arXiv 2510.111822025-10-13eess.IVcs.AIcs.CV

组织病理学全切片图像中跨多种癌症类型的自动肿瘤分割泛化研究

Generalisation of automatic tumour segmentation in histopathological whole-slide images across multiple cancer types

Institute for Cancer Genetics and Informatics（癌症基因组学与信息学研究所）；Oslo University Hospital（奥斯陆大学医院）；University of Oslo（奥斯陆大学）；Department of Gastrointestinal（胃肠科部）；Institute of Clinical Medicine（临床医学研究所）；Department of Gynaecological Oncology（妇科肿瘤科部）；Amsterdam University Medical Centres（阿姆斯特丹大学医学中心）；Department of Obstetrics and Gynaecology（妇产科部）；Comprehensive Cancer Center Innsbruck（因斯布鲁克综合癌症中心）；Innsbruck Medical University（因斯布鲁克医学院）；Vestre Viken Hospital Trust（维斯特维肯医院信托）；Department of Medical Biology（医学生物学部）；UiT The Arctic University of Norway（挪威北极大学（UiT））；Department of Clinical Pathology（临床病理学部）

Ole-Johan Skrede, Manohar Pradhan, Maria Xepapadakis Isaksen, Tarjei Sveinsgjerd Hveem, Ljiljana Vlatkovic, Arild Nesbakken, Kristina Lindemann, Gunnar B Kriste… 展开作者

Ole-Johan Skrede, Manohar Pradhan, Maria Xepapadakis Isaksen, Tarjei Sveinsgjerd Hveem, Ljiljana Vlatkovic, Arild Nesbakken, Kristina Lindemann, Gunnar B Kristensen, Jenneke Kasius, Alain G Zeimet, Odd Terje Brustugun, Lill-Tove Rasmussen Busund, Elin H Richardsen, Erik Skaaheim Haug, Bjørn Brennhovd, Emma Rewcastle, Melinda Lillesand, Vebjørn Kvikstad, Emiel Janssen, David J Kerr, Knut Liestøl, Fritz Albregtsen, Andreas Kleppe

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本研究开发了适用于组织病理学图像的通用肿瘤分割模型，并在多种癌症类型的外部队列中验证了其优异性能，证明了单一模型实现跨癌症类型通用分割的可行性。

摘要：

深度学习有望通过自动化肿瘤分割等任务来辅助病理学家。本研究旨在开发一个适用于组织病理学图像的通用肿瘤分割模型，并评估其在不同癌症类型中的表现。该模型使用了来自结直肠癌、子宫内膜癌、肺癌或前列腺癌的4000多名患者的20000多张全切片图像进行开发。在包含六种癌症类型、3000多名患者的外部队列中，通过预设分析验证了其性能。探索性分析还纳入了来自The Cancer Genome Atlas的1500多名额外患者。在所有采用整块切除标本的验证队列和The Cancer Genome Atlas队列中，平均Dice系数均超过80%。将通用模型与针对单一癌症类型特化的模型进行比较，未观察到性能下降。结论是，广泛且严格的评估表明，使用单一模型实现跨癌症类型、患者群体、样本制备和切片扫描仪的通用肿瘤分割是可行的。

英文摘要：

Deep learning is expected to aid pathologists by automating tasks such as tumour segmentation. We aimed to develop one universal tumour segmentation model for histopathological images and examine its performance in different cancer types. The model was developed using over 20 000 whole-slide images from over 4 000 patients with colorectal, endometrial, lung, or prostate carcinoma. Performance was validated in pre-planned analyses on external cohorts with over 3 000 patients across six cancer types. Exploratory analyses included over 1 500 additional patients from The Cancer Genome Atlas. Average Dice coefficient was over 80% in all validation cohorts with en bloc resection specimens and in The Cancer Genome Atlas cohorts. No loss of performance was observed when comparing the universal model with models specialised on single cancer types. In conclusion, extensive and rigorous evaluations demonstrate that generic tumour segmentation by a single model is possible across cancer types, patient populations, sample preparations, and slide scanners.

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。