied as the discriminator to learn the latent pattern
from the feature space and perform the multi-class classification. The schematic
diagram of the network were shown in Figure 2. the MDNN consisted of a cascade
of four four-layer Multilayer Perceptrons (MLPs). The schematic
diagram of the network were shown in Figure 2. the MDNN consisted of a cascade
of four four-layer Multilayer Perceptrons (MLPs).fake
, from the samples belong to true classes <ref:2109.05627#pg5> A Multiscale Deep Neural Network (MDNN) was applied as the discriminator to learn latent pattern from the feature space and perform multi-class classification <ref:2109. p. 4Where the paper says it
Where the paper says it
Where the paper says it
Experimental Validation and Results
Ten fold cross validation was performed on the 1954 T1 MRI images to validate the discriminant ability of the proposed framework <ref:2109.05627#pg4> Five deep learning based experiments were performed, including MLP with single scale feature extracted at 500, 1000, and 2000 voxels per patch, MDNN with multiscale features, and GAN with multiscale features The overall classification accuracy of the GAN approach was 87. p. 5 Because multiple images
could be acquired from the same subject at different time points, the partition
of the cross validation was performed on the subject-level instead of images to
avoid using images from the same subject in both training and testing. Five deep
learning based experiments, including MLP with single scale feature extracted at
500, 1000, 2000 voxels per patch, MDNN with multiscale features and GAN with
multiscale features, were performed on those data.Where the paper says it
Conclusion
The cross validation experiments proved that the MDNN could learn the latent representation among features extracted at different structural scales from MRI scans <ref:2109.05627#pg5> Further improvement on discriminant ability can be achieved by leveraging the GAN for data augmentation <ref:2109. p. 7 NC AD FTD
NC 992 48 23
AD 63 391 3
FTD 92 10 332
vantage of high level multi-scale feature representation learning through MDNN
and the data augmentation technique using GAN. Cross validation experiments
proved that, the MDNN could learn the latent representation among features
extracted at different structural scales from MRI scans, and further improvement on discriminant ability can be achieved by leveraging the GAN for data
augmentation. Experiments of 10-folds
cross-validation on 1,954 images achieved high accuracy. With the proposed framework, we have demonstrated that the combination of multiscale structural features and synthetic data augmentation based on generative adversarial network can improve the performance of challenging
tasks such as differentiating Dementia sub-types.Where the paper says it
Where the paper says it
References
Alladi, S., Xuereb, J. p. 7 References
1. , Xuereb, J. , Xuereb, J. , Nestor, P. , Nestor, P. , Knibb, J. , Knibb, J. , Patterson, K. , Patterson, K. , Hodges, J. , Hodges, J. : Focal cortical presentations of Alzheimer’s disease. Brain 130(10), 2636–2645 (2007)
2. Arjovsky, M. Arjovsky, M. , Bottou, L. , Bottou, L. : Towards principled methods for training generative adversarial networks (2017)
3. Differential Diagnosis of Frontotemporal
Dementia and Alzheimer’s Disease using
Generative Adversarial Network
Da Ma
1*, Donghuan Lu
2
,
1*, Karteek Popuri
1
, and Mirza Faisal Beg
1**
1 Simon Fraser University, School of Engineering Science, Burnaby, V5A 1S6, Canada 1 Tencent, Jarvis Lab, Shenzhen, 518057, China
Abstract. Frontotemporal dementia and Alzheimer’s disease are two
common forms of dementia and are easily misdiagnosed as each other
due to their similar pattern of clinical symptoms. : Towards principled methods for training generative adversarial networks (2017)
3. , Miller, M. , Miller, M. , Trouvé, A. , Trouvé, A. , Younes, L. , Younes, L. : Computing large deformation
metric mappings via geodesic flows of diffeomorphisms. International journal of
computer vision 61(2), 139–157 (2005)
4. Dale AM, Fischl B, S. Dale AM, Fischl B, S. : Cortical surface-based analysis. Neuroimage 9(2), 195–207 (1999)
5. Davatzikos, C. Davatzikos, C. , Resnick, S. , Resnick, S. , Parmpi, P. , Parmpi, P. , Clark, C. , Clark, C. : Individual patient diagnosis of AD and FTD via high-dimensional pattern classification of MRI. Neuroimage 41(4), 1220–1227 (2008)
6. , Schuff, N. , Schuff, N. , Kramer, J. , Schuff, N. , Kramer, J. , Kramer, J. , Rosen, H. , Kramer, J. , Rosen, H. , Rosen, H. , Gorno-Tempini, M. , Rosen, H. , Gorno-Tempini, M. , Gorno-Tempini, M. , Rankin,
K. : Towards principled methods for training generative adversarial networks (2017)
3. , Miller, M. : Towards principled methods for training generative adversarial networks (2017)
