Segmentation of brain tumor on magnetic resonance imaging using a convolutional architecture
This work addresses brain tumor segmentation for medical diagnosis and treatment planning, but it appears incremental as it uses a simple, computationally easy architecture without specifying major innovations.
The paper tackled brain tumor segmentation from MRI scans using a deep learning architecture, achieving an IoU of 0.95.
The brain is a complex organ controlling cognitive process and physical functions. Tumors in the brain are accelerated cell growths affecting the normal function and processes in the brain. MRI scans provides detailed images of the body being one of the most common tests to diagnose brain tumors. The process of segmentation of brain tumors from magnetic resonance imaging can provide a valuable guide for diagnosis, treatment planning and prediction of results. Here we consider the problem brain tumor segmentation using a Deep learning architecture for use in tumor segmentation. Although the proposed architecture is simple and computationally easy to train, it is capable of reaching $IoU$ levels of 0.95.