Classification and Diagnosis of Thyroid Carcinoma Using Reinforcement Residual Network with Visual Attention Mechanisms in Ultrasound Images

How to differentiate thyroid cancer nodules from a large number of benign nodules is always a challenging subject for clinicians. This paper proposes a novel Sal-deel network model to achieve the classification and diagnosis of thyroid cancer, which can simulate visual attention mechanism. The Sal-d...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Journal of medical systems Ročník 43; číslo 11; s. 323
Hlavný autor: Zhang, Yanming
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York Springer US 01.11.2019
Springer Nature B.V
Predmet:
Algorithms
Attention
Cancer
Classification
Computer simulation
Deep Learning
Diagnosis
Diagnosis, Differential
Distributed Analytics and Deep Learning in Health Care
Feature extraction
Health Informatics
Health Sciences
Humans
Image & Signal Processing
Image Processing, Computer-Assisted - methods
Medical diagnosis
Medicine
Medicine & Public Health
Model accuracy
Nodules
Statistics for Life Sciences
Thyroid
Thyroid cancer
Thyroid carcinoma
Thyroid Neoplasms - diagnosis
Thyroid Neoplasms - diagnostic imaging
Thyroid Neoplasms - pathology
Thyroid Nodule - diagnostic imaging
Ultrasonic imaging
Ultrasonography - methods
Ultrasound
Visual perception
Visual attention mechanisms
Connection combination
Reinforcement residual network
Sal-deep network
Classification rate
Thyroid carcinoma
ISSN:0148-5598, 1573-689X, 1573-689X
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:How to differentiate thyroid cancer nodules from a large number of benign nodules is always a challenging subject for clinicians. This paper proposes a novel Sal-deel network model to achieve the classification and diagnosis of thyroid cancer, which can simulate visual attention mechanism. The Sal-deep network introduces saliency map as an additional information on the deep residual network, which selectively enhances the feature extracted from different regions according to the mask map. Sal-deep network can work effectively for the benchmark networks with different data sets and different structures, and it is a universal network model. Sal-deep network increases the complexity of the network, but improves the efficiency of the network. A large number of qualitative and quantitative experiments show that our improved network is superior to other existing deep models in terms of classification accuracy rate and Recall, which is suitable for clinical application.
Bibliografia: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/s10916-019-1448-5