Deep Learning-based Brain Tumour Segmentation

Abstract

Artificial Intelligence has changed our outlook towards the whole world, and it is regularly used to better understand all the data and information that surround us in our everyday lives. One such application of Artificial Intelligence in a real-world scenario is the extraction of data from various images and interpreting them in different ways. This includes applications like object detection, image segmentation, image restoration, etc. While every technique has its own area of application, image segmentation has a variety of applications extending from the complex medical field to regular pattern identification. The aim of this paper is to research about several FCNN-based semantic segmentation techniques to develop a deep learning model that is able to segment tumours in brain MRI images to a high degree of precision and accuracy. The aim is to try several different architectures and experiments with several loss functions to improve the accuracy of our model and obtain the best model for our classification including newer loss functions like dice loss function, hierarchical dice loss function cross entropy, etc.

KEYWORDS:

• Dice loss
• FCNN
• Leaky ReLU
• MRI
• ReLU
• Segmentation
• U-Net

Acknowledgement

I would like to thank The Cancer Imaging Archive (TCIA) for compiling and providing this dataset.

Additional information

Notes on contributors

Pattabiraman Ventakasubbu

V Pattabiraman has 20 years of professional experience, out of which he spent as much as 18 years in teaching and research and the remaining 2 years in industry. He has published more than 40 papers in various national and international peer-reviewed journals in the last five years. He has also presented several papers in international conferences. His research expertise covers a wide range of subject areas, including knowledge discovery and data mining, big data analytics, machine learning, deep learning, database technologies, etc. Email: [email protected]

Parvathi Ramasubramanian

Parvathi R completed her doctoral degree from Anna University, Chennai, India, by contributing her ideas to the field of spatial data mining. She has a teaching experience of over 22 years in the field of computer applications. Her research interests include data mining, recommendation systems and social network analysis. She has authored articles in big data analytics for renowned publications. Corresponding Author. Email: [email protected]