The objective of this study was to test the relative and additive effectiveness of AI-based noise reduction techniques and edge enhancement filters on the visibility of anatomic structures and overall clarity of pediatric portable chest X-rays. Images were collected using a mobile x-ray system and wireless flat panel detector and then underwent AI-based noise reduction, upload to the clinic’s PACS system, and built-in edge enhancement. Four imaging process techniques were evaluated: standard portable X-ray, edge enhancement, noise reduction, and edge enhancement plus noise reduction. In total, 101 patients participated in the study, ranging from 0 to 7.9 years of age. Because of the range of patients involved, tube voltage, tube current, source-to-image distance, and entrance skin dose all varied on a case-to-case basis. Each radiograph was graded based on a prior study’s Visual Grading Analysis (VGA) approach using a 5 point system (1 being not fulfilled and 5 being fulfilled) and assessed the visibility of proximal bronchi, small peripheral airways, and vertebrae as well as the acceptability of image noise and image quality. The images were randomized and two radiologists independently used the VGA approach to grade each image. Scores were averaged to provide general data per item and applied condition, and interobserver agreement was tested using the intraclass coefficient (ICC). In this study, the ICC was found to be excellent, with a coefficient of 0.91 (scale from 0 to 1 with 1 being perfect agreement). It was found that in comparison to the original image, all enhancements performed increased image quality in a statistically significant way. NR+/Filter+ (noise reduction and edge enhancement) was found to most improve structure visibility. There was no statistically significant difference found between the NR+/Filter- (noise reduction) and NR+/Filter+ (noise reduction and edge enhancement) groups, providing evidence that edge enhancement did not have an additive impact on image noise. It was lastly noted that while there was no change in image quality resulting from patient age, there was a moderate positive correlation between body weight and image quality, most likely resulting from the higher radiation dose that is available to those with more body mass. The study found that AI noise reduction tools were incredibly useful in reducing noise and that edge enhancement made identifying anatomical structures easier. Fujikawa et. al note that too much enhancement may compromise image quality needed for accurate interpretation, and that a protocol is needed to ensure a reasonable balance in raw data and clean-up. Limitations were noted to be the small sample size, evaluation method of focusing on visual clarity instead of diagnostic assessments, and lack of pathological conditions identified. In the future, studies should further investigate the utility of these techniques in diagnosing specific conditions.