Evaluation of Preprocessing Techniques for U-Net Based Automated Liver Segmentation
Open Access
- 5 April 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 187-192
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.Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- Automatic 3D liver segmentation based on deep learning and globally optimized surface evolutionPhysics in Medicine & Biology, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Automated method for detection and segmentation of liver metastatic lesions in follow-up CT examinationsJournal of Medical Imaging, 2015
- Fully convolutional networks for semantic segmentation2015
- Deep learningNature, 2015
- An innovative technique for contrast enhancement of computed tomography images using normalized gamma-corrected contrast-limited adaptive histogram equalizationEURASIP Journal on Advances in Signal Processing, 2015
- Normalization: A Preprocessing StageIARJSET, 2015
- Automatic Liver Tumor Segmentation in Follow-Up CT Scans: Preliminary Method and Results2015
- Comparison and Evaluation of Methods for Liver Segmentation From CT DatasetsIEEE Transactions on Medical Imaging, 2009
- An evaluation of the effectiveness of adaptive histogram equalization for contrast enhancementIEEE Transactions on Medical Imaging, 1988