Radiomics using computed tomography to predict CD73 expression and prognosis of colorectal cancer liver metastases

Ralph Saber; David Henault; Nouredin Messaoudi; Rolando Rebolledo; Emmanuel Montagnon; Geneviève Soucy; John Stagg; An Tang; Simon Turcotte; Samuel Kadoury

doi:10.1186/s12967-023-04175-7

Radiomics using computed tomography to predict CD73 expression and prognosis of colorectal cancer liver metastases

Ralph Saber, David Henault, Nouredin Messaoudi, Rolando Rebolledo, Emmanuel Montagnon, Geneviève Soucy, John Stagg, An Tang, Simon Turcotte, Samuel Kadoury

Research output: Contribution to journal › Article › peer-review

17 Citations (Scopus)

37 Downloads (Pure)

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 catalyzes 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 associated 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 (CD73^High vs. CD73^Low) 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 performance 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-CD73^High 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). Conclusions: Our findings reveal promising results for non-invasive CT-scan-based prediction of CD73 expression in CRLM and warrant further validation as to whether rad-CD73 could assist oncologists as a biomarker of prognosis and response to immunotherapies targeting the adenosine pathway.

Original language	English
Article number	507
Number of pages	14
Journal	Journal of Translational Medicine
Volume	21
Issue number	1
DOIs	https://doi.org/10.1186/s12967-023-04175-7
Publication status	Published - 27 Jul 2023

Bibliographical note

Funding Information:
In this study, we developed a noninvasive imaging surrogate of CD73 by leveraging state-of-the-art deep learning techniques trained with radiomic features. Despite recent progress in prognostication based on immune features of CRLM resected with curative intent [], there are no noninvasive immune biomarkers that ultimately may guide clinical decision making. To our knowledge, this is the first work developing and testing a machine learning tool to predict immunosuppressive CD73 expression from diagnostic CT images. The proposed model exhibited good performance in classifying CRLM lesions into CD73 and CD73 groups. We also demonstrated that the predicted rad-CD73 score was highly correlated with the actual expression as measured in vitro by immunohistochemistry. Moreover, the clinical significance of rad-CD73 was supported by its association with patient prognosis. High Low

Funding Information:
This work was supported by the Canada Research Chairs, by the National Science and Engineering Research Council of Canada (NSERC) Discovery grant RGPIN-2020-06558 and the Université de Montréal Roger Des Groseillers Research Chair in Hepatopancreatobiliary Surgical Oncology. ST and SK are scientists of the Centre de recherche du Centre hospitalier de l’Université de Montréal (CRCHUM) supported by the Fonds de recherche du Québec—Santé (FRQ-S). ST was supported by the FRQ-S Young Clinician Scientist Seed Grant (No. 32633), the FRQS Clinician Scientist Junior-1&2 Salary Award (No. 30861, No. 298832), and the Institut du Cancer de Montréal establishment award. DH was supported by the FRQ-S phase 1 award for medical resident engaged in clinician-scientist training. NM was supported by the International Hepato-Pancreato-Biliary Association (IHPBA) Kenneth Warren Research Fellowship and Ethicon Inc. (Johnson & Johnson).

Publisher Copyright:
© 2023, The Author(s).

Keywords

Adenosine pathway
Cancer
CD73
Immune checkpoint
Interpretable machine learning
Radiomic biomarker

Access to Document

10.1186/s12967-023-04175-7Licence: CC BY

108585879Final published version, 2.36 MBLicence: CC BY

Handle.net

Persistent link

Cite this

@article{dc388d94e8164dcc9ba38a7f29433449,

title = "Radiomics using computed tomography to predict CD73 expression and prognosis of colorectal cancer liver metastases",

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 catalyzes 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 associated 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 performance 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{\textquoteright}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-CD73Low 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). Conclusions: Our findings reveal promising results for non-invasive CT-scan-based prediction of CD73 expression in CRLM and warrant further validation as to whether rad-CD73 could assist oncologists as a biomarker of prognosis and response to immunotherapies targeting the adenosine pathway.",

keywords = "Adenosine pathway, Cancer, CD73, Immune checkpoint, Interpretable machine learning, Radiomic biomarker",

author = "Ralph Saber and David Henault and Nouredin Messaoudi and Rolando Rebolledo and Emmanuel Montagnon and Genevi{\`e}ve Soucy and John Stagg and An Tang and Simon Turcotte and Samuel Kadoury",

