Electrical and Computer Engineering, University of British Columbia, Vancouver, Canada.
School of Computing, Queen's University, Kingston, Canada.
Int J Comput Assist Radiol Surg. 2024 Jun;19(6):1121-1128. doi: 10.1007/s11548-024-03104-3. Epub 2024 Apr 10.
The standard of care for prostate cancer (PCa) diagnosis is the histopathological analysis of tissue samples obtained via transrectal ultrasound (TRUS) guided biopsy. Models built with deep neural networks (DNNs) hold the potential for direct PCa detection from TRUS, which allows targeted biopsy and subsequently enhances outcomes. Yet, there are ongoing challenges with training robust models, stemming from issues such as noisy labels, out-of-distribution (OOD) data, and limited labeled data.
This study presents LensePro, a unified method that not only excels in label efficiency but also demonstrates robustness against label noise and OOD data. LensePro comprises two key stages: first, self-supervised learning to extract high-quality feature representations from abundant unlabeled TRUS data and, second, label noise-tolerant prototype-based learning to classify the extracted features.
Using data from 124 patients who underwent systematic prostate biopsy, LensePro achieves an AUROC, sensitivity, and specificity of 77.9%, 85.9%, and 57.5%, respectively, for detecting PCa in ultrasound. Our model shows it is effective for detecting OOD data in test time, critical for clinical deployment. Ablation studies demonstrate that each component of our method improves PCa detection by addressing one of the three challenges, reinforcing the benefits of a unified approach.
Through comprehensive experiments, LensePro demonstrates its state-of-the-art performance for TRUS-based PCa detection. Although further research is necessary to confirm its clinical applicability, LensePro marks a notable advancement in enhancing automated computer-aided systems for detecting prostate cancer in ultrasound.
前列腺癌（PCa）诊断的标准护理方法是通过经直肠超声（TRUS）引导活检获取组织样本进行组织病理学分析。基于深度神经网络（DNN）的模型具有从 TRUS 直接检测 PCa 的潜力，这可以实现靶向活检，并随后提高治疗效果。然而，由于标签噪声、离群（OOD）数据和有限的标记数据等问题，训练稳健模型仍然存在挑战。
本研究提出了 LensePro，这是一种不仅在标签效率方面表现出色，而且对标签噪声和 OOD 数据具有鲁棒性的统一方法。LensePro 由两个关键阶段组成：首先，从丰富的未标记 TRUS 数据中进行自我监督学习，以提取高质量的特征表示；其次，进行基于原型的标签噪声容忍学习，以对提取的特征进行分类。
使用来自 124 名接受系统前列腺活检的患者的数据，LensePro 在超声中检测 PCa 的 AUROC、敏感性和特异性分别为 77.9%、85.9%和 57.5%。我们的模型表明，它在测试时对 OOD 数据的检测效果有效，这对于临床部署至关重要。消融研究表明，我们方法的每个组件都通过解决三个挑战中的一个来提高 PCa 检测，从而增强了统一方法的优势。
通过全面的实验，LensePro 展示了其在基于 TRUS 的 PCa 检测方面的最新性能。尽管还需要进一步的研究来确认其临床适用性，但 LensePro 标志着增强用于超声检测前列腺癌的自动计算机辅助系统的显著进展。
