Intracranial hemorrhage detection using CNN-LSTM fusion model

Abstract

Intracranial Hemorrhage is a term used to describe bleeding between the brain tissue and the skull or within the brain tissue itself. It is life-threatening and needs immediate medical attention. As the first response, it is indispensable to detect the type of intracranial hemorrhage as soon as possible. Now, the manual detection methods require the help of an imaging expert and are certainly very time-consuming. Although there are several techniques for identifying them such as utilizing CT-scan images, magnetic resonance imaging (MRI), magnetic resonance angiogram (MRA), and ultrasound-based images, the results are still not adequate and have much room for improvement. In addition to these methods, researchers have also used imaging strategies based on Convolutional Neural Network (CNN) or Recurrent Neural Network (RNN) for this purpose. Therefore, this research aims to combine both these two fields and propose a model based on Deep Learning(DL) to detect intracranial hemorrhage. The goal of this paper is to automate the detection of intracranial hemorrhage and make the process more efficient and accurate. The model is expected to provide us with satisfactory results and can be used as an effective alternative to the existing methods.