An Efficient Implementation of Deep Convolutional Neural Networks for MRI Segmentation

Abstract

Image segmentation is one of the most common steps in digital image processing, classifying a digital image into different segments. The main goal of this paper is to segment brain tumors in magnetic resonance images (MRI) using deep learning. Tumors having different shapes, sizes, brightness and textures can appear anywhere in the brain. These complexities are the reasons to choose a high-capacity Deep Convolutional Neural Network (DCNN) containing more than one layer. The proposed DCNN contains two parts: architecture and learning algorithms. The architecture and the learning algorithms are used to design a network model and to optimize parameters for the network training phase, respectively. The architecture contains five convolutional layers, all using 3 × 3 kernels, and one fully connected layer. Due to the advantage of using small kernels with fold, it allows making the effect of larger kernels with smaller number of parameters and fewer computations. Using the Dice Similarity Coefficient metric, we report accuracy results on the BRATS 2016, brain tumor segmentation challenge dataset, for the complete, core, and enhancing regions as 0.90, 0.85, and 0.84 respectively. The learning algorithm includes the task-level parallelism. All the pixels of an MR image are classified using a patch-based approach for segmentation. We attain a good performance and the experimental results show that the proposed DCNN increases the segmentation accuracy compared to previous techniques.

Primary Central Nervous System Lymphoma: Clinical Evaluation of Automated Segmentation on Multiparametric MRI Using Deep Learning

“…In this study the DLM provided high segmentation performance, with the results being comparable to research focusing on automated glioblastoma and glioma segmentation 17,19,27,28 . In this context, Perkuhn et al reported DSCs between 0.62 and 0.86 for the differing tumor components of glioblastoma while using the same DLM as in the present study 17 .…”

“…17 Using a different CNN, Menze et al and Hoseini et al calculated DSCs of 0.74-0.85 and 0.84-0.90, for glioma segmentations, respectively. 19,27 Kickingereder et al reported DSCs between 0.89 and 0.93 for an artificial neural network trained on a larger cohort of patients with glioblastoma. 28 Given the comparable results of the study by Perkuhn et al 17 and the present study, a DLM trained on gliomas and achieving accurate segmentation of glioblastomas can be applied on PCNSL, despite their often different appearance and overall complex tumor structure without noticeably decreasing segmentation performance.…”

AdaptAhead Optimization Algorithm for Learning Deep CNN Applied to MRI Segmentation

“…We already used the DCNN model to improve segmentation of MR images. The model was evaluated on the public BRATS 2016 dataset with patch-based approach for segmentation, resulting in dice similarity metric 0.90 for complete, 0.85 for core, and 0.84 for enhancing regions [26].…”

A New Optimizer for Image Classification using Wide ResNet (WRN)

“…In recent years, the approach of deep convolutional neural networks (CNN) of sequential type has dominated the field of image classification and becoming superior to the traditional approach of handcrafted features [12][13][14] . In contrast to hand-crafted features, deep CNNs could learn rich highly abstract image features from the training dataset of large scale images to represent complex objects in an efficient way and can be faster.…”