Sam Ellis, Sandra Gomes, Matthew Trumble, Mark D Halling-Brown, Kenneth C Young, Nouman S Chaudhry, Peter Harris, Lucy M Warren
下载PDF
{"title":"Deep Learning for Breast Cancer Risk Prediction: Application to a Large Representative UK Screening Cohort.","authors":"Sam Ellis, Sandra Gomes, Matthew Trumble, Mark D Halling-Brown, Kenneth C Young, Nouman S Chaudhry, Peter Harris, Lucy M Warren","doi":"10.1148/ryai.230431","DOIUrl":null,"url":null,"abstract":"<p><p>Purpose To develop an artificial intelligence (AI) deep learning tool capable of predicting future breast cancer risk from a current negative screening mammographic examination and to evaluate the model on data from the UK National Health Service Breast Screening Program. Materials and Methods The OPTIMAM Mammography Imaging Database contains screening data, including mammograms and information on interval cancers, for more than 300 000 female patients who attended screening at three different sites in the United Kingdom from 2012 onward. Cancer-free screening examinations from women aged 50-70 years were performed and classified as risk-positive or risk-negative based on the occurrence of cancer within 3 years of the original examination. Examinations with confirmed cancer and images containing implants were excluded. From the resulting 5264 risk-positive and 191 488 risk-negative examinations, training (<i>n</i> = 89 285), validation (<i>n</i> = 2106), and test (<i>n</i> = 39 351) datasets were produced for model development and evaluation. The AI model was trained to predict future cancer occurrence based on screening mammograms and patient age. Performance was evaluated on the test dataset using the area under the receiver operating characteristic curve (AUC) and compared across subpopulations to assess potential biases. Interpretability of the model was explored, including with saliency maps. Results On the hold-out test set, the AI model achieved an overall AUC of 0.70 (95% CI: 0.69, 0.72). There was no evidence of a difference in performance across the three sites, between patient ethnicities, or across age groups. Visualization of saliency maps and sample images provided insights into the mammographic features associated with AI-predicted cancer risk. Conclusion The developed AI tool showed good performance on a multisite, United Kingdom-specific dataset. <b>Keywords:</b> Deep Learning, Artificial Intelligence, Breast Cancer, Screening, Risk Prediction <i>Supplemental material is available for this article.</i> ©RSNA, 2024.</p>","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":" ","pages":"e230431"},"PeriodicalIF":8.1000,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11294956/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Radiology-Artificial Intelligence","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1148/ryai.230431","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0
引用
批量引用
Abstract
Purpose To develop an artificial intelligence (AI) deep learning tool capable of predicting future breast cancer risk from a current negative screening mammographic examination and to evaluate the model on data from the UK National Health Service Breast Screening Program. Materials and Methods The OPTIMAM Mammography Imaging Database contains screening data, including mammograms and information on interval cancers, for more than 300 000 female patients who attended screening at three different sites in the United Kingdom from 2012 onward. Cancer-free screening examinations from women aged 50-70 years were performed and classified as risk-positive or risk-negative based on the occurrence of cancer within 3 years of the original examination. Examinations with confirmed cancer and images containing implants were excluded. From the resulting 5264 risk-positive and 191 488 risk-negative examinations, training (n = 89 285), validation (n = 2106), and test (n = 39 351) datasets were produced for model development and evaluation. The AI model was trained to predict future cancer occurrence based on screening mammograms and patient age. Performance was evaluated on the test dataset using the area under the receiver operating characteristic curve (AUC) and compared across subpopulations to assess potential biases. Interpretability of the model was explored, including with saliency maps. Results On the hold-out test set, the AI model achieved an overall AUC of 0.70 (95% CI: 0.69, 0.72). There was no evidence of a difference in performance across the three sites, between patient ethnicities, or across age groups. Visualization of saliency maps and sample images provided insights into the mammographic features associated with AI-predicted cancer risk. Conclusion The developed AI tool showed good performance on a multisite, United Kingdom-specific dataset. Keywords: Deep Learning, Artificial Intelligence, Breast Cancer, Screening, Risk Prediction Supplemental material is available for this article. ©RSNA, 2024.
深度学习用于乳腺癌风险预测:应用于英国大型代表性筛查队列。
"刚刚接受 "的论文经过同行评审,已被接受在《放射学》上发表:人工智能》上发表。这篇文章在以最终版本发表之前,还将经过校对、排版和校对审核。请注意,在制作最终校对稿的过程中,可能会发现影响内容的错误。目的 开发一种人工智能(AI)深度学习工具,该工具能够根据当前乳腺X光筛查的阴性结果预测未来的乳腺癌风险,并根据英国国民健康服务乳腺筛查项目的数据对模型进行评估。材料与方法 OPTIMAM 乳房 X 线照相术成像数据库包含从 2012 年起在英国三个不同地点参加筛查的超过 30 万名女性的筛查数据,包括乳房 X 线照相术和间期癌症信息。该数据库获取了 50-70 岁妇女的无癌症筛查数据,并根据原始检查后 3 年内癌症的发生情况将其分为风险阳性和风险阴性。排除了确诊癌症的检查和含有植入物的图像。在由此产生的 5264 例风险阳性和 191488 例风险阴性检查中,产生了用于模型开发和评估的训练数据集(n = 89285)、验证数据集(n = 2106)和测试数据集(n = 39351)。对人工智能模型进行了训练,以根据筛查乳房 X 线照片和患者年龄预测未来癌症发生率。使用接收者工作特征曲线下面积(AUC)对测试数据集的性能进行评估,并对不同亚群进行比较,以评估潜在的偏差。此外,还对模型的可解释性进行了探讨,包括使用突出图。结果 在保留测试集上,人工智能模型的总体 AUC 为 0.70(95% CI:0.69,0.72)。没有证据表明三个部位、不同种族或不同年龄组的患者在性能上存在差异 突出图和样本图像的可视化提供了与人工智能预测癌症风险相关的乳房 X 线摄影特征。结论 开发的人工智能工具在英国特定的多站点数据集上表现良好。©RSNA,2024。
本文章由计算机程序翻译,如有差异,请以英文原文为准。