Search

Objective. Fast and accurate auto-segmentation is essential for magnetic resonance-guided adaptive radiation therapy (MRgART). Deep learning auto-segmentation (DLAS) is not always clinically acceptable, particularly for complex abdominal organs. We previously reported an automatic contour refinement (ACR) solution of using an active contour model (ACM) to partially correct the DLAS contours. This study aims to develop a DL-based ACR model to work in conjunction with ACM-ACR to further improve the contour accuracy. Approach. The DL-ACR model was trained and tested using bowel contours created by an in-house DLAS system from 160 MR sets (76 from MR-simulation and 84 from MR-Linac). The contours were classified into acceptable, minor-error and major-error groups using two approaches of contour quality classification (CQC), based on the AAPM TG-132 recommendation and an in-house classification model, respectively. For the major-error group, DL-ACR was applied subsequently after ACM-ACR to further refine the contours. For the minor-error group, contours were directly corrected by DL-ACR without applying an initial ACM-ACR. The ACR workflow was performed separately for the two CQC methods and was evaluated using contours from 25 image sets as independent testing data. Main results. The best ACR performance was observed in the MR-simulation testing set using CQC by TG-132: (1) for the major-error group, 44% (177/401) were improved to minor-error group and 5% (22/401) became acceptable by applying ACM-ACR; among these 177 contours that shifted from major-error to minor-error with ACM-ACR, DL-ACR further refined 49% (87/177) to acceptable; and overall, 36% (145/401) were improved to minor-error contours, and 30% (119/401) became acceptable after sequentially applying ACM-ACR and DL-ACR; (2) for the minor-error group, 43% (320/750) were improved to acceptable contours using DL-ACR. Significance. The obtained ACR workflow substantially improves the accuracy of DLAS bowel contours, minimizing the manual editing time and accelerating the segmentation process of MRgART.

PURPOSE: To reduce workload and inconsistencies in organ segmentation for radiation treatment planning, we developed and evaluated general and custom auto-segmentation models on CT for three major tumor sites using a well-established deep convolutional neural network (DCNN). METHODS AND MATERIALS: Five CT-based auto-segmentation models for 42 organs at risk (OARs) in head and neck (HN), abdomen (ABD) and male pelvis (MP) were developed using a full 3D DCNN architecture. Two types of DL models were separately trained using either general diversified multi-institutional datasets or custom well controlled single institution datasets. To improve segmentation accuracy, an adaptive spatial resolution approach for small and/or narrow OARs and a pseudo scan extension approach, when CT scan length is too short to cover entire organs, were implemented. The performance of the obtained models was evaluated based on accuracy and clinical applicability of the auto-segmented contours using qualitative visual inspection and quantitative calculation of dice similarity coefficient (DSC), mean distance to agreement (MDA), and time efficiency. RESULTS: The five DL auto-segmentation models developed for the three anatomical sites were found to have high accuracy (DSC ranging from 0.8 – 0.98) for 74% OARs and marginally acceptable for 26% OARs. The custom models performed slightly better than the general models, even with smaller custom datasets used for the custom model training. The organ-based approaches improved auto-segmentation accuracy for small or complex organs (e.g., eye lens, optic nerves, inner ears, and bowels). Compared with traditional manual contouring times, the auto-segmentation times, including subsequent manual editing, if necessary, were substantially reduced by 88% for MP, 80% for HN, and 65% for ABD models. CONCLUSIONS: The obtained auto-segmentation models, incorporating organ-based approaches were found to be effective and accurate for most OARs in the male pelvis, head and neck and abdomen. We have demonstrated that our multi-anatomical deep learning auto-segmentation models are clinically useful for radiation treatment planning.