AI Denoising Improves Image Quality and Radiological Workflows in Pediatric Ultra-Low-Dose Thorax Computed Tomography Scans

Abstract

(1) This study evaluates the impact of an AI denoising algorithm on image quality, diagnostic accuracy, and radiological workflows in pediatric chest ultra-low-dose CT (ULDCT). (2) Methods: 100 consecutive pediatric thorax ULDCT were included and reconstructed using weighted filtered back projection (wFBP), iterative reconstruction (ADMIRE 2), and AI denoising (PixelShine). Place-consistent noise measurements were used to compare objective image quality. Eight blinded readers independently rated the subjective image quality on a Likert scale (1 = worst to 5 = best). Each reader wrote a semiquantitative report to evaluate disease severity using a severity score with six common pathologies. The time to diagnosis was measured for each reader to compare the possible workflow benefits. Properly corrected mixed-effects analysis with post-hoc subgroup tests were used. Spearman’s correlation coefficient measured inter-reader agreement for the subjective image quality analysis and the severity score sheets. (3) Results: The highest noise was measured for wFBP, followed by ADMIRE 2, and PixelShine (76.9 ± 9.62 vs. 43.4 ± 4.45 vs. 34.8 ± 3.27 HU; each p < 0.001). The highest subjective image quality was measured for PixelShine, followed by ADMIRE 2, and wFBP (4 (4–5) vs. 3 (4–5) vs. 3 (2–4), each p < 0.001) with good inter-rater agreement (r ≥ 0.790; p ≤ 0.001). In diagnostic accuracy analysis, there was a good inter-rater agreement between the severity scores (r ≥ 0.764; p < 0.001) without significant differences between severity score items per reconstruction mode (F (5.71; 566) = 0.792; p = 0.570). The shortest time to diagnosis was measured for the PixelShine datasets, followed by ADMIRE 2, and wFBP (2.28 ± 1.56 vs. 2.45 ± 1.90 vs. 2.66 ± 2.31 min; F (1.000; 99.00) = 268.1; p < 0.001). (4) Conclusions: AI denoising significantly improves image quality in pediatric thorax ULDCT without compromising the diagnostic confidence and reduces the time to diagnosis substantially.

AI Applications in Pediatrics: Past, Present, and Future

“…After the images were denoised, they were compared to standard weighted filtered back projection (wFBP), iterative reconstruction (ADMIRE 2), and PixelShine datasets. The results illustrated that wFBP datasets had the longest diagnosis time of 2.66 ± 2.31 min while PixelShine had the least of 2.28 ± 1.56 min [31]. The noise detected in PixelShine was also the smallest: 34.8 ± 3.27 Hounsfield Units [31].…”

“…One method to enhance the efficiency of CT scans is through improving image quality. In a study conducted by Brendlin et al, an AI algorithm PixelShine created by AlgoMedica was utilized to determine its denoising ability for pediatric ultra-low-dose CT scans in 100 pediatric patients [31]. This algorithm denoises the scans after they are obtained and helps reduce diagnosis time.…”

CT image denoising methods for image quality improvement and radiation dose reduction

“…Evaluating a DL denoising model involves assessing its ability to effectively reduce noise while preserving important image details. Generated denoised images are usually compared against the ground truth images such as FBP, 164–166 IR, 167–170 or other DL methods 158,159,163,171–182 . This comparison can provide insights into the model's relative strengths and weaknesses in terms of denoising performance.…”

“…Generalizability is an important consideration when evaluating the effectiveness of DL‐based CT image denoising models. Among 99 papers reviewed, only five studies conducted the independent test 106,139,156,168,180 . An independent test if a mode can be able to effectively denoise CT images in a variety of contexts is necessary, however, this is not yet realized.…”

Pediatric evaluations for deep learning CT denoising

“…12 Initial studies of using DL denoising models on pediatric image data have demonstrated DL denoising models to be effective in clinical settings, but only with small patient numbers and a limited range of body sizes. 5,13,14 Without subgroup analyses 15 as well as comparisons against adult patients, it is unclear whether disparities in DL denoising performance exist among pediatric subgroups. This work introduces a set of pediatric-sized IQ phantoms along with a computational framework to evaluate the performance of DL-based denoising across pediatric subgroups.…”