3. , Miller, M. , Miller, B. , Weiner, M. , Miller, B. , Weiner, M. , Miller, B. , Weiner, M. , Weiner, M. : Different regional patterns of cortical thinning in
Alzheimer’s disease and frontotemporal dementia. , Talbot, P. , Neary, D. , Talbot, P. , Neary, D. Human brain mapping (2018)
11. , Snowden, J. Human brain mapping (2018)
11. , Snowden, J. Human brain mapping (2018)
11. , Snowden, J. Differential Diagnosis of Frontotemporal
Dementia and Alzheimer’s Disease using
Generative Adversarial Network
Da Ma
1*, Donghuan Lu
2
,
1*, Karteek Popuri
1
, and Mirza Faisal Beg
1**
1 Simon Fraser University, School of Engineering Science, Burnaby, V5A 1S6, Canada 1 Tencent, Jarvis Lab, Shenzhen, 518057, China
Abstract. Frontotemporal dementia and Alzheimer’s disease are two
common forms of dementia and are easily misdiagnosed as each other
due to their similar pattern of clinical symptoms. , Talbot, P. , Neary, D. , Snowden, J. , Gustafson, L. , Gustafson, L. , Passant, U. , Passant, U. , Stuss, D. , Stuss, D. , Black, S. , Black, S. , Freedman, M. , Freedman, M. , Kertesz, A. , Kertesz, A. , Robert, P. , Robert, P. , Albert, M. , Albert, M. : Frontotemporal lobar degeneration A consensus on clinical diagnostic criteria. Neurology 51(6), 1546–1554
(1998)
13. Pasquier, F. Pasquier, F. : Telling the difference between frontotemporal dementia and
Alzheimer’s disease. Current opinion in psychiatry 18(6), 628–632 (2005)
14. Raamana, P. Current opinion in psychiatry 18(6), 628–632 (2005)
14. Raamana, P. , Weiner, M. : Threeclass differential diagnosis among Alzheimer disease, frontotemporal dementia, and
controls. Materials
Data used in the preparation of this article were obtained from two publicly available databases, i. , the Alzheimer’s Disease Neuroimaging Initiative (ADNI)
database and the frontotemporal lobar degeneration neuroimaging initiative
(NIFD) database. , Initiative, A. :
Thickness network features for prognostic applications in dementia. Neurobiology
of aging 36, S91–S102 (2015)
16. Rabinovici, G. Rabinovici, G. , Seeley, W. , Gorno-Tempini, M. , Rascovsky, K. , Rascovsky, K. , Pagliaro,
T. , Pagliaro,
T. , Allison, S. , Allison, S. , Halabi, C. , Kramer, J. , Johnson, J. , Johnson, J. : Distinct MRI atrophy
patterns in autopsy-proven Alzheimer’s disease and frontotemporal lobar degeneration. Differential Diagnosis of Frontotemporal
Dementia and Alzheimer’s Disease using
Generative Adversarial Network
Da Ma
1*, Donghuan Lu
2
,
1*, Karteek Popuri
1
, and Mirza Faisal Beg
1**
1 Simon Fraser University, School of Engineering Science, Burnaby, V5A 1S6, Canada 1 Tencent, Jarvis Lab, Shenzhen, 518057, China
Abstract. Frontotemporal dementia and Alzheimer’s disease are two
common forms of dementia and are easily misdiagnosed as each other
due to their similar pattern of clinical symptoms. Differential Diagnosis of Frontotemporal
Dementia and Alzheimer’s Disease using
Generative Adversarial Network
Da Ma
1*, Donghuan Lu
2
,
1*, Karteek Popuri
1
, and Mirza Faisal Beg
1**
1 Simon Fraser University, School of Engineering Science, Burnaby, V5A 1S6, Canada 1 Tencent, Jarvis Lab, Shenzhen, 518057, China
Abstract. Frontotemporal dementia and Alzheimer’s disease are two
common forms of dementia and are easily misdiagnosed as each other
due to their similar pattern of clinical symptoms. , Popuri, K. , Balachandar, R. , Balachandar, R. : Multiscale deep neural
network based analysis of FDG-PET images for the early diagnosis of Alzheimer’s
disease. , Popuri, K. , Bhalla, M. , Bhalla, M. , Sangha, O. , Sangha, O. , Jacova, C. , Initiative, A. : Quantitative assessment of field strength, total
intracranial volume, sex, and age effects on the goodness of harmonization for
volumetric analysis on the adni database. , Neary, D. : Evaluation
of the NINCDS-ADRDA criteria in the differentiation of Alzheimer’s disease and
frontotemporal dementia.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
--- Page 1 ---
Differential Diagnosis of Frontotemporal Dementia and Alzheimer’s Disease using Generative Adversarial Network
Da Ma, Donghuan Lu, Karteek Popuri, and Mirza Faisal Beg Simon Fraser University, School of Engineering Science, Burnaby, V5A 1S6, Canada Tencent, Jarvis Lab <ref:2109.05627#pg2>
Abstract. Frontotemporal dementia and Alzheimer’s disease are two common forms of dementia and are easily misdiagnosed as each other due to their similar pattern of clinical symptoms <ref:2109. p. 0 Differential Diagnosis of Frontotemporal
Dementia and Alzheimer’s Disease using
Generative Adversarial Network
Da Ma
1*, Donghuan Lu
2
,
1*, Karteek Popuri
1
, and Mirza Faisal Beg
1**
1 Simon Fraser University, School of Engineering Science, Burnaby, V5A 1S6, Canada 1 Tencent, Jarvis Lab, Shenzhen, 518057, China
Abstract. Frontotemporal dementia and Alzheimer’s disease are two
