Data Augmentation for Improved Brain Tumor Segmentation

Abstract

Deep neural networks (DNN) oblige large preprocessed samples of training annotated images for successful training, which makes the approach costly particularly in the biomedical imaging domain. The data augmentation technique is regularly used by researchers to enlarge the volume of training data, creating, and producing augmented data capable to train the network about the essential properties of uniformity and stoutness. The use of conventional methods of data augmentation in most training system scenarios strictly restrict its capabilities and negatively impact the output accuracy. In this paper, we propose an automatic data augmentation technique for synthesizing high-quality brain tumor images using generative adversarial network architecture to facilitate deep learning-based methods to be trained with the limited preprocessed samples more competently. The tumor segmentation has been performed through geodesic active contour via a level set formulation. The proposed technique has been validated with different modalities of magnetic resonance imaging brain image obtained from BRATS13 datasets. Simulational results showed an enhanced performance yielding a dice similarity coefficient of 0.942.

KEYWORDS:

• Active contour model
• Brain tumor
• Data augmentation
• DNN
• GAN,ROI
• Volumetric segmentation

Additional information

Notes on contributors

Ankur Biswas

Ankur Biswas is currently working as an assistant professor at TIT Narsingarh, Tripura(W) and obtained PhD from NIT Agartala in computer science & engineering. His research interest includes medical image analysis using machine learning.

Paritosh Bhattacharya

Paritosh Bhattacharya is currently working as associate professor in Mathematics Department of NIT Agartala. He has guided many PhD students in mathematics and computer science & engg. and published more than 60 research papers of international repute. Email: [email protected]

Santi P. Maity

Santi P Maity is currently working as professor in the Department of IT, IIEST, Shibpur, WB. He has guided so far 17 PhD students and published more than 260 research papers in international journals and conference proceedings. Email: [email protected]

Rita Banik

Rita Banik is currently working in ICFAI Universty, Tripura as assistant professor and pursuing PhD from NIT Agartala. Her research interest includes machine learning, hybrid power system, and HRES optimization. Email: [email protected]