HybridCATNet: an explainable CNN-Transformer framework with early multi-channel fusion and uncertainty…

AI / informaticsFrontiers in digital health· 2026

HybridCATNet: an explainable CNN-Transformer framework with early multi-channel fusion and uncertainty estimation for pneumonia detection from chest X-rays.

Abdullah, Muhammad Ateeb Ather, Kinza Sardar … Miguel Jesús Torres Ruiz

Cardiothoracic ImagingAI / informaticsDiagnosisQ1IF 5.4

AI model distinguished pneumonia from normal chest X-rays with near-perfect accuracy.

HybridCATNet: an explainable CNN-Transformer framework with early multi-channel fusion and uncertainty estimation for pneumonia detection from chest X-rays.

Abdullah … Miguel Jesús Torres Ruiz

Frontiers in digital health · 2026 · Q1 in General Medicine

Background

Pneumonia remains a leading cause of morbidity and mortality worldwide, particularly among children and older adults, making rapid and reliable interpretation of chest X-rays essential for timely clinical decision-making.

Purpose

This study proposes HybridCATNet, an explainable and uncertainty-aware deep learning framework for automated pneumonia detection from chest radiographs.

Methods

HybridCATNet integrates a convolutional neural network and a vision transformer to capture both fine-grained local radiographic features and long-range anatomical dependencies.

Results

correctly told pneumonia from normal x-rays almost every time

98.13%

Sensitivity

95.72%

Specificity

More results

External validation demonstrated robust cross-domain performance, with an accuracy of at least 94.8% across both independent cohorts.

Explainability analysis showed strong agreement between model-generated attention maps and radiologist-annotated pathological regions, achieving an intersection-over-union of 0.812 and a faithfulness correlation of 0.921.

“

Conclusion

By integrating multi-channel image fusion, hybrid CNN-Transformer feature learning, attention-guided refinement, predictive uncertainty estimation, and explainability, the proposed framework offers a clinically transparent decision-support approach with potential to assist pneumonia screening and improve confidence in AI-assisted radiographic diagnosis.

HybridCATNet: an explainable CNN-Transformer framework with early multi-channel fusion and uncertainty estimation for pneumonia detection from chest X-rays.

HybridCATNet: an explainable CNN-Transformer framework with early multi-channel fusion and uncertainty estimation for pneumonia detection from chest X-rays.

Related papers