A Machine Learning-Based Sonomics for Prediction of Thyroid Nodule Malignancies

A Machine Learning-Based Sonomics for Prediction of Thyroid Nodule Malignancies Publisher Pubmed

Arabi M¹ ; Nazari M² ; Salahshour A³ ; Jenabi E⁴ ; Hajianfar G⁵ ; Khateri M⁴ ; Shayesteh SP¹

Show Affiliations

1. Department of Physiology, Pharmacology and Medical Physics, Alborz University of Medical Sciences, Karaj, Iran
2. Department of Biomedical Engineering and Medical Physics, Shahid Beheshti University of Medical Sciences, Tehran, Iran
3. Department of Radiology, Alborz University of Medical Sciences, Karaj, Iran
4. Research Centre for Nuclear Medicine, Shariati Hospital, Tehran University of Medical Sciences, Tehran, Iran
5. Rajaie Cardiovascular, Medical & Research Center, Iran University of Medical Science, Tehran, Iran

Source: Endocrine Published:2023

Abstract

Objectives: This study aims to use ultrasound derived features as biomarkers to assess the malignancy of thyroid nodules in patients who were candidates for FNA according to the ACR TI-RADS guidelines. Methods: Two hundred and ten patients who met the selection criteria were enrolled in the study and subjected to ultrasound-guided FNA of thyroid nodules. Different radiomics features were extracted from sonographic images, including intensity, shape, and texture feature sets. Least Absolute Shrinkage and Selection Operator (LASSO), Minimum Redundancy Maximum Relevance (MRMR), and Random Forests/Extreme Gradient Boosting Machine (XGBoost) algorithms were used for feature selection and classification of the univariate and multivariate modeling, respectively. Evaluation of models performed using accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). Results: In the univariate analysis, Gray Level Run Length Matrix - Run-Length Non-Uniformity (GLRLM-RLNU) and gray-level zone length matrix - Run-Length Non-Uniformity (GLZLM-GLNU) (both with an AUC of 0.67) were top-performing for predicting nodules malignancy. In the multivariate analysis of the training dataset, the AUC of all combinations of feature selection algorithms and classifiers was 0.99, and the highest sensitivity was for XGBoost classifier and MRMR feature selection algorithms (0.99). Finally, the test dataset was used to evaluate our model in which XGBoost classifier with MRMR and LASSO feature selection algorithms had the highest performance (AUC = 0.95). Conclusions: Ultrasound-extracted features can be used as non-invasive biomarkers for thyroid nodules’ malignancy prediction. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

Related Docs

View other Related Docs

1. Evaluating Diagnostic Efficiency of Thyroid Imaging Reporting and Data Systems Proposed by the American College of Radiology in Surgically Resected Thyroid Nodules, Current Medical Imaging (2024)

2. Endorectal Ultrasound Radiomics in Locally Advanced Rectal Cancer Patients: Despeckling and Radiotherapy Response Prediction Using Machine Learning, Abdominal Radiology (2022)

3. Synergistic Impact of Motion and Acquisition/Reconstruction Parameters on 18F-Fdg Pet Radiomic Features in Non-Small Cell Lung Cancer: Phantom and Clinical Studies, Medical Physics (2022)

4. Repeatability of Radiomic Features in Magnetic Resonance Imaging of Glioblastoma: Test–Retest and Image Registration Analyses, Medical Physics (2020)

5. Machine Learning-Based Prognostic Modeling Using Clinical Data and Quantitative Radiomic Features From Chest Ct Images in Covid-19 Patients, Computers in Biology and Medicine (2021)

6. A Machine Learning Approach for Prediction of Auditory Brain Stem Response in Patients After Head-And-Neck Radiation Therapy, Journal of Cancer Research and Therapeutics (2023)

7. [18F]Fdg-Pet/Ct Radiomics and Artificial Intelligence in Lung Cancer: Technical Aspects and Potential Clinical Applications, Seminars in Nuclear Medicine (2022)

8. 3T Magnetic Resonance Spectroscopy As a Powerful Diagnostic Modality for Assessment of Thyroid Nodules, Archives of Endocrinology and Metabolism (2018)

Experts (# of related papers)

View all Related Experts

Mohammad Reza Ay (3)

Parham Geramifar (3)

Style	Citing Format
MLA	Arabi M, et al.. "A Machine Learning-Based Sonomics for Prediction of Thyroid Nodule Malignancies." Endocrine, vol. 82, no. 2, 2023, pp. 326-334.
APA	Arabi M, Nazari M, Salahshour A, Jenabi E, Hajianfar G, Khateri M, Shayesteh SP (2023). A Machine Learning-Based Sonomics for Prediction of Thyroid Nodule Malignancies. Endocrine, 82(2), 326-334.
Chicago	Arabi M, Nazari M, Salahshour A, Jenabi E, Hajianfar G, Khateri M, Shayesteh SP. "A Machine Learning-Based Sonomics for Prediction of Thyroid Nodule Malignancies." Endocrine 82, no. 2 (2023): 326-334.
Harvard	Arabi M et al. (2023) 'A Machine Learning-Based Sonomics for Prediction of Thyroid Nodule Malignancies', Endocrine, 82(2), pp. 326-334.
Vancouver	Arabi M, Nazari M, Salahshour A, Jenabi E, Hajianfar G, Khateri M, et al.. A Machine Learning-Based Sonomics for Prediction of Thyroid Nodule Malignancies. Endocrine. 2023;82(2):326-334.
BibTex	@article{ author = {Arabi M and Nazari M and Salahshour A and Jenabi E and Hajianfar G and Khateri M and Shayesteh SP}, title = {A Machine Learning-Based Sonomics for Prediction of Thyroid Nodule Malignancies}, journal = {Endocrine}, volume = {82}, number = {2}, pages = {326-334}, year = {2023} }
RIS	TY - JOUR AU - Arabi M AU - Nazari M AU - Salahshour A AU - Jenabi E AU - Hajianfar G AU - Khateri M AU - Shayesteh SP TI - A Machine Learning-Based Sonomics for Prediction of Thyroid Nodule Malignancies JO - Endocrine VL - 82 IS - 2 SP - 326 EP - 334 PY - 2023 ER -

Science Communicator Platform

Authors

Authors Affiliations

Abstract