Gerard M Healy1,2,3, Emmanuel Salinas-Miranda3, Rahi Jain4, Xin Dong3, Dominik Deniffel3,5, Ayelet Borgida6, Ali Hosni7, David T Ryan8, Nwabundo Njeze9, Anne McGuire9, Kevin C Conlon9,10, Jonathan D Dodd8,11, Edmund Ronan Ryan8,9,11, Robert C Grant6,12, Steven Gallinger3,12,13, Masoom A Haider14,15,16,17. 1. Joint Department of Medical Imaging, University Health Network, Sinai Health System and Women's College Hospital, University of Toronto, Toronto, ON, Canada. 2. Department of Medical Imaging, University of Toronto, Toronto, ON, Canada. 3. Lunenfeld-Tanenbaum Research Institute, Sinai Health System, Toronto, ON, Canada. 4. Department of Biostatistics, Princess Margaret Cancer Centre, University Health Network, Toronto, ON, Canada. 5. Department of Diagnostic and Interventional Radiology, Klinikum Rechts Der Isar, Technical University of Munich, Munich, Germany. 6. Department of Medical Oncology and Hematology, Princess Margaret Cancer Centre, University Health Network, Toronto, ON, Canada. 7. Radiation Medicine Program, Princess Margaret Cancer Centre, Department of Radiation Oncology, University of Toronto, Toronto, ON, Canada. 8. Department of Radiology, St Vincent's University Hospital, Dublin, Ireland. 9. National Surgical Centre for Pancreatic Cancer, St. Vincent's University Hospital, Dublin, Ireland. 10. School of Medicine, Trinity College Dublin, Dublin, Ireland. 11. School of Medicine, University College Dublin, Dublin, Ireland. 12. PanCuRx Translational Research Initiative, Ontario Institute for Cancer Research, Toronto, ON, Canada. 13. Surgical Oncology Program, Hepatobiliary Pancreatic, University Health Network, Toronto, ON, Canada. 14. Joint Department of Medical Imaging, University Health Network, Sinai Health System and Women's College Hospital, University of Toronto, Toronto, ON, Canada. mahaider@radfiler.com. 15. Department of Medical Imaging, University of Toronto, Toronto, ON, Canada. mahaider@radfiler.com. 16. Lunenfeld-Tanenbaum Research Institute, Sinai Health System, Toronto, ON, Canada. mahaider@radfiler.com. 17. PanCuRx Translational Research Initiative, Ontario Institute for Cancer Research, Toronto, ON, Canada. mahaider@radfiler.com.
Abstract
OBJECTIVES: In resectable pancreatic ductal adenocarcinoma (PDAC), few pre-operative prognostic biomarkers are available. Radiomics has demonstrated potential but lacks external validation. We aimed to develop and externally validate a pre-operative clinical-radiomic prognostic model. METHODS: Retrospective international, multi-center study in resectable PDAC. The training cohort included 352 patients (pre-operative CTs from five Canadian hospitals). Cox models incorporated (a) pre-operative clinical variables (clinical), (b) clinical plus CT-radiomics, and (c) post-operative TNM model, which served as the reference. Outcomes were overall (OS)/disease-free survival (DFS). Models were assessed in the validation cohort from Ireland (n = 215, CTs from 34 hospitals), using C-statistic, calibration, and decision curve analyses. RESULTS: The radiomic signature was predictive of OS/DFS in the validation cohort, with adjusted hazard ratios (HR) 2.87 (95% CI: 1.40-5.87, p < 0.001)/5.28 (95% CI 2.35-11.86, p < 0.001), respectively, along with age 1.02 (1.01-1.04, p = 0.01)/1.02 (1.00-1.04, p = 0.03). In the validation cohort, median OS was 22.9/37 months (p = 0.0092) and DFS 14.2/29.8 (p = 0.0023) for high-/low-risk groups and calibration was moderate (mean absolute errors 7%/13% for OS at 3/5 years). The clinical-radiomic model discrimination (C = 0.545, 95%: 0.543-0.546) was higher than the clinical model alone (C = 0.497, 95% CI 0.496-0.499, p < 0.001) or TNM (C = 0.525, 95% CI: 0.524-0.526, p < 0.001). Despite superior net benefit compared to the clinical model, the clinical-radiomic model was not clinically useful for most threshold probabilities. CONCLUSION: A multi-institutional pre-operative clinical-radiomic model for resectable PDAC prognostication demonstrated superior net benefit compared to a clinical model but limited clinical utility at external validation. This reflects inherent limitations of radiomics for PDAC prognostication, when deployed in real-world settings. KEY POINTS: • At external validation, a pre-operative clinical-radiomics prognostic model for pancreatic ductal adenocarcinoma (PDAC) outperformed pre-operative clinical variables alone or pathological TNM staging. • Discrimination and clinical utility of the clinical-radiomic model for treatment decisions remained low, likely due to heterogeneity of CT acquisition parameters. • Despite small improvements, prognosis in PDAC using state-of-the-art radiomics methodology remains challenging, mostly owing to its low discriminative ability. Future research should focus on standardization of CT protocols and acquisition parameters.
