Original ResearchFull Report: GI CancerQuantitative Pathologic Analysis of Digitized Images of Colorectal Carcinoma Improves Prediction of Recurrence-Free Survival
Graphical abstract
Section snippets
Study Populations
The study population consisted of CRCs from the Colon Cancer Family Registry (CCFR, participating sites: Seattle, Australia, Mayo, Ontario, and Hawaii) as well as 3 sites external to the CCFR: University of Pittsburgh Medical Center (UPMC), Mount Sinai Hospital Toronto, and Seattle-Puget Sound Cancer Registry. The CCFR enrolled participants after CRC diagnosis with prospective follow-up and has been described in detail.28,29 The UPMC and Mount Sinai cohorts consisted of consecutively resected
QuantCRC Is Significantly Associated With Tumor Stage, Tumor Location, and Histologic Features
QuantCRC was applied to 6468 CRCs (Figure 1). The full cohort details are shown in Supplementary Table 1. Significant differences were seen when QuantCRC results were stratified by TNM stage, tumor location, histologic category, tumor grade, venous/lymphatic/perineural invasion (VELIPI), and pathologist-derived TB grade (Table 1 and Supplementary Table 6). Increased tumor stage or presence of VELIPI were associated with decreased tumor:stroma ratio, %inflammatory stroma (both tumor bed and
Discussion
In this study, we applied our previously developed QuantCRC algorithm to 6468 CRCs from multiple centers. QuantCRC results had strong associations with pathologist-derived parameters, molecular features, and prognosis. A prognostic model was developed by combining the output from QuantCRC with MMR status and stage and shown to be prognostic in an external cohort. These results demonstrate the potential of quantitative digital pathology to provide a detailed assessment of known histologic
CRediT Authorship Contributions
Order of Authors (with Contributor Roles):
Reetesh K. Pai, MD (Conceptualization: Supporting; Formal analysis: Supporting; Writing – original draft: Supporting; Writing – review & editing: Supporting).
Imon Banerjee, PhD (Formal analysis: Equal; Methodology: Equal; Writing – original draft: Supporting; Writing – review & editing: Supporting).
Sameer Shivji, MD (Data curation: Supporting; Writing – original draft: Supporting; Writing – review & editing: Supporting).
Suchit Jain, BS (Formal analysis:
References (44)
- et al.
Analysis of tumor microenvironmental features to refine prognosis by T, N risk group in patients with stage III colon cancer (NCCTG N0147) (Alliance)
Ann Oncol
(2020) - et al.
Recommendations for reporting tumor budding in colorectal cancer based on the International Tumor Budding Consensus Conference (ITBCC) 2016
Mod Pathol
(2017) - et al.
The proportion of tumor-stroma as a strong prognosticator for stage II and III colon cancer patients: validation in the VICTOR trial
Ann Oncol
(2013) - et al.
Assessment of individual tumor buds using keratin immunohistochemistry: moderate interobserver agreement suggests a role for machine learning
Mod Pathol
(2020) - et al.
Challenges with colorectal cancer staging: results of an international study
Mod Pathol
(2020) - et al.
Deep learning for prediction of colorectal cancer outcome: a discovery and validation study
Lancet
(2020) - et al.
Deep learning model for the prediction of microsatellite instability in colorectal cancer: a diagnostic study
Lancet Oncol
(2021) - et al.
Clinical-grade detection of microsatellite instability in colorectal tumors by deep learning
Gastroenterology
(2020) - et al.
Development and validation of a weakly supervised deep learning framework to predict the status of molecular pathways and key mutations in colorectal cancer from routine histology images: a retrospective study
Lancet Digit Health
(2021) - et al.
Utility of CD8 score by automated quantitative image analysis in head and neck squamous cell carcinoma
Oral Oncol
(2018)
Association between molecular subtypes of colorectal tumors and patient survival, based on pooled analysis of 7 international studies
Gastroenterology
SATB2 and CDX2 are prognostic biomarkers in DNA mismatch repair protein deficient colon cancer
Mod Pathol
Low somatic K-ras mutation frequency in colorectal cancer diagnosed under the age of 45 years
Eur J Cancer
Objective criteria for crohn-like lymphoid reaction in colorectal cancer
Am J Clin Pathol
The prognostic implications of tumor infiltrating lymphocytes in colorectal cancer: a systematic review and meta-analysis
Sci Rep
Lymphocytic response to tumour and deficient DNA mismatch repair identify subtypes of stage II/III colorectal cancer associated with patient outcomes
Gut
Adjuvant therapy for stage II colon cancer: ASCO Guideline Update
J Clin Oncol
Poorly differentiated clusters in colorectal cancer: a current review and implications for future practice
Histopathology
Prognostic value of poorly differentiated clusters in liver metastatic lesions of colorectal carcinoma
Am J Surg Pathol
Tumour budding is associated with the mesenchymal colon cancer subtype and RAS/RAF mutations: a study of 1320 colorectal cancers with Consensus Molecular Subgroup (CMS) data
Br J Cancer
The carcinoma-stromal ratio of colon carcinoma is an independent factor for survival compared to lymph node status and tumor stage
Cell Oncol
Desmoplastic pattern at the tumor front defines poor-prognosis subtypes of colorectal cancer
Am J Surg Pathol
Cited by (6)
The Evolving Role of Artificial Intelligence in Gastrointestinal Histopathology: An Update
2024, Clinical Gastroenterology and HepatologyEnd-to-end prognostication in colorectal cancer by deep learning: a retrospective, multicentre study
2024, The Lancet Digital HealthDeep Learning and Colon Cancer Interpretation: Rise of the Machine
2023, Surgical Pathology ClinicsDeep learning quantification reveals a fundamental prognostic role for ductular reaction in biliary atresia
2023, Hepatology CommunicationsMulti-view Modelling of Longitudinal Health Data for Improved Prognostication of Colorectal Cancer Recurrence
2023, Proceedings of Machine Learning Research
Conflicts of Interest These authors disclose the following: David F. Schaeffer reports honoraria from Alimentiv Inc., Pfizer, Merck, Diaceutics, and Astellas; and stock ownership in Satisfai Health Inc outside of the submitted work. Reetesh K. Pai, Christophe Rosty, Richard Kirsch report consulting income from Alimentiv Inc. outside of the submitted work. Rish K. Pai reports consulting income from Alimentiv Inc., Eli Lilly, AbbVie, Allergan, Genentech, and PathAI outside of the submitted work. Thomas Westerling-Bui is an employee of Aiforia Inc. The remaining authors disclose no conflicts.
Funding The Colon Cancer Family Registry (CCFR, www.coloncfr.org) is supported in part by funding from the National Cancer Institute (NCI), National Institutes of Health (NIH) (award U01 CA167551). Support for case ascertainment was provided in part from the Surveillance, Epidemiology, and End Results (SEER) Program and the following US state cancer registries: AZ, CO, MN, NC, and NH; and by the Victoria Cancer Registry (Australia) and Ontario Cancer Registry (Canada). The content of this article does not necessarily reflect the views or policies of the NCI, NIH, or any of the collaborating centers in the CCFR, nor does mention of trade names, commercial products, or organizations imply endorsement by the US government, any cancer registry, or the CCFR. The CCFR data, including the images created for this study, can be requested at www.coloncfr.org. The University of Pittsburgh Medical Center and Mount Sinai data are available from the authors on reasonable request.
- ∗
Authors share co-first authorship.