基于深度学习神经网络在前列腺显微超声原始数据上检测前列腺癌
本研究回顾性纳入491例接受前列腺活检的男性，利用显微超声原始数据生成功率谱，开发卷积神经网络PSNet区分良性组织与临床显著前列腺癌，并与传统B模式CNN比较。结果显示，帧水平加入PSA后AUC达85%，患者水平AUC达91%，提示深度学习可捕捉组织声学特性辅助诊断。
要点
- PSNet无需前列腺分割即可从显微超声原始功率谱中识别临床显著前列腺癌。
- 加入PSA可提高特异度，患者水平特异度达0.99（0.98，1.00）。
- 该方法有望辅助实时靶向活检的图像解读。
关键影像表现/征象
- PSNet在未分割的显微超声数据区域上分类良性组织与临床显著前列腺癌。
- 传统CNN基于常规B模式图像训练作为对比。
诊断标准与关键数值
- 帧水平：PSNet不加PSA的ROC-AUC为82%（0.77，0.85），敏感度0.73（0.66，0.80），特异度0.74（0.71，0.77）。
- 帧水平：加入PSA后ROC-AUC升至85%（0.83，0.88），敏感度0.72（0.65，0.79），特异度0.82（0.80，0.84）。
- 患者水平：不加PSA的ROC-AUC为85%（0.77，0.92），敏感度0.74（0.70，0.79），特异度0.88（0.76，0.84）。
- 患者水平：加入PSA后ROC-AUC为91%（0.85，0.97），敏感度0.70（0.65，0.75），特异度0.99（0.98，1.00）。
临床应用与阅片要点
- 阅片时可关注显微超声原始功率谱特征，无需手动分割前列腺。
- 结合PSA可提高分类特异度，减少假阳性。
局限性
- 回顾性研究设计。
- 样本量有限（491例），需进一步验证。
以上解读依据论文摘要（全文未开放获取或许可不允许翻译转载）。
英文原文（摘要）· 点击展开
BACKGROUND: Micro-ultrasound (micro-US) is a clinically available novel high-resolution imaging technology for guiding prostate biopsies. However, clinical image interpretation during live biopsies remains a challenge.
PURPOSE: To develop a convolutional neural network (CNN) to classify prostate tissues as benign versus clinically significant prostate cancer (csPCa) from the power spectrums (PS) derived from raw micro-US, with the eventual goal of developing a tool for automating interpretation during image-guided biopsies.
METHODS: Retrospective Micro-US data were obtained from 491 men (mean age 62 y, SD 8) undergoing prostate biopsy across 5 sites between 2013 and 2016; associated raw data and prostate-specific antigen (PSA) were obtained for each targeted biopsy location and used to obtain spatially mapped PSs. The dataset was split at a patient-level into a train/validation (80%) and a set-aside test set (20%). This includes up to 12 image-frames at distinct prostate locations (total of 6530 single image-frames), each with a corresponding biopsy. No specific prostate tissue segmentation was carried out. A custom CNN named PSNet was developed to classify benign from csPCa in non-segmented regions of micro-US data, and its performance was compared to traditional CNNs trained on associated conventional B-Mode images. Biopsy histopathology served as the clinical standard labels. The area under the receiver operator curve (ROC-AUC) was used to evaluate all models; sensitivity, specificity, precision and the F1 score were also computed; 95% confidence interval is shown in parenthesis.
RESULTS: For frame-level performance, PSNet without PSA achieved an ROC-AUC of 82% (0.77, 0.85), a sensitivity of 0.73 (0.66, 0.80) and a specificity of 0.74 (0.71, 0.77) for classifying benign versus csPCa. After inclusion of PSA, the ROC-AUC increased to 85% (0.83, 0.88), with a sensitivity of 0.72 (0.65, 0.79) and a specificity of 0.82 (0.80, 0.84). For patient-level performance, which was obtained by aggregating image-level predictions, the models without and with PSA achieved patient-level ROC-AUCs of 85% (0.77, 0.92) and 91% (0.85, 0.97), sensitivities of 0.74 (0.70, 0.79) and 0.70 (0.65, 0.75) and specificities of 0.88 (0.76, 0.84) and 0.99 (0.98, 1.00), respectively.
CONCLUSION: In this pilot development study, we suggest that deep learning can capture unique tissue acoustic properties in raw micro-US data to help identify prostate cancer, without the need for segmentation of the prostate gland, and that the diagnostic value of these tissue properties can be augmented by PSA measurements to increase specificity. Our approach may be further leveraged to guide targeted prostate biopsy.
引用
- El Kaffas A, Tiyarattanachai T, Rusu M, et al. Prostate Cancer Detection on Micro-Ultrasound Raw Data Using a Deep Learning Neural Network. Ultrasound Med Biol. 2026. PMID: 42103595. doi:10.1016/j.ultrasmedbio.2026.04.002
供执业医师工作参考，不替代临床判断；数值与分级以指南原文为准。