Noise2Quality: non-reference, pixel-wise assessment of low dose CT image quality

Haque, Ayaan; Wang, Adam; Imran, Ali

doi:10.1117/12.2611254

Cited by 1 publication

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Evaluating CT images both quantitatively and qualitatively offers distinct advantages over solely assessing the effective dose. Quantitative assessment enables the precise measurement of image quality parameters such as contrast and noise levels, offering valuable insights into diagnostic potential [21]. This quantitative approach aids in determining optimal exposure levels for generating diagnostically suitable images [22].…”

Section: Discussionmentioning

confidence: 99%

Qualitative and Quantitative Evaluation of the Image Quality of MDCT Multiphasic Liver Scans in HCC Patients

Sayed,

Rawashdeh,

Safwany

et al. 2024

Preprint

View full text Add to dashboard Cite

Background: The quality of CT images obtained from hepatocellular carcinoma (HCC) patients is complex, affecting diagnostic accuracy, precision, and radiation dose assessment due to increased exposure risks. Objectives: The study evaluated image quality qualitatively and quantitatively by comparing quality levels with an effective radiation dose to ensure acceptable quality accuracy. Materials and Methods This study retrospectively reviewed 100 known HCC patients (Li-RADS-5) who underwent multidetector computed tomography (MDCT) multiphasic scans for follow-up of their health condition between January and October 2023. The evaluation involved quantitative and qualitative analyses of parameters such as SD, SNR, and CNR, as well as a qualitative assessment by two radiology consultants. The outcomes were compared, and the effective dose was calculated and compared with both quantitative and qualitative assessments of image quality. Results: ROC curve analysis revealed significant differences in CT image quality, with high to moderate specificity and sensitivity across all the quantitative parameters. However, multivariate examination revealed decreasing importance levels, except for the CNR (B, 0.203; p = 0.001) and SD BG (B, 0.330; p = 0.002), which increased in B. The CNR and SD BG remained independent variables for CT image quality prediction, but no statistically significant relationship was found between the effective dose and image quality, either quantitatively or qualitatively. Conclusion: This study underscores the vital role of both quantitative and qualitative assessments of CT images in evaluating their quality for patients with HCC and highlights the predictive importance of the CNR, SNR, and SD. These findings emphasize the value of these devices in assessing and predicting outcomes to minimize the effective dose.

show abstract

Section: Discussionmentioning

confidence: 99%