Medmain Research, Medmain Inc., 2-4-5-104, Akasaka, Chuo-ku, Fukuoka, 810-0042, Japan.
Department of Pathology, Tochigi Cancer Center, 4-9-13 Yohnan, Utsunomiya, 320-0834, Japan.
BMC Cancer. 2023 Jan 5;23(1):11. doi: 10.1186/s12885-022-10488-5.
Prostate cancer is often a slowly progressive indolent disease. Unnecessary treatments from overdiagnosis are a significant concern, particularly low-grade disease. Active surveillance has being considered as a risk management strategy to avoid potential side effects by unnecessary radical treatment. In 2016, American Society of Clinical Oncology (ASCO) endorsed the Cancer Care Ontario (CCO) Clinical Practice Guideline on active surveillance for the management of localized prostate cancer.
Based on this guideline, we developed a deep learning model to classify prostate adenocarcinoma into indolent (applicable for active surveillance) and aggressive (necessary for definitive therapy) on core needle biopsy whole slide images (WSIs). In this study, we trained deep learning models using a combination of transfer, weakly supervised, and fully supervised learning approaches using a dataset of core needle biopsy WSIs (n=1300). In addition, we performed an inter-rater reliability evaluation on the WSI classification.
We evaluated the models on a test set (n=645), achieving ROC-AUCs of 0.846 for indolent and 0.980 for aggressive. The inter-rater reliability evaluation showed s-scores in the range of 0.10 to 0.95, with the lowest being on the WSIs with both indolent and aggressive classification by the model, and the highest on benign WSIs.
The results demonstrate the promising potential of deployment in a practical prostate adenocarcinoma histopathological diagnostic workflow system.
前列腺癌通常是一种进展缓慢、惰性的疾病。过度诊断导致的不必要治疗是一个严重的问题，尤其是对于低级别疾病。主动监测被认为是一种风险管理策略，可以避免不必要的根治性治疗带来的潜在副作用。2016 年，美国临床肿瘤学会（ASCO）认可了加拿大安大略癌症护理临床实践指南，该指南推荐主动监测作为局限性前列腺癌管理的一种方法。
基于该指南，我们开发了一种深度学习模型，用于对前列腺腺癌在核心针活检全切片图像（WSI）上进行分类，分为惰性（适用于主动监测）和侵袭性（需要明确的治疗）。在这项研究中，我们使用了包括转移学习、弱监督学习和全监督学习在内的多种学习方法，使用了核心针活检 WSI 数据集（n=1300）对深度学习模型进行了训练。此外，我们还对 WSI 分类进行了组内可靠性评估。
我们在测试集（n=645）上评估了这些模型，得到的惰性和侵袭性的 ROC-AUC 分别为 0.846 和 0.980。组内可靠性评估显示，s 评分范围在 0.10 到 0.95 之间，评分最低的是模型同时对 WSI 进行惰性和侵袭性分类的情况，评分最高的是良性 WSI。
这些结果表明，该模型在实际前列腺腺癌组织病理学诊断工作流程系统中的应用具有广阔的应用前景。
