KiU-Net: Overcomplete Convolutional Architectures for Biomedical Image and Volumetric Segmentation

Most methods for medical image segmentation use U-Net or its variants as they have been successful in most of the applications. After a detailed analysis of these “traditional” encoder-decoder based approaches, we observed that they perform poorly in detecting smaller structures and are unable to segment boundary regions precisely. This issue can be attributed to the increase in receptive field size as we go deeper into the encoder. The extra focus on learning high level features causes U-Net based approaches to learn less information about low-level features which are crucial for detecting small structures. To overcome this issue, we propose using an overcomplete convolutional architecture where we project the input image into a higher dimension such that we constrain the receptive field from increasing in the deep layers of the network. We design a new architecture for im- age segmentation- KiU-Net which has two branches: (1) an overcomplete convolutional network Kite-Net which learns to capture fine details and accurate edges of the input, and (2) U-Net which learns high level features. Furthermore, we also propose KiU-Net 3D which is a 3D convolutional architecture for volumetric segmentation. We perform a detailed study of KiU-Net by performing experiments on five different datasets covering various image modalities. We achieve a good performance with an additional benefit of fewer parameters and faster convergence. We also demonstrate that the extensions of KiU-Net based on residual blocks and dense blocks result in further performance improvements. Code: https://github.com/jeya-maria-jose/KiU-Net-pytorch

I. Introduction

Medical image segmentation plays a pivotal role in computer-aided diagnosis systems which are helpful in making clinical decisions. Segmenting a region of interest like an organ or lesion from a medical scan is critical as it contains details like the volume, shape and location of the region of interest. Automatic methods proposed for medical image segmentation help in aiding radiologists for making fast and labor-less annotations. Early medical segmentation methods were based on traditional pattern recognition techniques like statistical modeling and edge detection filters. Later, machine learning approaches using hand-crafted features based on the modality and type of segmentation task were developed. Recently, the state of the art methods for medical image segmentation for most modalities like magnetic resonance imaging (MRI), computed tomography (CT) and ultrasound (US) are based on deep learning. As convolutional neural networks (CNNs) extract data-specific features which are rich in quality and effective in representing the image and the region of interest, deep learning reduces the hassle of extracting manual features from the image.