common forms of dementia and are easily misdiagnosed as each other
due to their similar pattern of clinical symptoms. Differential Diagnosis of Frontotemporal
Dementia and Alzheimer’s Disease using
Generative Adversarial Network
Da Ma
1*, Donghuan Lu
2
,
1*, Karteek Popuri
1
, and Mirza Faisal Beg
1**
1 Simon Fraser University, School of Engineering Science, Burnaby, V5A 1S6, Canada 1 Tencent, Jarvis Lab, Shenzhen, 518057, China
Abstract. Frontotemporal dementia and Alzheimer’s disease are two
common forms of dementia and are easily misdiagnosed as each other
due to their similar pattern of clinical symptoms. Frontotemporal dementia and Alzheimer’s disease are two
common forms of dementia and are easily misdiagnosed as each other
due to their similar pattern of clinical symptoms. Differentiating between the two dementia types is crucial for determining disease-specific
intervention and treatment. Frontotemporal dementia and Alzheimer’s disease are two
common forms of dementia and are easily misdiagnosed as each other
due to their similar pattern of clinical symptoms. Differentiating between the two dementia types is crucial for determining disease-specific
intervention and treatment. Differentiating between the two dementia types is crucial for determining disease-specific
intervention and treatment. Recent development of Deep-learning-based
approaches in the field of medical image computing are delivering some
of the best performance for many binary classification tasks, although
its application in differential diagnosis, such as neuroimage-based differentiation for multiple types of dementia, has not been explored. Differentiating between the two dementia types is crucial for determining disease-specific
intervention and treatment. Recent development of Deep-learning-based
approaches in the field of medical image computing are delivering some
of the best performance for many binary classification tasks, although
its application in differential diagnosis, such as neuroimage-based differentiation for multiple types of dementia, has not been explored. Recent development of Deep-learning-based
approaches in the field of medical image computing are delivering some
of the best performance for many binary classification tasks, although
its application in differential diagnosis, such as neuroimage-based differentiation for multiple types of dementia, has not been explored. In this
study, a novel framework was proposed by using the Generative Adversarial Network technique to distinguish FTD, AD and normal control
subjects, using volumetric features extracted at coarse-to-fine structural
scales from Magnetic Resonance Imaging scans. Recent development of Deep-learning-based
approaches in the field of medical image computing are delivering some
of the best performance for many binary classification tasks, although
its application in differential diagnosis, such as neuroimage-based differentiation for multiple types of dementia, has not been explored. In this
study, a novel framework was proposed by using the Generative Adversarial Network technique to distinguish FTD, AD and normal control
subjects, using volumetric features extracted at coarse-to-fine structural
scales from Magnetic Resonance Imaging scans. In this
study, a novel framework was proposed by using the Generative Adversarial Network technique to distinguish FTD, AD and normal control
subjects, using volumetric features extracted at coarse-to-fine structural
scales from Magnetic Resonance Imaging scans. Experiments of 10-folds
cross-validation on 1,954 images achieved high accuracy. In this
study, a novel framework was proposed by using the Generative Adversarial Network technique to distinguish FTD, AD and normal control
subjects, using volumetric features extracted at coarse-to-fine structural
scales from Magnetic Resonance Imaging scans. Experiments of 10-folds
cross-validation on 1,954 images achieved high accuracy. Experiments of 10-folds
cross-validation on 1,954 images achieved high accuracy. With the proposed framework, we have demonstrated that the combination of multiscale structural features and synthetic data augmentation based on generative adversarial network can improve the performance of challenging
tasks such as differentiating Dementia sub-types. Experiments of 10-folds
cross-validation on 1,954 images achieved high accuracy. With the proposed framework, we have demonstrated that the combination of multiscale structural features and synthetic data augmentation based on generative adversarial network can improve the performance of challenging
tasks such as differentiating Dementia sub-types.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
Keywords: Differential Diagnosis, Magnetic Resonance Imaging, Generative Adversarial Network <ref:2109.05627#pg2>
