Body Part Regression With Self-Supervision
- 9 February 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 40 (5), 1499-1507
- https://doi.org/10.1109/tmi.2021.3058281
Abstract
Body part regression is a promising new technique that enables content navigation through self-supervised learning. Using this technique, the global quantitative spatial location for each axial view slice is obtained from computed tomography (CT). However, it is challenging to define a unified global coordinate system for body CT scans due to the large variabilities in image resolution, contrasts, sequences, and patient anatomy. Therefore, the widely used supervised learning approach cannot be easily deployed. To address these concerns, we propose an annotation-free method named blind-unsupervised-supervision network (BUSN). The contributions of the work are in four folds: (1) 1030 multi-center CT scans are used in developing BUSN without any manual annotation. (2) the proposed BUSN corrects the predictions from unsupervised learning and uses the corrected results as the new supervision; (3) to improve the consistency of predictions, we propose a novel neighbor message passing (NMP) scheme that is integrated with BUSN as a statistical learning based correction; and (4) we introduce a new pre-processing pipeline with inclusion of the BUSN, which is validated on 3D multi-organ segmentation. The proposed method is trained on 1,030 whole body CT scans (230,650 slices) from five datasets, as well as an independent external validation cohort with 100 scans. From the body part regression results, the proposed BUSN achieved significantly higher median R-squared score (=0.9089) than the state-of-the-art unsupervised method (=0.7153). When introducing BUSN as a preprocessing stage in volumetric segmentation, the proposed pre-processing pipeline using BUSN approach increases the total mean Dice score of the 3D abdominal multi-organ segmentation from 0.7991 to 0.8145.Funding Information
- Vanderbilt-12Sigma Research Grant
- NSF CAREER (1452485)
- NIH
- NIH (1R01EB017230)
This publication has 23 references indexed in Scilit:
- 3D Deeply Supervised Network for Automatic Liver Segmentation from CT VolumesPublished by Springer Science and Business Media LLC ,2016
- Holistically-Nested Edge DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Efficient multi-atlas abdominal segmentation on clinically acquired CT with SIMPLE context learningMedical Image Analysis, 2015
- Deep convolutional networks for pancreas segmentation in CT imagingPublished by SPIE-Intl Soc Optical Eng ,2015
- Developing patient-specific dose protocols for a CT scanner and exam using diagnostic reference levelsPediatric Radiology, 2014
- Open Access Series of Imaging Studies (OASIS): Cross-sectional MRI Data in Young, Middle Aged, Nondemented, and Demented Older AdultsJournal of Cognitive Neuroscience, 2007
- Scanning protocols for multislice CT scannersThe British Journal of Radiology, 2004
- Unsupervised and supervised data clustering with competitive neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Least Median of Squares RegressionJournal of the American Statistical Association, 1984
- Random sample consensusCommunications of the ACM, 1981