A study of the phases of classification of liver diseases from ultrasound images and gray level difference weights based segmentation

2017 ◽  
Author(s):  
M. Midhila ◽  
K. Raghesh Krishnan ◽  
R. Sudhakar
Keyword(s):  
Liver Diseases ◽  
Ultrasound Images ◽  
Gray Level ◽  
Level Difference

scholarly journals Classification for Liver Diseases Based on Ultrasound Image Texture Features

2018 ◽  
Author(s):  
Sendren Sheng-Dong Xu ◽  
Chien-Tien Su ◽  
Chun-Chao Chang ◽  
Pham Quoc Phu
Keyword(s):  
Liver Abscess ◽  
Liver Diseases ◽  
Ultrasound Image ◽  
Texture Features ◽  
Image Texture ◽  
Support Vector ◽  
Svm Classifier ◽  
Ultrasound Images ◽  
Gray Level ◽  
Forward Selection

This paper discusses the computer-aided (CAD) classification between Hepatocellular Carcinoma (HCC), i.e., the most common type of liver cancer, and Liver Abscess, based on ultrasound image texture features and Support Vector Machine (SVM) classifier. Among 79 cases of liver diseases, with 44 cases of HCC and 35 cases of liver abscess, this research extracts 96 features of Gray-Level Co-occurrence Matrix (GLCM) and Gray-Level Run-Length Matrix (GLRLM) from the region of interests (ROIs) in ultrasound images. Three feature selection models, i) Sequential Forward Selection, ii) Sequential Backward Selection, and iii) F-score, are adopted to determine the identification of these liver diseases. Finally, the developed system can classify HCC and liver abscess by SVM with the accuracy of 88.875%. The proposed methods can provide diagnostic assistance while distinguishing two kinds of liver diseases by using a CAD system.

scholarly journals Hybrid classification of diffuse liver diseases in ultrasound images using deep convolutional neural networks

2021 ◽  
Vol 22 ◽  
pp. 100496
Author(s):  
Pezhman Pasyar ◽  
Tahereh Mahmoudi ◽  
Seyedeh-Zahra Mousavi Kouzehkanan ◽  
Alireza Ahmadian ◽  
Hossein Arabalibeik ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Liver Diseases ◽  
Ultrasound Images ◽  
Deep Convolutional Neural Networks ◽  
Hybrid Classification ◽  
Diffuse Liver Diseases

scholarly journals Gray level co-occurrence matrix feature extraction and histogram in breast cancer classification with ultrasonographic imagery

2021 ◽  
Vol 22 (2) ◽  
pp. 795
Author(s):  
Karina Djunaidi ◽  
Herman Bedi Agtriadi ◽  
Dwina Kuswardani ◽  
Yudhi S. Purwanto
Keyword(s):  
Breast Cancer ◽  
Feature Extraction ◽  
Ultrasound Image ◽  
Extraction Process ◽  
Ultrasound Images ◽  
Gray Level ◽  
K Nearest Neighbors ◽  
Cancer Types ◽  
Occurrence Matrix

One way to detect breast cancer is using the Ultrasonography (USG) procedure, but the ultrasound image is susceptible to the noise speckles so that the interpretation and diagnosis results are different. This paper discusses the classification of breast cancer ultrasound images that aims to improve the accuracy of the identification of the type and level of cancer malignancies based on the features of its texture. The feature extraction process uses a <em>histogram</em> which then the results are calculated using the Gray Level Co-Occurrence Matrix (GLCM). The results of the two extraction features are then classified using K-Nearest Neighbors (KNN) to obtain accurate figures from those images. The results of this study is that the accuracy in detecting cancer types is 80%.

Sign in / Sign up

Export Citation Format

Share Document