Mubaraq Yakubu, Navodini Wijethilake, Jonathan Shapey, Andrew King, Alexander Hammers
This review evaluates automatic segmentation methods for pituitary adenomas and glands in MRI, highlighting the promise of U-Net-based models but noting the need for further improvements and comprehensive reporting of metrics.
Accurate identification of the pituitary gland and related tumors in MRI scans is crucial for their effective diagnosis and treatment. This study reviews various automated techniques for segmenting these structures in MRI images, focusing on their accuracy and efficiency. Many studies use deep learning models, particularly U-Net, which show potential in identifying adenomas. However, more work is needed to improve these methods, especially for smaller structures like the pituitary gland, and to ensure they are reliable across different patient demographics and MRI settings.
