Artificial Intelligence in Chest CT Scans: Low-Dose Protocol and Deep Learning Algorithm Show Promise

Strategic Insights -

Researchers at the Huazhong University of Science and Technology in Wuhan, China, have conducted a study on the use of artificial intelligence (AI) in chest computed tomography (CT) scans. The study aimed to investigate the effects of a precise imaging (PI) deep-learning AI algorithm combined with a low-dose scanning protocol on image quality and radiation dose. The research concluded that the low-dose scanning protocol combined with high-intensity PI deep learning-based algorithm reconstruction achieves high image quality while maintaining a low radiation dose.

Key Takeaways:

  • The study involved 100 patients who underwent non-contrast chest CT scans between October and December 31, 2024, using a Philips Incisive CT scanner.
  • The patients were divided into two groups: an experimental group (n=50) and a control group (n=50).
  • The experimental group was scanned using a low-dose protocol with a tube voltage of 100 kVp, and the images were reconstructed using the PI deep-learning AI algorithm at a high-intensity level.
  • The control group was scanned using a conventional-dose protocol with a tube voltage of 120 kVp, and the images were reconstructed by iDose iterative reconstruction.
  • The results showed that the noise level of the mediastinal and lung window images in the experimental group was significantly lower than that in the control group (P < 0.05).
  • The subjective image quality scores of the experimental group and the control group were 4.40±0.53 and 4.30±0.51, respectively, with no significant difference between the two groups (P < 0.05).
  • The mean volume CT dose index (CTDIvol) values were 1.37±0.22 and 7.07±1.70 mGy, the mean dose-length product (DLP) values were 56.36±9.82 and 296.8±80.72 mGy·cm, and the mean effective dose (ED) values were 0.79±0.14 and 4.16±1.13 mSv, respectively.
  • The study concluded that the low-dose scanning protocol combined with high-intensity PI deep learning-based algorithm reconstruction achieves high image quality while maintaining a low radiation dose.

Statistics:

  • 100 patients underwent non-contrast chest CT scans between October and December 31, 2024.
  • The experimental group consisted of 50 patients, and the control group consisted of 50 patients.
  • The mean CTDIvol value was 1.37±0.22 mGy, a reduction of 81.00% compared to the control group.
  • The mean DLP value was 56.36±9.82 mGy·cm, a reduction of 81.00% compared to the control group.
  • The mean ED value was 0.79±0.14 mSv, a reduction of 81.00% compared to the control group.

Sources:

  • The application of deep learning-based artificial intelligence algorithms combined with low-dose scanning protocols in chest CT. Quantitative Imaging in Medicine and Surgery, 2025;15(10):8897-8909.
  • NewsRx. Researchers from Huazhong University of Science and Technology Report Recent Findings in Artificial Intelligence (The application of deep learning-based artificial intelligence algorithms combined with low-dose scanning protocols in chest CT). Education Letter. October 29, 2025; p 664.