Accès ouvert déclaré
2026
other
Analysis of computational tumor-infiltrating lymphocytes in breast cancer from the results of the TIGER challenge
Mart van Rijthoven, Witali Aswolinskiy, Leslie Tessier, Roberto Salgado, Jeroen A.W. M. Van Der Laak, Francesco Ciompi, Maschenka Balkenhol, Joep Bogaerts, Damien Drubay, Dieter Peeters, Laura Comerma Blesa, Elisabeth Specht Stovgaard, Anne-Vibeke Laenkholm, Harry Haynes, Ligia Craciun, Denis Larsimont, Mohamed Amgad, Lee Cooper, Cyril de Kock, Valerie Dechering, Johannes Lotz, Nick Weiss, Mieke van Bockstal, Christine Galant, Esther H. Lips, Hugo M. Horlings, Jelle Wesseling, Lennart Mulder, Kyungdoc Kim, Chanmin Park, Hyungjoon Jang, Dong-hee Kim, Sungduk Cho, Nasir Mahmood Rajpoot, Mostafa Jahanifar, Shan Raza, Adam Shephard, Anne L. Martel, Vishwesh Ramanathan, Martin Fergie, Richard Byers, Anna Maria Tsakiroglou, Brandon D. Gallas, Nicholas Petrick, Victor L. Garcia, Weijie Chen, Arian Arab, Liliang Chen, Xulin Chen, Jinbo Kuang, Feng Xie, Zheng Ji, Shuoyu Xu, Jeongyeol Kim, Kangwon Byun, Jaehyung Ye, Daehong Lee, Ming Fan, Heikki T. Joensuu, Bram Van Ginneken, James Meakin, Anne Mickan, Miriam Groeneveld, Scott Maurits, Rogier Donders, Stefan Phd Michiels, Julia R. Dixon-Douglas, Sherene Loi, Alexander Lemm, Christoph Russ, Giuseppe Bogina, E. Munari, Carsten Denkert, Paul Jank, Karsten E. Weber, S. Belt, Jeroen van der Laak, Mart van Rijthoven, :unav
0Citations signalées — pas une note de qualité
0Institutions déclarées
0Pays d’affiliation déclarés
Résumé fourni par la source
Tumor-infiltrating lymphocytes (TILs) is a recognized prognostic biomarker in breast cancer. However, poor interobserver agreement and limited reproducibility highlight the need for computational approaches. Despite advances, adoption of computational models has been hindered by lack of standardized methods and robust benchmarks. To address this, we launched TIGER, an international competition to build open-source computational TILs (cTILs) models. Here, we present a multi-centric analysis of cTILs methods on resections and biopsies from 3,708 human epidermal growth factor receptor 2-positive (HER2+) or triple-negative breast cancers (TNBC) from clinical practice and phase 3 trials. We report benchmarks on image analysis performance, show strong agreement of cTILs with pathologists, and demonstrate positive association of cTILs with neoadjuvant therapy response in HER2+, superior to visually scored TILs. We also show that cTILs add independent prognostic information to clinical variables in TNBC resections. Data, methods and benchmarks are publicly available: https://tiger.grand-challenge.org/.
Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.
Contrôle bibliographique ouvert
La source scientifique ouverte est momentanément indisponible.