Deep learning–based CT lesion analysis and radiological burden stratification in clinically diagnosed ventilator-associated pneumonia
- 1chool of Medical Sciences, Universiti Sains Malaysia, Health Campus, Kubang Kerian, Kelantan, Malaysia
Abstract
Ventilator associated pneumonia (VAP) is a major complication in the intensive care unit (ICU) and requires objective computed tomography (CT) evaluation. Therefore, this article conducted a retrospective research analysis and developed a multimodal deep learning framework. Firstly, this retrospective study included 512 patients clinically diagnosed with VAP, and then utilized a developed multimodal deep learning framework for voxel-level lesion segmentation, multi-label radiological discovery classification, and radiological burden grading. This framework integrates the anatomical priors of TotalSegmenter, a three-dimensional (3D) Swin UNETR multitasking network, and cross attention fusion of CT features and ventilation parameters. Ultimately, the study showed that the Dice score for internal validation was 0.847, the macroscopic mean area (AUC) under the subject's working characteristic curve was 0.919, and the weighted kappa was 0.826. External validation showed a Dice score of 0.821, with no significant difference between scanner manufacturers. After adjusting for clinical covariates, including acute physiology and chronic health assessment II (APACHE II) scores, there was still a significant correlation between radiation load level and 28 day mortality (hazard ratio [HR] = 2.34, P < 0.001), supporting its potential prognostic relevance.
Related
- Accelerometer-derived 24-hour behavior composition and incident clinically diagnosed sleep apnoea: a prospective cohort study
- Clinical-Radiological Discordance in the Detection of Chronic Constipation in Children Newly Diagnosed with Autism Spectrum Disorder: A Retrospective Study.
- Clinically Accessible Phenotypes Refine Cardiovascular Risk Stratification Beyond Contemporary Clinical Equations
- Plasma proteomics for prognostic stratification in newly diagnosed primary central nervous system lymphoma
- Refining Home-Based Squat Training: The Role of Hip Adduction in Improving Neuromuscular Control for Clinically Diagnosed Patellofemoral Pain Syndrome.
BibTeX
@article{zheng2026deep,
title = {{Deep learning–based CT lesion analysis and radiological burden stratification in clinically diagnosed ventilator-associated pneumonia}},
author = {Fuwen Zheng and Andee Dzulkarnaen Zakaria},
journal = {Frontiers in Medicine},
year = {2026},
month = oct,
doi = {10.3389/fmed.2026.1966805},
url = {https://doi.org/10.3389/fmed.2026.1966805},
note = {CC BY},
}
RIS
TY - JOUR
TI - Deep learning–based CT lesion analysis and radiological burden stratification in clinically diagnosed ventilator-associated pneumonia
AU - Fuwen Zheng
AU - Andee Dzulkarnaen Zakaria
PY - 2026
DA - 2026/10/23
JO - Frontiers in Medicine
DO - 10.3389/fmed.2026.1966805
UR - https://doi.org/10.3389/fmed.2026.1966805
AB - Ventilator associated pneumonia (VAP) is a major complication in the intensive care unit (ICU) and requires objective computed tomography (CT) evaluation. Therefore, this article conducted a retrospective research analysis and developed a multimodal deep learning framework. Firstly, this retrospective study included 512 patients clinically diagnosed with VAP, and then utilized a developed multimodal deep learning framework for voxel-level lesion segmentation, multi-label radiological discovery classification, and radiological burden grading. This framework integrates the anatomical priors of TotalSegmenter, a three-dimensional (3D) Swin UNETR multitasking network, and cross attention fusion of CT features and ventilation parameters. Ultimately, the study showed that the Dice score for internal validation was 0.847, the macroscopic mean area (AUC) under the subject's working characteristic curve was 0.919, and the weighted kappa was 0.826. External validation showed a Dice score of 0.821, with no significant difference between scanner manufacturers. After adjusting for clinical covariates, including acute physiology and chronic health assessment II (APACHE II) scores, there was still a significant correlation between radiation load level and 28 day mortality (hazard ratio [HR] = 2.34, P < 0.001), supporting its potential prognostic relevance.
SN - 2296-858X
ER -