Laurent Dercle1,2, Lin Lu1, Lawrence H Schwartz1, Min Qian3, Sabine Tejpar4, Peter Eggleton5, Binsheng Zhao1, Hubert Piessevaux6. 1. Department of Radiology, New York Presbyterian Hospital, Columbia University Medical Center, New York, NY, USA. 2. Gustave Roussy, Université Paris-Saclay, Villejuif, France. 3. Department of Biostatistics, Columbia University Medical Center, New York, NY, USA. 4. Molecular Digestive Oncology, University Hospitals Leuven and KU Leuven, Leuven, Belgium. 5. Merck KGaA, Darmstadt, Germany. 6. Department of Hepato-Gastroenterology, Cliniques Universitaires Saint-Luc, UCLouvain Brussels, Brussels, Belgium.
Abstract
BACKGROUND: The authors sought to forecast survival and enhance treatment decisions for patients with liver metastatic colorectal cancer by using on-treatment radiomics signature to predict tumor sensitiveness to irinotecan, 5-fluorouracil, and leucovorin (FOLFIRI) alone (F) or in combination with cetuximab (FC). METHODS: We retrospectively analyzed 667 metastatic colorectal cancer patients treated with F or FC. Computed tomography quality was classified as high (HQ) or standard (SD). Four datasets were created using the nomenclature (treatment) - (quality). Patients were randomly assigned (2:1) to training or validation sets: FCHQ: 78:38, FCSD: 124:62, FHQ: 78:51, FSD: 158:78. Four tumor-imaging biomarkers measured quantitative radiomics changes between standard of care computed tomography scans at baseline and 8 weeks. Using machine learning, the performance of the signature to classify tumors as treatment sensitive or treatment insensitive was trained and validated using receiver operating characteristic (ROC) curves. Hazard ratio and Cox regression models evaluated association with overall survival (OS). RESULTS: The signature (area under the ROC curve [95% confidence interval (CI)]) used temporal decrease in tumor spatial heterogeneity plus boundary infiltration to successfully predict sensitivity to antiepidermal growth factor receptor therapy (FCHQ: 0.80 [95% CI = 0.69 to 0.94], FCSD: 0.72 [95% CI = 0.59 to 0.83]) but failed with chemotherapy (FHQ: 0.59 [95% CI = 0.44 to 0.72], FSD: 0.55 [95% CI = 0.43 to 0.66]). In cetuximab-containing sets, radiomics signature outperformed existing biomarkers (KRAS-mutational status, and tumor shrinkage by RECIST 1.1) for detection of treatment sensitivity and was strongly associated with OS (two-sided P < .005). CONCLUSIONS: Radiomics response signature can serve as an intermediate surrogate marker of OS. The signature outperformed known biomarkers in providing an early prediction of treatment sensitivity and could be used to guide cetuximab treatment continuation decisions.
RCT Entities:
BACKGROUND: The authors sought to forecast survival and enhance treatment decisions for patients with liver metastatic colorectal cancer by using on-treatment radiomics signature to predict tumor sensitiveness to irinotecan, 5-fluorouracil, and leucovorin (FOLFIRI) alone (F) or in combination with cetuximab (FC). METHODS: We retrospectively analyzed 667 metastatic colorectal cancerpatients treated with F or FC. Computed tomography quality was classified as high (HQ) or standard (SD). Four datasets were created using the nomenclature (treatment) - (quality). Patients were randomly assigned (2:1) to training or validation sets: FCHQ: 78:38, FCSD: 124:62, FHQ: 78:51, FSD: 158:78. Four tumor-imaging biomarkers measured quantitative radiomics changes between standard of care computed tomography scans at baseline and 8 weeks. Using machine learning, the performance of the signature to classify tumors as treatment sensitive or treatment insensitive was trained and validated using receiver operating characteristic (ROC) curves. Hazard ratio and Cox regression models evaluated association with overall survival (OS). RESULTS: The signature (area under the ROC curve [95% confidence interval (CI)]) used temporal decrease in tumor spatial heterogeneity plus boundary infiltration to successfully predict sensitivity to antiepidermal growth factor receptor therapy (FCHQ: 0.80 [95% CI = 0.69 to 0.94], FCSD: 0.72 [95% CI = 0.59 to 0.83]) but failed with chemotherapy (FHQ: 0.59 [95% CI = 0.44 to 0.72], FSD: 0.55 [95% CI = 0.43 to 0.66]). In cetuximab-containing sets, radiomics signature outperformed existing biomarkers (KRAS-mutational status, and tumor shrinkage by RECIST 1.1) for detection of treatment sensitivity and was strongly associated with OS (two-sided P < .005). CONCLUSIONS: Radiomics response signature can serve as an intermediate surrogate marker of OS. The signature outperformed known biomarkers in providing an early prediction of treatment sensitivity and could be used to guide cetuximab treatment continuation decisions.
