arXiv cs.AI· Shkelqim Sherifi·· 11 小时前AI 评分22
EfficientNet 家族在固定分辨率迁移学习下的 SD-OCT 视网膜疾病分类效果评估
Within-Family EfficientNet Scaling under Fixed-Resolution Transfer Learning for Spectral-Domain Optical Coherence Tomography Retinal Disease Classification
AI 导读
研究在 224x224 固定分辨率下评估 8 个 ImageNet 预训练 EfficientNet-B0–B7 变体（4.05–64.10M 主干参数）对 Kermany 数据集四类 SD-OCT 图像的分类表现，测试准确率从 B0 的 95.93% 非单调变化至 B1 的 96.95%，B7 为 96.73%。
正文 · 原文
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.
| Comments: | 46 pages, 20 figures, 18 tables |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.06452 [cs.CV] |
| (or arXiv:2611.06452v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.06452 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Shkelqim Sherifi [view email]
[v1]
Wed, 4 Nov 2026 12:53:44 UTC (14,102 KB)
来源：arXiv cs.AI · arxiv.org