Brain tumor segmentation and classification: A one-decade review

Image segmentation is a common technique in digital image processing and analysis that partitions an image into several regions or zones, frequently based on the pixels' attributes. Brain tumor segmentation is a crucial task in medical image processing. Early identification of brain tumors enhances treatment options and increases the patient's chance of survival. Brain segmentation from a significant number of MR images obtained in medical treatment is a challenging and time-consuming assignment for cancer diagnosis and other brain diseases. That is why it is crucial to establish an efficient automatic image segmentation system for the diagnosis of brain tumors and other prevalent nervous diseases. The goal of this research is to undertake a systematic review of MRI-based brain tumor segmentation approaches. Deep learning techniques have proven useful for automatic segmentation in recent years and gained prominence, as these methods produce superior results and are thus better suited to this task than other methods. Deep learning algorithms may also be used to process enormous volumes of MRI-based image data quickly and objectively. Many review papers on traditional MRI-based brain tumor image segmentation algorithms are available.