Yucheng Zhang1, Edrise M Lobo-Mueller2, Paul Karanicolas3, Steven Gallinger4, Masoom A Haider4,5, Farzad Khalvati1,6,7. 1. Department of Medical Imaging, University of Toronto, Toronto, ON, Canada. 2. Department of Diagnostic Imaging and Department of Oncology, Faculty of Medicine and Dentistry, Cross Cancer Institute, University of Alberta, Edmonton, AB, Canada. 3. Department of Surgery, Sunnybrook Health Sciences Centre, Toronto, ON, Canada. 4. Lunenfeld-Tanenbaum Research Institute, Sinai Health System, Toronto, ON, Canada. 5. Joint Department of Medical Imaging, Sinai Health System, University Health Network, University of Toronto, Toronto, ON, Canada. 6. Research Institute, The Hospital for Sick Children, Toronto, ON, Canada. 7. Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, ON, Canada.
Abstract
Background: Pancreatic Ductal Adenocarcinoma (PDAC) is one of the most aggressive cancers with an extremely poor prognosis. Radiomics has shown prognostic ability in multiple types of cancer including PDAC. However, the prognostic value of traditional radiomics pipelines, which are based on hand-crafted radiomic features alone is limited. Methods: Convolutional neural networks (CNNs) have been shown to outperform radiomics models in computer vision tasks. However, training a CNN from scratch requires a large sample size which is not feasible in most medical imaging studies. As an alternative solution, CNN-based transfer learning models have shown the potential for achieving reasonable performance using small datasets. In this work, we developed and validated a CNN-based transfer learning model for prognostication of overall survival in PDAC patients using two independent resectable PDAC cohorts. Results: The proposed transfer learning-based prognostication model for overall survival achieved the area under the receiver operating characteristic curve of 0.81 on the test cohort, which was significantly higher than that of the traditional radiomics model (0.54). To further assess the prognostic value of the models, the predicted probabilities of death generated from the two models were used as risk scores in a univariate Cox Proportional Hazard model and while the risk score from the traditional radiomics model was not associated with overall survival, the proposed transfer learning-based risk score had significant prognostic value with hazard ratio of 1.86 (95% Confidence Interval: 1.15-3.53, p-value: 0.04). Conclusions: This result suggests that transfer learning-based models may significantly improve prognostic performance in typical small sample size medical imaging studies.
Background: Pancreatic Ductal Adenocarcinoma (PDAC) is one of the most aggressive cancers with an extremely poor prognosis. Radiomics has shown prognostic ability in multiple types of cancer including PDAC. However, the prognostic value of traditional radiomics pipelines, which are based on hand-crafted radiomic features alone is limited. Methods: Convolutional neural networks (CNNs) have been shown to outperform radiomics models in computer vision tasks. However, training a CNN from scratch requires a large sample size which is not feasible in most medical imaging studies. As an alternative solution, CNN-based transfer learning models have shown the potential for achieving reasonable performance using small datasets. In this work, we developed and validated a CNN-based transfer learning model for prognostication of overall survival in PDACpatients using two independent resectable PDAC cohorts. Results: The proposed transfer learning-based prognostication model for overall survival achieved the area under the receiver operating characteristic curve of 0.81 on the test cohort, which was significantly higher than that of the traditional radiomics model (0.54). To further assess the prognostic value of the models, the predicted probabilities of death generated from the two models were used as risk scores in a univariate Cox Proportional Hazard model and while the risk score from the traditional radiomics model was not associated with overall survival, the proposed transfer learning-based risk score had significant prognostic value with hazard ratio of 1.86 (95% Confidence Interval: 1.15-3.53, p-value: 0.04). Conclusions: This result suggests that transfer learning-based models may significantly improve prognostic performance in typical small sample size medical imaging studies.
Authors: Linda C Chu; Seyoun Park; Satomi Kawamoto; Daniel F Fouladi; Shahab Shayesteh; Eva S Zinreich; Jefferson S Graves; Karen M Horton; Ralph H Hruban; Alan L Yuille; Kenneth W Kinzler; Bert Vogelstein; Elliot K Fishman Journal: AJR Am J Roentgenol Date: 2019-04-23 Impact factor: 3.959
Authors: Masoom A Haider; Alireza Vosough; Farzad Khalvati; Alexander Kiss; Balaji Ganeshan; Georg A Bjarnason Journal: Cancer Imaging Date: 2017-01-23 Impact factor: 3.909
Authors: Jayasree Chakraborty; Liana Langdon-Embry; Kristen M Cunanan; Joanna G Escalon; Peter J Allen; Maeve A Lowery; Eileen M O'Reilly; Mithat Gönen; Richard G Do; Amber L Simpson Journal: PLoS One Date: 2017-12-07 Impact factor: 3.240