Related Experiment Video
Updated: Sep 20, 2025
Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph
Published on: February 21, 2025
Deep Learning Image Reconstruction (DLIR) Algorithm to Maintain High Image Quality and Diagnostic Accuracy in
Haoyan Li1, Yuchen Zhang2, Shan Hua3
1Department of radiology, Beijing Children's Hospital, Capital Medical University, National Center for Children's Health, No.56, Nanlishi Road, Xicheng District, Beijing 100045, China (H.L., Y.Z., R.S., Y.P., J.S.).
Insights
Quadruple-low CT angiography (4L-CTA) with deep learning image reconstruction significantly reduces radiation and contrast doses in children with pulmonary sequestration (PS). This method maintains high diagnostic accuracy and visualization of small arteries, proving effective for pediatric PS detection.
Area of Science:
- Medical Imaging
- Pediatric Radiology
- Diagnostic Accuracy
Background:
- CT angiography (CTA) is crucial for diagnosing pulmonary sequestration (PS).
- Reducing radiation and contrast dose in pediatric CTA is essential but challenging.
- Deep learning image reconstruction (DLIR) offers potential for dose reduction while maintaining image quality.
Purpose of the Study:
- To evaluate the diagnostic accuracy of quadruple-low CTA (4L-CTA) using DLIR in children with PS.
- To compare 4L-CTA with DLIR against routine CTA with ASIR-V in terms of radiation dose, contrast medium dosage, injection parameters, and diagnostic performance.
- To assess image quality metrics including contrast-to-noise ratio (CNR) and edge-rise distance (ERD).
Main Methods:
- A retrospective study comparing 53 children undergoing 4L-CTA with DLIR to 53 children undergoing routine CTA with ASIR-V.
- 4L-CTA utilized 70kVp, low radiation dose (0.90 mGy CTDIvol), and reduced contrast (0.8 ml/kg) injected over 16s.
- Image quality (CNR, ERD) and diagnostic sensitivity/specificity for PS were assessed. Subjective image quality and artery visualization were also evaluated.
Main Results:
- 4L-CTA achieved significant reductions in radiation dose (51%), contrast dose (47%), injection flow rate (44%), and injection pressure (44%) compared to routine CTA (p<0.05).
- Both protocols demonstrated 100% sensitivity and specificity for diagnosing PS, with satisfactory subjective image quality.
- 4L-CTA showed a reduced CNR (27%, p<0.05) but comparable ERD, indicating preserved spatial resolution and visualization of small arteries (down to 0.8 mm).
Conclusions:
- Deep learning image reconstruction enables effective quadruple-low CTA in pediatric patients with pulmonary sequestration.
- 4L-CTA significantly reduces radiation and contrast medium doses while preserving diagnostic accuracy and visualization of critical arterial structures.
- This approach represents a promising advancement for safer and effective pediatric pulmonary sequestration diagnosis.
Rationale And Objectives:
CT angiography (CTA) is a commonly used clinical examination to detect abnormal arteries and diagnose pulmonary sequestration (PS). Reducing the radiation dose, contrast medium dosage, and injection pressure in CTA, especially in children, has always been an important research topic, but few research is proven by pathology. The current study aimed to evaluate the diagnostic accuracy for children with PS in a quadruple-low CTA (4L-CTA: low tube voltage, radiation, contrast medium, and injection flow rate) using deep learning image reconstruction (DLIR) in comparison with routine protocol CTA with adaptive statistical iterative reconstruction-V (ASIR-V) MATERIALS AND METHODS: 53 patients (1.50±1.36years) suspected with PS were enrolled to undergo chest 4L-CTA using 70kVp tube voltage with radiation dose or 0.90 mGy in volumetric CT dose index (CTDIvol) and contrast medium dose of 0.8 ml/kg injected in 16 s. Images were reconstructed using DLIR. Another 53 patients (1.25±1.02years) with a routine dose protocol was used for comparison, and images were reconstructed with ASIR-V. The contrast-to-noise ratio (CNR) and edge-rise distance (ERD) of the aorta were calculated. The subjective overall image quality and artery visualization were evaluated using a 5-point scale (5, excellent; 3, acceptable). All patients underwent surgery after CT, the sensitivity and specificity for diagnosing PS were calculated.
Results:
4L-CTA reduced radiation dose by 51%, contrast dose by 47%, injection flow rate by 44% and injection pressure by 44% compared to the routine CTA (all p<0.05). Both groups had satisfactory subjective image quality and achieved 100% in both sensitivity and specificity for diagnosing PS. 4L-CTA had a reduced CNR (by 27%, p<0.05) but similar ERD, which reflects the image spatial resolution (p>0.05) compared to the routine CTA. 4L-CTA revealed small arteries with a diameter of 0.8 mm.
Conclusion:
DLIR ensures the realization of 4L-CTA in children with PS for significant radiation and contrast dose reduction, while maintaining image quality, visualization of small arteries, and high diagnostic accuracy.
