Article Text

Download PDFPDF

Original article
Artificial intelligence-guided tissue analysis combined with immune infiltrate assessment predicts stage III colon cancer outcomes in PETACC08 study
  1. Cynthia Reichling1,
  2. Julien Taieb2,
  3. Valentin Derangere3,
  4. Quentin Klopfenstein3,
  5. Karine Le Malicot4,
  6. Jean-Marc Gornet5,
  7. Hakim Becheur6,
  8. Francis Fein7,
  9. Oana Cojocarasu8,
  10. Marie Christine Kaminsky9,
  11. Jean Paul Lagasse10,
  12. Dominique Luet11,
  13. Suzanne Nguyen12,
  14. Pierre-Luc Etienne13,
  15. Mohamed Gasmi14,
  16. Andre Vanoli15,
  17. Hervé Perrier16,
  18. Pierre-Laurent Puig17,
  19. Jean-François Emile18,
  20. Come Lepage1,
  21. François Ghiringhelli19
  1. 1Département d'hépato-gastroentérologie et en oncologie digestive, Hôpital du Bocage, Dijon, Bourgogne-Franche-Comté, France
  2. 2Service d'hépato-gastroentérologie, Hopital Europeen Georges Pompidou, Paris, France
  3. 3Plateforme de recherche biologique en oncologie, Georges-Francois Leclerc Centre, Dijon, Bourgogne-Franche-Comté, France
  4. 4Fédération Francophone de Cancérologie Digestive, Hôpital du Bocage, Dijon, Bourgogne-Franche-Comté, France
  5. 5Département d'hépato-gastroentérologie, Hospital Saint-Louis, Paris, Île-de-France, France
  6. 6Département d'hépato-gastroentérologie, Hôpital Bichat Claude-Bernard, Paris, Île-de-France, France
  7. 7Département d'hépato-gastroentérologie, CHU Besancon, Besancon, France
  8. 8Département d'onco-hématologie, Le Mans Universite, Le Mans, Pays de la Loire, France
  9. 9Département d'oncologie médicale, Institut de Cancérologie de Lorraine, Vandoeuvre-les-Nancy, Lorraine, France
  10. 10Département d'hépato-gastroentérologie et en oncologie digestive, Orleans University, Orleans, France
  11. 11Département d'hépato-gastroentérologie et en oncologie digestive, CHU Angers, Angers, Pays de la Loire, France
  12. 12Service d'Oncologie Médicale, CH Pau, Pau, Aquitaine-Limousin-Poitou, France
  13. 13Service d'Oncologie Médicale, Hospital Centre Saint Brieuc, Saint Brieuc, Bretagne, France
  14. 14Département d'hépato-gastroentérologie, Assistance Publique Hopitaux de Marseille, Marseille, Provence-Alpes-Côte d'Azu, France
  15. 15Département d'oncologie médicale, Clinique Sainte Marthe, Dijon, Bourgogne, France
  16. 16service d'oncologie, Hopital Saint Joseph, Marseille, Provence-Alpes-Côte d'Azu, France
  17. 17pole biologie, Hospital European George Pompidou, Paris, Île-de-France, France
  18. 18EA4340, Ambroise Pare Hospital, Beuvry, Hauts-de-France, France
  19. 19Département d'oncologie médicale, Georges-Francois Leclerc Centre, Dijon, Bourgogne-Franche-Comté, France
  1. Correspondence to Professor François Ghiringhelli, Département d'oncologie médicale, Georges-Francois Leclerc Centre, Dijon 21000, France; fghiringhelli{at}cgfl.fr

Abstract

Objective Diagnostic 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.

Design We 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.

Results Within 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; p<0.0001) and high DGMate (HR 2.72; 95% CI 1.92 to 3.85; p<0.001). Higher CD3+ TC, CD3+ IM and CD8+ TC densities were significantly associated with a longer RFS. Analysis of variance showed that CD3+ TC yielded a similar prognostic value to the classical CD3/CD8 Immunoscore (p=0.44). A combination of the IM stromal area, DGMate and CD3, designated ‘DGMuneS’, outperformed Immunoscore when used in estimating patients’ prognosis (C-index=0.601 vs 0.578, p=0.04) and was independently associated with patient outcomes following Cox multivariate analysis. A predictive nomogram based on DGMuneS and clinical variables identified a group of patients with less than 10% relapse risk and another group with a 50% relapse risk.

Conclusion These findings suggest that artificial intelligence can potentially improve patient care by assisting pathologists in better defining stage III colon cancer patients’ prognosis.

  • colorectal cancer
  • adjuvant treatment
  • immunohistopathology
  • computerised image analysis

This is an open access article distributed in accordance with the Creative Commons Attribution Non Commercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited, appropriate credit is given, any changes made indicated, and the use is non-commercial. See: http://creativecommons.org/licenses/by-nc/4.0/.

View Full Text

Statistics from Altmetric.com

Footnotes

  • Contributors FG designed the study, interpreted data and wrote the manuscript. CR conducted the majority of the experiments. QK generates the R software and perform statistical analysis. VD generates the groovy software. VD and CR perform histological slide analysis. JT and CL are clinical researchers who coordinate PETACC08 study. JFE collect and store all tissue sample, provide unstained slide for CD8 labelling and perform CD3 labelling. P-LP makes all molecular analysis (RAS, BRAF, MMR determination), KLM performed statistical analysis of PETACC08 and provided clinical database. J-MG, HB, FF, OC, MCK, JPL, DL, SN, P-LE, MG, AV, HP, JT, CL and FG are main clinical investigators of this study.

  • Funding This work was supported by Ligue National Contre le Cancer (Labelisation F. Ghiringhellli).

  • Competing interests JPL served on external advisory board or Sanofi Avantis France; received fee for travel from Ipsen, Novartis, Amgen, Roche; received fee for communication from Novartis and funding for research was provided by Merck Serono, Roche and MSD. DL received fee for travel from Merck Serono and Amgen. CL receives speakers bureau honoraria from Amgen, Novartis and Bayer and is a consultant/advisory board member for Novartis and Halio-DX. P-LP is a consultant/advisory board member for Merck Serono, Amgen, Boerhinger Ingelheim, Biocartis, Roche, Bristol-Myers Squibb and MSD. JT has received honoraria for speaker or advisory role from Sanofi, Roche, Merck, Amgen, Sirtex, Servier, Lilly, Celgene and MSD. FG served on external advisory boards for Roche. Research funding received from Roche, Genentech, Amgen, Enterome and Servier. Received funding for clinical trial from Astra Zeneca; received fee for communication from Amgen, Astra Zeneca, BMS, Sanofi, Merck-Serono and Servier and received fee for travel from Roche and Servier.

  • Patient consent for publication Not required.

  • Provenance and peer review Not commissioned; externally peer reviewed.

  • Data availability statement Data are available on reasonable request.

Request Permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.