Universität zu Köln

Wang, Yuan, Lami, Kris, Ahmad, Waleed, Schallenberg, Simon, Bychkov, Andrey, Ye, Yuanzi, Jonigk, Danny, Zhu, Xiaoya, Campelos, Sofia, Schultheis, Anne, Heldwein, Matthias ORCID: 0000-0002-2084-795X, Quaas, Alexander ORCID: 0000-0002-3537-6011, Ryska, Ales, Moreira, Andre L., Fukuoka, Junya, Büttner, Reinhard ORCID: 0000-0001-8806-4786 and Tolkach, Yuri ORCID: 0000-0001-5239-2841 (2025). AI Algorithm for Lung Adenocarcinoma Pattern Quantification (PATQUANT): International Validation and Advanced Risk Stratification Superior to Conventional Grading. MedComm, 6 (9). pp. 1-14. Wiley. ISSN 2688-2663

PDF MedComm - 2025 - Wang - AI Algorithm for Lung Adenocarcinoma Pattern Quantification PATQUANT International Validation.pdf Bereitstellung unter der CC-Lizenz: Creative Commons Attribution. Download (6MB)

Abstract

[Artikel-Nr.: e70380] The morphological patterns of lung adenocarcinoma (LUAD) are recognized for their prognostic significance, with ongoing debate regarding the optimal grading strategy. This study aimed to develop a clinical‐grade, fully quantitative, and automated tool for pattern classification/quantification (PATQUANT), to evaluate existing grading strategies, and determine the optimal grading system. PATQUANT was trained on a high‐quality dataset, manually annotated by expert pathologists. Several independent test datasets and 13 expert pathologists were involved in validation. Five large, multinational cohorts of resectable LUAD (patient n = 1120) were analyzed concerning prognostic value. PATQUANT demonstrated excellent pattern segmentation/classification accuracy and outperformed 8 out of 13 pathologists. The prognostic study revealed a distinct prognostic profile for the complex glandular pattern. While all contemporary grading systems had prognostic value, the predominant pattern‐based and simplified IASLC systems were superior. We propose and validate two new, fully explainable grading principles, providing fine‐grained, statistically independent patient risk stratification. We developed a fully automated, robust AI tool for pattern analysis/quantification that surpasses the performance of experienced pathologists. Additionally, we demonstrate the excellent prognostic capabilities of two new grading approaches that outperform traditional grading methods. We make our extensive agreement dataset publicly available to advance the developments in the field.

Item Type:	Article
Creators:	Creators Email ORCID ORCID Put Code Wang, Yuan UNSPECIFIED UNSPECIFIED UNSPECIFIED Lami, Kris UNSPECIFIED UNSPECIFIED UNSPECIFIED Ahmad, Waleed UNSPECIFIED UNSPECIFIED UNSPECIFIED Schallenberg, Simon UNSPECIFIED UNSPECIFIED UNSPECIFIED Bychkov, Andrey UNSPECIFIED UNSPECIFIED UNSPECIFIED Ye, Yuanzi UNSPECIFIED UNSPECIFIED UNSPECIFIED Jonigk, Danny UNSPECIFIED UNSPECIFIED UNSPECIFIED Zhu, Xiaoya UNSPECIFIED UNSPECIFIED UNSPECIFIED Campelos, Sofia UNSPECIFIED UNSPECIFIED UNSPECIFIED Schultheis, Anne UNSPECIFIED UNSPECIFIED UNSPECIFIED Heldwein, Matthias UNSPECIFIED https://orcid.org/0000-0002-2084-795X UNSPECIFIED Quaas, Alexander UNSPECIFIED https://orcid.org/0000-0002-3537-6011 UNSPECIFIED Ryska, Ales UNSPECIFIED UNSPECIFIED UNSPECIFIED Moreira, Andre L. UNSPECIFIED UNSPECIFIED UNSPECIFIED Fukuoka, Junya UNSPECIFIED UNSPECIFIED UNSPECIFIED Büttner, Reinhard UNSPECIFIED https://orcid.org/0000-0001-8806-4786 UNSPECIFIED Tolkach, Yuri UNSPECIFIED https://orcid.org/0000-0001-5239-2841 UNSPECIFIED
URN:	urn:nbn:de:hbz:38-801683
Identification Number:	10.1002/MCO2.70380
Journal or Publication Title:	MedComm
Volume:	6
Number:	9
Page Range:	pp. 1-14
Number of Pages:	14
Date:	8 September 2025
Publisher:	Wiley
ISSN:	2688-2663
Language:	English
Faculty:	Faculty of Medicine
Divisions:	Faculty of Medicine > Chirurgie > Klinik und Poliklinik für Allgemein-, Viszeral-, Thorax- und Transplantationschirurgie Faculty of Medicine > Pathologie und Neuropathologie > Institut für Pathologie
Subjects:	Medical sciences Medicine
Uncontrolled Keywords:	Keywords Language AI ; grading ; lung adenocarcinoma ; lung cancer ; pattern ; PATQUANT English
['eprint_fieldname_oa_funders' not defined]:	Publikationsfonds UzK
Refereed:	Yes
URI:	http://kups.ub.uni-koeln.de/id/eprint/80168