Within-Family EfficientNet Scaling under Fixed-Resolution Transfer Learning for Spectral-Domain Optical Coherence Tomography Retinal Disease Classification
cs.CV, cs.AI, cs.LG
Submitted: 2026-11-04
Updated: 2026-11-04
Comments: 46 pages, 20 figures, 18 tables
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
The gist: Background/Objectives: CNNs perform well in retinal disease classification from spectral-domain optical coherence tomography (SD-OCT)…
Terminology
Abstract
Background/Objectives: CNNs perform well in retinal disease classification from spectral-domain optical coherence tomography (SD-OCT), but whether EfficientNet's natural-image scaling hierarchy transfers to medical-image transfer learning at fixed resolution remains unclear. This study evaluates EfficientNet-B0-B7 for four-class SD-OCT classification and accuracy-efficiency trade-offs. Methods: Eight ImageNet-pretrained variants (4.05-64.10M instantiated backbone parameters) were evaluated at 224x224 on the Kermany dataset. Grayscale images were replicated to RGB and processed using model-embedded preprocessing and augmentation. Training comprised frozen-backbone head training followed by partial fine-tuning. Metrics covered classification, discrimination, efficiency, and visual analyses. Results: Test accuracy varied non-monotonically from 95.93% (B0) to 96.95% (B1); B7 achieved 96.73%. B1 had the highest accuracy and Drusen F1 (0.8780), while B7 had Drusen F1 of 0.8720 and the highest Drusen recall (0.9177). Drusen had the lowest F1 across all variants and contributed 82.2% of the summed squared deviation in class-specific F1; class ranking remained Normal > CNV > DME > Drusen. The OCT accuracy ranking differed from the reported ImageNet hierarchy, where B7 ranked first. The accuracy-to-parameter ratio fell from 19.82 to 1.48 percentage points per million total parameters. The final train-test gap had a weak, non-significant association with test accuracy (r = 0.26, p = 0.53). Conclusions: Larger EfficientNet variants did not consistently improve SD-OCT classification. B1 achieved the highest accuracy and Drusen F1, whereas B7 showed a secondary accuracy recovery at greater model size and CPU latency, indicating task and protocol dependent scaling effects. As cross-partition duplicates have not been independently audited, results are conditional on the supplied split.
Sources
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
- Multi-Scale Convolutional Neural Network for Automated AMD Classification using Retinal OCT Images
- CNN-Based Retinal OCT Classification: Research Gap Analysis and a From-Scratch Baseline, ED126-A
- Squeeze-and-Excitation Networks
- Do Better ImageNet Models Transfer Better?
- Transfusion: Understanding Transfer Learning for Medical Imaging
- CBAM: Convolutional Block Attention Module
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs