Evaluation of Preprocessing Techniques for U-Net Based Automated Liver Segmentation

TL;DR

This study evaluates how different preprocessing techniques affect U-Net based automated liver segmentation in CT images, finding that a combination of HU-windowing, median filtering, and z-score normalization yields optimal results.

Contribution

It systematically investigates the impact of various preprocessing methods on liver segmentation accuracy using deep learning, identifying the most effective combination.

Findings

Optimal preprocessing combination: HU-windowing, median filtering, z-score normalization

Achieved Dice coefficient of 96.93% in training

Validated high segmentation accuracy with 90.77% and 90.84% in validation and testing

Abstract

To extract liver from medical images is a challenging task due to similar intensity values of liver with adjacent organs, various contrast levels, various noise associated with medical images and irregular shape of liver. To address these issues, it is important to preprocess the medical images, i.e., computerized tomography (CT) and magnetic resonance imaging (MRI) data prior to liver analysis and quantification. This paper investigates the impact of permutation of various preprocessing techniques for CT images, on the automated liver segmentation using deep learning, i.e., U-Net architecture. The study focuses on Hounsfield Unit (HU) windowing, contrast limited adaptive histogram equalization (CLAHE), z-score normalization, median filtering and Block-Matching and 3D (BM3D) filtering. The segmented results show that combination of three techniques; HU-windowing, median filtering and z-score normalization achieve optimal performance with Dice coefficient of 96.93%, 90.77% and 90.84% for training, validation and testing respectively.