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

Thagaard J, Broeckx G, Page DB, Jahangir CA, Verbandt S, Kos Z, Gupta R, Khiroya R, Abduljabbar K, Acosta Haab G, Acs B, Akturk G, Almeida JS, Alvarado-Cabrero I, Amgad M, Azmoudeh-Ardalan F, Badve S, Baharun NB, Balslev E, Bellolio ER, Bheemaraju V, Blenman KR, Botinelly Mendonça Fujimoto L, Bouchmaa N, Burgues O, Chardas A, Chon U Cheang M, Ciompi F, Cooper LA, Coosemans A, Corredor G, Dahl AB, Dantas Portela FL, Deman F, Demaria S, Doré Hansen J, Dudgeon SN, Ebstrup T, Elghazawy M, Fernandez-Martín C, Fox SB, Gallagher WM, Giltnane JM, Gnjatic S, Gonzalez-Ericsson PI, Grigoriadis A, Halama N, Hanna MG, Harbhajanka A, Hart SN, Hartman J, Hauberg S, Hewitt S, Hida AI, Horlings HM, Husain Z, Hytopoulos E, Irshad S, Janssen EA, Kahila M, Kataoka TR, Kawaguchi K, Kharidehal D, Khramtsov AI, Kiraz U, Kirtani P, Kodach LL, Korski K, Kovács A, Laenkholm AV, Lang-Schwarz C, Larsimont D, Lennerz JK, Lerousseau M, Li X, Ly A, Madabhushi A, Maley SK, Manur Narasimhamurthy V, Marks DK, McDonald ES, Mehrotra R, Michiels S, Minhas FuAA, Mittal S, Moore DA, Mushtaq S, Nighat H, Papathomas T, Penault-Llorca F, Perera RD, Pinard CJ, Pinto-Cardenas JC, Pruneri G, Pusztai L, Rahman A, Rajpoot NM, Rapoport BL, Rau TT, Reis-Filho JS, Ribeiro JM, Rimm D, Roslind A, Vincent-Salomon A, Salto-Tellez M, Saltz J, Sayed S, Scott E, Siziopikou KP, Sotiriou C, Stenzinger A, Sughayer MA, Sur D, Fineberg S, Symmans F, Tanaka S, Taxter T, Tejpar S, Teuwen J, Thompson EA, Tramm T, Tran WT, van der Laak J, van Diest PJ, Verghese GE, Viale G, Vieth M, Wahab N, Walter T, Waumans Y, Wen HY, Yang W, Yuan Y, Zin RM, Adams S, Bartlett J, Loibl S, Denkert C, Savas P, Loi S, Salgado R, Specht Stovgaard E (2023)

Publication Language: English

Publication Type: Journal article, Review article

Publication year: 2023

Journal

Book Volume: 260

Pages Range: 498-513

Journal Issue: 5

DOI: 10.1002/path.6155

Abstract

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. © 2023 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

