Scholarlink

<p>Reading and summarizing insights from Optical Coherence Tomography (OCT) images is a routine yet time-consuming task that requires expensive time from experienced ophthalmologists. This paper introduces the Multi-label OCT Report Generation (MORG) model, a deep learning approach to assist in the interpretation of OCT images. MORG employs dual image encoders to extract features from OCT image pairs, fusing them through a multi-scale module with an attention mechanism, followed by a sentence decoder to produce reports. Trained and tested on 57,308 retinal OCT image pairs, MORG achieved high classification accuracy for 16 pathologies with 37 descriptive types. It also excelled in a blind grading test against general large language models and other state-of-the-art image captioning models, scoring 4.55 compared to ophthalmologists’ 4.63 out of a maximum of 5. Furthermore, MORG has the potential to reduce the report drafting time for ophthalmologists by 58.9%, significantly alleviating their workload.</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

A deep learning based automatic report generator for retinal optical coherence tomography images

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年10月20日

查看全文
  • Xinjian Chen,
  • Huazhu Fu,
  • Jingtao Wang,
  • Tian Lin,
  • Qian Cheng,
  • Cangxin Li,
  • Meng Wang,
  • Zhongyue Chen,
  • Aidi Lin,
  • Anlin Zhang,
  • Weifang Zhu,
  • Shirong Chen,
  • Fei Shi,
  • Dehui Xiang,
  • Baoqing Nie,
  • Yi Zhou,
  • Yuanyuan Peng,
  • Danqi Fang,
  • Chao Guo,
  • Ting Wang,
  • Mingzhi Zhang,
  • Chi Pui Pang,
  • Haoyu Chen

摘要

Reading and summarizing insights from Optical Coherence Tomography (OCT) images is a routine yet time-consuming task that requires expensive time from experienced ophthalmologists. This paper introduces the Multi-label OCT Report Generation (MORG) model, a deep learning approach to assist in the interpretation of OCT images. MORG employs dual image encoders to extract features from OCT image pairs, fusing them through a multi-scale module with an attention mechanism, followed by a sentence decoder to produce reports. Trained and tested on 57,308 retinal OCT image pairs, MORG achieved high classification accuracy for 16 pathologies with 37 descriptive types. It also excelled in a blind grading test against general large language models and other state-of-the-art image captioning models, scoring 4.55 compared to ophthalmologists’ 4.63 out of a maximum of 5. Furthermore, MORG has the potential to reduce the report drafting time for ophthalmologists by 58.9%, significantly alleviating their workload.