Related Experiment Video
Updated: Mar 14, 2026
08:41
Novel In Vivo Micro-Computed Tomography Imaging Techniques for Assessing the Progression of Non-Alcoholic Fatty Liver Disease
Published on: March 24, 2023
1.9K
IFCM Based Segmentation Method for Liver Ultrasound Images.
1Department of Electrical Engineering, Indian Institute of Technology Roorkee, Roorkee, 247667, India. nishantjain86@gmail.com.
Journal of Medical Systems
|October 6, 2016
Summary
A novel iterative Fuzzy C-Mean (IFCM) method accurately segments liver lesions in ultrasound images, outperforming existing techniques in accuracy and speed. This image segmentation approach offers improved diagnostic capabilities.
Area of Science:
- Medical Imaging
- Computer Vision
- Image Segmentation
Background:
- Accurate segmentation of focal liver lesions in ultrasound images is crucial for diagnosis.
- Existing segmentation methods may suffer from issues like non-uniform centroid distribution.
Purpose of the Study:
- To propose and evaluate an iterative Fuzzy C-Mean (IFCM) method for segmenting focal liver lesions.
- To compare the performance of IFCM against established segmentation techniques.
Main Methods:
- An iterative Fuzzy C-Mean (IFCM) algorithm was developed to cluster image pixels.
- The IFCM method was implemented in MATLAB and compared with Chan-Vese (CV), MAP-MRF, and Region-Scalable Fitting Energy (RSFE) methods.
- Performance was evaluated on a common database of liver ultrasound images.
Main Results:
- The proposed IFCM method achieved the highest accuracy at 99.8%.
- Comparative accuracies for CV, MAP-MRF, and RSFE were 99.46%, 95.81%, and 90.08%, respectively.
- IFCM demonstrated significantly faster computation time (14.25s) compared to CV (44.71s), MAP-MRF (41.27s), and RSFE (49.02s).
Conclusions:
- The iterative Fuzzy C-Mean (IFCM) method provides a highly accurate and efficient solution for liver lesion segmentation.
- IFCM offers a superior alternative to existing methods for medical image analysis in ultrasound diagnostics.
