Early detection of malignant thyroid nodules is crucial for effective treatment, but traditional diagnostic methods face challenges such as variability in expert opinions and limited integration of advanced imaging techniques. This prospective cohort study investigates a novel multimodal approach, integrating traditional methods with advanced machine learning techniques. We studied 181 patients who underwent fine-needle aspiration (FNA) biopsy, each contributing one nodule, resulting in a total of 181 nodules for our analysis. Data collection included sex, age, and ultrasound imaging, which incorporated elastography. Features extracted from these images included Thyroid Imaging Reporting and Data System (TIRADS) scores, elastography parameters, and radiomic features. The pathological results based on the FNA biopsy, provided by the pathologists, served as our gold standard for nodule classification. Our methodology, termed ELTIRADS, combines these features with interpretable machine learning techniques. Performance evaluation showed that a Support Vector Machine (SVM) classifier using TIRADS, elastography data, and radiomic features achieved high accuracy (0.92), with sensitivity (0.89), specificity (0.94), precision (0.89), and F1 score (0.89). To enhance interpretability, we used hierarchical clustering, shapley additive explanations (SHAP), and partial dependence plots (PDP). This combined approach holds promise for enhancing the accuracy of thyroid nodule malignancy detection, thereby contributing to advancements in personalized and precision medicine in the field of thyroid cancer research.

2nd Faculty of Medicine Charles University Prague Czech Republic

Advanced Diagnostic and Interventional Radiology Research Center Tehran University of Medical Sciences Tehran Iran

Department of Biomedical Engineering Tarbiat Modares University Tehran Iran

Department of Pathology Tehran University of Medical Sciences Tehran Iran

Department of Radiology Iran University of Medical Sciences Tehran Iran

Department of Radiology Kermanshah University of Medical Sciences Kermanshah Iran

Department of Radiology Tehran University of Medical Science Tehran Iran

Institut de Biologie Valrose Université Côte d'Azur CNRS Inserm Nice France

Rajaie Cardiovascular Medical and Research Institute Iran University of Medical Sciences Tehran Iran

See more in PubMed

WM T: The spectrum of thyroid disease in a community: the Whickham survey. Clin Endocrinol (Oxf) 7:481-493, 1977 PubMed

Vander, J. B., Gaston, E. A. & Dawber, T. R. The significance of nontoxic thyroid nodules: final report of a 15-year study of the incidence of thyroid malignancy. Annals of internal medicine69, 537–540 (1968). PubMed

Shi, M., Nong, D., Xin, M. & Lin, L. Accuracy of Ultrasound Diagnosis of Benign and Malignant Thyroid Nodules: A Systematic Review and Meta-Analysis. International Journal of Clinical Practice2022, 5056082 (2022). PubMed PMC

Durante, C. et al. The natural history of benign thyroid nodules. Jama313, 926–935 (2015). PubMed

Durante, C. et al. The Diagnosis and Management of Thyroid Nodules: A Review. Jama319, 914–924 (2018). PubMed

Stoian D, Cornianuz M, Dobrescu A, Lazăr F: Nodular thyroid cancer. Diagnostic value of real time elastography. Chirurgia (Bucur) 107:39-46, 2012 PubMed

Monpeyssen, H., Tramalloni, J., Poirée, S., Hélénon, O. & Correas, J. M. Elastography of the thyroid. Diagn Interv Imaging94, 535–544 (2013). PubMed

Rago, T., Santini, F., Scutari, M., Pinchera, A. & Vitti, P. Elastography: new developments in ultrasound for predicting malignancy in thyroid nodules. J Clin Endocrinol Metab92, 2917–2922 (2007). PubMed

Kwak, J. Y. et al. Thyroid imaging reporting and data system for US features of nodules: a step in establishing better stratification of cancer risk. Radiology260, 892–899 (2011). PubMed

Tessler, F. N. et al. ACR Thyroid Imaging, Reporting and Data System (TI-RADS): White Paper of the ACR TI-RADS Committee. J Am Coll Radiol14, 587–595 (2017). PubMed

Nikiforova, M. N. & Nikiforov, Y. E. Molecular diagnostics and predictors in thyroid cancer. Thyroid19, 1351–1361 (2009). PubMed

Kumar, V. et al. Automated Segmentation of Thyroid Nodule, Gland, and Cystic Components From Ultrasound Images Using Deep Learning. IEEE Access8, 63482–63496 (2020). PubMed PMC

Sabouri, M. et al. Machine learning based readmission and mortality prediction in heart failure patients. Scientific Reports13, 18671 (2023). PubMed PMC

Daskareh, M. et al. Predicting Rheumatoid Arthritis Development Using Hand Ultrasound and Machine Learning-A Two-Year Follow-Up Cohort Study. Diagnostics14, 1181 (2024). PubMed PMC

Taleie H, et al.: Left Ventricular Myocardial Dysfunction Evaluation in Thalassemia Patients Using Echocardiographic Radiomic Features and Machine Learning Algorithms. Journal of digital imaging:1-13, 2023 PubMed PMC

Khodabakhshi, Z. et al. Overall survival prediction in renal cell carcinoma patients using computed tomography radiomic and clinical information. Journal of digital imaging34, 1086–1098 (2021). PubMed PMC

