Repositorio UFRO · Omeka S

Pitfalls in machine learning-based assessment of tumor-infiltrating lymphocytes in breast cancer: a report of the international immuno-oncology biomarker working group

Primer Autor	Stovgaard, Elisabeth Specht
Co-autores	Thagaard, Jeppe Broeckx, Glenn Page, David B. Jahangir, Chowdhury Arif Verbandt, Sara Kos, Zuzana Gupta, Rajarsi Khiroya, Reena Abduljabbar, Khalid Acosta Haab, Gabriela Acs, Balazs Akturk, Guray Almeida, Jonas S. Alvarado-Cabrero, Isabel Amgad, Mohamed Azmoudeh-Ardalan, Farid Badve, Sunil Baharun, Nurkhairul Bariyah Balslev, Eva Bellolio, Enrique R. Bheemaraju, Vydehi Blenman, Kim R. M. Botinelly Mendonca Fujimoto, Luciana Bouchmaa, Najat Burgues, Octavio Chardas, Alexandros Cheang, Maggie U. Ciompi, Francesco Cooper, Lee A. D. Coosemans, An Corredor, German Dahl, Anders B. Dantas Portela, Flavio Luis Deman, Frederik Demaria, Sandra Dore Hansen, Johan Dudgeon, Sarah N. Ebstrup, Thomas Elghazawy, Mahmoud Fernandez-Martin, Claudio Fox, Stephen B. Gallagher, William M. Giltnane, Jennifer M. Gnjatic, Sacha Gonzalez-Ericsson, Paula, I Grigoriadis, Anita Halama, Niels Hanna, Matthew G. Harbhajanka, Aparna Hart, Steven N. Hartman, Johan Hauberg, Soren Hewitt, Stephen Hida, Akira, I Horlings, Hugo M. Husain, Zaheed Hytopoulos, Evangelos Irshad, Sheeba Janssen, Emiel A. M. Kahila, Mohamed Kataoka, Tatsuki R. Kawaguchi, Kosuke Kharidehal, Durga Khramtsov, Andrey, I Kiraz, Umay Kirtani, Pawan Kodach, Liudmila L. Korski, Konstanty Kovacs, Aniko Laenkholm, Anne-Vibeke Lang-Schwarz, Corinna Larsimont, Denis Lennerz, Jochen K. Lerousseau, Marvin Li, Xiaoxian Ly, Amy Madabhushi, Anant Maley, Sai K. Manur Narasimhamurthy, Vidya Marks, Douglas K. McDonald, Elizabeth S. Mehrotra, Ravi Michiels, Stefan Minhas, Fayyaz ul Amir Afsar Mittal, Shachi Moore, David A. Mushtaq, Shamim Nighat, Hussain Papathomas, Thomas Salto-Tellez, Manuel Tran, William T.
Título	Pitfalls in machine learning-based assessment of tumor-infiltrating lymphocytes in breast cancer: a report of the international immuno-oncology biomarker working group
Editorial	WILEY
Revista	JOURNAL OF PATHOLOGY
Lenguaje	en
Resumen	The clinical significance of the tumor-immune interaction in breast cancer is now established, and tumor-infiltrating lymphocytes (TILs) have emerged as predictive and prognostic biomarkers for patients with triple-negative (estrogen receptor, progesterone receptor, and HER2-negative) breast cancer and HER2-positive breast cancer. How computational assessments of TILs might complement manual TIL assessment in trial and daily practices is currently debated. Recent efforts to use machine learning (ML) to automatically evaluate TILs have shown promising results. We review state-of-the-art approaches and identify pitfalls and challenges of automated TIL evaluation by studying the root cause of ML discordances in comparison to manual TIL quantification. We categorize our findings into four main topics: (1) technical slide issues, (2) ML and image analysis aspects, (3) data challenges, and (4) validation issues. The main reason for discordant assessments is the inclusion of false-positive areas or cells identified by performance on certain tissue patterns or design choices in the computational implementation. To aid the adoption of ML for TIL assessment, we provide an in-depth discussion of ML and image analysis, including validation issues that need to be considered before reliable computational reporting of TILs can be incorporated into the trial and routine clinical management of patients with triple-negative breast cancer. & COPY, 2023 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.
Fecha Publicación	2023
Tipo de Recurso	artículo de revisión
doi	10.1002/path.6155
Formato Recurso	PDF
Palabras Claves	deep learning machine learning digital pathology guidelines image analysis pitfalls prognostic biomarker triple-negative breast cancer tumor-infiltrating lymphocytes
Ubicación del archivo	http://dx.doi.org/10.1002/path.6155
Categoría OCDE	Oncología Patología
Materias	deep learning machine learning patología digital pautas análisis de imagen trampas biomarcador pronóstico cáncer de mama triple negativo linfocitos infiltrantes de tumores
Página de inicio (Recomendado-único)	498.0
Página final (Recomendado-único)	513
Identificador del recurso (Mandatado-único)	artículo de revisión
Versión del recurso (Recomendado-único)	versión publicada
License	CC BY-NC 4.0
Condición de la licencia (Recomendado-repetible)	CC BY-NC 4.0
Derechos de acceso	acceso abierto
Access Rights	acceso abierto
Id de Web of Science	WOS:001053491400001
ISSN	0022-3417
Tipo de ruta	Verde# hibrida
Categoría WOS	Oncología Patología