Paper
A Clinically Anchored Radiomics Dictionary for Explainable TI-RADS-Based Thyroid Nodule Classification in Ultrasound; Dictionary Version TU1.0
Authors
Mohammad Salmanpour, Shahram Taeb, Ali Fathi Jouzdani, Mohammad Ayazi, Siavash Hosseinpour Saffarian, Mehdi Maghsudi, Ilker Hacihaliloglu, Arman Rahmim
Abstract
Artificial intelligence based radiomics models for thyroid ultrasound (US) often achieve strong diagnostic performance but remain difficult to interpret, limiting clinical trust and adoption. We developed and validated an interpretable radiomic feature (RF) framework for thyroid nodule classification by linking quantitative US features to the Thyroid Imaging Reporting and Data System (TI-RADS) semantic lexicon through a clinically grounded radiomics dictionary. The dictionary mapped TI-RADS categories, including composition, echogenicity, shape, margin, and echogenic foci, to Image Biomarker Standardization Initiative compliant RFs extracted from two-dimensional US images. Relationships were defined through expert consensus and examined using Shapley Additive Explanations (SHAP). Three multicenter datasets were combined, yielding 5,542 nodules. A total of 107 RFs were extracted using PyRadiomics and normalized with min-max scaling. For benign versus malignant classification, 27 feature selection methods were paired with 25 classifiers and evaluated using stratified five-fold cross-validation on 70% of the data, followed by testing on the remaining 30%. Robust model selection used a stability-aware composite score combining mean performance and variability across balanced accuracy, precision, recall, F1-score, and ROC-AUC. The proposed dictionary enabled direct interpretation of radiomic signatures in TI-RADS terms. The best model, Select-From-Model based on logistic regression with Extra-Trees, achieved a test ROC-AUC of 0.941 +/- 0.005. SHAP analysis showed that texture heterogeneity was the dominant malignancy signal, with gray level run length matrix non-uniformity, intensity dispersion, and kurtosis aligning with high-risk TI-RADS descriptors. These findings support transparent and clinically meaningful thyroid nodule risk stratification from US.
Metadata
Related papers
Fractal universe and quantum gravity made simple
Fabio Briscese, Gianluca Calcagni • 2026-03-25
POLY-SIM: Polyglot Speaker Identification with Missing Modality Grand Challenge 2026 Evaluation Plan
Marta Moscati, Muhammad Saad Saeed, Marina Zanoni, Mubashir Noman, Rohan Kuma... • 2026-03-25
LensWalk: Agentic Video Understanding by Planning How You See in Videos
Keliang Li, Yansong Li, Hongze Shen, Mengdi Liu, Hong Chang, Shiguang Shan • 2026-03-25
Orientation Reconstruction of Proteins using Coulomb Explosions
Tomas André, Alfredo Bellisario, Nicusor Timneanu, Carl Caleman • 2026-03-25
The role of spatial context and multitask learning in the detection of organic and conventional farming systems based on Sentinel-2 time series
Jan Hemmerling, Marcel Schwieder, Philippe Rufin, Leon-Friedrich Thomas, Mire... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.22692v1</id>\n <title>A Clinically Anchored Radiomics Dictionary for Explainable TI-RADS-Based Thyroid Nodule Classification in Ultrasound; Dictionary Version TU1.0</title>\n <updated>2026-03-24T01:31:21Z</updated>\n <link href='https://arxiv.org/abs/2603.22692v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.22692v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>Artificial intelligence based radiomics models for thyroid ultrasound (US) often achieve strong diagnostic performance but remain difficult to interpret, limiting clinical trust and adoption. We developed and validated an interpretable radiomic feature (RF) framework for thyroid nodule classification by linking quantitative US features to the Thyroid Imaging Reporting and Data System (TI-RADS) semantic lexicon through a clinically grounded radiomics dictionary. The dictionary mapped TI-RADS categories, including composition, echogenicity, shape, margin, and echogenic foci, to Image Biomarker Standardization Initiative compliant RFs extracted from two-dimensional US images. Relationships were defined through expert consensus and examined using Shapley Additive Explanations (SHAP). Three multicenter datasets were combined, yielding 5,542 nodules. A total of 107 RFs were extracted using PyRadiomics and normalized with min-max scaling. For benign versus malignant classification, 27 feature selection methods were paired with 25 classifiers and evaluated using stratified five-fold cross-validation on 70% of the data, followed by testing on the remaining 30%. Robust model selection used a stability-aware composite score combining mean performance and variability across balanced accuracy, precision, recall, F1-score, and ROC-AUC. The proposed dictionary enabled direct interpretation of radiomic signatures in TI-RADS terms. The best model, Select-From-Model based on logistic regression with Extra-Trees, achieved a test ROC-AUC of 0.941 +/- 0.005. SHAP analysis showed that texture heterogeneity was the dominant malignancy signal, with gray level run length matrix non-uniformity, intensity dispersion, and kurtosis aligning with high-risk TI-RADS descriptors. These findings support transparent and clinically meaningful thyroid nodule risk stratification from US.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='physics.med-ph'/>\n <published>2026-03-24T01:31:21Z</published>\n <arxiv:primary_category term='physics.med-ph'/>\n <author>\n <name>Mohammad Salmanpour</name>\n </author>\n <author>\n <name>Shahram Taeb</name>\n </author>\n <author>\n <name>Ali Fathi Jouzdani</name>\n </author>\n <author>\n <name>Mohammad Ayazi</name>\n </author>\n <author>\n <name>Siavash Hosseinpour Saffarian</name>\n </author>\n <author>\n <name>Mehdi Maghsudi</name>\n </author>\n <author>\n <name>Ilker Hacihaliloglu</name>\n </author>\n <author>\n <name>Arman Rahmim</name>\n </author>\n </entry>"
}