| Literature DB >> 33574288 |
Mohamed Amgad1, Elisabeth Specht Stovgaard2, Eva Balslev2, Jeppe Thagaard3,4, Weijie Chen5, Sarah Dudgeon5, Ashish Sharma1, Jennifer K Kerner6, Carsten Denkert7,8,9, Yinyin Yuan10,11, Khalid AbdulJabbar10,11, Stephan Wienert7, Peter Savas12,13, Leonie Voorwerk14, Andrew H Beck6, Anant Madabhushi15,16, Johan Hartman17, Manu M Sebastian18, Hugo M Horlings19, Jan Hudeček20, Francesco Ciompi21, David A Moore22, Rajendra Singh23, Elvire Roblin24, Marcelo Luiz Balancin25, Marie-Christine Mathieu26, Jochen K Lennerz27, Pawan Kirtani28, I-Chun Chen29, Jeremy P Braybrooke30,31, Giancarlo Pruneri32, Sandra Demaria33, Sylvia Adams34, Stuart J Schnitt35, Sunil R Lakhani36, Federico Rojo37,38, Laura Comerma37,38, Sunil S Badve39, Mehrnoush Khojasteh40, W Fraser Symmans41, Christos Sotiriou42,43, Paula Gonzalez-Ericsson44, Katherine L Pogue-Geile45, Rim S Kim45, David L Rimm46, Giuseppe Viale47, Stephen M Hewitt48, John M S Bartlett49,50, Frédérique Penault-Llorca51,52, Shom Goel53, Huang-Chun Lien54, Sibylle Loibl55, Zuzana Kos56, Sherene Loi13,57, Matthew G Hanna58, Stefan Michiels59,60, Marleen Kok61,62, Torsten O Nielsen63, Alexander J Lazar41,64,65,66, Zsuzsanna Bago-Horvath67, Loes F S Kooreman68,69, Jeroen A W M van der Laak21,70, Joel Saltz71, Brandon D Gallas5, Uday Kurkure40, Michael Barnes72, Roberto Salgado73,74, Lee A D Cooper75.
Abstract
Assessment of tumor-infiltrating lymphocytes (TILs) is increasingly recognized as an integral part of the prognostic workflow in triple-negative (TNBC) and HER2-positive breast cancer, as well as many other solid tumors. This recognition has come about thanks to standardized visual reporting guidelines, which helped to reduce inter-reader variability. Now, there are ripe opportunities to employ computational methods that extract spatio-morphologic predictive features, enabling computer-aided diagnostics. We detail the benefits of computational TILs assessment, the readiness of TILs scoring for computational assessment, and outline considerations for overcoming key barriers to clinical translation in this arena. Specifically, we discuss: 1. ensuring computational workflows closely capture visual guidelines and standards; 2. challenges and thoughts standards for assessment of algorithms including training, preanalytical, analytical, and clinical validation; 3. perspectives on how to realize the potential of machine learning models and to overcome the perceptual and practical limits of visual scoring.Year: 2020 PMID： 33574288 DOI： 10.1038/s41523-020-0154-2
Source DB: PubMed Journal: NPJ Breast Cancer ISSN： 2374-4677