Radiation dose optimization is particularly important in pediatric radiology, as children are more susceptible to potential harmful effects of ionizing radiation. However, only one narrative review about artificial intelligence (AI) for dose optimization in pediatric computed tomography (CT) has been published yet. The purpose of this systematic review is to answer the question “What are the AI techniques and architectures introduced in pediatric radiology for dose optimization, their specific application areas, and performances?” Literature search with use of electronic databases was conducted on 3 June 2022. Sixteen articles that met selection criteria were included. The included studies showed deep convolutional neural network (CNN) was the most common AI technique and architecture used for dose optimization in pediatric radiology. All but three included studies evaluated AI performance in dose optimization of abdomen, chest, head, neck, and pelvis CT; CT angiography; and dual-energy CT through deep learning image reconstruction. Most studies demonstrated that AI could reduce radiation dose by 36–70% without losing diagnostic information. Despite the dominance of commercially available AI models based on deep CNN with promising outcomes, homegrown models could provide comparable performances. Future exploration of AI value for dose optimization in pediatric radiology is necessary due to small sample sizes and narrow scopes (only three modalities, CT, positron emission tomography/magnetic resonance imaging and mobile radiography, and not all examination types covered) of existing studies.

Generative artificial intelligence, especially with regard to the generative adversarial network (GAN), is an important research area in radiology as evidenced by a number of literature reviews on the role of GAN in radiology published in the last few years. However, no review article about GAN in pediatric radiology has been published yet. The purpose of this paper is to systematically review applications of GAN in pediatric radiology, their performances, and methods for their performance evaluation. Electronic databases were used for a literature search on 6 April 2023. Thirty-seven papers met the selection criteria and were included. This review reveals that the GAN can be applied to magnetic resonance imaging, X-ray, computed tomography, ultrasound and positron emission tomography for image translation, segmentation, reconstruction, quality assessment, synthesis and data augmentation, and disease diagnosis. About 80% of the included studies compared their GAN model performances with those of other approaches and indicated that their GAN models outperformed the others by 0.1–158.6%. However, these study findings should be used with caution because of a number of methodological weaknesses. For future GAN studies, more robust methods will be essential for addressing these issues. Otherwise, this would affect the clinical adoption of the GAN-based applications in pediatric radiology and the potential advantages of GAN could not be realized widely.

The purpose of this study was to finetune a deep learning model, real-enhanced super-resolution generative adversarial network (Real-ESRGAN), and investigate its diagnostic value in calcified coronary plaques with the aim of suppressing blooming artifacts for the further improvement of coronary lumen assessment. We finetuned the Real-ESRGAN model and applied it to 50 patients with 184 calcified plaques detected at three main coronary arteries (left anterior descending [LAD], left circumflex [LCx] and right coronary artery [RCA]). Measurements of coronary stenosis were collected from original coronary computed tomography angiography (CCTA) and Real-ESRGAN-processed images, including Real-ESRGAN-high-resolution, Real-ESRGAN-average and Real-ESRGAN-median (Real-ESRGAN-HR, Real-ESRGAN-A and Real-ESRGAN-M) with invasive coronary angiography as the reference. Our results showed specificity and positive predictive value (PPV) of the Real-ESRGAN-processed images were improved at all of the three coronary arteries, leading to significant reduction in the false positive rates when compared to those of the original CCTA images. The specificity and PPV of the Real-ESRGAN-M images were the highest at the RCA level, with values being 80% (95% CI: 64.4%, 90.9%) and 61.9% (95% CI: 45.6%, 75.9%), although the sensitivity was reduced to 81.3% (95% CI: 54.5%, 95.9%) due to false negative results. The corresponding specificity and PPV of the Real-ESRGAN-M images were 51.9 (95% CI: 40.3%, 63.5%) and 31.5% (95% CI: 25.8%, 37.8%) at LAD, 62.5% (95% CI: 40.6%, 81.2%) and 43.8% (95% CI: 30.3%, 58.1%) at LCx, respectively. The area under the receiver operating characteristic curve was also the highest at the RCA with value of 0.76 (95% CI: 0.64, 0.89), 0.84 (95% CI: 0.73, 0.94), 0.85 (95% CI: 0.75, 0.95) and 0.73 (95% CI: 0.58, 0.89), corresponding to original CCTA, Real-ESRGAN-HR, Real-ESRGAN-A and Real-ESRGAN-M images, respectively. This study proves that the finetuned Real-ESRGAN model significantly improves the diagnostic performance of CCTA in assessing calcified plaques.

To compare the diagnostic value of coronary CT angiography (CCTA) with use of 2 image postprocessing methods (CCTA_S) and (CCTA_OS) and original data (CCTA_O) for the assessment of heavily calcified plaques.Fifty patients (41 men, 9 women; mean age 61.9 years ± 9.1) with suspected coronary artery disease who underwent CCTA and invasive coronary angiography (ICA) examinations were included in the study. Image data were postprocessed with "sharpen" and smooth reconstruction algorithms in comparison with the original data without undergoing any image postprocessing to determine the effects on suppressing blooming artifacts due to heavy calcification in the coronary arteries. Minimal lumen diameter and degree of stenosis were measured and compared between CCTA_S, CCTA_OS, and CCTA_O with ICA as the reference method. The area under the curve (AUC) by receiver-operating characteristic curve analysis (ROC) was also compared among these 3 CCTA techniques.On a per-vessel assessment, the sensitivity, specificity, positive predictive value and negative predictive value, and 95% confidence interval (CI) were 100% (95% CI: 89%, 100%), 33% (95% CI: 22%, 45%), 41% (95% CI: 30%, 53%), 100% (95% CI: 85%, 100%) for CCTA_O, 94% (95% CI: 79%, 99%), 66% (95% CI: 54%, 77%), 57% (95% CI: 43%, 70%), and 95% (95% CI: 85%, 99%) for CCTA_S, 94% (95% CI: 79%, 99%), 44% (95% CI: 32%, 57%), 44% (95% CI: 32%, 57%), and 97% (95% CI: 79%, 99%) for CCTA_OS, respectively. The AUC by ROC curve analysis for CCTA_S showed significant improvement for detection of >50% coronary stenosis in left anterior descending coronary artery compared to that of CCTA_OS and CCTA_O methods (P < 0.05), with no significance differences for detection of coronary stenosis in the left circumflex and right coronary arteries (P > 0.05).CCTA with "sharpen" reconstruction reduces blooming artifacts from heavy calcification, thus, leading to significant improvement of specificity and positive predictive value of CCTA in patients with heavily calcified plaques. However, specificity is still moderate and additional functional imaging may be needed.