1. Artificial intelligence-guided tissue analysis combined with immune infiltrate assessment predicts stage III colon cancer outcomes in PETACC08 study
- Author
-
S. Nguyen, Quentin Klopfenstein, Oana Cojocarasu, Francis Fein, Mohamed Gasmi, Cynthia Reichling, Pierre-Laurent Puig, Karine Le Malicot, Jean Paul Lagasse, Côme Lepage, Pierre-Luc Etienne, Jean-Marc Gornet, Julien Taieb, Jean-François Emile, Hakim Becheur, Dominique Luet, François Ghiringhelli, André Vanoli, Hervé Perrier, Marie Christine Kaminsky, Valentin Derangère, Centre Régional de Lutte contre le cancer Georges-François Leclerc [Dijon] (UNICANCER/CRLCC-CGFL), and UNICANCER
- Subjects
0301 basic medicine ,Colorectal cancer ,Lymphocyte ,0302 clinical medicine ,Antineoplastic Combined Chemotherapy Protocols ,Medicine ,immunohistopathology ,MESH: Lymphocytes, Tumor-Infiltrating ,biology ,Gastroenterology ,MESH: Neoplasm Staging ,Prognosis ,3. Good health ,MESH: Antineoplastic Combined Chemotherapy Protocols ,medicine.anatomical_structure ,030220 oncology & carcinogenesis ,Colonic Neoplasms ,Stromal cell ,CD3 ,adjuvant treatment ,colorectal cancer ,[SDV.CAN]Life Sciences [q-bio]/Cancer ,Adenocarcinoma ,Disease-Free Survival ,MESH: Prognosis ,03 medical and health sciences ,Lymphocytes, Tumor-Infiltrating ,Immune system ,computerised image analysis ,Stroma ,Artificial Intelligence ,Image Interpretation, Computer-Assisted ,Humans ,MESH: Artificial Intelligence ,Neoplasm Invasiveness ,Pathological ,Neoplasm Staging ,MESH: Colonic Neoplasms ,MESH: Humans ,business.industry ,MESH: Adenocarcinoma ,MESH: Neoplasm Invasiveness ,medicine.disease ,030104 developmental biology ,MESH: Disease-Free Survival ,biology.protein ,Artificial intelligence ,[INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM] ,business ,MESH: Image Interpretation, Computer-Assisted ,CD8 - Abstract
ObjectiveDiagnostic tests, such as Immunoscore, predict prognosis in patients with colon cancer. However, additional prognostic markers could be detected on pathological slides using artificial intelligence tools.DesignWe have developed a software to detect colon tumour, healthy mucosa, stroma and immune cells on CD3 and CD8 stained slides. The lymphocyte density and surface area were quantified automatically in the tumour core (TC) and invasive margin (IM). Using a LASSO algorithm, DGMate (DiGital tuMor pArameTErs), we detected digital parameters within the tumour cells related to patient outcomes.ResultsWithin the dataset of 1018 patients, we observed that a poorer relapse-free survival (RFS) was associated with high IM stromal area (HR 5.65; 95% CI 2.34 to 13.67; pConclusionThese findings suggest that artificial intelligence can potentially improve patient care by assisting pathologists in better defining stage III colon cancer patients’ prognosis.
- Published
- 2020
- Full Text
- View/download PDF