Deep Learning: A Pathway for Automated Brain Tumor Segmentation in MRI Images

Abstract

Deep learning techniques are recently exploited for segmentation of medical images. These deep learning techniques have accomplished state-of-art conduct for automatic medical image segmentation. Image segmentation helps in quantitative and qualitative analysis of the medical images, which leads to diagnosis of various diseases. Manual segmentation of medical images is a laborious task that prevents early diagnosis of diseases. For these particular reasons, automated techniques play a major role in medical image segmentation. The recent research is focused on deep learning algorithms for efficient automatic medical image segmentation. Deep learning algorithms are classified as supervised as well as unsupervised learning. Supervised learning consists of convolutional neural networks (CNNs) and unsupervised learning consists of stacked auto-encoder, restricted Boltzmann’s machine (RBM), and deep belief networks. CNNs comprise convolutional layer, pooling layer, dropout layer, and fully connected layer. The convolutional layer carries out the convolution operation with a set of kernels along with weights and added biases individually creating a new feature map on the input image at each layer. Stacked auto-encoder models are designed by insertion of different layers termed to be auto-encoder layers in the form of stack. These layers take image as an input and extracts different features in the form of feature maps in an unsupervised mode lacking labeled data. It is a model that takes input data, gathers feature representations from this, and then uses these feature representations to restructure output data. According to the literature survey, auto-encoder layers are trained independently after which the full network is used to make a prediction by fine-tuning it using supervised training. The neurons present in deep belief nets are densely connected which helps in rapid and accurate learning of a good set of parameters. RBMs are a type of Markov random fields, consisting of input layer or visible layer and a hidden layer that brings hidden feature representation. There are bidirectional connections between the nodes, so latent feature representation extracted from an input vector and vice versa. This chapter provides an outline on the state of deep learning algorithms for medical image segmentation, highlighting those facets that are frequently useful for brain tumor segmentation. In addition, comparative analysis of the deep learning algorithms is discussed. This concludes that with the different algorithms for segmentation tumor regions from brain MRI images, deep learning has proven to be the most effective in the recent trends.