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 mm³ and for lesions in the distal pancreas with up to 96.2%. The number of false-positive detections for cysts ≥220 mm³ 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.

1. In one experiment the effect on rumen pH of feeding with restricted amounts of whole or pelleted barley was studied. With whole barley there was little variation in rumen pH associated with feeding time, but with pelleted barley the pH decreased from about 7.0 before feeding to about 5.3, 2–3 h after feeding. 2. The rate of disappearance of dried grass during incubation in the rumens of sheep receiving either whole or pelleted barley was studied in a second experiment. After 24 h incubation only 423 mg/g incubated had disappeared in the rumen of sheep receiving pelleted barley while 625 mg/g incubated had disappeared when it was incubated in the rumen of sheep receiving whole barley. 3. The voluntary intake of dried grass by lambs was studied in a third experiment when they received supplements of either 25 or 50 g whole or pelleted barley/kg live weight0.75. At the high level, pelleted barley reduced intake of dried grass by 534 g/kg but whole barley reduced it by only 352 g/kg. The digestibility of acid-detergent fibre was reduced more by pelleted barley than by whole barley but there was a tendency for a small increase in digestibility of the barley due to processing. 4. The implications of these findings on supplementation of roughages with cereals are discussed.