# Lung Infection Severity Prediction Using Transformers with Conditional TransMix Augmentation and Cross-Attention Source: [Lung Infection Severity Prediction Using Transformers with Conditional TransMix Augmentation and Cross-Attention]() Collection index: [llms.txt]() Data updated: 2025-10-26T05:52:16.996Z Authors: Bouthaina Slika, Fadi Dornaika, Fares Bougourzi, Karim Hammoudi Published: 2025-10-08T11:08:34.000Z ## Abstract Lung infections, particularly pneumonia, pose serious health risks that can escalate rapidly, especially during pandemics. Accurate AI-based severity prediction from medical imaging is essential to support timely clinical decisions and optimize patient outcomes. In this work, we present a novel method applicable to both CT scans and chest X-rays for assessing lung infection severity. Our contributions are twofold: (i) QCross-Att-PVT, a Transformer-based architecture that integrates parallel encoders, a cross-gated attention mechanism, and a feature aggregator to capture rich multi-scale features; and (ii) Conditional Online TransMix, a custom data augmentation strategy designed to address dataset imbalance by generating mixed-label image patches during training. Evaluated on two benchmark datasets, RALO CXR and Per-COVID-19 CT, our method consistently outperforms several state-of-the-art deep learning models. The results emphasize the critical role of data augmentation and gated attention in improving both robustness and predictive accuracy. This approach offers a reliable, adaptable tool to support clinical diagnosis, disease monitoring, and personalized treatment planning. The source code of this work is available at https://github.com/bouthainas/QCross-Att-PVT. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Severity Scoring (Geographic Extent) on RALO (test)](): Severity Scoring (Geographic Extent); RALO (test); MAE: 0.362. - [Severity Scoring (Lung Opacity) on RALO (test)](): Severity Scoring (Lung Opacity); RALO (test); MAE: 0.337. - [COVID-19 Infection Percentage estimation on Per-COVID-19 CT (test)](): COVID-19 Infection Percentage estimation; Per-COVID-19 CT (test); MAE: 4.45. - [COVID-19 Infection Percentage (CIP) estimation on Per-COVID-19 CT (val)](): COVID-19 Infection Percentage (CIP) estimation; Per-COVID-19 CT (val); MAE: 5.42. ## Original sources and implementation [Original paper]() [PDF]()