Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, Shanghai 200032, China; Shanghai Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention, Shanghai 200032, China.
Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, Shanghai 200032, China; Shanghai Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention, Shanghai 200032, China.
Phys Med. 2020 Dec;80:92-100. doi: 10.1016/j.ejmp.2020.10.013. Epub 2020 Nov 1.
This study aims to develop a deep-learning-basedmethod to classify clinically significant (CS) and clinically insignificant (CiS) prostate cancer (PCa) on multiparametric magnetic resonance imaging (mpMRI) automatically, and to select suitable mpMRI sequences for PCa classificationin different anatomic zones.
A multi-input selection network (MISN) is proposed for both PCa classification and theselection of the optimal combination of sequences for PCa classification in a specific zone.MISN is a multi-input/-output classification network consisting of nine branches to process nine input images from the mpMRI data. To improve classification accuracy and reduce model parameters, a pruning strategy is proposed to select a subset of the nine branches of MIST to form two more effective networks for the peripheral zone (PZ) PCa and transition zone (TZ) PCa, which are named as PZN and TZN, respectively. Besides, a new penalized cross-entropy loss function is adopted to train the networks tobalance the classification sensitivity and specificity.
The proposed methods were evaluated on the PROSTATEx challenge dataset and achieved an area under the receiver operator characteristics curve of 0.95, which was much higher than currently published results and ranked first out of more than 1500 entries submitted to the challenge at the time of submission of this paper. For PZ-PCa and TZ-PCa classification, PZN and TZN achieved better performance than MISN.
Higher performance can be achieved by selecting a suitable subset of the mpMRI sequences in PCa classification.
本研究旨在开发一种基于深度学习的方法，自动对多参数磁共振成像（mpMRI）上的临床显著（CS）和临床不显著（CiS）前列腺癌（PCa）进行分类，并为不同解剖区域的 PCa 分类选择合适的 mpMRI 序列。
提出了一种多输入选择网络（MISN），用于 PCa 分类以及在特定区域为 PCa 分类选择最佳序列组合。MISN 是一个多输入/输出分类网络，由九个分支组成，用于处理来自 mpMRI 数据的九个输入图像。为了提高分类准确性并减少模型参数，提出了一种剪枝策略，从 MIST 的九个分支中选择一个子集，以形成两个用于外周区（PZ）PCa 和移行区（TZ）PCa 的更有效的网络，分别命名为 PZN 和 TZN。此外，采用新的惩罚交叉熵损失函数来训练网络，以平衡分类敏感性和特异性。
所提出的方法在 PROSTATEx 挑战数据集上进行了评估，获得了 0.95 的接收器工作特征曲线下面积，明显高于目前发表的结果，在提交本文时提交的 1500 多个参赛作品中排名第一。对于 PZ-PCa 和 TZ-PCa 分类，PZN 和 TZN 比 MISN 具有更好的性能。
通过在 PCa 分类中选择合适的 mpMRI 序列子集，可以获得更高的性能。
