Brain Disease Classification along with Age Estimation from MRI

Abstract

Deep neural networks can effectively be used to predict the type of brain disease caused to the patient and to estimate the age of the patient. This can be used for identifying the age related disorders. So, we are using MobileNet a machine learning algorithm, and Res Net deep convolutional neural network, by using transfer learning. In transfer learning these models are pre trained on larger data sets. These algorithms have been used to train brain MRI scans that have been divided into three classes [1] Normal, which has not been affected by any disease, [2] Mild Cognitive Impairment, and [3] Alzheimer disease. From the categorized photographs the age of the patient is determined easily. We are going to train our model by using MOBILENET and RESNET algorithms by using the dataset of MRI images along with the accompanying disease type.By using this knowledge, the model may identify patterns in the MRI data that point to particular brain illnesses and patient age. The trained model is further used to find the disease type and age of the patients. The outcomes demonstrate that the technique is capable of achieving high accuracy in tasks involving both disease categorization and age estimation. In general, the suggested techniques for categorizing brain disorders and determining age from MRI scans offer a viable answer for enhancing the effectiveness and precision of medical diagnosis and treatment planning for patients with brain diseases. By this model we can predict results in larger scale real time data in short period of time.