Deep learning based automatic contour refinement for inaccurate auto-segmentation in MR-guided adaptive radiotherapy

Abstract

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.

Pretreatment information–aided automatic segmentation for online magnetic resonance imaging‐guided prostate radiotherapy

“…In this case, radiation oncologists are still required to edit the contours, prolonging the treatment time. 28,29 In contrast, the conventional DL was good in delineating the bladder (94.5%) and femur heads (91.5%) but was poor for CTV (80.8%) and rectum (77.9%). This was because DL could easily identify structures with clear boundaries, such as the bladder and femur heads.…”

“…However, it failed in the segmentation of the bladder (81.4%) and rectum (83.1%) because the current DIR algorithms could not precisely align structures with excessive deformation. In this case, radiation oncologists are still required to edit the contours, prolonging the treatment time 28,29 …”

“…The DL model trained from popular data will not perform well when applied to new and unseen cases. [26][27][28][29] The existing DIR and DL methods are suboptimal, so the development of a reliable and efficient automatic segmentation algorithm is an urgent need of online MRI-guided prostate radiotherapy. Ding et al 27,28 developed a DL-based automatic contour refinement to correct the segmentation errors in regular method.…”

“…[26][27][28][29] The existing DIR and DL methods are suboptimal, so the development of a reliable and efficient automatic segmentation algorithm is an urgent need of online MRI-guided prostate radiotherapy. Ding et al 27,28 developed a DL-based automatic contour refinement to correct the segmentation errors in regular method. They focused on algorithmic enhancements, instead of using supplemental information.…”

“…Moreover, significant intensity inhomogeneities among MR images across patients can be observed even with the same scanner. The DL model trained from popular data will not perform well when applied to new and unseen cases 26–29 …”