Quantification of CT images for the classification of high- and low-risk pancreatic cysts Conference Paper
| Authors: | Gazit, L.; Chakraborty, J.; Attiyeh, M.; Langdon-Embry, L.; Allen, P. J.; Do, R. K. G.; Simpson, A. L. |
| Editors: | Armato, S. G. 3rd; Petrick, N. A. |
| Title: | Quantification of CT images for the classification of high- and low-risk pancreatic cysts |
| Conference Title: | Medical Imaging 2017: Computer-Aided Diagnosis |
| Abstract: | Pancreatic cancer is the most lethal cancer with an overall 5-year survival rate of 7%1 due to the late stage at diagnosis and the ineffectiveness of current therapeutic strategies. Given the poor prognosis, early detection at a pre-cancerous stage is the best tool for preventing this disease. Intraductal papillary mucinous neoplasms (IPMN), cystic tumors of the pancreas, represent the only radiographically identifiable precursor lesion of pancreatic cancer and are known to evolve stepwise from low-to-high-grade dysplasia before progressing into an invasive carcinoma. Observation is usually recommended for low-risk (low- and intermediate-grade dysplasia) patients, while high-risk (high-grade dysplasia and invasive carcinoma) patients undergo resection; hence, patient selection is critically important in the management of pancreatic cysts.2 Radiologists use standard criteria such as main pancreatic duct size, cyst size, or presence of a solid enhancing component in the cyst to optimally select patients for surgery.3 However, these findings are subject to a radiologist's interpretation and have been shown to be inconsistent with regards to the presence of a mural nodule or solid component.4 We propose objective classification of risk groups based on quantitative imaging features extracted from CT scans. We apply new features that represent the solid component (i.e. areas of high intensity) within the cyst and extract standard texture features. An adaptive boost classifier5 achieves the best performance with area under receiver operating characteristic curve (AUC) of 0.73 and accuracy of 77.3% for texture features. The random forest classifier achieves the best performance with AUC of 0.71 and accuracy of 70.8% with the solid component features. © 2017 SPIE. |
| Keywords: | risk assessment; computerized tomography; medical imaging; tumors; diagnosis; risk stratification; quantitative imaging; fish; decision trees; diseases; intraductal papillary mucinous neoplasms; texture analysis; computer aided diagnosis; classification (of information); receiver operating characteristic curves; image classification; solid component; classification of risk; random forest classifier; solid components |
| Journal Title | Progress in Biomedical Optics and Imaging - Proceedings of SPIE |
| Volume: | 10134 |
| Conference Dates: | 2017 Feb 13-16 |
| Conference Location: | Orlando, FL |
| ISBN: | 1605-7422 |
| Publisher: | SPIE |
| Date Published: | 2017-03-03 |
| Start Page: | 101340X |
| Language: | English |
| DOI: | 10.1117/12.2255626 |
| PROVIDER: | scopus |
| DOI/URL: | |
| Notes: | Conference Paper -- Export Date: 3 July 2017 -- Source: Scopus |
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
Related MSK Work