Ontology-guided neuro-symbolic convNeXtV2–swin transformer for explainable cytological classification of papillary thyroid carcinoma
Abstract
The cytological assessment of papillary thyroid carcinoma (PTC) relies on microscopic evaluation of cellular and nuclear morphology. Subtle cytomorphological differences, interobserver variability, and specimen heterogeneity can complicate interpretation. This study developed an explainable hybrid ConvNeXtV2–Swin Transformer framework that integrates fine-grained cytological representation with broader spatial-context modeling for PTC classification. ConvNeXtV2 provides fine-grained nuclear and cellular representations, whereas Swin Transformer captures broader contextual relationships across cytological regions. These complementary representations support classification and subsequent pathology-informed interpretation of nuclear, architectural, and stromal evidence. Interpretability combines Biomarker-Guided Attention Modeling, Gradient-weighted Class Activation Mapping (Grad-CAM)-style quantitative attribution analysis, and ontology-guided post-classification semantic interpretation. On the independent test set, the hybrid framework achieved 96.19% accuracy, 96.16% sensitivity, and 96.16% specificity. Precision was 95.27%, and the area under the receiver operating characteristic curve (ROC-AUC) reached 0.9702. External testing achieved 91.4% accuracy, 91.0% sensitivity, 92.0% specificity, and 94.0% precision. Quantitative attribution analysis showed greater activation heterogeneity and stronger localized responses in PTC tissue. Non-PTC tissue showed broader and more uniform responses associated with preserved follicular morphology. The neuro-symbolic component subsequently organized compartment-level responses according to predefined thyroid cytopathology relationships. These outputs provide pathology-informed computational interpretation without constituting independent biomarker detection or expert-equivalent pathological reasoning.
Related
- An explainable hybrid CNN-transformer framework for multi-representation leukaemia classification
- HemaNest-UNet++ and explainable vision transformer for acute lymphoblastic leukemia classification
- Comparative and explainable deep learning for cherry (Prunus avium L.) cultivar classification using convolutional neural networks (CNN) and transformer architectures
- An Explainable Self‐Supervised Temporal Transformer for Participant‐Level Classification of Depressive Symptoms From Resting‐State EEG
- Hybrid CNN–Transformer–LSTM Architectures for Explainable Brain Tumor MRI Classification
BibTeX
@article{ahmed2026ontologyguided,
title = {{Ontology-guided neuro-symbolic convNeXtV2–swin transformer for explainable cytological classification of papillary thyroid carcinoma}},
author = {Ibrahim Abdulrab Ahmed and Ebrahim Mohammed Senan and Awad Alyousef and M. Attique Khan and Elham Ali and Esam Mohammed Asem Othman and Suliman Mohamed Fati},
journal = {Scientific Reports},
year = {2026},
month = oct,
doi = {10.1038/s41598-026-74498-0},
url = {https://www.nature.com/articles/s41598-026-74498-0},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Ontology-guided neuro-symbolic convNeXtV2–swin transformer for explainable cytological classification of papillary thyroid carcinoma
AU - Ibrahim Abdulrab Ahmed
AU - Ebrahim Mohammed Senan
AU - Awad Alyousef
AU - M. Attique Khan
AU - Elham Ali
AU - Esam Mohammed Asem Othman
AU - Suliman Mohamed Fati
PY - 2026
DA - 2026/10/22
JO - Scientific Reports
DO - 10.1038/s41598-026-74498-0
UR - https://www.nature.com/articles/s41598-026-74498-0
AB - The cytological assessment of papillary thyroid carcinoma (PTC) relies on microscopic evaluation of cellular and nuclear morphology. Subtle cytomorphological differences, interobserver variability, and specimen heterogeneity can complicate interpretation. This study developed an explainable hybrid ConvNeXtV2–Swin Transformer framework that integrates fine-grained cytological representation with broader spatial-context modeling for PTC classification. ConvNeXtV2 provides fine-grained nuclear and cellular representations, whereas Swin Transformer captures broader contextual relationships across cytological regions. These complementary representations support classification and subsequent pathology-informed interpretation of nuclear, architectural, and stromal evidence. Interpretability combines Biomarker-Guided Attention Modeling, Gradient-weighted Class Activation Mapping (Grad-CAM)-style quantitative attribution analysis, and ontology-guided post-classification semantic interpretation. On the independent test set, the hybrid framework achieved 96.19% accuracy, 96.16% sensitivity, and 96.16% specificity. Precision was 95.27%, and the area under the receiver operating characteristic curve (ROC-AUC) reached 0.9702. External testing achieved 91.4% accuracy, 91.0% sensitivity, 92.0% specificity, and 94.0% precision. Quantitative attribution analysis showed greater activation heterogeneity and stronger localized responses in PTC tissue. Non-PTC tissue showed broader and more uniform responses associated with preserved follicular morphology. The neuro-symbolic component subsequently organized compartment-level responses according to predefined thyroid cytopathology relationships. These outputs provide pathology-informed computational interpretation without constituting independent biomarker detection or expert-equivalent pathological reasoning.
SN - 2045-2322
ER -