Institute of Transport and Territory, Universitat Politècnica de València, Valencia, Spain.
Institute of Research and Innovation in Bioengineering, Universitat Politècnica de València, Valencia, Spain.
Comput Med Imaging Graph. 2021 Mar;88:101846. doi: 10.1016/j.compmedimag.2020.101846. Epub 2021 Jan 13.
Prostate cancer is one of the main diseases affecting men worldwide. The Gleason scoring system is the primary diagnostic tool for prostate cancer. This is obtained via the visual analysis of cancerous patterns in prostate biopsies performed by expert pathologists, and the aggregation of the main Gleason grades in a combined score. Computer-aided diagnosis systems allow to reduce the workload of pathologists and increase the objectivity. Nevertheless, those require a large number of labeled samples, with pixel-level annotations performed by expert pathologists, to be developed. Recently, efforts have been made in the literature to develop algorithms aiming the direct estimation of the global Gleason score at biopsy/core level with global labels. However, these algorithms do not cover the accurate localization of the Gleason patterns into the tissue. These location maps are the basis to provide a reliable computer-aided diagnosis system to the experts to be used in clinical practice by pathologists. In this work, we propose a deep-learning-based system able to detect local cancerous patterns in the prostate tissue using only the global-level Gleason score obtained from clinical records during training.
The methodological core of this work is the proposed weakly-supervised-trained convolutional neural network, WeGleNet, based on a multi-class segmentation layer after the feature extraction module, a global-aggregation, and the slicing of the background class for the model loss estimation during training.
Using a public dataset of prostate tissue-micro arrays, we obtained a Cohen's quadratic kappa (κ) of 0.67 for the pixel-level prediction of cancerous patterns in the validation cohort. We compared the model performance for semantic segmentation of Gleason grades with supervised state-of-the-art architectures in the test cohort. We obtained a pixel-level κ of 0.61 and a macro-averaged f1-score of 0.58, at the same level as fully-supervised methods. Regarding the estimation of the core-level Gleason score, we obtained a κ of 0.76 and 0.67 between the model and two different pathologists.
WeGleNet is capable of performing the semantic segmentation of Gleason grades similarly to fully-supervised methods without requiring pixel-level annotations. Moreover, the model reached a performance at the same level as inter-pathologist agreement for the global Gleason scoring of the cores.
前列腺癌是全球男性主要的疾病之一。格里森评分系统是前列腺癌的主要诊断工具。该系统通过对前列腺活检中癌性模式的专家病理学家的视觉分析获得，并通过主要格里森分级的综合评分进行聚合。计算机辅助诊断系统可以减少病理学家的工作量并提高客观性。然而，这些系统需要大量经过标记的样本，并由专家病理学家进行像素级注释。最近，文献中已经在努力开发旨在直接估计活检/核心水平的全局格里森评分的算法，这些算法仅使用全局标签。然而，这些算法并未涵盖对组织内格里森模式的精确定位。这些位置图是为专家提供可靠的计算机辅助诊断系统的基础，以便病理学家在临床实践中使用。在这项工作中，我们提出了一种基于深度学习的系统，该系统仅使用从临床记录中获得的全局格里森评分，即可在前列腺组织中检测局部癌性模式。
这项工作的方法论核心是所提出的弱监督训练卷积神经网络 WeGleNet，它基于特征提取模块后的多分类分割层、全局聚合以及背景类的切片，用于在训练期间进行模型损失估计。
使用公共的前列腺组织微阵列数据集，我们在验证队列中获得了癌症模式像素级预测的科恩二次kappa（κ）为 0.67。我们在测试队列中比较了语义分割格里森分级的模型性能与监督的最先进架构。我们获得了像素级κ为 0.61 和宏平均 f1 分数为 0.58，与完全监督方法的水平相同。关于核心级格里森评分的估计，我们获得了模型与两位不同病理学家之间的κ为 0.76 和 0.67。
WeGleNet 能够执行与完全监督方法相似的格里森分级语义分割，而无需像素级注释。此外，该模型在核心的全局格里森评分方面达到了与病理学家间一致性相同的水平。
