Published Paper Details:

In recent years, there has been a surge of interest in the healthcare research community for AI to help with big data analytic and decision-making. One of the primary reasons for this is the massive influence of deep learning on the use of complicated healthcare data. The main goal here is to identify brain tumors and brain bleeding by means of deep learning and improve care for those who are suffering. Tumors are the term used to describe abnormal cell growths in the brain, while cancer is the term used to describe malignant tumors. Brain cancer regions are typically discovered via CT or MRI imaging. For the detection of brain tumors, there are certain methods. These include molecular testing, lumbar puncture, cerebral angiogram, and positron emission tomography (PET scan or PET-CT scan). This study analyses the illness state using data or images from an MRI scan. The goals of this research are to (i) segment the tumor region and (ii) identify the abnormal image. The segmented mask can be used to evaluate the tumor's density, which will aid in treating the tumor in the easiest and fastest way possible given the data collected. A deep learning algorithm is used to analyze MRI pictures and find anomalies. Multi-level thresholding is used to divide the tumor region for analysis. The quantity of cancerous pixels indicates the density of the afflicted area.