Brain Tumor Detection and Classification from MRI Images using Fuzzy Thresholding, a Convolutional Neural Network and Grad-CAM Explanation

Brain tumor is a serious disease and finding it early on the nearby tissue and cause headaches, seizures, vision helps a lot in planning the treatment. Reading MRI scans by problems or changes in memory and behaviour. Because of hand takes time and it depends on how experienced the doctor this, finding the tumor early and knowing its type is very is. In this paper we present a system that detects and classifies important for choosing the treatment, and the type decides if a brain tumors from MRI images using fuzzy thresholding, a the doctor will go for surgery, radiation, drugs or just careful convolutional neural network (CNN) and Grad-CAM follow-up [2]. explanation. First the images are converted to grayscale, resized, filtered with a median filter and enhanced with MRI is the scan most often used for this job. It uses a CLAHE. Then fuzzy c-means thresholding picks out the strong magnetic field and radio waves, it shows the soft tissue suspected tumor region and the tumor area is estimated from of the brain in good detail, and it does not use ionizing the mask. A small CNN with four convolutional blocks and radiation. A single patient can have many slices in different about 0.39 million learnable parameters classifies each image planes and with different sequences, so a radiologist has a lot into glioma, meningioma, pituitary tumor or no tumor, and of images to go through. The reading is slow and it depends on Grad-CAM draws a heatmap on the tumor region so that the the experience of the person. Two doctors can also disagree on doctor can see why the network gave that answer. The system a difficult slice, mainly when the tumor is small or when its was built in MATLAB and tried on a dataset of 5589 MRI edge is blurred. images. The CNN reached an overall accuracy of 71.93% with an average precision of 75.99%, recall of 71.98% and F1-score of 70.26%. The no-tumor class was classified best (F1 88.37%) while meningioma was often mixed up with pituitary (recall 32.29%). When the three tumor classes are merged into one, the same predictions separate tumor from no tumor with 94.31% accuracy. The fuzzy segmentation and the heatmap worked well on the sample shown, but the four-class classifier needs more training before it can be trusted, and we discuss the reasons, the limits of the evaluation and the next steps.