# Deep Learning-Based Detection of Carotid Artery Atheromas in Panoramic Radiographs

## TL;DR

This paper introduces a deep learning model to detect carotid artery atheromas in dental radiographs, enabling early stroke risk assessment using AI.

## Contribution

A novel deep learning method using MobileNetV2 for automatic detection of carotid atheromas in panoramic radiographs is proposed.

## Key findings

- The model achieved 94.7% accuracy and 95.7% sensitivity in detecting carotid atheromas on test data.
- Using a sensitivity-targeted threshold, the model maintained high specificity (97.1%) while achieving 82.6% sensitivity.
- The results suggest panoramic radiographs can serve as an opportunistic screening tool for vascular risk assessment.

## Abstract

Radiographically visible carotid artery calcifications are typically seen at the level of the C3–C4 cervical vertebrae and can be detected on panoramic dental radiographs. Their early identification is clinically relevant, as they represent a potential marker for increased risk of stroke. In this context, the present study proposes a deep learning method for automatic identification of carotid atheromas using MobileNetV2. From a publicly available dataset, 378 region-of-interest (ROI) images (640 × 320) were prepared and split into train/val/test = 264/57/57 with class counts train 157/107, val 34/23, test 34/23 (negatives/positives). Images underwent standardized preprocessing and on-the-fly augmentation; training used a two-stage scheme (backbone frozen “head” training followed by partial fine-tuning of the top layers), class-weighting, dropout = 0.3, batch normalization (BN) head, early stopping, and partial unfreezing (~70% of the backbone). The decision threshold was selected on validation by Youden’s J. On the independent test set, the model achieved an accuracy (ACC) of 94.7%, sensitivity (SEN) of 95,7%, specificity (SPE) of 0.941, area under the receiver operating characteristic curve (AUC) 0.963, and area under the precision–recall curve (AUPRC) of 0.968. Using a sensitivity-targeted threshold (SEN ≈ 0.80), the model yielded ACC = 91.2%, SEN = 82.6%, and SPE = 97.1%. These results support panoramic radiographs as an opportunistic screening modality for systemic vascular risk and highlight the potential of artificial intelligence (AI)-assisted methods to enable earlier identification within preventive healthcare.