A novel MRI segmentation method using CNN‐based correction network for MRI‐guided adaptive radiotherapy. Issue 11 (28th October 2018)

• Record Type: Journal Article
• Authors: Fu, Yabo; Mazur, Thomas R.; Wu, Xue; Liu, Shi; Chang, Xiao; Lu, Yonggang; Li, H. Harold; Kim, Hyun; Roach, Michael C.; Henke, Lauren; Yang, Deshan
• Is Part Of: Medical physics. Volume 45:Issue 11(2018)
• Page Start: 5129
• Page End: 5137
• Publication Date: 2018-10-28
• Subjects: deep learning -- image‐guided radiation therapy -- image segmentation -- MRI; Medical physics -- Periodicals; Medical physics; Geneeskunde; Natuurkunde; Toepassingen; Biophysics; Periodicals; Periodicals; Electronic journals; 610.153
• DOI: 10.1002/mp.13221
• Languages: English
• ISSNs: 0094-2405

Abstract

Abstract : Purpose: The purpose of this study was to expedite the contouring process for MRI‐guided adaptive radiotherapy (MR‐IGART), a convolutional neural network (CNN) deep‐learning (DL) model is proposed to accurately segment the liver, kidneys, stomach, bowel and duodenum in 3D MR images. Methods: Images and structure contours for 120 patients were collected retrospectively. Treatment sites included pancreas, liver, stomach, adrenal gland, and prostate. The proposed DL model contains a voxel‐wise label prediction CNN and a correction network which consists of two sub‐networks. The prediction CNN and sub‐networks in the correction network each includes a dense block which consists of twelve densely connected convolutional layers. The correction network was designed to improve the voxel‐wise labeling accuracy of a CNN by learning and enforcing implicit anatomical constraints in the segmentation process. Its sub‐networks learn to fix the erroneous classification of its previous network by taking as input both the original images and the softmax probability maps generated from its previous sub‐network. The parameters of each sub‐network were trained independently using piecewise training. The model was trained on 100 datasets, validated on 10 datasets and tested on the remaining 10 datasets. Dice coefficient, Hausdorff distance (HD) were calculated to evaluate the segmentation accuracy. Results: The proposed DL model was able to segment the organs with good accuracy. The correction network outperformed the conditional random field (CRF), a most comparable method that is usually applied as a post‐processing step. For the 10 testing patients, the average Dice coefficients were 95.3 ± 0.73, 93.1 ± 2.22, 85.0 ± 3.75, 86.6 ± 2.69, and 65.5 ± 8.90 for liver, kidneys, stomach, bowel, and duodenum, respectively. The mean Hausdorff Distance (HD) were 5.41 ± 2.34, 6.23 ± 4.59, 6.88 ± 4.89, 5.90 ± 4.05, and 7.99 ± 6.84 mm, respectively. Manual contouring, as to correct the automatic segmentation results, was four times as fast as manual contouring from scratch. Conclusion: The proposed method can automatically segment the liver, kidneys, stomach, bowel, and duodenum in 3D MR images with good accuracy. It is useful to expedite the manual contouring for MR‐IGART.