OBJECTIVES: In resectable pancreatic ductal adenocarcinoma (PDAC), few pre-operative prognostic biomarkers are available. Radiomics has demonstrated potential but lacks external validation. We aimed to develop and externally validate a pre-operative clinical-radiomic prognostic model. METHODS: Retrospective international, multi-center study in resectable PDAC. The training cohort included 352 patients (pre-operative CTs from five Canadian hospitals). Cox models incorporated (a) pre-operative clinical variables (clinical), (b) clinical plus CT-radiomics, and (c) post-operative TNM model, which served as the reference. Outcomes were overall (OS)/disease-free survival (DFS). Models were assessed in the validation cohort from Ireland (n = 215, CTs from 34 hospitals), using C-statistic, calibration, and decision curve analyses. RESULTS: The radiomic signature was predictive of OS/DFS in the validation cohort, with adjusted hazard ratios (HR) 2.87 (95% CI: 1.40-5.87, p < 0.001)/5.28 (95% CI 2.35-11.86, p < 0.001), respectively, along with age 1.02 (1.01-1.04, p = 0.01)/1.02 (1.00-1.04, p = 0.03). In the validation cohort, median OS was 22.9/37 months (p = 0.0092) and DFS 14.2/29.8 (p = 0.0023) for high-/low-risk groups and calibration was moderate (mean absolute errors 7%/13% for OS at 3/5 years). The clinical-radiomic model discrimination (C = 0.545, 95%: 0.543-0.546) was higher than the clinical model alone (C = 0.497, 95% CI 0.496-0.499, p < 0.001) or TNM (C = 0.525, 95% CI: 0.524-0.526, p < 0.001). Despite superior net benefit compared to the clinical model, the clinical-radiomic model was not clinically useful for most threshold probabilities. CONCLUSION: A multi-institutional pre-operative clinical-radiomic model for resectable PDAC prognostication demonstrated superior net benefit compared to a clinical model but limited clinical utility at external validation. This reflects inherent limitations of radiomics for PDAC prognostication, when deployed in real-world settings. KEY POINTS: • At external validation, a pre-operative clinical-radiomics prognostic model for pancreatic ductal adenocarcinoma (PDAC) outperformed pre-operative clinical variables alone or pathological TNM staging. • Discrimination and clinical utility of the clinical-radiomic model for treatment decisions remained low, likely due to heterogeneity of CT acquisition parameters. • Despite small improvements, prognosis in PDAC using state-of-the-art radiomics methodology remains challenging, mostly owing to its low discriminative ability. Future research should focus on standardization of CT protocols and acquisition parameters.
Authors: Cameron E Gaskill; Jessica Maxwell; Naruhiko Ikoma; Michael P Kim; Ching-Wei Tzeng; Jeffrey E Lee; Matthew H G Katz Journal: J Surg Oncol Date: 2021-05 Impact factor: 3.454
Authors: Eva Versteijne; Mustafa Suker; Karin Groothuis; Janine M Akkermans-Vogelaar; Marc G Besselink; Bert A Bonsing; Jeroen Buijsen; Olivier R Busch; Geert-Jan M Creemers; Ronald M van Dam; Ferry A L M Eskens; Sebastiaan Festen; Jan Willem B de Groot; Bas Groot Koerkamp; Ignace H de Hingh; Marjolein Y V Homs; Jeanin E van Hooft; Emile D Kerver; Saskia A C Luelmo; Karen J Neelis; Joost Nuyttens; Gabriel M R M Paardekooper; Gijs A Patijn; Maurice J C van der Sangen; Judith de Vos-Geelen; Johanna W Wilmink; Aeilko H Zwinderman; Cornelis J Punt; Casper H van Eijck; Geertjan van Tienhoven Journal: J Clin Oncol Date: 2020-02-27 Impact factor: 44.544
Authors: Lei Huang; Lina Jansen; Yesilda Balavarca; Esther Molina-Montes; Masoud Babaei; Lydia van der Geest; Valery Lemmens; Liesbet Van Eycken; Harlinde De Schutter; Tom B Johannesen; Claus W Fristrup; Michael B Mortensen; Maja Primic-Žakelj; Vesna Zadnik; Nikolaus Becker; Thilo Hackert; Margit Mägi; Tiziana Cassetti; Romano Sassatelli; Robert Grützmann; Susanne Merkel; Ana F Gonçalves; Maria J Bento; Péter Hegyi; Gábor Lakatos; Andrea Szentesi; Michel Moreau; Tony van de Velde; Annegien Broeks; Milena Sant; Pamela Minicozzi; Vincenzo Mazzaferro; Francisco X Real; Alfredo Carrato; Xavier Molero; Marc G Besselink; Núria Malats; Markus W Büchler; Petra Schrotz-King; Hermann Brenner Journal: Gut Date: 2017-11-20 Impact factor: 23.059
Authors: Brian B Haab; Ying Huang; Seetharaman Balasenthil; Katie Partyka; Huiyuan Tang; Michelle Anderson; Peter Allen; Aaron Sasson; Herbert Zeh; Karen Kaul; Doron Kletter; Shaokui Ge; Marshall Bern; Richard Kwon; Ivan Blasutig; Sudhir Srivastava; Marsha L Frazier; Subrata Sen; Michael A Hollingsworth; Jo Ann Rinaudo; Ann M Killary; Randall E Brand Journal: PLoS One Date: 2015-10-02 Impact factor: 3.240