Abstract When abnormal cells form in the brain, it is called a brain tumour. The unique blocking and proliferation of abnormal tissues in the brain can be found using magnetic resonance imaging (MRI) imaging of the brain. Due to advancements in medical imaging technology for auto detecting equipment, it is no longer necessary for a doctor to look at MRI scans to determine whether a patient has a tumour. As a result, it has proven handy for patients who do not wish to see a doctor immediately. Our study describes a method for segmenting abnormal brain tissues and determining whether the patient has a tumour. This approach detects a unique area of the brain and forecasts the likelihood of a tumour developing there. Mask regional-based convolutional neural network (Mask R-CNN) is a pre-trained deep neural network model that is used to distinguish objects from an image such as cars, animals, trees, and other objects. In comparison to many other similar methods based on MLP, VGG-16 model, and U-net model, we discovered that Mask R-CNN method performs the best. The clarity of the MRI scans has a big impact on the accuracy. The proposed system was able to outperform similar systems on the same dataset, achieving 74 percent Intersection over Union (IoU) score on the reference dataset, Brain MRI Images for Brain Tumour Detection.
Alan : Mühendislik
Dergi Türü : Uluslararası
Benzer Makaleler | Yazar | # |
---|
Makale | Yazar | # |
---|