Segmentation and Diagnosis of Papillary Thyroid Carcinomas Based on Generalized Clustering Algorithm in Ultrasound Elastography

Papillary thyroid carcinomas (PTC) are the most common type of thyroid malignant tumors. Existing methods for clustering high-noise ultrasound images tend to degrade the clustering performance. In order to realize accurate segmentation of thyroid nodule in noisy environment, this paper proposes an i...

Full description

Saved in:
Bibliographic Details
Published in:Journal of medical systems Vol. 44; no. 1; pp. 13 - 8
Main Author: Huang, Weiqiang
Format: Journal Article
Language:English
Published: New York Springer US 01.01.2020
Springer Nature B.V
Subjects:
Adaptive algorithms
Adaptive filters
Algorithms
Clustering
Convolution
Diagnosis
Distributed Analytics and Deep Learning in Health Care
Health Informatics
Health Sciences
Image & Signal Processing
Image filters
Image processing
Image segmentation
Medical diagnosis
Medicine
Medicine & Public Health
Noise
Papillary thyroid carcinoma
Pixels
Statistics for Life Sciences
Thyroid
Thyroid cancer
Thyroid gland
Tumors
Ultrasonic imaging
Ultrasound
Diagnosis
Spatial structure
Papillary thyroid carcinomas
Object segmentation
Balance factor
Generalized clustering
ISSN:0148-5598, 1573-689X, 1573-689X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Papillary thyroid carcinomas (PTC) are the most common type of thyroid malignant tumors. Existing methods for clustering high-noise ultrasound images tend to degrade the clustering performance. In order to realize accurate segmentation of thyroid nodule in noisy environment, this paper proposes an improved segmentation algorithm based on adaptive fast generalized clustering. Firstly, the parameter balance factor is adaptively determined according to the noise probability of non-local pixels so as to reflect the spatial structure information in the image more accurately. Then, the balance factor is used to effectively combine the linear weighted filtered image in the AFGC algorithm so as to create the adaptive filtered image. Since the filtering degree depends on the probability whether the pixel is noise in the image, the dynamic noise suppression performance of the proposed method can be greatly improved. A large number of qualitative and quantitative experimental results show that the proposed generalized clustering algorithm can obtain more accurate results when clustering images with high noise. It is suitable for intelligent diagnosis of papillary thyroid convolution in clinical examination.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0148-5598
1573-689X
1573-689X
DOI:10.1007/s10916-019-1462-7