Publications by authors named "Hong-Li Wan"
Objective: To establish a brain hematoma CT image segmentation method based on watershed and region-growing algorithm so as to measure hematoma volume quickly and accurately, to explore the consistency between the results of this segmentation method and those of manual segmentation, the clinical gold standard, and to compare the results of this method with the calculation of the two Tada formulas commonly used in clinical practice.
Methods: The preoperative CT images of 152 patients who were treated for spontaneous cerebral hemorrhage at the Department of Neurosurgery, West China Hospital, Sichuan University between January 2018 and June 2019 were retrospectively collected. The CT images were randomly assigned, by using a random number table, to the training set, the test set and the validation set, which contained 100 patients, 22 patients and 30 patients, respectively.
[Application of Improved Unet Network in the Recognition and Segmentation of Hemorrhage Regions in Brain CT Images].
Sichuan Da Xue Xue Bao Yi Xue Ban
January 2022
Article Synopsis
- The study aimed to evaluate the effectiveness of the improved Unet network for identifying and segmenting areas of hemorrhage in brain CT scans from patients with spontaneous intracerebral hemorrhage.
- Researchers analyzed 476 CT images, with 430 images used for training the Unet model and 46 for testing its ability to segment hemorrhage regions, comparing its performance to other networks like FCN-8s and Unet++.
- Results showed that the improved Unet network significantly outperformed the other models in segmentation accuracy, indicating it could be a valuable tool for helping clinicians in decision-making and managing brain hemorrhages.