文献速递角膜与眼表疾病眼底病与葡萄膜炎

使用人工智能结合眼前节光学相干断层扫描检测眼表鳞状上皮肿瘤

Detection of Ocular Surface Squamous Neoplasia Using Artificial Intelligence With Anterior Segment Optical Coherence Tomography.
PubMed 文献 · Am J Ophthalmol · 2025-02-19

这项回顾性诊断准确性研究开发并验证了一种深度学习模型,利用高分辨率眼前节光学相干断层扫描(AS-OCT)区分眼表鳞状上皮肿瘤(OSSN)与翼状胬肉和睑裂斑。模型在独立测试样本中达到90.3%的准确率、86.4%的敏感性和93.2%的特异性,其ROC曲线下面积(0.945)显著高于专家阅片者(0.688,P<.001)。结论认为该模型展现出高准确性,并有助增强临床决策,但需进一步研究探索其在常规筛查和诊断流程中的整合。

要点

  • 深度学习模型基于AS-OCT区分OSSN与翼状胬肉/睑裂斑,准确率90.3%、敏感性86.4%、特异性93.2%。
  • 模型ROC曲线下面积0.945,显著高于专家阅片者的0.688(P<.001)。
  • 专家敏感性69.8%、特异性98.5%;模型敏感性更高、特异性略低。

核心结论

  • 深度学习模型应用于AS-OCT扫描在区分OSSN与翼状胬肉和睑裂斑方面表现出高准确率、敏感性和特异性。
  • 该模型在本研究中与专家临床医生的诊断性能相当,并显示出增强临床决策的潜力。
  • 需要进一步研究探索将这种人工智能驱动方法整合到OSSN的常规筛查和诊断流程中。

研究设计与样本

  • 回顾性诊断准确性研究,单中心设置。
  • 研究人群为所有临床或活检证实诊断为OSSN、翼状胬肉或睑裂斑并接受AS-OCT成像的眼睛。
  • 使用105859张AS-OCT图像(5746只眼)的无标签数据训练掩码自编码器,并使用标注数据微调Vision Transformer监督模型构建二分类器(OSSN vs 非OSSN病变)。
  • 由专家阅片者将523只眼(427例患者)的2022张AS-OCT图像分类为「OSSN或疑似OSSN」和「翼状胬肉或睑裂斑」。
  • 在独立测试样本中使用566次扫描(62只眼,48例患者)的活检证实OSSN评估算法诊断性能,并与对诊断设盲的专家临床医生比较,分析在扫描层面进行。

主要发现

  • 深度学习模型与活检证实诊断相比,准确率为90.3%(95%CI:87.5%-92.6%),敏感性为86.4%(95%CI:81.4%-90.4%),特异性为93.2%(95%CI:89.9%-95.7%)。
  • 专家阅片者敏感性为69.8%(95%CI:63.6%-75.5%),低于深度学习模型的86.4%;特异性为98.5%(95%CI:96.4%-99.5%),略高于深度学习模型的93.2%。
  • 深度学习模型的ROC曲线下面积为0.945(95%CI:0.918-0.972),显著大于专家阅片者的0.688(P<.001)。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

PURPOSE: To develop and validate a deep learning (DL) model to differentiate ocular surface squamous neoplasia (OSSN) from pterygium and pinguecula using high-resolution anterior segment optical coherence tomography (AS-OCT). DESIGN: Retrospective Diagnostic Accuracy Study. METHODS: Setting: Single-center. STUDY POPULATION: All eyes with a clinical or biopsy-proven diagnosis of OSSN, pterygium, or pinguecula that received AS-OCT imaging. PROCEDURES: Imaging data was extracted from Optovue AS-OCT (Fremont, CA) and patients' clinical or biopsy-proven diagnoses were collected from electronic medical records. A DL classification model was developed using two methodologies: (1) a masked autoencoder was trained with unlabeled data from 105,859 AS-OCT images of 5746 eyes and (2) a Vision Transformer supervised model coupled to the autoencoder used labeled data for fine-tuning a binary classifier (OSSN vs non-OSSN lesions). A sample of 2022 AS-OCT images from 523 eyes (427 patients) were classified by expert graders into "OSSN or suspicious for OSSN" and "pterygium or pinguecula." The algorithm's diagnostic performance was evaluated in a separate test sample using 566 scans (62 eyes, 48 patients) with biopsy-proven OSSN and compared with expert clinicians who were masked to the diagnosis. Analysis was conducted at the scan-level for both the DL model and expert clinicians, who were not provided with clinical images or supporting clinical data. MAIN OUTCOME: Diagnostic performance of expert clinicians and the DL model in identifying OSSN on AS-OCT scans. RESULTS: The DL model had an accuracy of 90.3% (95% confidence intervals [CI]: 87.5%-92.6%), with sensitivity of 86.4% (95% CI: 81.4%-90.4%) and specificity of 93.2% (95% CI: 89.9%-95.7%) compared to the biopsy-proven diagnosis. Expert graders had a lower sensitivity 69.8% (95% CI: 63.6%-75.5%) and slightly higher specificity 98.5% (95% CI: 96.4%-99.5%) than the DL model. The area under the receiver operating characteristic curve for the DL model was 0.945 (95% CI: 0.918-0.972) and significantly greater than expert graders (area under the receiver operating characteristic curve = 0.688, P < .001). CONCLUSIONS: A DL model applied to AS-OCT scans demonstrated high accuracy, sensitivity, and specificity in differentiating OSSN from pterygium and pinguecula. Interestingly, the model had comparable diagnostic performance to expert clinicians in this study and shows promise for enhancing clinical decision-making. Further research is warranted to explore the integration of this artificial intelligence-driven approach in routine screening and diagnostic protocols for OSSN.

来源:Am J Ophthalmol,查看原文。版权归原作者所有。

引用

  1. Greenfield JA, Scherer R, Alba D, et al. Detection of Ocular Surface Squamous Neoplasia Using Artificial Intelligence With Anterior Segment Optical Coherence Tomography. Am J Ophthalmol. 2025. PMID: 39983942. doi:10.1016/j.ajo.2025.02.019

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。