arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.08331eess.IVcs.CVq-bio.QM

数字体积活检芯通过深度学习改进前列腺癌Gleason分级

Digital Volumetric Biopsy Cores Improve Gleason Grading of Prostate Cancer Using Deep Learning

University of California, Los Angeles（加州大学洛杉矶分校）

Ekaterina Redekop, Mara Pleasure, Zichen Wang, Anthony Sisk, Yang Zong, Kimberly Flores, William Speier, Corey W. Arnold

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对现有2D深度学习方法难以分析前列腺癌活检复杂组织结构的问题，研究提出体积芯数据源及形态保持对齐框架，结合改进视频Transformer与ABMIL实现Gleason分级，性能显著优于2D基线。

摘要：

前列腺癌（PCa）是2023年美国男性中最常被诊断出的癌症。活检的组织学分级对诊断至关重要，目前已开发出多种基于深度学习的解决方案来辅助这项任务。现有深度学习框架通常应用于从3D活检组织标本中切取的单个2D横截面。这一过程阻碍了对腺体等复杂组织结构的分析，而这类结构的形态会因所检查的组织切片不同而发生变化。我们提出了一种名为“volumetric core（体积芯）”的新型数字病理数据源，它通过一种新型的形态保持对齐框架对连续切片的组织切片进行提取和共对齐得到。我们在从体积块中提取的深度特征上训练了基于注意力的多实例学习（ABMIL）框架，以自动对Gleason Grade Group（GGG，Gleason分级组）进行分类。为处理体积块，我们使用了一种改进的视频Transformer，其搭配的深度特征提取器通过自监督学习进行了预训练。我们运行形态保持对齐框架构建了10210个体积芯，留出30%用于预训练。其余数据集用于训练ABMIL，最终在全部五个GGG上的平均宏平均AUC为0.958、F1得分为0.671、精确率为0.661、召回率为0.695，性能显著优于2D基线模型。

英文摘要：

Prostate cancer (PCa) was the most frequently diagnosed cancer among American men in 2023. The histological grading of biopsies is essential for diagnosis, and various deep learning-based solutions have been developed to assist with this task. Existing deep learning frameworks are typically applied to individual 2D cross-sections sliced from 3D biopsy tissue specimens. This process impedes the analysis of complex tissue structures such as glands, which can vary depending on the tissue slice examined. We propose a novel digital pathology data source called a "volumetric core," obtained via the extraction and co-alignment of serially sectioned tissue sections using a novel morphology-preserving alignment framework. We trained an attention-based multiple-instance learning (ABMIL) framework on deep features extracted from volumetric patches to automatically classify the Gleason Grade Group (GGG). To handle volumetric patches, we used a modified video transformer with a deep feature extractor pretrained using self-supervised learning. We ran our morphology-preserving alignment framework to construct 10,210 volumetric cores, leaving out 30% for pretraining. The rest of the dataset was used to train ABMIL, which resulted in a 0.958 macro-average AUC, 0.671 F1 score, 0.661 precision, and 0.695 recall averaged across all five GGG significantly outperforming the 2D baselines.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