--- Page 3 ---
Structural magnetic Resonance Imaging (MRI) is commonly used to detect pathological atrophic changes in the brain for diagnosis of neurodegenerative diseases such as AD and FTD <ref:2109.05627#pg4> The atrophy patterns of these two types of dementia differs in terms of affected regions and rate of change, and the volumetric structural change measured by T1-weighted MRI is an effective biomarker for differential diagnosis [5] <ref:2109. p. 1 2 Da Ma, Donghuan Lu, Karteek Popuri, Mirza Faisal Beg
Structural magnetic Resonance Imaging (MRI) is commonly used to detect
pathological atrophic changes in the brain for diagnosis of neurodegenerative
diseases such as AD and FTD. The atrophy patterns of these two types of dementia differs in terms of affected regions and rate of change, and the volumetric
structural change measured by T1-weighted MRI is an effective biomarker for
differential diagnosis [5]. The atrophy patterns of these two types of dementia differs in terms of affected regions and rate of change, and the volumetric
structural change measured by T1-weighted MRI is an effective biomarker for
differential diagnosis [5]. Example of volumetric-based features includes gray
matter (GM) volume loss [16], cortical thinning [6], High-dimensional features
based on GM and white matter (WM) volumes distribution of whole brain [5],
as well as atrophy and shape deformity of individual structures [8]. Example of volumetric-based features includes gray
matter (GM) volume loss [16], cortical thinning [6], High-dimensional features
based on GM and white matter (WM) volumes distribution of whole brain [5],
as well as atrophy and shape deformity of individual structures [8]. Most previous dementia classification studies focused on binary classification,
e. Recent development of Deep-learning-based
approaches in the field of medical image computing are delivering some
of the best performance for many binary classification tasks, although
its application in differential diagnosis, such as neuroimage-based differentiation for multiple types of dementia, has not been explored. In this
study, a novel framework was proposed by using the Generative Adversarial Network technique to distinguish FTD, AD and normal control
subjects, using volumetric features extracted at coarse-to-fine structural
scales from Magnetic Resonance Imaging scans. Recent development of Deep-learning-based
approaches in the field of medical image computing are delivering some
of the best performance for many binary classification tasks, although
its application in differential diagnosis, such as neuroimage-based differentiation for multiple types of dementia, has not been explored. In this
study, a novel framework was proposed by using the Generative Adversarial Network technique to distinguish FTD, AD and normal control
subjects, using volumetric features extracted at coarse-to-fine structural
scales from Magnetic Resonance Imaging scans. has built a random undersampling boosting classifier for a five-class differential
diagnostics of neurodegenerative diseases using csf, age, volume and grading
features of whole brain as features [18]. To the best of our knowledge, no deep
learning based approach has been applied to the differential diagnosis of AD and
FTD. To the best of our knowledge, no deep
learning based approach has been applied to the differential diagnosis of AD and
FTD. In this study, a novel framework was proposed which combine multiscale
structural information from MRI scans. In this study, a novel framework was proposed which combine multiscale
structural information from MRI scans. We segmented the structural images
into different patches of superpixels with each anatomical structures following
a hierarchical level of patch size based on brain anatomy thereby extracting
features in a coarse-to-fine manner. We segmented the structural images
into different patches of superpixels with each anatomical structures following
a hierarchical level of patch size based on brain anatomy thereby extracting
features in a coarse-to-fine manner. A multi-scale deep neural network was developed encapsulating the latent representation of features extracted at different
scales, along with Generative Adversarial Network (GAN) technique for data
augmentation. In this
study, a novel framework was proposed by using the Generative Adversarial Network technique to distinguish FTD, AD and normal control
subjects, using volumetric features extracted at coarse-to-fine structural
scales from Magnetic Resonance Imaging scans. Experiments of 10-folds
cross-validation on 1,954 images achieved high accuracy.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
--- Page 4 ---
