Deep Learning-Based Multilayer Perceptron Model for Classifying Benign and Malignant Thyroid Nodules: Enhancing Diagnostic Accuracy in Clinical Practice
DOI:
https://doi.org/10.33317/ssurj.701Keywords:
Benign and Malignant Classification, Deep Learning, Multilayer Perceptron, Thyroid Nodules, Ultrasound ImagingAbstract
This study concludes that the most utilized and diagnostic tool for thyroid nodule assessment is Ultrasound (US), by which the size of the nodule, structure, and other features can be measured. Involving some deep learning systems and particularly Multilayer Perception (MLP), which studies and classifies thyroid nodules as benign and malignant, is illustrated. An MLP-based technique has been performed on a cohort of 847 patients, 1,978 of which are benign and 3,608 are malignant, separated into two batches. The MLP model recorded a remarkable accuracy of 98.91%, indicating precise consistency of the training and validation datasets, with minor fluctuations, hence, solid
generalization. The model manifested exceptional diagnostic consistency and dependability on account of its admirable learning, steady enhancement of its accuracy, and convergence of the loss curves. With respect to the last-defended deep learning techniques, this MLP model stands out, especially in thyroid nodule classification, assuring a decline in diagnostic-related human mistakes and a faster diagnosis. Future research would enhance the model by involving larger and more diverse datasets and exploring more advanced architectures of neural networks, Convolutional Neural Networks (CNNs), or hybrid models. This MLP model will be integrated into clinical practice to streamline decision-making, enhance patient outcomes, and take one step forward in the evolution of medical image analysis.
References
Shankarlal, B., et al. (2020). CAD of Thyroid Nodules using Machine and Deep Learning. IETE Journal of Research.
Swathi, G., et al. (2024). QuCNet: Quantum-Inspired CNNs for Thyroid Nodule Classification. IEEE Access.
Göreke, V. (2023). Deep-Learning CADx for Thyroid Nodule Classification using Ultrasound. Interdisciplinary Sciences.
Yadav, N., et al. (2024). Deep Learning CAD for Thyroid Tumor Characterization. Multimedia Tools and Applications.
Ludwig, M., et al. (2023). AI in Diagnosis and Classification of Thyroid Nodules: An Update. Cancers, 15, 708.
Zhang, X., & Lee, V. C. S. (2024). Deep Learning Decision Support for Thyroid Cancer Detection. Procedia Computer Science, 237,945–954.
Habchi, Y., et al. (2023). AI in Thyroid Cancer Diagnosis: Techniques and Trends. Systems, 11, 519.
Zhao, H., et al. (2023). Diagnosis of Thyroid Disease using Deep CNNs on Scintigraphy Images. Frontiers in Endocrinology, 14.
Chen, C., Jiang, Y., Yao, J., et al. (2024). Deep Learning for Thyroid Nodule Diagnosis: A Multicenter Study. European Radiology, 34, 2323–2333.
Kaur, G., et al. (2024). Deep Learning Methods for Diagnosing Thyroid Cancer. ASME Journal of Medical Diagnostics, 7(3),
Zhang, B., et al. (2019). Machine Learning-Assisted System for Thyroid Nodule Diagnosis.
Peng, S., et al. (2021). Deep Learning AI Model for Thyroid Nodule Diagnosis and Management. Lancet Digital Health, 3.
Anari, S., Sarshar, N. T., Mahjoori, N., & Dorosti, S. (2022). Review of Deep Learning Approaches for Thyroid Cancer
Diagnosis.
Lin, Y.-J., et al. (2021). Deep Learning Fast Screening on Cytology Slides for Thyroid Cancer. Cancers, 13, 3891.
Zhu, X., Chen, C., Guo, Q., Ma, J., Sun, F., & Lu, H. (2022). Deep Learning Recognition of Thyroid Cancer Categories using FrozenSlide Images. Frontiers in Bioengineering and Biotechnology, 10, 857377.
Li, X., et al. (2019). Diagnosis of Thyroid Cancer using Deep CNNs on Sonographic Images: A Multicohort Study. Lancet Oncology, 20.
Lee, J. H., Ha, E. J., & Kim, J. H. (2019). Deep Learning for Cervical Lymph Node Metastasis Diagnosis from Thyroid Cancer
using CT. European Radiology, 29, 5452–5457.
Ni, J., et al. (2025). Performance Evaluation of Deep Learning for Thyroid Nodule Detection and Segmentation. Journal of Medical Internet Research.
Li, Y., et al. (2025). Innovations in Thyroid Nodule Ultrasound Diagnosis: Robot and AI Applications. Quantitative Imaging in Medicine and Surgery.
Xu, Y., et al. (2025). Thyroid Nodule Classification using Deep Transfer Learning and ML Fusion. BMC Cancer, 25, 544.
Xiao, Y., et al. (2025). LGF-Net: Multi-Scale Feature Fusion for Thyroid Nodule Classification. Medical Physics.
Banerjee, T., et al. (2025). Hybrid Deep Learning with Feature Attention for Thyroid Ultrasound Segmentation. Scientific Reports.
Risk Assessment of Thyroid Nodules with a Multi-Instance Learning CNN. (2025). Frontiers in Oncology.
