Multi-organ auto-delineation in head-and-neck MRI for radiation therapy using mask scoring regional convolutional neural network

MRI allows accurate and reliable organ delineation for many disease sites in radiation therapy due to its superior soft-tissue contrast. Manual organ-at-risk (OAR) delineation is labor-intensive, time-consuming and subjective. This study aims to develop a deep learning-based automated multi-organ segmentation method to release the labor and accelerate the treatment planning process for head-and-neck (HN) cancer radiotherapy. We propose a novel regional convolutional neural network (R-CNN) architecture, namely, mask scoring R-CNN, where, a deep attention feature pyramid network is used as backbone to extract the coarse features given MRI, followed by the feature refinement using R-CNN. The final segmentation is obtained through mask and mask scoring networks taking those refined feature maps as input. With the mask scoring mechanism incorporated into conventional mask supervision, the classification error can be highly minimized in conventional mask R-CNN architecture. A retrospective study was carried out on a cohort of 60 HN cancer patients receiving external beam radiation therapy. Five-fold cross validation was performed for the assessment of our proposed method. The Dice similarity coefficients of brain stem, left/right cochlea, left/right eye, larynx, left/right lens, mandible, optic chiasm, left/right optic nerve, oral cavity, left/right parotid, pharynx, and spinal cord are 0.89±0.06, 0.68±0.14/0.68±0.18, 0.89±0.07/0.89±0.05, 0.90±0.07, 0.67±0.18/0.67±0.10, 0.82±0.10, 0.61±0.14, 0.67±0.11/0.68±0.11, 0.92±0.07, 0.85±0.06/0.86±0.05, 0.80±0.13, and 0.77±0.15, respectively. After the model training, all OARs can be segmented within 1 minute. We have proposed and investigated a novel deep learning-based fully automatic HN multi-organ segmentation algorithm for MRI of HN cancer patients. The accurate HN OAR delineation enables further development of MRI-only based radiotherapy workflow for HN cancer.