文章目录

基于人工智能的ANORAK模型提高了肺腺癌的组织病理学分级

原文发布日期：2024-01-10

英文摘要：

摘要翻译：

原文链接：

文章：

基于人工智能的ANORAK模型提高了肺腺癌的组织病理学分级

The artificial intelligence-based model ANORAK improves histopathological grading of lung adenocarcinoma

原文发布日期：2024-01-10

英文摘要：

The introduction of the International Association for the Study of Lung Cancer grading system has furthered interest in histopathological grading for risk stratification in lung adenocarcinoma. Complex morphology and high intratumoral heterogeneity present challenges to pathologists, prompting the development of artificial intelligence (AI) methods. Here we developed ANORAK (pyrAmid pooliNg crOss stReam Attention networK), encoding multiresolution inputs with an attention mechanism, to delineate growth patterns from hematoxylin and eosin-stained slides. In 1,372 lung adenocarcinomas across four independent cohorts, AI-based grading was prognostic of disease-free survival, and further assisted pathologists by consistently improving prognostication in stage I tumors. Tumors with discrepant patterns between AI and pathologists had notably higher intratumoral heterogeneity. Furthermore, ANORAK facilitates the morphological and spatial assessment of the acinar pattern, capturing acinus variations with pattern transition. Collectively, our AI method enabled the precision quantification and morphology investigation of growth patterns, reflecting intratumoral histological transitions in lung adenocarcinoma.

摘要翻译：

肺癌亚型研究协会引入的分类系统进一步推动了对肺癌高危分层的 histopathological 分类兴趣。复杂的形态学特征和肿瘤内部高度异质性给病理学家带来了挑战，促使开发人工智能（AI）方法。我们在此基础上开发了 ANORAK（pyrAmid pooliNg crOss stReam Attention networK），通过引入注意力机制对多分辨率输入进行编码，以从血红蛋白和 eosin 染色的切片中识别肿瘤生长模式。在四个独立研究组共 1,372 例肺癌亚型病例中，基于人工智能的分类对无进展生存期具有预测价值，并且通过持续提高 ISt 瘵前肿瘤的预判能力，进一步辅助了病理学家。AI 和病理学家之间在某些肿瘤样本中表现出显著分歧，这些差异性肿瘤内部高度异质性明显较高。此外，ANORAK 有助于从形态学和空间上评估气道模式，捕捉气窗结构的变化特征。我们的人工智能方法使生长模式的定量分析和形态研究成为可能，反映了肺癌亚型在组织内 histological 的变化过程。