Topological Neutrosophic Analysis for Uncertainty Aware Thyroid Nodule Classification in Ultrasound Imaging

Authors

  • A. A. Salama Dept. of Math and Computer Sci., Faculty of Science, Port Said Univ., Egypt.
  • Huda E. Khalid University of Telafer, The Administration Assistant for the President of the Telafer University, Telafer, Iraq;
  • Ahmed K. Essa University of Telafer, The Administration Assistant for the President of the Telafer University, Telafer, Iraq;
  • H.A.Elagamy Department of Mathematics and Basic Sciences, Ministry of Higher Education Higher Future Institute of Engineering and Technology, Mansour, Egypt

Keywords:

Thyroid Nodule Classification; Neutrosophic Topology; Ultrasound Imaging; Indeterminacy Quantification; Confusion Matrix Topology; Diagnostic Confidence; Neutrosophic Neural Networks (NNN); Medical Decision Support; Explainable AI (XAI); Uncertainty Modeling.

Abstract

The classification of thyroid nodules in ultrasound imaging remains clinically 
challenging due to inherent ambiguities in visual interpretation, signal noise, and overlapping 
morphological features. To address these limitations, this study introduces an innovative 
diagnostic framework integrating Neutrosophic Set Theory with topological analysis to 
quantify and interpret uncertainty in medical image classification. Leveraging 
a Neutrosophic Neural Network (NNN), image features are mapped into a tripartite 
representation (truth, indeterminacy, and falsity), enabling granular modeling of diagnostic 
uncertainty. Further, the framework embeds classification outcomes within a neutrosophic 
topological space to reveal latent relational patterns such as confidence boundaries, 
ambiguity propagation, and misclassification topology that conventional metrics overlook. 
Experimental validation was performed on a dataset of 1,000 thyroid ultrasound 
images (Kaggle), with the proposed method achieving 92.1% accuracy, 91.4% sensitivity, 
and 93.2% specificity. Crucially, topological analysis was extended to performance metrics 
and confusion matrices, yielding a multidimensional assessment of classifier behavior 
under uncertainty. This approach not only improves diagnostic precision but also provides 
a topological lens for evaluating decision resilience, interpretability, and boundary-case 
vulnerabilities. The results demonstrate that neutrosophic topology offers a novel 
paradigm for explainable AI (XAI) in computer-aided diagnosis, bridging the gap between 
statistical performance and clinical trust. 

 

DOI: 10.5281/zenodo.15926371

Downloads

Download data is not yet available.

Downloads

Published

2025-11-01

How to Cite

A. A. Salama, Huda E. Khalid, Ahmed K. Essa, & H.A.Elagamy. (2025). Topological Neutrosophic Analysis for Uncertainty Aware Thyroid Nodule Classification in Ultrasound Imaging . Neutrosophic Sets and Systems, 90, 58-85. https://fs.unm.edu/nss8/index.php/111/article/view/6758

Most read articles by the same author(s)

<< < 1 2 3 4 5