Redefining Diagnosis: A Novel Approach to Detect Brain Hemorrhages using Modified Learning Principles with Artificial Intelligence Association

Numerous studies have concentrated on developing computer-aided diagnostic methods. They work on the principle of fast and accurate diagnosis by processing and analysis of pictures of various human body parts. In order to determine if a brain haemorrhage is present in Computed Topography (CT) images of the brain, this research follows the aforementioned technique. In addition, the kind of haemorrhage is determined. An AI-assisted prediction scheme, AI-based Brain Haemorrhages Detection (AIBHD), is presented in this paper. In order to determine how well the suggested model works, it is cross-validated with regard to the conventional learning scheme, Random Forest Classifier (RFC). Image preprocessing, segmentation, feature extraction, and classification are some of the steps that make up the developed system. The trials that were carried out yielded really encouraging outcomes. A brain haemorrhage is a form of stroke in which blood clots form in the brain's surrounding tissues as a result of an arterial burst. This method classifies brain haemorrhages using computed tomography (CT) scans. The suggested approach, AIBHD, is used for picture segmentation after preprocessing and morphological procedures. The classification model takes this extracted picture as input and outputs details on the area and percentage of haemorrhage. The results of this study improve the likelihood of identifying haemorrhage in a picture and categorize it accordingly. On average, the system's accuracy in haemorrhage classification is determined to be 97.34%.