Predicting Breast Cancer by Applying Deep Learning to Linked Health Records and Mammograms

医学 乳腺摄影术 乳腺癌 置信区间 恶性肿瘤 接收机工作特性 双雷达 乳房成像 健康档案 回顾性队列研究 放射科 试验装置 机器学习 人工智能 内科学 妇科 癌症 乳腺癌筛查 医疗保健 计算机科学 经济 经济增长
作者
Ayelet Akselrod-Ballin,Michal Chorev,Yoel Shoshan,Adam Spiro,Alon Hazan,Roie Melamed,Ella Barkan,Esma Herzel,Shaked Naor,Ehud Karavani,Gideon Koren,Yaara Goldschmidt,Varda Shalev,Michal Rosen-Zvi,Michal Guindy
出处
期刊:Radiology [Radiological Society of North America]
卷期号:292 (2): 331-342 被引量:139
标识
DOI:10.1148/radiol.2019182622
摘要

Background Computational models on the basis of deep neural networks are increasingly used to analyze health care data. However, the efficacy of traditional computational models in radiology is a matter of debate. Purpose To evaluate the accuracy and efficiency of a combined machine and deep learning approach for early breast cancer detection applied to a linked set of digital mammography images and electronic health records. Materials and Methods In this retrospective study, 52 936 images were collected in 13 234 women who underwent at least one mammogram between 2013 and 2017, and who had health records for at least 1 year before undergoing mammography. The algorithm was trained on 9611 mammograms and health records of women to make two breast cancer predictions: to predict biopsy malignancy and to differentiate normal from abnormal screening examinations. The study estimated the association of features with outcomes by using t test and Fisher exact test. The model comparisons were performed with a 95% confidence interval (CI) or by using the DeLong test. Results The resulting algorithm was validated in 1055 women and tested in 2548 women (mean age, 55 years ± 10 [standard deviation]). In the test set, the algorithm identified 34 of 71 (48%) false-negative findings on mammograms. For the malignancy prediction objective, the algorithm obtained an area under the receiver operating characteristic curve (AUC) of 0.91 (95% CI: 0.89, 0.93), with specificity of 77.3% (95% CI: 69.2%, 85.4%) at a sensitivity of 87%. When trained on clinical data alone, the model performed significantly better than the Gail model (AUC, 0.78 vs 0.54, respectively; P < .004). Conclusion The algorithm, which combined machine-learning and deep-learning approaches, can be applied to assess breast cancer at a level comparable to radiologists and has the potential to substantially reduce missed diagnoses of breast cancer. © RSNA, 2019 Online supplemental material is available for this article.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
汉堡包应助结实傲蕾采纳,获得10
刚刚
1秒前
友好老黑发布了新的文献求助10
2秒前
2秒前
wang发布了新的文献求助10
2秒前
zhaosh发布了新的文献求助10
2秒前
猫捡球完成签到,获得积分10
3秒前
3秒前
Dannerys完成签到 ,获得积分10
3秒前
研友_8KXRPL发布了新的文献求助10
3秒前
小二郎应助胡柱柱采纳,获得10
3秒前
娇娇发布了新的文献求助30
3秒前
wjx关闭了wjx文献求助
4秒前
guojin发布了新的文献求助10
4秒前
英俊的铭应助Anhydride采纳,获得10
4秒前
苍蝇搓手发布了新的文献求助10
4秒前
cindy发布了新的文献求助10
4秒前
5秒前
怕孤独的机器猫完成签到,获得积分10
6秒前
Ava应助刺猬采纳,获得10
7秒前
jiangjiang发布了新的文献求助10
7秒前
宁地啊完成签到 ,获得积分10
8秒前
月亮三分糖完成签到,获得积分10
8秒前
8秒前
wjx关闭了wjx文献求助
8秒前
9秒前
烟花应助威武鸵鸟采纳,获得10
9秒前
张狗蛋完成签到,获得积分20
9秒前
9秒前
小宝发布了新的文献求助10
9秒前
try关注了科研通微信公众号
9秒前
10秒前
10秒前
10秒前
欣妹儿完成签到,获得积分10
10秒前
倪满分完成签到,获得积分10
10秒前
青争发布了新的文献求助10
10秒前
11秒前
11秒前
高分求助中
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
Effective Learning and Mental Wellbeing 300
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3974463
求助须知:如何正确求助?哪些是违规求助? 3518823
关于积分的说明 11196212
捐赠科研通 3255008
什么是DOI,文献DOI怎么找? 1797655
邀请新用户注册赠送积分活动 877052
科研通“疑难数据库(出版商)”最低求助积分说明 806130