Artificial intelligence and machine learning in ocular oncology, retinoblastoma (ArMOR).

IF 2.1 4区医学 Q2 OPHTHALMOLOGY

Indian Journal of Ophthalmology Pub Date : 2025-05-01 Epub Date: 2025-04-24 DOI:10.4103/IJO.IJO_1768_24

Vijitha S Vempuluru, Gaurav Patil, Rajiv Viriyala, Krishna K Dhara, Swathi Kaliki

{"title":"Artificial intelligence and machine learning in ocular oncology, retinoblastoma (ArMOR).","authors":"Vijitha S Vempuluru, Gaurav Patil, Rajiv Viriyala, Krishna K Dhara, Swathi Kaliki","doi":"10.4103/IJO.IJO_1768_24","DOIUrl":null,"url":null,"abstract":"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.","PeriodicalId":13329,"journal":{"name":"Indian Journal of Ophthalmology","volume":"73 5","pages":"741-743"},"PeriodicalIF":2.1000,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Indian Journal of Ophthalmology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.4103/IJO.IJO_1768_24","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/4/24 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"OPHTHALMOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

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.

查看原文本刊更多论文

人工智能和机器学习在眼肿瘤学，视网膜母细胞瘤（ArMOR）。

目的：在更大的队列中测试基于国际视网膜母细胞瘤分类（ICRB）的训练有素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：采用人工智能、机器学习和开放式计算机视觉技术进行回顾性观察研究。结果：对于1266张图像，AI/ML模型检测RB的准确率为95%，灵敏度为94%，特异性为98%，阳性预测值为99%，阴性预测值为80%。对于173只眼，AI/ML模型检测RB的准确率、灵敏度、特异性、PPV和NPV分别为85%、98%、94%、98%和94%。由两位独立眼科肿瘤学家根据ICRB进行分类的173只眼中，A组9只（5%），B组32只（19%），C组21只（12%），D组37只（21%），E组38只（22%），正常36只（21%）。基于173只眼睛的ICRB分类，AI/ML模型的准确率、灵敏度、特异性、PPV和NPV分别为98%、94%、99%、94%和99%；A组97%、56%、99%、71%、98%；B组95%、75%、99%、96%、95%；C组95%、86%、96%、75%、98%；D组92%，76%,96%,85%,94%；E组分别为94%、100%、93%、79%、100%。结论：这些观察结果表明，扩展图像数据集以及测试和重新测试AI模型有助于识别AI/ML模型的缺陷并提高其准确性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Indian Journal of Ophthalmology OPHTHALMOLOGY-

CiteScore

3.80

自引率

19.40%

发文量

1963

审稿时长

38 weeks

期刊介绍： Indian Journal of Ophthalmology covers clinical, experimental, basic science research and translational research studies related to medical, ethical and social issues in field of ophthalmology and vision science. Articles with clinical interest and implications will be given preference.