In the proposed framework, the original MRI images were first parcellated into patches with different level of sizes <ref:2109.05627#pg4> The patch volume and local cortical thickness were extracted at each level; 2) differential classification: a generative adversarial network was trained with the multiscale features to perform differential diagnosis among NC, AD and FTD subjects <ref:2109. p. 1 2 Methods
In the proposed framework, the original MRI images were first parcellated into
patches with different level of sizes. The patch volume and local cortical thickness
were extracted at each level ; 2) differential classification: a generative adversarial
network was trained with the multiscale features to perform differential diagnosis
among NC, AD and FTD subjects.Where the paper says it
--- Page 5 ---
Generative Adversarial Network with multiscale as discriminator
Generative Adversarial Network (GAN) [7] has proven to be power tool to synthesize data, and grained great popularity in the generation of realistic natural image <ref:2109.05627#pg5> Considering the limited number of available MRI scans in this study, we investigated the possibility of applying GAN to augment data samples and improve the classification performance <ref:2109. p. 3 Generative Adversarial Network with multiscale as discriminator
Generative Adversarial Network (GAN) [7] has proven to be power tool to synthesize data, and grained great popularity in the generation of realistic natural
image. Considering the limited number of available MRI scans in this study,
we investigated the possibility of applying GAN to augment data samples and
improve the classification performance. Considering the limited number of available MRI scans in this study,
we investigated the possibility of applying GAN to augment data samples and
improve the classification performance. As shown in Figure 1, a GAN was trained with the patch-wise features extracted at multiscales from MRI. As shown in Figure 1, a GAN was trained with the patch-wise features extracted at multiscales from MRI. It consisted of a generator (G) and a discriminator (D). It is therefore essential to develop a computer-aided diagnosis system with improved accuracy for
differential diagnosis. arXiv:2109.Where the paper says it
Where the paper says it
Where the paper says it
fake
, from the samples belong to true classes, i.e., NC, AD and FTD <ref:2109. p. 0Where the paper says it
--- Page 6 ---
Fig. 1. Architecture of Generative Adversarial Network. p. 3 Competition between G
and D could drive both network to improve their performance. Architecture of Generative Adversarial Network. Architecture of Generative Adversarial Network. The number of units in generator layers are 512 and 2536(1488+705+343), respectively.Where the paper says it
Where the paper says it
--- Page 7 ---
A Multiscale Deep Neural Network (MDNN) [9] With the feature extracted at different scales was applied as the discriminator to learn the latent pattern from the feature space and perform the multi-class classification <ref:2109.05627#pg5> The MDNN consisted of a cascade of four four-layer Multilayer Perceptrons (MLPs) <ref:2109.05627#pg5>
--- Page 8 ---
Network Optimization
For the optimization of GAN, the cost function was defined as: min D max G V (D, G) = Ex∼pdata(x) [logD(x)] + Ez∼pz(z) [log(−D(G(z)))] (1) <ref:2109.05627#pg5> Root mean square propagation (RMSProp) optimizer was used to train the network and the batch size was set as 100 <ref:2109. p. 4 log(−D(G(z))) was used instead of log(1 − D(G(z))) to avoid gradient vanish
and mode collapse [2]. Root mean square propagation (RMSProp) optimizer was
used to train the network and the batch size was set as 100. Root mean square propagation (RMSProp) optimizer was
used to train the network and the batch size was set as 100. Two strategies were applied during the training process to prevent overfitting: random dropout and early stop. Two strategies were applied during the training process to prevent overfitting: random dropout and early stop. Firstly, dropout layers were inserted
in the network after each hidden layer of the discriminator. 5 to randomly drop half of the units during training stage to prevent
complex co-adaptations on training data. Secondly, during the training procedure, the optimization stops when the classification accuracy of validation set
ceased to increase for 20 epochs. Furthermore, due to the limited number of
data samples, early stopping with a small set of validation could still result in
an unstable classification performance. Finally, an ensemble classification framework [9] was used.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
--- Page 9 ---
Fig. 3. Sample images of the A) initial Freesurfer structural segmentation results and B) multisale subROI patch parcellation <ref:2109. p. 6 Differential Diagnosis of FTD and AD using GAN 7
