An Efficient Encoder-Decoder CNN for Brain Tumor Segmentation in MRI Images

Abstract

An improved Encoder-Decoder Convolutional Neural Network (CNN) architecture is proposed for segmenting brain tumors in Magnetic Resonance Imaging (MRI). It consists of three encoding and decoding blocks. In the first encoding block, each input slice is convolved separately with two different filters and processed into upcoming encoding and decoding blocks for extracting the hierarchy of tumoral features. These are classified using softmax and compared with ground truth for evaluating performance. Experimental results were evaluated based on training and validation images in BRATS-2012, BRATS-2013 and BRATS-2018 datasets, which achieved 46.7%, 30.4% and 5.7% higher dice scores, respectively, compared to the existing segmentation methods.

KEYWORDS:

• Brain tumor
• Encoder-Decoder Convolutional Neural Network
• Feature visualization
• Magnetic Resonance Imaging (MRI)
• Segmentation

DISCLOSURE STATEMENT

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

G. Dheepa

G Dheepa is research scholar in the Department of Computer Science at the University of Madras and currently working as assistant professor in the Department of Master of Computer Applications, SRM Institute of Science and Technology, Ramapuram, Chennai. She received her MCA and MTech degrees from Dr MGR University and Sathyabama University, Tamil Nadu, India, respectively. She is specialized in image processing and artificial intelligence. Her main research area includes machine learning, artificial neural networks, medical image processing, and pattern recognition. Email: [email protected]

P. L. Chithra

P L Chithra is professor in the Department of Computer Science at the University of Madras. She received her MCA and PhD degrees from Alagappa University, Tamil Nadu, India and the University of Madras, Tamil Nadu, India, respectively. She has more than 30 years of experience in teaching. She has been serving as organizing chair and program chair of several international conferences and program committees of several international conferences. She is a PhD and MPhil research supervisor for guiding image processing techniques, big data analytics, and network security. She has conducted several refresher courses and published more than 110 papers in national and international journals. Corresponding author. Email: [email protected]