偶发性前列腺癌 (iPCa) 是具有临床意义的前列腺癌 (csPCa) 的早期阶段，通常无症状，因此在临床实践中很难检测到。本研究的目的是通过使用深度卷积神经网络 (CNN) 分析前列腺 MRI 来预测 iPCa。虽然基于 CNN 的模型在医学图像分析方面取得了重大进展，但 iPCa 预测任务提出了两个具有挑战性的问题：人眼无法察觉的 MRI 差异更细微，以及发病率较低，导致与常规癌症相比样本不平衡更加明显预言。为了解决这两个挑战，我们提出了一种名为 iPCa-Net 的新的基于 CNN 的框架，该框架旨在联合优化两项任务：前列腺过渡区分割和 iPCa 预测。为了评估我们模型的性能，我们构建了一个前列腺 MRI 数据集，其中包含来自我们机构诊断为良性前列腺增生 (BPH) 的 448 名患者的 9536 个前列腺 MRI 切片。在我们的研究中，iPCa 的发病率为 5.13%（448 例中有 23 例）。我们使用我们的数据集分别将我们的模型与八种最先进的分割任务方法和九种既定的预测任务方法进行比较，实验结果证明了我们模型的优越性能。具体来说，在前列腺过渡区分割任务中，我们的 iPCa-Net 在 mIoU 方面比表现最好的方法高出 1.23%。在 iPCa 预测任务中，我们的 iPCa-Net 在 F1 分数方面超越了表现最好的方法 2.06%。总之，与最先进的方法相比，我们的 iPCa-Net 在 iPCa 患者的早期识别方面表现出卓越的性能。这一进步对于适当的疾病管理具有重要意义，对患者非常有益。版权所有 © 2023 Elsevier Ltd. 保留所有权利。

Incidental prostate cancer (iPCa) is an early stage of clinically significant prostate cancer (csPCa) and is typically asymptomatic, making it difficult to detect in clinical practice. The objective of this study is to predict iPCa by analyzing prostatic MRIs using deep convolutional neural network (CNN). While CNN-based models in medical image analysis have made significant advancements, the iPCa prediction task presents two challenging problems: subtler differences in MRIs that are imperceptible to human eyes and a lower incidence rate, resulting in a more pronounced sample imbalance compared to routine cancer prediction. To address these two challenges, we propose a new CNN-based framework called iPCa-Net, which is designed to jointly optimize two tasks: prostate transition zone segmentation and iPCa prediction. To evaluate the performance of our model, we construct a prostatic MRI dataset comprising 9536 prostate MRI slices from 448 patients diagnosed with benign prostatic hyperplasia (BPH) at our institution. In our study, the incidence rate of iPCa is 5.13% (23 out of 448) . We compare our model with eight state-of-the-art methods for segmentation task and nine established methods for prediction task respectively using our dataset, and experimental results demonstrate the superior performance of our model. Specifically, in the prostate transition zone segmentation task, our iPCa-Net outperforms the top-performing method by 1.23% with respect to mIoU. In the iPCa prediction task, our iPCa-Net surpasses the top-performing method by 2.06% with respect to F1 score. In conclusion, our iPCa-Net demonstrates superior performance in the early identification of iPCa patients compared to state-of-the-art methods. This advancement holds great significance for appropriate disease management and is highly beneficial for patients.Copyright © 2023 Elsevier Ltd. All rights reserved.