Deep learning for automated segmentation of radiation-induced changes in cerebral arteriovenous malformations following radiosurgery.
Authors
Affiliations (9)
Affiliations (9)
- School of Medicine, College of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan.
- Department of Neurosurgery, Neurological Institute, Taipei Veterans General Hospital, Taipei, Taiwan.
- Department of Neurosurgery, New Taipei City Hospital Sanchong Branch, Taipei, Taiwan.
- Department of Computer Science & Information Engineering, National United University, Miaoli, Taiwan.
- Department of Radiology, Taipei Veterans General Hospital, Taipei, Taiwan.
- Department of Heavy Particles & Radiation Oncology, Taipei Veterans General Hospital, Taipei, Taiwan.
- University of Texas Health Science Center, Houston, TX, USA.
- In-Service Master Program in Artificial Intelligence in Medicine, College of Medicine, Taipei Medical University, No.250, Wuxing St., Xinyi Dist, Taipei City, 110, Taiwan. [email protected].
- Clinical Big Data Research Center, Taipei Medical University Hospital, Taipei Medical University, Taipei, Taiwan. [email protected].
Abstract
Despite the widespread use of stereotactic radiosurgery (SRS) to treat cerebral arteriovenous malformations (AVMs), this procedure can lead to radiation-induced changes (RICs) in the surrounding brain tissue. Volumetric assessment of RICs is crucial for therapy planning and monitoring. RICs that appear as hyper-dense areas in magnetic resonance T2-weighted (T2w) images are clearly identifiable; however, physicians lack tools for the segmentation and quantification of these areas. This paper presents an algorithm to calculate the volume of RICs in patients with AVMs following SRS. The algorithm could be used to predict the course of RICs and facilitate clinical management. We trained a Mask Region-based Convolutional Neural Network (Mask R-CNN) as an alternative to manual pre-processing in designating regions of interest. We also applied transfer learning to the DeepMedic deep learning model to facilitate the automatic segmentation and quantification of AVM edema regions in T2w images. The resulting quantitative findings were used to explore the effects of SRS treatment among 28 patients with unruptured AVMs based on 139 regularly tracked T2w scans. The actual range of RICs in the T2w images was labeled manually by a clinical radiologist to serve as the gold standard in supervised learning. The trained model was tasked with segmenting the test set for comparison with the manual segmentation results. The average Dice similarity coefficient in these comparisons was 71.8%. The proposed segmentation algorithm achieved results on par with conventional manual calculations in determining the volume of RICs, which were shown to peak at the end of the first year after SRS and then gradually decrease. These findings have the potential to enhance clinical decision-making. Not applicable.