Auto-Segmentation and Classification of Glioma Tumors with the Goals of Treatment Response Assessment Using Deep Learning Based on Magnetic Resonance Imaging

Abstract

Background: Glioma is the most common primary intracranial neoplasm in adults. Radiotherapy is a treatment approach in glioma patients, and Magnetic Resonance Imaging (MRI) is a bene cial diagnostic tool in treatment planning. Treatment response assessment in glioma patients is usually based on the Response Assessment in Neuro Oncology (RANO) criteria. The limitation of assessment based on RANO is two-dimensional (2D) manual measurements. Deep learning (DL) has great potential in neuro-oncology to improve the accuracy of response assessment.Method: In the current research, rstly, the BraTS 2018 Challenge dataset included 210 HGG and 75 LGG were applied to train a designed U-Net network for automatic tumor and intra-tumoral segmentation, followed by training of the designed classi er with transfer learning for determining grading HGG andLGG. Then, designed networks were employed for the segmentation and classi cation of local MRI images of 49 glioma patients pre and post-radiotherapy. The results of tumor segmentation and its intratumoral regions were utilized to determine the volume of different regions and treatment response assessment.Results: Treatment response assessment demonstrated that radiotherapy is effective on the whole tumor and enhancing region with p-value ≤ 0.05 with a 95% con dence level, while it did not affect necrosis and peri-tumoral edema regions.Conclusion: This work demonstrated the potential of using deep learning in MRI images to provide a bene cial tool in the automated treatment response assessment so that the patient can obtain the best treatment.