Fig. Sample images of the A) initial Freesurfer structural segmentation results and
B) multisale subROI patch parcellation
The accuracy and sensitivity for each class of these 6 experiments were reported in Table 2.Where the paper says it
--- Page 1 ---
Differential Diagnosis of Frontotemporal Dementia and Alzheimer’s Disease using GAN
Da Ma, Donghuan Lu, Karteek Popuri, and Mirza Faisal Beg Simon Fraser University, School of Engineering Science, Burnaby, V5A 1S6, Canada Tencent, Jarvis Lab <ref:2109.05627#pg2>
Abstract. Frontotemporal dementia and Alzheimer’s disease are two common forms of dementia and are easily misdiagnosed as each other due to their similar pattern of clinical symptoms <ref:2109.05627#pg2> Differentiating between the two dementia types is crucial for determining disease-specific intervention and treatment <ref:2109.05627#pg2> Recent development of Deep-learning-based approaches in the field of medical image computing are delivering some of the best performance for many binary classification tasks, although its application in differential diagnosis, such as neuroimage-based differentiation for multiple types of dementia, has not been explored <ref:2109.05627#pg2> In this study, a novel framework was proposed by using the Generative Adversarial Network technique to distinguish FTD, AD and normal control subjects, using volumetric features extracted at coarse-to-fine structural scales from Magnetic Resonance Imaging scans <ref:2109.05627#pg2> Experiments of 10-folds cross validation on 1,954 images achieved high accuracy <ref:2109.05627#pg4> With the proposed framework, we have demonstrated that the combination of multiscale structural features and synthetic data augmentation based on generative adversarial network can improve the performance of challenging tasks such as differentiating Dementia sub-types <ref:2109.05627#pg2>
Keywords: Differential Diagnosis, Magnetic Resonance Imaging, Generative Adversarial Network <ref:2109.
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
-
Multiscale Feature Extraction for Enhanced Discrimination The framework extracts features at three different scales (500, 1000, and 2000 voxels per patch) to
keep as much information as possible during feature dimension reduction.
This allows the system to capture discriminating information across different structural levels, which the paper suggestscould exist in different scale of images.
-
Generative Adversarial Network for Data Augmentation The GAN is used to augment data samples by training a generator (G) and a discriminator (D) to synthesize realistic data, which helps with
limited number of available MRI scans.
This augmentation is shown to further improve the classification accuracy by about 2%. -
Multiscale Deep Neural Network for Latent Pattern Learning The Multiscale Deep Neural Network (MDNN) is applied as the discriminator and is designed
to learn the latent pattern from the feature space and perform the multi-class classification.
It achieves a slightly higher overall accuracy than single-scale MLPs, suggesting itcould learn hidden pattern across the small to large patches.
-
Ensemble Classification Framework for Robust Results The system employs an ensemble classification framework by training 10 networks with independently separated splits of training and validation subsets and obtaining the final result through majority voting. This strategy helps prevent overfitting given the
limited number of data samples
and results in a more stable classification performance.
Abstract
Frontotemporal dementia and Alzheimer's disease are two common forms of dementia and are easily misdiagnosed as each other due to their similar pattern of clinical symptoms. Differentiating between the two dementia types is crucial for determining disease-specific intervention and treatment. Recent development of Deep-learning-based approaches in the field of medical image computing are delivering some of the best performance for many binary classification tasks, although its application in differential diagnosis, such as neuroimage-based differentiation for multiple types of dementia, has not been explored. In this study, a novel framework was proposed by using the Generative Adversarial Network technique to distinguish FTD, AD and normal control subjects, using volumetric features extracted at coarse-to-fine structural scales from Magnetic Resonance Imaging scans. Experiments of 10-folds cross-validation on 1,954 images achieved high accuracy. With the proposed framework, we have demonstrated that the combination of multi-scale structural features and synthetic data augmentation based on generative adversarial network can improve the performance of challenging tasks such as differentiating Dementia sub-types.
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