Scholarlink

Purpose <p>To evaluate the efficacy of a self-supervised learning Vision Transformer (ViT) for classification of the nucleus, cortex, and posterior capsule cataract severity utilizing anterior segment optical coherence tomography (AS-OCT) images.</p> Study design <p>Artificial intelligence (AI) model training.</p> Methods <p>Overall, 1,693 eyes were imaged using AS-OCT, with 1,023 classified according to the Lens Opacities Classification System III for supervised training at the Department of Ophthalmology, University of Tsukuba Hospital, Japan. Five AI models were compared: ResNet18, ViT with/without ImageNet pre-training, and Self-Supervised ViT (SS-ViT) constructed using AS-OCT images from 670 eyes. These models were evaluated across five classification tasks: nuclear cataract 2-class (N1 vs. N2≥), 3-class (N1, N2-N3, N4≥), and 6-class classifications; and 2-class classifications for both cortical (C1 vs. C2≥) and posterior subcapsular cataracts (P1 vs. P2≥). Performance was measured using Area Under the Precision-Recall Curve (AUPRC).</p> Results <p>In the nuclear cataract 2-class classification, ResNet18, ViT, and SS-ViT, which were pre-trained on ImageNet, demonstrated the highest AUPRC of 0.999. For the nuclear cataract 3-class classification, SS-ViT exhibited the highest AUPRC of 0.939. In the 6-class classification of nuclear cataract, SS-ViT attained the highest value with an AUPRC of 0.788. In the 2-class classification of cortical cataract, SS-ViT demonstrated the highest performance with an AUPRC of 0.774, while in the 2-class classification of posterior subcapsular cataract, SS-ViT exhibited the most favorable performance with an AUPRC of 0.506.</p> Conclusion <p>Our findings demonstrate the effectiveness of a self-supervised ViT model for severity classification of nuclear, cortical, and posterior subcapsular cataracts on AS-OCT.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Advancement of cataract classification with artificial intelligence using anterior segment optical coherence tomography images with self-supervised vision transformer

  • 期刊论文

  • 发表日期：

    2026年1月28日

查看全文
  • Shumpei Takinami,
  • Yuta Ueno,
  • Haruhiro Mori,
  • Yuka Morita,
  • Jun Seita,
  • Tetsuro Oshika

摘要

Purpose

To evaluate the efficacy of a self-supervised learning Vision Transformer (ViT) for classification of the nucleus, cortex, and posterior capsule cataract severity utilizing anterior segment optical coherence tomography (AS-OCT) images.

Study design

Artificial intelligence (AI) model training.

Methods

Overall, 1,693 eyes were imaged using AS-OCT, with 1,023 classified according to the Lens Opacities Classification System III for supervised training at the Department of Ophthalmology, University of Tsukuba Hospital, Japan. Five AI models were compared: ResNet18, ViT with/without ImageNet pre-training, and Self-Supervised ViT (SS-ViT) constructed using AS-OCT images from 670 eyes. These models were evaluated across five classification tasks: nuclear cataract 2-class (N1 vs. N2≥), 3-class (N1, N2-N3, N4≥), and 6-class classifications; and 2-class classifications for both cortical (C1 vs. C2≥) and posterior subcapsular cataracts (P1 vs. P2≥). Performance was measured using Area Under the Precision-Recall Curve (AUPRC).

Results

In the nuclear cataract 2-class classification, ResNet18, ViT, and SS-ViT, which were pre-trained on ImageNet, demonstrated the highest AUPRC of 0.999. For the nuclear cataract 3-class classification, SS-ViT exhibited the highest AUPRC of 0.939. In the 6-class classification of nuclear cataract, SS-ViT attained the highest value with an AUPRC of 0.788. In the 2-class classification of cortical cataract, SS-ViT demonstrated the highest performance with an AUPRC of 0.774, while in the 2-class classification of posterior subcapsular cataract, SS-ViT exhibited the most favorable performance with an AUPRC of 0.506.

Conclusion

Our findings demonstrate the effectiveness of a self-supervised ViT model for severity classification of nuclear, cortical, and posterior subcapsular cataracts on AS-OCT.