Abel Lorraine, Wasserthal Jakob, Weikert Thomas, Sauter Alexander W, Nesic Ivan, Obradovic Marko, Yang Shan, Manneck Sebastian, Glessgen Carl, Ospel Johanna M, Stieltjes Bram, Boll Daniel T, Friebe Björn
Clinic of Radiology & Nuclear Medicine, University Hospital Basel, University of Basel, Petersgraben 4, 4031 Basel, Switzerland.
Diagnostics (Basel). 2021 May 19;11(5):901. doi: 10.3390/diagnostics11050901.
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 and for lesions in the distal pancreas with up to 96.2%. The number of false-positive detections for cysts ≥220 mm 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.
胰腺囊性病变（PCL）是CT扫描中常见但报告不足的偶然发现，并且可能转变为具有严重后果的肿瘤。我们开发并评估了一种基于两步nnU-Net架构的算法，用于在CT上自动检测PCL。一名放射科住院医师与一名专门从事腹部放射学的委员会认证放射科医生达成共识，对221例腹部CT上的总共543个囊肿进行了3D手动分割。这些信息用于训练一个两步nnU-Net进行检测，并将其性能与三名经验不同的人类读者进行比较，根据病变的体积和位置评估性能。平均敏感性为78.8±0.1%。对于大囊肿，敏感性最高，囊肿≥220mm时为87.8%，胰腺远端病变时高达96.2%。囊肿≥220mm的假阳性检测数为每例0.1个。该算法的性能与人类读者相当。总之，在CT上自动检测PCL是可行的。所提出的模型可以作为放射科医生的二次阅读工具。本研究中使用的所有成像数据和代码均可在网上免费获取。
