期刊
DIAGNOSTICS
卷 11, 期 5, 页码 -出版社
MDPI
DOI: 10.3390/diagnostics11050901
关键词
pancreatic cystic lesion; intraductal papillary mucinous neoplasia; tomography; X-ray computed; detection; artificial intelligence; deep learning; nnU-Net
An algorithm based on a two-step nnU-Net architecture was developed for automated detection of pancreatic cystic lesions on CT scans, showing comparable performance to human readers. The algorithm had high sensitivity for large lesions and those located in the distal pancreas.
Pancreatic cystic lesions (PCL) are a frequent and underreported incidental finding on CT scans and can transform into neoplasms with devastating consequences. We developed and evaluated an algorithm based on a two-step nnU-Net architecture for automated detection of PCL on CTs. A total of 543 cysts on 221 abdominal CTs were manually segmented in 3D by a radiology resident in consensus with a board-certified radiologist specialized in abdominal radiology. This information was used to train a two-step nnU-Net for detection with the performance assessed depending on lesions' volume and location in comparison to three human readers of varying experience. Mean sensitivity was 78.8 +/- 0.1%. The sensitivity was highest for large lesions with 87.8% for cysts >= 220 mm(3) and for lesions in the distal pancreas with up to 96.2%. The number of false-positive detections for cysts >= 220 mm(3) was 0.1 per case. The algorithm's performance was comparable to human readers. To conclude, automated detection of PCL on CTs is feasible. The proposed model could serve radiologists as a second reading tool. All imaging data and code used in this study are freely available online.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据