Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{183134,
        author = {Mohammed Muzaffar Mohiuddin and Nazia Tazeen and Md. Ateeq Ur Rahman},
        title = {THYROIDMIND: AN EXPLAINABLE DEEP LEARNING ARCHITECTURE FOR RISK-AWARE NODULE CLASSIFICATION},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {3},
        pages = {491-497},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=183134},
        abstract = {Effective classification and early thyroid nodule detection are vital given the rising incidence of thyroid cancer.  Physicians can greatly benefit from automated systems that speed up diagnostic procedures.  Due to the scarcity of medical imaging datasets and the difficulty of feature extraction, this objective is still difficult to accomplish.  By concentrating on the extraction of significant traits that are necessary for tumour diagnosis, this work tackles these issues.  The suggested method incorporates cutting-edge feature extraction techniques, improving the ability to identify thyroid nodules in ultrasound pictures.  The classification system covers recognising particular worrisome classifications and differentiating between benign and malignant nodules. In first assessments, the combined classifiers show promise accuracy in providing a thorough characterisation of thyroid nodules.  These findings represent a substantial improvement in thyroid nodule categorisation techniques.  The novel approach taken in this study may prove beneficial in clinical settings by enabling a quicker and more precise identification of thyroid cancer.},
        keywords = {},
        month = {August},
        }