3D Deep Learning for Anatomical Structure Segmentation in Multiple Imaging Modalities
- 12 July 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Proceedings. IEEE International Symposium on Computer-Based Medical Systems
- Vol. 2021, 166-171
Abstract
Accurate, automated quantitative segmentation of anatomical structures in radiological scans, such as Magnetic Resonance Imaging (MRI) and Computer Tomography (CT), can produce significant biomarkers and can be integrated into computer-aided diagnosis (CADx) systems to support the interpretation of medical images from multi-protocol scanners. However, there are serious challenges towards developing robust automated segmentation techniques, including high variations in anatomical structure and size, varying image spatial resolutions resulting from different scanner protocols, and the presence of blurring artefacts. This paper presents a novel computing approach for automated organ and muscle segmentation in medical images from multiple modalities by harnessing the advantages of deep learning techniques in a two-part process. (1) a 3D encoder-decoder, Rb-UNet, builds a localisation model and a 3D Tiramisu network generates a boundary-preserving segmentation model for each target structure; (2) the fully trained Rb-UNet predicts a 3D bounding box encapsulating the target structure of interest, after which the fully trained Tiramisu model performs segmentation to reveal organ or muscle boundaries for every protrusion and indentation. The proposed approach is evaluated on six different datasets, including MRI, Dynamic Contrast Enhanced (DCE) MRI and CT scans targeting the pancreas, liver, kidneys and iliopsoas muscles. We achieve quantitative measures of mean Dice similarity coefficient (DSC) that surpasses or are comparable with the state-of-the-art and demonstrate statistical stability. A qualitative evaluation performed by two independent experts in radiology and radiography verified the preservation of detailed organ and muscle boundaries.Keywords
Funding Information
- Royal Academy of Engineering
- Leverhulme Trust (LTRFI920\16\26)
- Crohn's and Colitis Foundation of America's (CCFA) (2018)
- National Institutes of Health (1R21DK123569-01)
This publication has 23 references indexed in Scilit:
- Fully Convolutional Networks for Semantic SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- 25 Years of Contrast-Enhanced MRI: Developments, Current Challenges and Future PerspectivesAdvances in Therapy, 2016
- Improving Computer-Aided Detection UsingConvolutional Neural Networks and Random View AggregationIEEE Transactions on Medical Imaging, 2015
- Discriminative dictionary learning for abdominal multi-organ segmentationMedical Image Analysis, 2015
- Fully convolutional networks for semantic segmentation2015
- A Likelihood and Local Constraint Level Set Model for Liver Tumor Segmentation from CT VolumesIEEE Transactions on Biomedical Engineering, 2013
- Computer-Aided Detection and Diagnosis in Medical ImagingComputational and Mathematical Methods in Medicine, 2013
- From label fusion to correspondence fusion: A new approach to unbiased groupwise registration2012
- Abdominal Multi-Organ Segmentation of CT Images Based on Hierarchical Spatial Modeling of Organ InterrelationsLecture Notes in Computer Science, 2012
- Automated segmentation of psoas major muscle in X-ray CT images by use of a shape model: preliminary studyRadiological Physics and Technology, 2011