Authors with CRIS profile

Involved external institutions

Kuala Lumpur Hospital Malaysia (MY) New York University (NYU) United States (USA) (US) University of Edinburgh United Kingdom (GB) Philipps-Universität Marburg Germany (DE) Peter MacCallum Cancer Centre Australia (AU) GZA Ziekenhuizen Belgium (BE) Copenhagen University Hospital Denmark (DK) Karolinska Institute Sweden (SE) National Cancer Institute (NCI) United States (USA) (US) Centro Medico Nacional Siglo XXI Mexico (MX) Northwestern University United States (USA) (US) Tehran University of Medical Sciences (TUMS) / دانشگاه علوم پزشکی تهران Iran, Islamic Republic of (IR) Emory University United States (USA) (US) The National University of Malaysia / Universiti Kebangsaan Malaysia (UKM) Malaysia (MY) University of the Frontier / Universidad de La Frontera (UFRO) Chile (CL) Université Mohammed VI Polytechnique (UM6P) Morocco (MA) Radboud University Nijmegen Medical Centre / Radboudumc of voluit Radboud Universitair Medisch Centrum (UMC) Netherlands (NL) Katholieke Universiteit Leuven (KUL) / Catholic University of Leuven Belgium (BE) Technical University of Denmark / Danmarks Tekniske Universitet (DTU) Denmark (DK) Hospital Universitário Getúlio Vargas (HUGV) Brazil (BR) Visiopharm A/S Denmark (DK) Yale University United States (USA) (US) University of Surrey United Kingdom (GB) Polytechnic University of Valencia / Universidad Politécnica de Valencia Spain (ES) The University of Melbourne Australia (AU) University College Dublin (UCD) Ireland (IE) Genentech Inc. United States (USA) (US) Icahn School of Medicine at Mount Sinai United States (USA) (US) King’s College London United Kingdom (GB) Deutsches Krebsforschungszentrum (DKFZ) Germany (DE) Memorial Sloan Kettering Cancer Center United States (USA) (US) Case Western Reserve University United States (USA) (US) Matsuyama Shimin Hospital / 松山市民病院 Japan (JP) Netherlands Cancer Institute - Antoni van Leeuwenhoek Hospital (NKI / NKI-AVL) Netherlands (NL) Praava Health Bangladesh (BD) iRhythm Technologies, Inc. United States (USA) (US) Guy's and St Thomas' (NHS Foundation Trust) United Kingdom (GB) Sahlgrenska University Hospital / Sahlgrenska Universitetssjukhuset Sweden (SE) Sjællands Universitetshospital, Roskilde Denmark (DK) Institut Jules Bordet Belgium (BE) Massachusetts General Hospital United States (USA) (US) Mines ParisTech / École Nationale Supérieure des Mines de Paris (ENSMP) France (FR) Manipal Hospitals India India (IN) University of Pennsylvania (UPenn) United States (USA) (US) ICGA Foundation India (IN) Institut Gustave-Roussy France (FR) University of Warwick United Kingdom (GB) Ziauddin University (ZU) Pakistan (PK) Centre Jean-Perrin (UNICANCER) France (FR) University of Washington United States (USA) (US) University College London (UCL) United Kingdom (GB) All India Institute of Medical Sciences Raipur (AIIMS) / अखिल भारतीय आयुर्विज्ञान संस्थान रायपुर India (IN) Heinrich-Heine-Universität Düsseldorf Germany (DE) Bristol-Myers Squibb United States (USA) (US) Fondazione IRCCS: Istituto Nazionale dei Tumori Italy (IT) Medical Oncology Centre of Rosebank South Africa (ZA) Universitätsklinikum Heidelberg Germany (DE) King Hussein Cancer Center (KHCC) / مركز الحسين للسرطان Jordan (JO) Cardiovascular Research Foundation United States (USA) (US) University of Texas MD Anderson Cancer Center United States (USA) (US) Kyoto University / 京都大学 Kyōto daigaku Japan (JP) Tempus Labs United States (USA) (US) Mayo Clinic Hospital United States (USA) (US) Aarhus University Hospital / Aarhus Universitetshospital Denmark (DK) Sunnybrook Health Sciences Centre Canada (CA) University Medical Centre Utrecht (UMC Utrecht) Netherlands (NL) European Institute of Oncology / Istituto Europeo di Oncologia (IEO) Italy (IT) CellCarta Canada (CA) Fudan University / 复旦大学 China (CN) Institut Curie France (FR) The Institute of Cancer Research (ICR) United Kingdom (GB) State University of New York at Albany (UNY Albany / UAlbany) United States (USA) (US) Aga Khan University (AKU) / آغا خان یونیورسٹی‎ Pakistan (PK) University of British Columbia Canada (CA) Stavanger University Hospital Norway (NO) Iwate Medical University Japan (JP) Narayana Medical College & Hospital India (IN) Ann & Robert H. Lurie Children's Hospital of Chicago United States (USA) (US) Aakash Healthcare Super Speciality Hospital India (IN) F. Hoffmann-La Roche Ltd Switzerland (CH) Georgia Institute of Technology United States (USA) (US) National Surgical Adjuvant Breast and Bowel Project Foundation (NSABP) United States (USA) (US) University of Birmingham United Kingdom (GB) Federal University of Amazonas / Universidade Federal do Amazonas (UFAM) Brazil (BR) Hospital Clínico Universitario de Valencia Spain (ES) Weill Cornell Medicine United States (USA) (US) Vanderbilt University United States (USA) (US) Mayo Clinic United States (USA) (US) Iuliu Hațieganu University of Medicine and Pharmacy / Universitatea de Medicină și Farmacie "Iuliu Hațieganu" (UMF Cluj) Romania (RO) Earle A. Chiles Research Institute at the Robert W. Franz Cancer Center United States (USA) (US) University of London United Kingdom (GB) University College Hospital United Kingdom (GB) Merck & Co., Inc. / Merck Sharp & Dohme Corp (MSD) United States (USA) (US)

How to cite

APA:

Thagaard, J., Broeckx, G., Page, D.B., Jahangir, C.A., Verbandt, S., Kos, Z.,... Specht Stovgaard, E. (2023). Pitfalls in machine learning-based assessment of tumor-infiltrating lymphocytes in breast cancer: a report of the international immuno-oncology biomarker working group. Journal of Pathology, 260(5), 498-513. https://doi.org/10.1002/path.6155

MLA:

Thagaard, Jeppe, et al. "Pitfalls in machine learning-based assessment of tumor-infiltrating lymphocytes in breast cancer: a report of the international immuno-oncology biomarker working group." Journal of Pathology 260.5 (2023): 498-513.

BibTeX: Download