Mixed Supervision of Histopathology Improves Prostate Cancer Classification From MRI

组织病理学 前列腺癌 前列腺切除术 前列腺 一致性 癌症 磁共振成像 活检 医学 放射科 前列腺活检 病理 内科学
作者
Abhejit Rajagopal,Antonio C. Westphalen,Nathan Velarde,Jeffry Simko,Hao Gia Nguyen,Thomas A. Hope,Peder E. Z. Larson,Kirti A. Magudia
出处
期刊:IEEE Transactions on Medical Imaging [Institute of Electrical and Electronics Engineers]
卷期号:43 (7): 2610-2622 被引量:14
标识
DOI:10.1109/tmi.2024.3382909
摘要

Non-invasive prostate cancer classification from MRI has the potential to revolutionize patient care by providing early detection of clinically significant disease, but has thus far shown limited positive predictive value. To address this, we present a image-based deep learning method to predict clinically significant prostate cancer from screening MRI in patients that subsequently underwent biopsy with results ranging from benign pathology to the highest grade tumors. Specifically, we demonstrate that mixed supervision via diverse histopathological ground truth improves classification performance despite the cost of reduced concordance with image-based segmentation. Where prior approaches have utilized pathology results as ground truth derived from targeted biopsies and whole-mount prostatectomy to strongly supervise the localization of clinically significant cancer, our approach also utilizes weak supervision signals extracted from nontargeted systematic biopsies with regional localization to improve overall performance. Our key innovation is performing regression by distribution rather than simply by value, enabling use of additional pathology findings traditionally ignored by deep learning strategies. We evaluated our model on a dataset of 973 (testing n=198 ) multi-parametric prostate MRI exams collected at UCSF from 2016-2019 followed by MRI/ultrasound fusion (targeted) biopsy and systematic (nontargeted) biopsy of the prostate gland, demonstrating that deep networks trained with mixed supervision of histopathology can feasibly exceed the performance of the Prostate Imaging-Reporting and Data System (PI-RADS) clinical standard for prostate MRI interpretation (71.6% vs 66.7% balanced accuracy and 0.724 vs 0.716 AUC).
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
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
超级无敌的应助被强健的篮球采纳,获得10
刚刚
东都行发布了新的文献求助10
刚刚
1秒前
1秒前
1秒前
1秒前
2秒前
吃西瓜不吐籽完成签到 ,获得积分10
3秒前
elysia发布了新的文献求助10
3秒前
3秒前
六月雪发布了新的文献求助10
4秒前
所所的应助被lzh采纳,获得10
4秒前
林正心完成签到,获得积分10
5秒前
奇思妙想安德鲁完成签到,获得积分10
6秒前
顾矜的应助被热情的乐荷采纳,获得10
7秒前
9202211125完成签到,获得积分10
7秒前
郭夹心发布了新的文献求助10
7秒前
Akim的应助被一期一会采纳,获得10
7秒前
hmh发布了新的文献求助15
7秒前
水煮电吹风的应助被00hello00采纳,获得10
7秒前
8秒前
drfwjuikesv发布了新的文献求助10
8秒前
9秒前
一米阳光发布了新的文献求助10
9秒前
香蕉觅云的应助被Besttin9799采纳,获得30
9秒前
刘白完成签到,获得积分10
9秒前
Tracy发布了新的文献求助10
9秒前
LIUDAN发布了新的文献求助10
10秒前
11秒前
dieeee完成签到,获得积分10
12秒前
TaoJ的应助被ku采纳,获得10
13秒前
平淡的凌寒完成签到,获得积分10
13秒前
温柔发卡发布了新的文献求助10
13秒前
...完成签到,获得积分10
14秒前
哈基米德发布了新的文献求助10
15秒前
朴实的哲瀚完成签到 ,获得积分20
15秒前
展望未来完成签到 ,获得积分10
17秒前
18秒前
18秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8183667
求助须知:如何正确求助?哪些是违规求助? 9572953
关于积分的说明 21828185
捐赠科研通 7780853
什么是DOI,文献DOI怎么找? 3434031
关于科研通互助平台的介绍 2558251
邀请新用户注册赠送积分活动 2480500