Shen, P., Yang, Z., Yao, S., et al. (2025). Explainable Multimodal Deep Learning for Thyroid Cancer Lymph Node Metastasis. Nature Communications.
Zhou, Y., et al. (2025). TNVis: Deep Learning Ultrasound Tool for Thyroid Nodules. npj Digital Medicine.
Wang, X., et al. (2025). ThyroNet-X4 Genesis: Deep Learning for Automated Thyroid Nodule Classification. Scientific Reports, 15,27207.
Kim, J., et al. (2025). Deep Learning Technology for Thyroid Nodule Classification. Endocrinology and Metabolism.
Wang, L., Yang, S., Yang, S., et al. (2019). Automatic Thyroid Nodule Recognition using YOLOv2. World Journal of Surgical
Oncology, 17, 12.
Yang, J., et al. (2022). Ultrasound Image Classification of Thyroid Nodules using Deep Learning. Frontiers in Oncology, 12.
Abdolali, F., et al. (2020). Automated Thyroid Nodule Detection using Deep CNNs. Computers in Biology and Medicine, 122.
Song, R., et al. (2020). Thyroid Nodule Ultrasound Classification Via Hybrid Feature Cropping Network. IEEE Access, 8, 64064– 64074.
Chen, J., You, H., & Li, K. (2020). Review of Thyroid Gland and Nodule Segmentation in Ultrasound. Computer Methods and Programs in Biomedicine, 185.
Zhu, Y. C., et al. (2021). Thyroid Ultrasound Classification using CNN. Annals of Translational Medicine, 9(20), 1526.
Kim, Y.-J., et al. (2022). Deep CNN for Thyroid Nodule Classification: Comparison with Radiologists. European Journal of
Radiology, 152.
Vadhiraj, V. V., et al. (2021). Ultrasound Classification of Thyroid Nodules using Machine Learning. Medicina, 57, 527.
Zhu, J., et al. (2021). Deep CNN for Localization and Diagnosis of Thyroid Nodules on Ultrasound. Quantitative Imaging in Medicine and Surgery, 11(4), 1368–1380.
Moussa, O., Khachnaoui, H., Guetari, R., & Khlifa, N. (2023). Thyroid Nodule Classification using Fine-Tuned CNN.
Wang, L., et al. (2020). Automatic Diagnosis of Thyroid Nodules using Deep Neural Networks. Medical Image Analysis, 61.
Liu, Z., et al. (2021). Thyroid Nodule Recognition using Joint CNN with Information Fusion. European Radiology, 31, 5001–5011.
[Zhu, Y.-C., et al. (2021). Generic Deep Learning Framework for Thyroid and Breast Lesion Classification in Ultrasound.
Ultrasonics, 110.
Rho, M., et al. (2023). Diagnosis of Thyroid Micronodules on Ultrasound using Deep CNN. Scientific Reports, 13, 7231.
Zhu, P.-S., et al. (2022). Ultrasound-Based Deep Learning using VGGNet for Thyroid Nodule Differentiation: Meta-Analysis.
Frontiers in Oncology, 12.
Ravishankar, T. N., et al. (2023). Deep Learning for Ovarian Cyst Detection using Fuzzy CNN. Measurement: Sensors, 27.
[Esfe, M. H., Amoozadkhalili, F., & Toghraie, D. (2023). Optimal Structure for Estimating Viscosity of Oil-Based Hybrid Nanofluid. Powder Technology, 415.
Chauhan, D., Yadav, A., & Neri, F. (2024). Multi-Agent Optimization for Training Multilayer Perceptrons. Evolving
Systems, 15, 849–879.
Yan, Z., et al. (2023). Multi-Energy Load Prediction using MLP with Different Optimization Algorithms.
Sahoo, M., et al. (2023). MLP and RBF Neural Network Approach for 6-Gingerol Estimation and Optimization. Industrial Crops & Products, 198.
Ghosh, B. P., et al. (2024). Deep Learning in Stock Market Forecasting: Comparative Analysis. Journal of Computer Science
Technology Studies, 6(1), 68–75.
Angell, T. E., et al. (2017). Differential Growth Rates of Benign Vs Malignant Thyroid Nodules. Journal of Clinical Endocrinology & Metabolism, 102(12), 4642–4647.
Hou, X., et al. (2024). Ultrasonography of Thyroid Nodules Dataset with Pathological Annotation for Deep Learning. Figshare Dataset
Ajlilsa, A., Patel, S., & Lee, H.-J. (2023). Explainable Deep Learning for Thyroid Ultrasound Diagnosis: A Multicenter Study.
Computers in Biology and Medicine, 158, Article 107012.
Fang, N., Liu, Y., Zhang, L., & Chen, J. (2024). Deep Transfer Learning for Ultrasound-Based Thyroid Nodule Classification.
Journal of Medical Imaging and Health Informatics, 14(5), 1253– 1264.
Gulame, M. B., & Dixit, V. V. (2024). Malignant Thyroid Lump Multi-Classification by TIRADS using DBA with Transfer
Learning. Indonesian Journal of Electrical Engineering and Computer Science (IJEECS), 35(2), 996–1003.
Downloads
Published
How to Cite
Issue
Section
Categories
License
Copyright (c) 2025 Ammar Oad, Imtiaz Hussain Koondhar, Beenish Ayesha Akram, Leezna Saleem, Rajkumri Oad (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