note = "Funding Information: In this study, we developed a noninvasive imaging surrogate of CD73 by leveraging state-of-the-art deep learning techniques trained with radiomic features. Despite recent progress in prognostication based on immune features of CRLM resected with curative intent [], there are no noninvasive immune biomarkers that ultimately may guide clinical decision making. To our knowledge, this is the first work developing and testing a machine learning tool to predict immunosuppressive CD73 expression from diagnostic CT images. The proposed model exhibited good performance in classifying CRLM lesions into CD73 and CD73 groups. We also demonstrated that the predicted rad-CD73 score was highly correlated with the actual expression as measured in vitro by immunohistochemistry. Moreover, the clinical significance of rad-CD73 was supported by its association with patient prognosis. High Low Funding Information: This work was supported by the Canada Research Chairs, by the National Science and Engineering Research Council of Canada (NSERC) Discovery grant RGPIN-2020-06558 and the Universit{\'e} de Montr{\'e}al Roger Des Groseillers Research Chair in Hepatopancreatobiliary Surgical Oncology. ST and SK are scientists of the Centre de recherche du Centre hospitalier de l{\textquoteright}Universit{\'e} de Montr{\'e}al (CRCHUM) supported by the Fonds de recherche du Qu{\'e}bec—Sant{\'e} (FRQ-S). ST was supported by the FRQ-S Young Clinician Scientist Seed Grant (No. 32633), the FRQS Clinician Scientist Junior-1&2 Salary Award (No. 30861, No. 298832), and the Institut du Cancer de Montr{\'e}al establishment award. DH was supported by the FRQ-S phase 1 award for medical resident engaged in clinician-scientist training. NM was supported by the International Hepato-Pancreato-Biliary Association (IHPBA) Kenneth Warren Research Fellowship and Ethicon Inc. (Johnson & Johnson). Publisher Copyright: {\textcopyright} 2023, The Author(s).",

year = "2023",

month = jul,

day = "27",

doi = "10.1186/s12967-023-04175-7",

language = "English",

volume = "21",

journal = "Journal of Translational Medicine",

issn = "1479-5876",

publisher = "BioMed Central",

number = "1",

}

TY - JOUR

T1 - Radiomics using computed tomography to predict CD73 expression and prognosis of colorectal cancer liver metastases

AU - Saber, Ralph

AU - Henault, David

AU - Messaoudi, Nouredin

AU - Rebolledo, Rolando

AU - Montagnon, Emmanuel

AU - Soucy, Geneviève

AU - Stagg, John

AU - Tang, An

AU - Turcotte, Simon

AU - Kadoury, Samuel

N1 - Funding Information: In this study, we developed a noninvasive imaging surrogate of CD73 by leveraging state-of-the-art deep learning techniques trained with radiomic features. Despite recent progress in prognostication based on immune features of CRLM resected with curative intent [], there are no noninvasive immune biomarkers that ultimately may guide clinical decision making. To our knowledge, this is the first work developing and testing a machine learning tool to predict immunosuppressive CD73 expression from diagnostic CT images. The proposed model exhibited good performance in classifying CRLM lesions into CD73 and CD73 groups. We also demonstrated that the predicted rad-CD73 score was highly correlated with the actual expression as measured in vitro by immunohistochemistry. Moreover, the clinical significance of rad-CD73 was supported by its association with patient prognosis. High Low Funding Information: This work was supported by the Canada Research Chairs, by the National Science and Engineering Research Council of Canada (NSERC) Discovery grant RGPIN-2020-06558 and the Université de Montréal Roger Des Groseillers Research Chair in Hepatopancreatobiliary Surgical Oncology. ST and SK are scientists of the Centre de recherche du Centre hospitalier de l’Université de Montréal (CRCHUM) supported by the Fonds de recherche du Québec—Santé (FRQ-S). ST was supported by the FRQ-S Young Clinician Scientist Seed Grant (No. 32633), the FRQS Clinician Scientist Junior-1&2 Salary Award (No. 30861, No. 298832), and the Institut du Cancer de Montréal establishment award. DH was supported by the FRQ-S phase 1 award for medical resident engaged in clinician-scientist training. NM was supported by the International Hepato-Pancreato-Biliary Association (IHPBA) Kenneth Warren Research Fellowship and Ethicon Inc. (Johnson & Johnson). Publisher Copyright: © 2023, The Author(s).

PY - 2023/7/27

Y1 - 2023/7/27

N2 - 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 catalyzes 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 associated 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 performance 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-CD73Low 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). Conclusions: Our findings reveal promising results for non-invasive CT-scan-based prediction of CD73 expression in CRLM and warrant further validation as to whether rad-CD73 could assist oncologists as a biomarker of prognosis and response to immunotherapies targeting the adenosine pathway.

AB - 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 catalyzes 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 associated 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 performance 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-CD73Low 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). Conclusions: Our findings reveal promising results for non-invasive CT-scan-based prediction of CD73 expression in CRLM and warrant further validation as to whether rad-CD73 could assist oncologists as a biomarker of prognosis and response to immunotherapies targeting the adenosine pathway.

KW - Adenosine pathway

KW - Cancer

KW - CD73

KW - Immune checkpoint

KW - Interpretable machine learning

KW - Radiomic biomarker

UR - http://www.scopus.com/inward/record.url?scp=85165922324&partnerID=8YFLogxK

U2 - 10.1186/s12967-023-04175-7

DO - 10.1186/s12967-023-04175-7

M3 - Article

C2 - 37501197

AN - SCOPUS:85165922324

SN - 1479-5876

VL - 21

JO - Journal of Translational Medicine

JF - Journal of Translational Medicine

IS - 1

M1 - 507

ER -

Radiomics using computed tomography to predict CD73 expression and prognosis of colorectal cancer liver metastases

Abstract

Bibliographical note

Keywords

Access to Document

Handle.net

Other files and links

Fingerprint

Cite this