Title:Morphological Segmentation Analysis and Texture-based Support Vector Machines Classification on Mice Liver Fibrosis Microscopic Images
VOLUME: 14 ISSUE: 4
Author(s):Yu Wang, Fuqian Shi*, Luying Cao, Nilanjan Dey, Qun Wu, Amira Salah Ashour, Robert Simon Sherratt, Venkatesan Rajinikanth and Lijun Wu
Affiliation:The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, Department of Information Technology, Techno India College of Technology, West Bengal, Universal Design Institute, Zhejiang Sci-Tech University, Hangzhou, Department of Electronics and Electrical Communications Engineering, Faculty of Engineering, Tanta University, Tanta, Department of Biomedical Engineering, University of Reading, Reading, Department of EIE, St. Joseph's College of Engineering, Chennai, Institute of Digitized Medicine, Wenzhou Medical University, Wenzhou
Keywords:Morphological segmentation, top-hat transformation, threshold based Watershed segmentation, texture feature
extraction, mice liver fibrosis, microscopic images, support vector machine.
Abstract:
Background: To reduce the intensity of the work of doctors, pre-classification work
needs to be issued. In this paper, a novel and related liver microscopic image classification
analysis method is proposed.
Objective: For quantitative analysis, segmentation is carried out to extract the quantitative
information of special organisms in the image for further diagnosis, lesion localization, learning
and treating anatomical abnormalities and computer-guided surgery.
Methods: In the current work, entropy-based features of microscopic fibrosis mice’ liver images
were analyzed using fuzzy c-cluster, k-means and watershed algorithms based on distance
transformations and gradient. A morphological segmentation based on a local threshold was
deployed to determine the fibrosis areas of images.
Results: The segmented target region using the proposed method achieved high effective
microscopy fibrosis images segmenting of mice liver in terms of the running time, dice ratio and
precision. The image classification experiments were conducted using Gray Level Co-occurrence
Matrix (GLCM). The best classification model derived from the established characteristics was
GLCM which performed the highest accuracy of classification using a developed Support Vector
Machine (SVM). The training model using 11 features was found to be accurate when only trained
by 8 GLCMs.
Conclusion: The research illustrated that the proposed method is a new feasible research approach
for microscopy mice liver image segmentation and classification using intelligent image analysis
techniques. It is also reported that the average computational time of the proposed approach was
only 2.335 seconds, which outperformed other segmentation algorithms with 0.8125 dice ratio and
0.5253 precision.