Ralph Saber, David Henault, Nouredin Messaoudi, Rolando Rebolledo, Emmanuel Montagnon, Geneviève Soucy, John Stagg, An Tang, Simon Turcotte and Samuel Kadoury
Article (2023)
Open Acess document in PolyPublie and at official publisher |
|
Open Access to the full text of this document Published Version Terms of Use: Creative Commons Attribution Download (2MB) |
Abstract
Background
Finding a noninvasive radiomic surrogate of tumor immune features could help identify patients more likely to respond to novel immune checkpoint inhibitors. Particularly, CD73 is an ectonucleotidase that cata- lyzes the breakdown of extracellular AMP into immunosuppressive adenosine, which can be blocked by therapeutic antibodies. High CD73 expression in colorectal cancer liver metastasis (CRLM) resected with curative intent is associ- ated with early recurrence and shorter patient survival. The aim of this study was hence to evaluate whether machine learning analysis of preoperative liver CT-scan could estimate high vs low CD73 expression in CRLM and whether such radiomic score would have a prognostic significance.
Methods
We trained an Attentive Interpretable Tabular Learning (TabNet) model to predict, from preoperative CT images, stratified expression levels of CD73 (CD73High vs. CD73Low ) assessed by immunofluorescence (IF) on tissue microarrays. Radiomic features were extracted from 160 segmented CRLM of 122 patients with matched IF data, preprocessed and used to train the predictive model. We applied a five-fold cross-validation and validated the perfor- mance on a hold-out test set.
Results
TabNet provided areas under the receiver operating characteristic curve of 0.95 (95% CI 0.87 to 1.0) and 0.79 (0.65 to 0.92) on the training and hold-out test sets respectively, and outperformed other machine learning models. The TabNet-derived score, termed rad-CD73, was positively correlated with CD73 histological expression in matched CRLM (Spearman’s ρ = 0.6004; P < 0.0001). The median time to recurrence (TTR) and disease-specific survival (DSS) after CRLM resection in rad-CD73High vs rad-CD73 Low patients was 13.0 vs 23.6 months (P = 0.0098) and 53.4 vs 126.0 months (P = 0.0222), respectively. The prognostic value of rad-CD73 was independent of the standard clinical risk score, for both TTR (HR = 2.11, 95% CI 1.30 to 3.45, P < 0.005) and DSS (HR = 1.88, 95% CI 1.11 to 3.18, P = 0.020).
Uncontrolled Keywords
Cancer; Immune checkpoint; Adenosine pathway; CD73; Radiomic biomarker; Interpretable machine
Additional Information: | MedICAL Laboratory |
---|---|
Subjects: | 1900 Biomedical engineering > 1900 Biomedical engineering |
Department: |
Department of Computer Engineering and Software Engineering Institut de génie biomédical |
Research Center: | Other |
Funders: | Canada Excellence Research Chairs, Government of Canada, Fonds de Recherche du Québec - Santé, National Science and Engineering Research Council of Canada (NSERC), Université de Montréal, Research Chair in Hepatopancreatobiliary Surgical Oncology., FRQ-S Young Clinician Scientist Seed, FRQS Clinician Scientist Junior-1&2 Salary Award, Institut du Cancer de Montréal establishment award, FRQ-S phase 1, International Hepato- Pancreato-Biliary Association (IHPBA, Kenneth Warren Research Fellowship, Ethicon Inc. (Johnson & Johnson) |
Grant number: | RGPIN-2020-06558, 32633, 30861, 298832 |
PolyPublie URL: | https://publications.polymtl.ca/54819/ |
Journal Title: | Journal of Translational Medicine (vol. 21, no. 1) |
Publisher: | BioMed Central Ltd |
DOI: | 10.1186/s12967-023-04175-7 |
Official URL: | https://doi.org/10.1186/s12967-023-04175-7 |
Date Deposited: | 29 Aug 2023 15:32 |
Last Modified: | 27 Sep 2024 11:47 |
Cite in APA 7: | Saber, R., Henault, D., Messaoudi, N., Rebolledo, R., Montagnon, E., Soucy, G., Stagg, J., Tang, A., Turcotte, S., & Kadoury, S. (2023). Radiomics using computed tomography to predict CD73 expression and prognosis of colorectal cancer liver metastases. Journal of Translational Medicine, 21(1), 16 pages. https://doi.org/10.1186/s12967-023-04175-7 |
---|---|
Statistics
Total downloads
Downloads per month in the last year
Origin of downloads
Dimensions