Deep learning-based artificial intelligence for prostate cancer detection at biparametric MRI.
Deep learning-based artificial intelligence for prostate cancer detection at biparametric MRI.
复制标题
双脂肪MRI上的深度学习的人工智能检测前列腺癌检测。
DOI：
10.1007/s00261-022-03419-2
复制
发表时间：
2022-04
影响因子：
2.4
通讯作者：
Turkbey, Baris
中科院分区：
文献类型：
--
作者：
Mehralivand, Sherif;Yang, Dong;Harmon, Stephanie A.;Xu, Daguang;Xu, Ziyue;Roth, Holger;Masoudi, Samira;Kesani, Deepak;Lay, Nathan;Merino, Maria J.;Wood, Bradford J.;Pinto, Peter A.;Choyke, Peter L.;Turkbey, Baris
介绍用于前列腺MRI的全自动DL前列腺癌检测系统。来自两个机构的MRI扫描用于算法训练、验证、测试。由经验丰富的放射科医生勾画MRI可见病变轮廓。使用MRI-TRUS引导对所有病变进行活检。病变掩模、组织病理学结果被用作基础事实标签来训练用于前列腺癌病变检测、分割的UNet、AH-Net架构。训练算法以检测任何≥ ISUP 1的前列腺癌。检测灵敏度、阳性预测值、每例患者的假阳性病变平均数用作性能指标。纳入525例患者进行算法的培训、验证和测试。数据集分为训练（n = 368，70%）、验证（n = 79，15%）和测试（n = 78，15%）队列。AHNet模型的训练集和验证集的Dice系数分别为0.403和0.307，而UNet模型的Dice系数分别为0.372和0.287。在验证集中，UNet模型的检测灵敏度为70.9%，PPV为35.5%，平均假阳性病灶数/患者为1.41（范围0-6），而AHNet模型的检测灵敏度为74.4%，PPV为47.8%，平均假阳性病灶数/患者为0.87（范围0-5）。在测试集中，UNet和AHNet的检测灵敏度分别为72.8%和63.0%，UNet和AHNet模型的平均假阳性病灶数分别为1.90（范围0-7）和1.40（范围0-6）。我们开发了一种基于DL的AI方法，该方法可以在双参数MRI上预测前列腺癌病变，并具有合理的性能指标。虽然假阳性病变调用仍然是人工智能辅助检测算法的一个挑战，但该系统可以被放射科医生用作辅助工具。
To present fully automated DL-based prostate cancer detection system for prostate MRI. MRI scans from two institutions, were used for algorithm training, validation, testing. MRI-visible lesions were contoured by an experienced radiologist. All lesions were biopsied using MRI-TRUS-guidance. Lesions masks, histopatho-logical results were used as ground truth labels to train UNet, AH-Net architectures for prostate cancer lesion detection, segmentation. Algorithm was trained to detect any prostate cancer ≥ ISUP1. Detection sensitivity, positive predictive values, mean number of false positive lesions per patient were used as performance metrics. 525 patients were included for training, validation, testing of the algorithm. Dataset was split into training (n = 368, 70%), validation (n = 79, 15%), test (n = 78, 15%) cohorts. Dice coefficients in training, validation sets were 0.403, 0.307, respectively, for AHNet model compared to 0.372, 0.287, respectively, for UNet model. In validation set, detection sensitivity was 70.9%, PPV was 35.5%, mean number of false positive lesions/patient was 1.41 (range 0–6) for UNet model compared to 74.4% detection sensitivity, 47.8% PPV, mean number of false positive lesions/patient was 0.87 (range 0–5) for AHNet model. In test set, detection sensitivity for UNet was 72.8% compared to 63.0% for AHNet, mean number of false positive lesions/patient was 1.90 (range 0–7), 1.40 (range 0–6) in UNet, AHNet models, respectively. We developed a DL-based AI approach which predicts prostate cancer lesions at biparametric MRI with reason-able performance metrics. While false positive lesion calls remain as a challenge of AI-assisted detection algorithms, this system can be utilized as an adjunct tool by radiologists.
登录
查看更多内容
MR/超声融合引导的活检与超声引导活检的比较，以诊断前列腺癌。
DOI：
10.1001/jama.2014.17942
发表时间：
2015-01-27
期刊：
JAMA
影响因子：
--
作者：
Siddiqui MM;Rais-Bahrami S;Turkbey B;George AK;Rothwax J;Shakir N;Okoro C;Raskolnikov D;Parnes HL;Linehan WM;Merino MJ;Simon RM;Choyke PL;Wood BJ;Pinto PA
通讯作者：
Pinto PA
影响因子：
19.7
作者：
Schelb, Patrick;Kohl, Simon;Bonekamp, David
通讯作者：
Bonekamp, David
影响因子：
4.4
作者：
Clark, Kenneth;Vendt, Bruce;Prior, Fred
通讯作者：
Prior, Fred
影响因子：
5.2
作者：
Syer T;Mehta P;Antonelli M;Mallett S;Atkinson D;Ourselin S;Punwani S
通讯作者：
Punwani S
影响因子：
64.8
作者：
Esteva A;Kuprel B;Novoa RA;Ko J;Swetter SM;Blau HM;Thrun S
通讯作者：
Thrun S