Linda C Chu1, Seyoun Park2, Sahar Soleimani2, Daniel F Fouladi2, Shahab Shayesteh2, Jin He3, Ammar A Javed4, Christopher L Wolfgang4, Bert Vogelstein5, Kenneth W Kinzler5, Ralph H Hruban6, Elham Afghani7, Anne Marie Lennon7, Elliot K Fishman2, Satomi Kawamoto2. 1. Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, MD, USA. lchu1@jhmi.edu. 2. Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, MD, USA. 3. Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, MD, USA. 4. Department of Surgery, New York University Grossman School of Medicine, New York, NY, USA. 5. Sidney Kimmel Comprehensive Cancer Center, Johns Hopkins University School of Medicine, Baltimore, MD, USA. 6. Department of Pathology, Sol Goldman Pancreatic Cancer Research Center, Johns Hopkins University School of Medicine, Baltimore, MD, USA. 7. Division of Gastroenterology and Hepatology, Johns Hopkins University School of Medicine, Baltimore, MD, USA.
Abstract
PURPOSE: A wide array of benign and malignant lesions of the pancreas can be cystic and these cystic lesions can have overlapping imaging appearances. The purpose of this study is to compare the diagnostic accuracy of a radiomics-based pancreatic cyst classifier to an experienced academic radiologist. METHODS: In this IRB-approved retrospective single-institution study, patients with surgically resected pancreatic cysts who underwent preoperative abdominal CT from 2003 to 2016 were identified. Pancreatic cyst(s) and background pancreas were manually segmented, and 488 radiomics features were extracted. Random forest classification based on radiomics features, age, and gender was evaluated with fourfold cross-validation. An academic radiologist blinded to the final pathologic diagnosis reviewed each case and provided the most likely diagnosis. RESULTS: 214 patients were included (64 intraductal papillary mucinous neoplasms, 33 mucinous cystic neoplasms, 60 serous cystadenomas, 24 solid pseudopapillary neoplasms, and 33 cystic neuroendocrine tumors). The radiomics-based machine learning approach showed AUC of 0.940 in pancreatic cyst classification, compared with AUC of 0.895 for the radiologist. CONCLUSION: Radiomics-based machine learning achieved equivalent performance as an experienced academic radiologist in the classification of pancreatic cysts. The high diagnostic accuracy can potentially maximize the efficiency of healthcare utilization by maximizing detection of high-risk lesions.
PURPOSE: A wide array of benign and malignant lesions of the pancreas can be cystic and these cystic lesions can have overlapping imaging appearances. The purpose of this study is to compare the diagnostic accuracy of a radiomics-based pancreatic cyst classifier to an experienced academic radiologist. METHODS: In this IRB-approved retrospective single-institution study, patients with surgically resected pancreatic cysts who underwent preoperative abdominal CT from 2003 to 2016 were identified. Pancreatic cyst(s) and background pancreas were manually segmented, and 488 radiomics features were extracted. Random forest classification based on radiomics features, age, and gender was evaluated with fourfold cross-validation. An academic radiologist blinded to the final pathologic diagnosis reviewed each case and provided the most likely diagnosis. RESULTS: 214 patients were included (64 intraductal papillary mucinous neoplasms, 33 mucinous cystic neoplasms, 60 serous cystadenomas, 24 solid pseudopapillary neoplasms, and 33 cystic neuroendocrine tumors). The radiomics-based machine learning approach showed AUC of 0.940 in pancreatic cyst classification, compared with AUC of 0.895 for the radiologist. CONCLUSION: Radiomics-based machine learning achieved equivalent performance as an experienced academic radiologist in the classification of pancreatic cysts. The high diagnostic accuracy can potentially maximize the efficiency of healthcare utilization by maximizing detection of high-risk lesions.
Authors: Konstantin Dmitriev; Arie E Kaufman; Ammar A Javed; Ralph H Hruban; Elliot K Fishman; Anne Marie Lennon; Joel H Saltz Journal: Med Image Comput Comput Assist Interv Date: 2017-09-04