Computer-Aided Diagnosis of Thyroid Nodule from Ultrasound Images Using Transfer Learning from Deep Convolutional Neural Network Models

Ajilisa, O. A.; Jagathyraj, V. P.; Sabu, M. K.

doi:10.1109/accthpa49271.2020.9213210

Cited by 7 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Addressing this issue is directed as an attribute assignment (19) , (20) . Different feature selection metrics are utilized at every level to classify the feature that can be regarded as the root node (21)(22)(23)(24)(25) .Figure 2 represents the structure of the decision tree.…”

Section: 3decision Treementioning

confidence: 99%

A Novel Classification Methodology for Thyroid Cancer using C4.5 with Firefly Optimization Algorithm (CFOA)

Vanitha¹,

Perumal²

2022

IJST

View full text Add to dashboard Cite

Objectives:The main objective of this research is to detect thyroid cancer in its early stages and to improve the accuracy using a novel method C4.5 with Firefly Optimization Algorithm (CFOA). This research also focuses on developing an effective machine learning-based accurate prediction model. Methods: The images in this investigation are associated to thyroid disorder with 4672 samples of people including both females and males having hypothyroidism and hyperthyroidism, as well as healthy people without thyroid disorder. The data was gathered for one year with the primary goal of classifying thyroid disease using machine learning (ML) algorithms. These data comprise of Gender, Age, Thyroid hormone (T4), Triiodothyronine (T3), Thyroid stimulating hormone (TSH), etc. The performance of this proposed method was measured using parameters such as accuracy, precision, F1-score and recall. Findings: The performance of this proposed method was assessed with the state-ofthe-art existing methods like Naive Bayes (NB) algorithm, K-Nearest Neighbor (KNN) Algorithm and Adaboost. The proposed algorithm showed maximum precision of 0.9935, recall of 0.9971, F1-score of 0.9951 and accuracy of 0.9981 respectively when compared with the existing algorithms. Novelty: A novel algorithm C4.5 with Firefly Optimization Algorithm was proposed in this paper to speed-up and to increase the effectiveness of the machine learning algorithm. Moreover, this study focuses on developing an accurate prediction model by comparing classification algorithms based on accuracy and confusion matrices and then identifying the most effective classifier based on performance.

show abstract

Section: 3decision Treementioning

confidence: 99%

A Novel Classification Methodology for Thyroid Cancer using C4.5 with Firefly Optimization Algorithm (CFOA)

Vanitha¹,

Perumal²

2022

IJST

View full text Add to dashboard Cite

show abstract

“…The classification challenge for thyroid nodule CAD can be stated as a machine learning problem where the model automatically identifies between benign and malignant nodules on ultrasound images [4]. By decreasing effort and diagnostic variances across doctors, ultrasound can offer a trustworthy, consistent, highly effective, and repeatable ultrasound diagnosis pathway for thyroid nodules [5]. Recently, a number of researchers have conducted extensive research in the field of CAD to reduce the impact of subjective factors on physician diagnosis and improve diagnostic precision.…”

Section: Introductionmentioning

confidence: 99%

Classification of Thyroid Nodules Using Follow the Regularized Leader Optimization Based Deep Neural Networks

Beyyala,

Priya,

Choudari

et al. 2023

RIA

View full text Add to dashboard Cite

Thyroid cancer, the most common endocrine malignancy, has exhibited a steadily increasing incidence worldwide. Recently, ultrasound (US) imaging has been recognized as a potential diagnostic tool for early assessment of thyroid nodules. However, visual interpretation of nodules is subject to the radiologists' subjective evaluations. To address this, a computer-aided Diagnostic (CAD) system has been developed to differentiate between benign and malignant thyroid nodules. The efficiency of this nodule classifier is heavily dependent on the features employed in the classification process. In this study, the efficacy of the RREMI-RF approach, employing the Multi-Channel Convolutional Neural Network (MCNN) and Hybrid Feature Cropping Network (HFCN) techniques, was evaluated. An innovative Follow the Regularised Leader-based Deep Neural Network (FTRL-DNN) technique is proposed for the precise classification of thyroid nodules. In this method, the AlexNet learning-based feature extraction system was utilized to extract features during the classification process. Images from the Digital Database Thyroid Image (DDTI) dataset were classified using the Long Short Term Memory (LSTM) classifier. Performance metrics, including accuracy, sensitivity, specificity, precision, and error rate, were used to assess the effectiveness of the FTRL-DNN algorithm. Compared to the HFCN and MCNN, the FTRL-DNN-based thyroid nodule classification demonstrated superior accuracy, achieving a rate of 98.94%. This research presents a significant advancement in the automated classification of thyroid nodules, potentially improving early detection and treatment of thyroid cancer.

show abstract

Classification of Stages of Thyroid Nodules in Ultrasound Images Using Transfer Learning Methods

Pavithra

Vanithamani

Justin

2021

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Computer-Aided Diagnosis of Thyroid Nodule from Ultrasound Images Using Transfer Learning from Deep Convolutional Neural Network Models

Cited by 7 publications

References 18 publications

A Novel Classification Methodology for Thyroid Cancer using C4.5 with Firefly Optimization Algorithm (CFOA)

A Novel Classification Methodology for Thyroid Cancer using C4.5 with Firefly Optimization Algorithm (CFOA)

Classification of Thyroid Nodules Using Follow the Regularized Leader Optimization Based Deep Neural Networks

Classification of Stages of Thyroid Nodules in Ultrasound Images Using Transfer Learning Methods

Contact Info

Product

Resources

About