Proietto Salanitri F.Bellitto G.Irmakci I.Palazzo S.Bagci U.Spampinato C.2023-01-122023-01-1220219783030875886030297430302-9743https://doi.org/10.1007/978-3-030-87589-3_25https://hdl.handle.net/11454/7943012th International Workshop on Machine Learning in Medical Imaging, MLMI 2021, held in conjunction with 24th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2021 -- 27 September 2021 through 27 September 2021 -- -- 266089We propose a novel 3D fully convolutional deep network for automated pancreas segmentation from both MRI and CT scans. More specifically, the proposed model consists of a 3D encoder that learns to extract volume features at different scales; features taken at different points of the encoder hierarchy are then sent to multiple 3D decoders that individually predict intermediate segmentation maps. Finally, all segmentation maps are combined to obtain a unique detailed segmentation mask. We test our model on both CT and MRI imaging data: the publicly available NIH Pancreas-CT dataset (consisting of 82 contrast-enhanced CTs) and a private MRI dataset (consisting of 40 MRI scans). Experimental results show that our model outperforms existing methods on CT pancreas segmentation, obtaining an average Dice score of about 88%, and yields promising segmentation performance on a very challenging MRI data set (average Dice score is about 77%). Additional control experiments demonstrate that the achieved performance is due to the combination of our 3D fully-convolutional deep network and the hierarchical representation decoding, thus substantiating our architectural design. © 2021, Springer Nature Switzerland AG.en10.1007/978-3-030-87589-3_25info:eu-repo/semantics/openAccessCT and MRI pancreas segmentationFully convolutional neural networksHierarchical encoder-decoder architecture3D modelingComputerized tomographyConvolutionConvolutional neural networksDecodingMachine learningMedical computingMedical imagingNetwork codingStatistical testsConvolutional neural networkCT and MRI pancreas segmentationCT-scanEncoder-decoder architectureFeature learningFully convolutional neural networkHierarchical encoder-decoder architectureLearn+MRI scanSegmentation mapMagnetic resonance imagingConference Object12966 LNCS2382472-s2.0-85116503336Q3