TY  - JOUR
AU  - Thagaard, Jeppe
AU  - Broeckx, Glenn
AU  - Page, David B
AU  - Jahangir, Chowdhury Arif
AU  - Verbandt, Sara
AU  - Kos, Zuzana
AU  - Gupta, Rajarsi
AU  - Khiroya, Reena
AU  - Abduljabbar, Khalid
AU  - Acosta Haab, Gabriela
AU  - Acs, Balazs
AU  - Akturk, Guray
AU  - Almeida, Jonas S
AU  - Alvarado-Cabrero, Isabel
AU  - Amgad, Mohamed
AU  - Azmoudeh-Ardalan, Farid
AU  - Badve, Sunil
AU  - Baharun, Nurkhairul Bariyah
AU  - Balslev, Eva
AU  - Bellolio, Enrique R
AU  - Bheemaraju, Vydehi
AU  - Blenman, Kim Rm
AU  - Botinelly Mendonça Fujimoto, Luciana
AU  - Bouchmaa, Najat
AU  - Burgues, Octavio
AU  - Chardas, Alexandros
AU  - Chon U Cheang, Maggie
AU  - Ciompi, Francesco
AU  - Cooper, Lee Ad
AU  - Coosemans, An
AU  - Corredor, Germán
AU  - Dahl, Anders B
AU  - Dantas Portela, Flavio Luis
AU  - Deman, Frederik
AU  - Demaria, Sandra
AU  - Doré Hansen, Johan
AU  - Dudgeon, Sarah N
AU  - Ebstrup, Thomas
AU  - Elghazawy, Mahmoud
AU  - Fernandez-Martín, Claudio
AU  - Fox, Stephen B
AU  - Gallagher, William M
AU  - Giltnane, Jennifer M
AU  - Gnjatic, Sacha
AU  - Gonzalez-Ericsson, Paula I
AU  - Grigoriadis, Anita
AU  - Halama, Niels
AU  - Hanna, Matthew G
AU  - Harbhajanka, Aparna
AU  - Hart, Steven N
AU  - Hartman, Johan
AU  - Hauberg, Søren
AU  - Hewitt, Stephen
AU  - Hida, Akira I
AU  - Horlings, Hugo M
AU  - Husain, Zaheed
AU  - Hytopoulos, Evangelos
AU  - Irshad, Sheeba
AU  - Janssen, Emiel Am
AU  - Kahila, Mohamed
AU  - Kataoka, Tatsuki R
AU  - Kawaguchi, Kosuke
AU  - Kharidehal, Durga
AU  - Khramtsov, Andrey I
AU  - Kiraz, Umay
AU  - Kirtani, Pawan
AU  - Kodach, Liudmila L
AU  - Korski, Konstanty
AU  - Kovács, Anikó
AU  - Laenkholm, Anne-Vibeke
AU  - Lang-Schwarz, Corinna
AU  - Larsimont, Denis
AU  - Lennerz, Jochen K
AU  - Lerousseau, Marvin
AU  - Li, Xiaoxian
AU  - Ly, Amy
AU  - Madabhushi, Anant
AU  - Maley, Sai K
AU  - Manur Narasimhamurthy, Vidya
AU  - Marks, Douglas K
AU  - McDonald, Elizabeth S
AU  - Mehrotra, Ravi
AU  - Michiels, Stefan
AU  - Minhas, Fayyaz Ul Amir Afsar
AU  - Mittal, Shachi
AU  - Moore, David A
AU  - Mushtaq, Shamim
AU  - Nighat, Hussain
AU  - Papathomas, Thomas
AU  - Penault-Llorca, Frederique
AU  - Perera, Rashindrie D
AU  - Pinard, Christopher J
AU  - Pinto-Cardenas, Juan Carlos
AU  - Pruneri, Giancarlo
AU  - Pusztai, Lajos
AU  - Rahman, Arman
AU  - Rajpoot, Nasir Mahmood
AU  - Rapoport, Bernardo Leon
AU  - Rau, Tilman T
AU  - Reis-Filho, Jorge S
AU  - Ribeiro, Joana M
AU  - Rimm, David
AU  - Roslind, Anne
AU  - Vincent-Salomon, Anne
AU  - Salto-Tellez, Manuel
AU  - Saltz, Joel
AU  - Sayed, Shahin
AU  - Scott, Ely
AU  - Siziopikou, Kalliopi P
AU  - Sotiriou, Christos
AU  - Stenzinger, Albrecht
AU  - Sughayer, Maher A
AU  - Sur, Daniel
AU  - Fineberg, Susan
AU  - Symmans, Fraser
AU  - Tanaka, Sunao
AU  - Taxter, Timothy
AU  - Tejpar, Sabine
AU  - Teuwen, Jonas
AU  - Thompson, E Aubrey
AU  - Tramm, Trine
AU  - Tran, William T
AU  - van der Laak, Jeroen
AU  - van Diest, Paul J
AU  - Verghese, Gregory E
AU  - Viale, Giuseppe
AU  - Vieth, Michael
AU  - Wahab, Noorul
AU  - Walter, Thomas
AU  - Waumans, Yannick
AU  - Wen, Hannah Y
AU  - Yang, Wentao
AU  - Yuan, Yinyin
AU  - Zin, Reena Md
AU  - Adams, Sylvia
AU  - Bartlett, John
AU  - Loibl, Sibylle
AU  - Denkert, Carsten
AU  - Savas, Peter
AU  - Loi, Sherene
AU  - Salgado, Roberto
AU  - Specht Stovgaard, Elisabeth
TI  - Pitfalls in machine learning-based assessment of tumor-infiltrating lymphocytes in breast cancer: a report of the international immuno-oncology biomarker working group.
JO  - The journal of pathology
VL  - 260
IS  - 5
SN  - 0368-3494
CY  - Bognor Regis [u.a.]
PB  - Wiley
M1  - DKFZ-2023-01701
SP  - 498-513
PY  - 2023
N1  - 2023 Aug;260(5):498-513
AB  - 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 </td><td width="150">
AB  -  Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.
KW  - deep learning (Other)
KW  - digital pathology (Other)
KW  - guidelines (Other)
KW  - image analysis (Other)
KW  - machine learning (Other)
KW  - pitfalls (Other)
KW  - prognostic biomarker (Other)
KW  - triple-negative breast cancer (Other)
KW  - tumor-infiltrating lymphocytes (Other)
LB  - PUB:(DE-HGF)16
C6  - pmid:37608772
DO  - DOI:10.1002/path.6155
UR  - https://inrepo02.dkfz.de/record/278730
ER  -