Proposed Hybrid CNN+LSTM method to Diagnosing different type ofTumor in Magnetic Resonance Brain Images

Diagnosing tumor size and distinguishing tumor types from each other is one of the mainchallenges in treating tumors and assessing disease progression. Manual tumor segmentation inthree-dimensional Magnetic Resonance images (volume MRI) is a time-consuming and tedioustask. Its accuracy depends heavily on the operator's experience doing it. The need for an accurateand fully automatic method for segmenting brain tumors and measuring tumor size is strongly felt.This paper first uses a combined CNN-LSTM method to detect HG and LG tumors in ۳D brainimages. Then it used the UNET Neural Network to improve the location of the tumor in the brain.In this article, we use BRATS ۲۰۱۸ database images, and manual segmentation is used as theGrand truth. In this paper, we showed that the proposed method could effectively performsegmentation.

Keywords:

Brain Tumor , Classification MR Images , Deep Learning Algorithms , Long shortterm Memory , Convolutional Neural Networks.