Using deep learning models to analyze patients with intracranial tumors, to study the image segmentation and standard results by clinical depiction complications of cerebral edema after receiving radiotherapy. In this study, patients with intracranial tumors receiving computer knife (CyberKnife M6) stereotactic radiosurgery were followed using the treatment planning system (MultiPlan 5.1.3) to obtain before-treatment and four-month follow-up images of patients. Images were preprocessed using images of cerebral edema complications (22 images, T2-flair) after treatment. The image interpolation was increased to 109 images and depicted as a standard image (ground truth segmentation, GTS) by the clinician. The TensorFlow platform was used as the core architecture for training neural networks. Supervised learning was used to build labels for the cerebral edema dataset by using Labelme, Mask region-based convolutional neural networks (R-CNN), and region growing algorithms. The three evaluation coefficients DICE, Jaccard (intersection over union, IoU), and volumetric overlap error (VOE) were used to analyze and calculate the algorithms in the image collection for cerebral edema image segmentation and the standard as described by the oncologists. When DICE and IoU indices were 1, and the VOE index was 0, the results were similar to those described by the clinician. The study found using the Mask R-CNN model in the segmentation of cerebral edema, the DICE index was 0.88, the IoU index was 0.79, and the VOE index was 2.0. The DICE, IoU, and VOE indices using region growing were 0.77, 0.64, and 3.2, respectively. Using the evaluated index, the Mask R-CNN model had the best segmentation effect, the volume of cerebral edema that most closely described the patient by the clinician. This study analyzes the situation of patients with intracranial tumors following radiotherapy after four months of follow-up to check for radiation-induced cerebral edema, using two methods to segment medical images. Among them, the instance segmentation method based on the deep learning Mask R-CNN has obtained the best results compared to the standard of the clinician in terms of describing the complications of cerebral edema. This method can be implemented in the clinical workflow in the future to achieve good complication segmentation and provide clinical evaluation and guidance suggestions.