arXiv 2311.054522023-11-09eess.IVcs.CVcs.LG

基于Transformer的口腔上皮不典型增生分割模型

Transformer-based Model for Oral Epithelial Dysplasia Segmentation

University of Warwick（华威大学）；University of Sheffield（谢菲尔德大学）；University of Campinas（坎皮纳斯大学）；Queen’s University Belfast（贝尔法斯特女王大学）；University of Birmingham（伯明翰大学）

Adam J Shephard, Hanya Mahmood, Shan E Ahmed Raza, Anna Luiza Damaceno Araujo, Alan Roger Santos-Silva, Marcio Ajudarte Lopes, Pablo Agustin Vargas, Kris McComb… 展开作者

Adam J Shephard, Hanya Mahmood, Shan E Ahmed Raza, Anna Luiza Damaceno Araujo, Alan Roger Santos-Silva, Marcio Ajudarte Lopes, Pablo Agustin Vargas, Kris McCombe, Stephanie Craig, Jacqueline James, Jill Brooks, Paul Nankivell, Hisham Mehanna, Syed Ali Khurram, Nasir M Rajpoot

备注：: 5 pages, 2 figures, 4 tables

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对口腔上皮不典型增生（OED）分级评估变异性大的问题，提出基于Transformer的分割流程，在多中心数据上取得优异泛化效果，是首个经外部验证的Transformer癌前组织图像分割研究，可助力更早更高效的OED诊断。

摘要：

口腔上皮不典型增生（OED）是针对口腔病变给出的一种癌前组织病理学诊断。OED的分级存在较大的评估者间/评估者内变异性，会导致患者治疗不足或过度。我们开发了一种全新的基于Transformer的流程，用于改进苏木精-伊红（H&E）染色全玻片图像（WSIs）中OED的检测与分割。我们的模型在通过三种不同扫描仪收集的OED病例（n=260）和对照病例（n=105）上训练，并在来自英国和巴西三个外部中心的测试数据（n=78）上验证。内部实验中OED分割的平均F1得分为0.81，在外部测试中略微降至0.71，展现出良好的泛化能力，取得了当前最优结果。这是首项经过外部验证、将Transformer用于癌前组织学图像分割的研究。我们公开可用的模型有望成为全集成流程的第一步，实现更早、更高效的OED诊断，最终改善患者预后。

英文摘要：

Oral epithelial dysplasia (OED) is a premalignant histopathological diagnosis given to lesions of the oral cavity. OED grading is subject to large inter/intra-rater variability, resulting in the under/over-treatment of patients. We developed a new Transformer-based pipeline to improve detection and segmentation of OED in haematoxylin and eosin (H&E) stained whole slide images (WSIs). Our model was trained on OED cases (n = 260) and controls (n = 105) collected using three different scanners, and validated on test data from three external centres in the United Kingdom and Brazil (n = 78). Our internal experiments yield a mean F1-score of 0.81 for OED segmentation, which reduced slightly to 0.71 on external testing, showing good generalisability, and gaining state-of-the-art results. This is the first externally validated study to use Transformers for segmentation in precancerous histology images. Our publicly available model shows great promise to be the first step of a fully-integrated pipeline, allowing earlier and more efficient OED diagnosis, ultimately benefiting patient outcomes.

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。