A novel MRI segmentation method using CNN‐based correction network for MRI‐guided adaptive radiotherapy

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.

Cardiac substructure segmentation with deep learning for improved cardiac sparing

“…Additionally, there were improvements in MDA up to 1.21 mm and 1.96 mm for the LV and LA, respectively. Aside from removing spurious outlying points, CRFs also improved the smoothed appearance of the segmentations as needed for clinical application . CRF tuning required different parameters for cardiac substructures based on size and shape, much like the work completed by Rajchl et al .…”

Deep learning-based auto-segmentation of targets and organs-at-risk for magnetic resonance imaging only planning of prostate radiotherapy

“…A pretrained model that is publicly available was used as an initialization point for both the encoder and decoder portions of the DeepLabV3+ architecture, except the last 3 × 3 layer, which was adjusted to the output number of structures, including the constraining structure, large bowel (7). The model weights for all other layers were initialized using the same network pretrained on the Microsoft Common Objects in Context (COCO) and PASCAL Visual Object Classes (VOC) challenge datasets.…”

“…Because these methods are the most accurate machine learning techniques [5], a deep learning approach to automatically segment targets and OARs in prostate radiotherapy was performed. Recent works on deep learning have shown the feasibility to generate highly accurate segmentations https://doi.org/10.1016/j.phro.2019.11.006 for clinical use in radiation therapy, but require large, expert-segmented datasets (on the order of hundreds of patients) [6,7]. The large expert-labeled datasets are required to estimate the high number of parameters of convolutional layers in these deep learning models.…”

Deep learning in medical image registration: a review

“…The field of medical image registration has been evolving rapidly with hundreds of papers published each year. Recently, DL-based methods have changed the landscape of medical image processing research and achieved the-state-of-art performances in many applications [25,27,45,58,84,85,86,88,89,97,98,156,157,158,160,161]. However, deep learning in medical image registration has not been extensively studied until the past three to four years.…”