MKIS-Net: A Light-Weight Multi-Kernel Network for Medical Image Segmentation

TL;DR

MKIS-Net is a lightweight, multi-kernel neural network that improves medical image segmentation accuracy while significantly reducing the number of trainable parameters, making it efficient for clinical applications.

Contribution

The paper introduces MKIS-Net, a novel multi-kernel architecture that enhances segmentation performance with fewer parameters compared to existing methods.

Findings

Outperforms state-of-the-art segmentation methods on multiple tasks

Has over an order of magnitude fewer trainable parameters

Is at least four times smaller than comparable lightweight architectures

Abstract

Image segmentation is an important task in medical imaging. It constitutes the backbone of a wide variety of clinical diagnostic methods, treatments, and computer-aided surgeries. In this paper, we propose a multi-kernel image segmentation net (MKIS-Net), which uses multiple kernels to create an efficient receptive field and enhance segmentation performance. As a result of its multi-kernel design, MKIS-Net is a light-weight architecture with a small number of trainable parameters. Moreover, these multi-kernel receptive fields also contribute to better segmentation results. We demonstrate the efficacy of MKIS-Net on several tasks including segmentation of retinal vessels, skin lesion segmentation, and chest X-ray segmentation. The performance of the proposed network is quite competitive, and often superior, in comparison to state-of-the-art methods. Moreover, in some cases MKIS-Net has more than an order of magnitude fewer trainable parameters than existing medical image segmentation alternatives and is at least four times smaller than other light-weight architectures.