Mohebi M, et al.: Post-revascularization Ejection Fraction Prediction for Patients Undergoing Percutaneous Coronary Intervention Based on Myocardial Perfusion SPECT Imaging Radiomics: a Preliminary Machine Learning Study. Journal of Digital Imaging:1-16, 2023 PubMed PMC

Sabouri, M. et al. Myocardial Perfusion SPECT Imaging Radiomic Features and Machine Learning Algorithms for Cardiac Contractile Pattern Recognition. Journal of Digital Imaging36, 497–509 (2023). PubMed PMC

Amini, M. et al. Overall survival prognostic modelling of non-small cell lung cancer patients using positron emission tomography/computed tomography harmonised radiomics features: The quest for the optimal machine learning algorithm. Clinical Oncology34, 114–127 (2022). PubMed

Shiri I, et al.: Diagnosis of COVID-19 using CT image radiomics features: a comprehensive machine learning study involving 26,307 patients. medRxiv:2021.2012. 2007.21267367, 2021

Khodabakhshi, Z. et al. Non-small cell lung carcinoma histopathological subtype phenotyping using high-dimensional multinomial multiclass CT radiomics signature. Computers in biology and medicine136, 104752 (2021). PubMed

Gharibi O, et al.: Maximizing the Predictive Power of Radiomic Features in SPECT Images: A Comparative Study of Reconstruction Algorithms Using Machine Learning. Proc. 2023 IEEE Nuclear Science Symposium, Medical Imaging Conference and International Symposium on Room-Temperature Semiconductor Detectors (NSS MIC RTSD): City

Shayesteh SP, et al.: Machine Learning Based Malignancy Prediction in Thyroid Nodules Malignancy: Radiomics Analysis of Ultrasound Images. Proc. 2020 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC): City

arabi M, et al.: A machine learning-based sonomics for prediction of thyroid nodule malignancies. Endocrine 82:326-334, 2023 PubMed

Xi, N. M., Wang, L. & Yang, C. Improving the diagnosis of thyroid cancer by machine learning and clinical data. Scientific Reports12, 11143 (2022). PubMed PMC

Alyas, T. et al. Empirical Method for Thyroid Disease Classification Using a Machine Learning Approach. BioMed Research International2022, 9809932 (2022). PubMed PMC

Gomes Ataide, E. J. et al. Thyroid Nodule Classification for Physician Decision Support Using Machine Learning-Evaluated Geometric and Morphological Features. Sensors20, 6110 (2020). PubMed PMC

Zhang, B. et al. Machine Learning-Assisted System for Thyroid Nodule Diagnosis. Thyroid29, 858–867 (2019). PubMed

Wang, L. et al. Multimodal Ultrasound Radiomic Technology for Diagnosing Benign and Malignant Thyroid Nodules of Ti-Rads 4–5: A Multicenter Study. Sensors24, 6203 (2024). PubMed PMC

Chen, J. H. et al. Applying machine-learning models to differentiate benign and malignant thyroid nodules classified as C-TIRADS 4 based on 2D-ultrasound combined with five contrast-enhanced ultrasound key frames. Front Endocrinol15, 1299686 (2024). PubMed PMC

Ioachim, D. The Bethesda System for Reporting Thyroid Cytopathology. Acta Endocrinol (Buchar)14, 282–283 (2018).

Moon, H. J. et al. Diagnostic performance of gray-scale US and elastography in solid thyroid nodules. Radiology262, 1002–1013 (2012). PubMed

Haralick RM, Shanmugam K, Dinstein IH: Textural features for image classification. IEEE Transactions on systems, man, and cybernetics:610-621, 1973

Dash, S. & Jena, U. R. Multi-resolution Laws’ Masks based texture classification. Journal of applied research and technology15, 571–582 (2017).

Pitas I: Digital image processing algorithms and applications: John Wiley & Sons, 2000

Costa AF, Humpire-Mamani G, Traina AJM: An efficient algorithm for fractal analysis of textures. Proc. 2012 25th SIBGRAPI Conference on Graphics, Patterns and Images: City

Prasad L, Iyengar SS: Wavelet analysis with applications to image processing: CRC press, 1997

Liang, J. et al. Predicting malignancy in thyroid nodules: radiomics score versus 2017 American College of Radiology Thyroid Imaging. Reporting and Data System. Thyroid28, 1024–1033 (2018). PubMed

Colakoglu B, Alis D, Yergin M: Diagnostic value of machine learning-based quantitative texture analysis in differentiating benign and malignant thyroid nodules. Journal of oncology 2019, 2019 PubMed PMC

Zhang, B. et al. Machine learning-assisted system for thyroid nodule diagnosis. Thyroid29, 858–867 (2019). PubMed

Lundberg SM, Lee S-I: A unified approach to interpreting model predictions. Advances in neural information processing systems 30, 2017

Friedman JH: Greedy function approximation: a gradient boosting machine. Annals of statistics:1189-1232, 2001

Sørlie, T. et al. Gene expression patterns of breast carcinomas distinguish tumor subclasses with clinical implications. Proceedings of the National Academy of Sciences98, 10869–10874 (2001). PubMed PMC

Mayerhoefer, M. E. et al. Introduction to Radiomics. J Nucl Med61, 488–495. 10.2967/jnumed.118.222893 (2020). PubMed PMC