Mehrtash Alireza, Kapur Tina, Tempany Clare M, Abolmaesumi Purang, Wells William M
ECE Department, University of British Columbia, Vancouver, BC.
Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA.
Proc IEEE Int Symp Biomed Imaging. 2021 Apr;2021:443-447. doi: 10.1109/isbi48211.2021.9433892. Epub 2021 May 25.
Prostate cancer is the second most prevalent cancer in men worldwide. Deep neural networks have been successfully applied for prostate cancer diagnosis in magnetic resonance images (MRI). Pathology results from biopsy procedures are often used as ground truth to train such systems. There are several sources of noise in creating ground truth from biopsy data including sampling and registration errors. We propose: 1) A fully convolutional neural network (FCN) to produce cancer probability maps across the whole prostate gland in MRI; 2) A Gaussian weighted loss function to train the FCN with sparse biopsy locations; 3) A probabilistic framework to model biopsy location uncertainty and adjust cancer probability given the deep model predictions. We assess the proposed method on 325 biopsy locations from 203 patients. We observe that the proposed loss improves the area under the receiver operating characteristic curve and the biopsy location adjustment improves the sensitivity of the models.
前列腺癌是全球男性中第二常见的癌症。深度神经网络已成功应用于磁共振成像（MRI）中的前列腺癌诊断。活检程序的病理结果常被用作训练此类系统的基本事实。从活检数据创建基本事实时存在多种噪声来源，包括采样和配准误差。我们提出：1）一种全卷积神经网络（FCN），用于在MRI中生成整个前列腺的癌症概率图；2）一种高斯加权损失函数，用于在活检位置稀疏的情况下训练FCN；3）一个概率框架，用于对活检位置的不确定性进行建模，并根据深度模型预测调整癌症概率。我们在来自203名患者的325个活检位置上评估了所提出的方法。我们观察到，所提出的损失函数提高了受试者操作特征曲线下的面积，活检位置调整提高了模型的灵敏度。
