We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Use of Artificial Intelligence Deep Learning to Determine the Malignant Potential of Pancreatic Cystic Neoplasms With Preoperative Computed Tomography Imaging.
- Authors
Watson, Michael D.; Lyman, William B.; Passeri, Michael J.; Murphy, Keith J.; Sarantou, John P.; Iannitti, David A.; Martinie, John B.; Vrochides, Dionisios; Baker, Erin H.
- Abstract
<bold>Background: </bold>Society consensus guidelines are commonly used to guide management of pancreatic cystic neoplasms (PCNs). However, downsides of these guidelines include unnecessary surgery and missed malignancy. The aim of this study was to use computed tomography (CT)-guided deep learning techniques to predict malignancy of PCNs.<bold>Materials and Methods: </bold>Patients with PCNs who underwent resection were retrospectively reviewed. Axial images of the mucinous cystic neoplasms were collected and based on final pathology were assigned a binary outcome of advanced neoplasia or benign. Advanced neoplasia was defined as adenocarcinoma or intraductal papillary mucinous neoplasm with high-grade dysplasia. A convolutional neural network (CNN) deep learning model was trained on 66% of images, and this trained model was used to test 33% of images. Predictions from the deep learning model were compared to Fukuoka guidelines.<bold>Results: </bold>Twenty-seven patients met the inclusion criteria, with 18 used for training and 9 for model testing. The trained deep learning model correctly predicted 3 of 3 malignant lesions and 5 of 6 benign lesions. Fukuoka guidelines correctly classified 2 of 3 malignant lesions as high risk and 4 of 6 benign lesions as worrisome. Following deep learning model predictions would have avoided 1 missed malignancy and 1 unnecessary operation.<bold>Discussion: </bold>In this pilot study, a deep learning model correctly classified 8 of 9 PCNs and performed better than consensus guidelines. Deep learning can be used to predict malignancy of PCNs; however, further model improvements are necessary before clinical use.
- Subjects
FUKUOKA-shi (Japan); ARTIFICIAL intelligence; DEEP learning; COMPUTED tomography; CONVOLUTIONAL neural networks; TUMORS; TUMOR surgery; PANCREATIC tumors; PILOT projects; PREOPERATIVE period; RETROSPECTIVE studies
- Publication
American Surgeon, 2021, Vol 87, Issue 4, p602
- ISSN
0003-1348
- Publication type
journal article
- DOI
10.1177/0003134820953779