用异常检测辅助分割，提升前列腺癌识别准确率。
Anomaly-Driven Approach for Enhanced Prostate Cancer Segmentation
- 基于双参数MRI生成异常图，引导模型聚焦可疑区域。
- 在外部测试集上平均得分0.618，优于基线模型的0.605。
- 适合医疗影像中数据少、病灶不规则的分割任务。
磁共振成像（MRI）在识别临床显著性前列腺癌（csPCa）中具有重要作用，但自动化方法面临数据不平衡、肿瘤大小不一及标注数据不足等挑战。本文提出异常驱动的U-Net（adU-Net），将双参数MRI序列生成的异常图融入深度学习分割框架，以提升csPCa识别效果。采用固定点GAN重建生成异常图，突出正常组织的偏离区域，指导模型定位潜在癌变区。通过比较不同异常检测方法，评估其与分割流程的融合效果。以平均分数（AUROC与平均精度AP的均值）衡量性能，在外部测试集上adU-Net达到0.618的最高分，优于基线nnU-Net的0.605。结果表明，引入异常检测可增强模型泛化能力与性能，尤其在基于ADC的异常图下表现更优，为自动化csPCa识别提供新路径。
原文摘要 · Abstract (English)
Magnetic Resonance Imaging (MRI) plays an important role in identifying clinically significant prostate cancer (csPCa), yet automated methods face challenges such as data imbalance, variable tumor sizes, and a lack of annotated data. This study introduces Anomaly-Driven U-Net (adU-Net), which incorporates anomaly maps derived from biparametric MRI sequences into a deep learning-based segmentation framework to improve csPCa identification. We conduct a comparative analysis of anomaly detection methods and evaluate the integration of anomaly maps into the segmentation pipeline. Anomaly maps, generated using Fixed-Point GAN reconstruction, highlight deviations from normal prostate tissue, guiding the segmentation model to potential cancerous regions. We compare the performance by using the average score, computed as the mean of the AUROC and Average Precision (AP). On the external test set, adU-Net achieves the best average score of 0.618, outperforming the baseline nnU-Net model (0.605). The results demonstrate that incorporating anomaly detection into segmentation improves generalization and performance, particularly with ADC-based anomaly maps, offering a promising direction for automated csPCa identification.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。