Multi-Class Classification of Thyroid Disorders Utilizing Modified DenseNet-201 and Tc-99m Scintigraphy Through Deep Learning Techniques - Takeaways - MDSpire

Multi-Class Classification of Thyroid Disorders Utilizing Modified DenseNet-201 and Tc-99m Scintigraphy Through Deep Learning Techniques

  • By

  • Hafiz Muhammad Usman Ghani

  • Javed Khan

  • Naimat Ullah Khan

  • Zahid Ullah Khan

  • Sajid Ullah Khan

  • Nazik Alturki

  • Shantanu Awasthi

  • Sarra Ayouni

  • February 1, 2026

  • 0 min

Share

  • 1

    The study classifies seven thyroid disorders, including cold nodule and hot nodule, which have not been extensively researched previously.

  • 2

    A modified DenseNet-201 convolutional neural network model enhances feature extraction and classification from low-resolution scintigraphy images.

  • 3

    The dataset comprises 1599 thyroid scintigraphy scans collected over 10 years, ensuring moderate diversity and high relevance.

  • 4

    The focus is exclusively on thyroid scintigraphy data, aligning with real-world nuclear medicine workflows rather than high-resolution anatomical data.

  • 5

    Artificial intelligence, particularly deep learning, shows promise in improving diagnostic precision for thyroid disorders through extensive medical data analysis.

Original Source(s)

Multi-Class Classification of Thyroid Disorders Utilizing Modified DenseNet-201 and Tc-99m Scintigraphy Through Deep Learning Techniques

  • by Hafiz Muhammad Usman Ghani, Javed Khan, Naimat Ullah Khan, Zahid Ullah Khan, Sajid Ullah Khan, Nazik Alturki, Shantanu Awasthi, Sarra Ayouni

  • February 1, 2026

Related Content

Evaluating AI for thyroid nodule diagnosis

Ultrasound based AI–assisted diagnostic systems “demonstrated high clinical potential."

IOPTH Widely Used, Variation Persists

Most surgeons reported using intraoperative parathyroid hormone monitoring, but approaches to imaging and intraoperative criteria varied, particularly in secondary and tertiary disease

Mandatory Training Modules Deserve a Harder Look

A JAMA Viewpoint argues that 4 million physician-hours spent on compliance modules each year warrants institutional reassessment.