Authors: Geoffrey R Oxnard; Binsheng Zhao; Camelia S Sima; Michelle S Ginsberg; Leonard P James; Robert A Lefkowitz; Pingzhen Guo; Mark G Kris; Lawrence H Schwartz; Gregory J Riely Journal: J Clin Oncol Date: 2011-07-05 Impact factor: 44.544
Authors: Roger Sun; Elaine Johanna Limkin; Maria Vakalopoulou; Laurent Dercle; Stéphane Champiat; Shan Rong Han; Loïc Verlingue; David Brandao; Andrea Lancia; Samy Ammari; Antoine Hollebecque; Jean-Yves Scoazec; Aurélien Marabelle; Christophe Massard; Jean-Charles Soria; Charlotte Robert; Nikos Paragios; Eric Deutsch; Charles Ferté Journal: Lancet Oncol Date: 2018-08-14 Impact factor: 41.316
Authors: E J Limkin; R Sun; L Dercle; E I Zacharaki; C Robert; S Reuzé; A Schernberg; N Paragios; E Deutsch; C Ferté Journal: Ann Oncol Date: 2017-06-01 Impact factor: 32.976
Authors: Haesun Choi; Chuslip Charnsangavej; Silvana C Faria; Homer A Macapinlac; Michael A Burgess; Shreyaskumar R Patel; Lei L Chen; Donald A Podoloff; Robert S Benjamin Journal: J Clin Oncol Date: 2007-05-01 Impact factor: 44.544
Authors: Yun Shin Chun; Jean-Nicolas Vauthey; Piyaporn Boonsirikamchai; Dipen M Maru; Scott Kopetz; Martin Palavecino; Steven A Curley; Eddie K Abdalla; Harmeet Kaur; Chusilp Charnsangavej; Evelyne M Loyer Journal: JAMA Date: 2009-12-02 Impact factor: 56.272
Authors: Binsheng Zhao; Yongqiang Tan; Daniel J Bell; Sarah E Marley; Pingzhen Guo; Helen Mann; Marietta L J Scott; Lawrence H Schwartz; Dana C Ghiorghiu Journal: Eur J Radiol Date: 2013-03-13 Impact factor: 3.528
Authors: Haesun Choi; Chuslip Charnsangavej; Silvana de Castro Faria; Eric P Tamm; Robert S Benjamin; Marcella M Johnson; Homer A Macapinlac; Donald A Podoloff Journal: AJR Am J Roentgenol Date: 2004-12 Impact factor: 3.959
Authors: Laetitia Vercellino; Dorine de Jong; Roberta di Blasi; Salim Kanoun; Ran Reshef; Lawrence H Schwartz; Laurent Dercle Journal: Front Oncol Date: 2021-05-28 Impact factor: 6.244
Authors: Lin Lu; Firas S Ahmed; Oguz Akin; Lyndon Luk; Xiaotao Guo; Hao Yang; Jin Yoon; A Aari Hakimi; Lawrence H Schwartz; Binsheng Zhao Journal: Front Oncol Date: 2021-05-27 Impact factor: 6.244