Next-generation lung cancer pathology: Development and validation of diagnostic and prognostic algorithms
Non-small cell lung cancer (NSCLC) is one of the most common malignant tumors. In this study, we develop a clinically useful computational pathology platform for NSCLC that can be a foundation for multiple downstream applications and provide immediate value for patient care optimization and individu...
Saved in:
Published in | Cell reports. Medicine Vol. 5; no. 9; p. 101697 |
---|---|
Main Authors | , , , , , , , , , , , , , , , , , , , |
Format | Journal Article |
Language | English |
Published |
United States
Elsevier Inc
17.09.2024
Elsevier |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Non-small cell lung cancer (NSCLC) is one of the most common malignant tumors. In this study, we develop a clinically useful computational pathology platform for NSCLC that can be a foundation for multiple downstream applications and provide immediate value for patient care optimization and individualization. We train the primary multi-class tissue segmentation algorithm on a substantial, high-quality, manually annotated dataset of whole-slide images with lung adenocarcinoma and squamous cell carcinomas. We investigate two downstream applications. NSCLC subtyping algorithm is trained and validated using a large, multi-institutional (n = 6), multi-scanner (n = 5), international cohort of NSCLC cases (slides/patients 4,097/1,527). Moreover, we develop four AI-derived, fully explainable, quantitative, prognostic parameters (based on tertiary lymphoid structure and necrosis assessment) and validate them for different clinical endpoints. The computational platform enables the high-precision, quantitative analysis of H&E-stained slides. The developed prognostic parameters facilitate robust and independent risk stratification of patients with NSCLC.
[Display omitted]
•AI-based pipeline allows for explainable analysis of histological slides•Accurate non-small cell lung cancer subtyping is possible•Quantitative prognostic parameters provide reliable patient risk stratification•Developed pipeline can be used in numerous downstream clinical applications
Kludt et al. develop an AI-based digital pathology platform for lung cancer. This advanced platform enables the extraction of explainable features from benign and tumor tissue, facilitating the creation of powerful tools for both improved diagnosis and more accurate assessment of lung cancer aggressiveness and patient prognosis. |
---|---|
Bibliography: | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 ObjectType-Undefined-3 |
ISSN: | 2666-3791 2666-3791 |
DOI: | 10.1016/j.xcrm.2024.101697 |