Xu Yibo, Wang Rongjiang, Fang Zhihai, Tang Jianer
The Department of Urology, The First Affiliated Hospital of Huzhou Normal College, Huzhou, 31300, Zhejiang Province, China.
Huzhou Key Laboratory of Precise Diagnosis and Treatment of Urinary Tumors, Huzhou, 313000, Zhejiang Province, China.
Sci Rep. 2025 Mar 27;15(1):10530. doi: 10.1038/s41598-024-84516-8.
Distinguishing between benign and malignant prostate lesions in magnetic resonance imaging (MRI) poses challenges that affect prostate cancer screening accuracy. We propose a novel computer-aided diagnosis (CAD) system to extract cancerous lesions from the prostate in multi-parametric MRI (mp-MRI), assessing the feasibility of using artificial intelligence for detecting clinically significant prostate cancer (PCa). A retrospective study was conducted on 106 patients who underwent mp-MRI from 2021 to 2024 at a single center. We analyzed three sequences (T2W, DCE, and DWI) and collected 137 mp-MRI images corresponding to pathological sections. From these, we obtained 274 sets of ROI data, using 206 for training and validation, and 68 for testing. A feature extractor was developed using a pre-trained ResNet50 model combined with a multi-head attention mechanism to fuse modality-specific features and perform classification. The experimental results indicate that our model demonstrates high classification performance, achieving an AUC of 0.89. The PR curve shows high precision across most recall values, with an AUC of 0.91. We developed a novel CAD system based on deep learning ResNet50 models to assess the risk of prostate malignancy in mpMRI images. High classification ability is achieved, and combining the attention mechanism or optimization strategy can improve the performance of the model in medical imaging.
在磁共振成像（MRI）中区分前列腺良性和恶性病变存在挑战，这会影响前列腺癌筛查的准确性。我们提出了一种新型计算机辅助诊断（CAD）系统，用于在多参数MRI（mp-MRI）中从前列腺提取癌性病变，评估使用人工智能检测具有临床意义的前列腺癌（PCa）的可行性。对2021年至2024年在单一中心接受mp-MRI检查的106例患者进行了回顾性研究。我们分析了三个序列（T2W、DCE和DWI），并收集了与病理切片对应的137幅mp-MRI图像。从中，我们获得了274组感兴趣区域（ROI）数据，其中206组用于训练和验证，68组用于测试。使用预训练的ResNet50模型结合多头注意力机制开发了一个特征提取器，以融合特定模态特征并进行分类。实验结果表明，我们的模型具有较高的分类性能，曲线下面积（AUC）达到0.89。精确率-召回率（PR）曲线显示在大多数召回值下具有较高的精确率，AUC为0.91。我们基于深度学习ResNet50模型开发了一种新型CAD系统，以评估mpMRI图像中前列腺恶性肿瘤的风险。实现了较高的分类能力，并且结合注意力机制或优化策略可以提高模型在医学成像中的性能。
