眼部肿瘤学中的人工智能与机器学习，视网膜母细胞瘤（ArMOR）。
Artificial intelligence and machine learning in ocular oncology, retinoblastoma (ArMOR).
作者信息
Vempuluru Vijitha S, Patil Gaurav, Viriyala Rajiv, Dhara Krishna K, Kaliki Swathi
机构信息
Ocular Oncology Services, Operation Eyesight Universal Institute for Eye Cancer, L. V. Prasad Eye Institute, Hyderabad, Telangana, India.
出版信息
Indian J Ophthalmol. 2025 May 1;73(5):741-743. doi: 10.4103/IJO.IJO_1768_24. Epub 2025 Apr 24.
PURPOSE
To test the accuracy of a trained artificial intelligence and machine learning (AI/ML) model in the diagnosis and grouping of intraocular retinoblastoma (iRB) based on the International Classification of Retinoblastoma (ICRB) in a larger cohort.
METHODS
Retrospective observational study that employed AI, ML, and open computer vision techniques.
RESULTS
For 1266 images, the AI/ML model displayed accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of 95%, 94%, 98%, 99%, and 80%, respectively, for the detection of RB. For 173 eyes, the accuracy, sensitivity, specificity, PPV, and NPV of the AI/ML model were 85%, 98%, 94%, 98%, and 94% for detecting RB. Of 173 eyes classified based on the ICRB by two independent ocular oncologists, 9 (5%) were Group A, 32 (19%) were Group B, 21 (12%) were Group C, 37 (21%) were Group D, 38 (22%) were Group E, and 36 (21%) were classified as normal. Based on the ICRB classification of 173 eyes, the AI/ML model displayed accuracy, sensitivity, specificity, PPV, and NPV of 98%, 94%, 99%, 94%, and 99% for normal; 97%, 56%, 99%, 71% and 98% for Group A; 95%, 75%, 99%, 96%, and 95% for Group B; 95%, 86%, 96%, 75%, and 98% for Group C; 92%, 76%, 96%, 85%, and 94% for Group D; and 94%, 100%, 93%, 79%, 100% for Group E, respectively.
CONCLUSION
These observations show that expanding the image datasets, as well as testing and retesting AI models, helps identify deficiencies in the AI/ML model and improves its accuracy.
目的
在更大的队列中，基于视网膜母细胞瘤国际分类（ICRB），测试经过训练的人工智能和机器学习（AI/ML）模型在眼内视网膜母细胞瘤（iRB）诊断和分组中的准确性。
方法
采用AI、ML和开放计算机视觉技术的回顾性观察研究。
结果
对于1266张图像，AI/ML模型检测视网膜母细胞瘤（RB）的准确性、敏感性、特异性、阳性预测值（PPV）和阴性预测值（NPV）分别为95%、94%、98%、99%和80%。对于173只眼，AI/ML模型检测RB的准确性、敏感性、特异性、PPV和NPV分别为85%、98%、94%、98%和94%。在由两名独立的眼科肿瘤学家根据ICRB分类的173只眼中，9只（5%）为A组，32只（19%）为B组，21只（12%）为C组，37只（21%）为D组, 38只（22%）为E组，36只（21%）分类为正常。基于173只眼的ICRB分类，AI/ML模型对于正常眼的准确性、敏感性、特异性、PPV和NPV分别为98%、94%、99%、94%和99%；对于A组分别为97%、56%、99%、71%和98%；对于B组分别为95%、75%、99%、96%和95%；对于C组分别为95%、86%、96%、75%和98%；对于D组分别为92%、76%、96%、85%和94%；对于E组分别为94%、100%、93%、79%和100%。
结论
这些观察结果表明，扩大图像数据集以及对AI模型进行测试和重新测试，有助于识别AI/ML模型中的缺陷并提高其准确性。
Zotero 插件