Using Correlative Properties of Neighboring Pixels to Improve Gray-White Differentiation in Pediatric Head CT Images

Madaelil, Thomas P; Sharma, Aseem; Hildebolt, Charles F.; Parsons, Matthew S.

doi:10.3174/ajnr.a5506

Cited by 5 publications

(2 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…23 It has been previously shown to improve the contrast-to-noise ratio (CNR) between diseased and normal brain tissue in brain infarction and mesial temporal sclerosis. 24,25 The objective of this study was to test whether image processing of existing MR imaging scans with CIE can be used to improve detection of optic neuritis by selectively improving the CNR of diseased optic nerves.…”

mentioning

confidence: 99%

Evaluating the Utility of a Postprocessing Algorithm for MRI Evaluation of Optic Neuritis

Stunkel

Sharma

Parsons

et al. 2019

AJNR Am J Neuroradiol

Self Cite

View full text Add to dashboard Cite

BACKGROUND AND PURPOSE: MR imaging is useful for the detection and/or confirmation of optic neuritis. The objective of this study was to determine whether a postprocessing algorithm selectively increases the contrast-to-noise ratio of abnormal optic nerves in optic neuritis, facilitating this diagnosis on MR imaging. MATERIALS AND METHODS: In this retrospective case-control study, coronal FLAIR images and coronal contrast-enhanced T1WI from 44 patients (31 eyes with clinically confirmed optic neuritis and 28 control eyes) underwent processing using a proprietary postprocessing algorithm designed to detect and visually highlight regions of contiguous increases in signal intensity by increasing the signal intensities of regions that exceed a predetermined threshold. For quantitative evaluation of the effect on image processing, the contrast-to-noise ratio of equivalent ROIs and the contrast-to-noise ratio between optic nerves and normal-appearing white matter were measured on baseline and processed images. The effect of image-processing on diagnostic performance was evaluated by masked reviews of baseline and processed images by 6 readers with varying experience levels. RESULTS: In abnormal nerves, processing resulted in an increase in the median contrast-to-noise ratio from 17.8 to 85.0 (P Ͻ .001) on FLAIR and from 19.4 to 93.7 (P Ͻ .001) on contrast-enhanced images. The contrast-to-noise ratio for control optic nerves was not affected by processing (P ϭ 0.13). Image processing had a beneficial effect on radiologists' diagnostic performance, with an improvement in sensitivities for 5/6 readers and relatively unchanged specificities. Interobserver agreement improved following processing. CONCLUSIONS: Processing resulted in a selective increase in the contrast-to-noise ratio for diseased nerves and corresponding improvement in the detection of optic neuritis on MR imaging by radiologists.

show abstract

mentioning

confidence: 99%

Evaluating the Utility of a Postprocessing Algorithm for MRI Evaluation of Optic Neuritis

Stunkel

Sharma

Parsons

et al. 2019

AJNR Am J Neuroradiol

Self Cite

View full text Add to dashboard Cite

show abstract

“…The image-processing algorithm used by us has been used to improve conspicuity of normal structures or in improving visual separation of normal and abnormal tissues. 27,[30][31][32][33][34][35] The algorithm in all these applications was utilized to improve visual separation of structures with intensities separated by a single threshold. In the current study, however, we applied 2 thresholds that allowed us to maintain visual separation between OAF and presumed IAF, while, facilitating separation of presumed IAF and the NP.…”

Section: Discussionmentioning

confidence: 99%

Delineation of Inner Annulus Fibrosus and Nucleus Pulposus on Routine T2-weighted MR Images

Eldaya

Parsons

Rhea

et al. 2021

Spine

View full text Add to dashboard Cite

Study Design. Retrospective study of 150 IVDs. Objective. Assessment of costume algorithm ability to delineate the IAF and NP on routine T2 images. Summary of Background Data. Central hyperintense region on T2-weighted MR images of normal lumbar IVDs represents a combination of IAF and NP. Ability to identify NP as distinct from IAF can help improve our understanding of IVD morphology in-vivo. Methods. Sagittal T2-weighted TSE MR images of 150 lumbar IVDs from 25 patients were analyzed. MR images were processed using a custom algorithm that markedly increased the signal intensity of structures with inherent signal intensity within 2 defined intensity thresholds. Signal intensity and contrast-to- noise ratio between outer annulus fibrosus, IAF, and NP were assessed at baseline and after processing. To assess consistency of underlying T2 differences, similar analysis was done on 108 discs from 18 patients in whom additional sagittal T2-weighted STIR images were available. Results. Following image processing, apparent IAF and NP were rendered visible in 86% and 84.3% IVDs on T2-weighted TSE and STIR images respectively. While signal intensity of these 2 regions was inherently different (P< 0.001) before processing on TSE and STIR images, their visualization was facilitated by a significant increase (P<0.001) in contrast-to-noise ratio after processing. Nonvisualization of NP was associated with disc degeneration (P<0.001). Conclusion. Inherent differences exist in signal intensities of normal NP and IAF on T2-weighted MR images. Accentuating these differences using image postprocessing techniques can render these 2 structures visible.

show abstract

Evaluating the effect of a post-processing algorithm in detection of annular fissure on MR imaging

et al. 2021

View full text Add to dashboard Cite

Using Correlative Properties of Neighboring Pixels to Improve Gray-White Differentiation in Pediatric Head CT Images

Cited by 5 publications

References 28 publications

Evaluating the Utility of a Postprocessing Algorithm for MRI Evaluation of Optic Neuritis

Evaluating the Utility of a Postprocessing Algorithm for MRI Evaluation of Optic Neuritis

Delineation of Inner Annulus Fibrosus and Nucleus Pulposus on Routine T2-weighted MR Images

Evaluating the effect of a post-processing algorithm in detection of annular fissure on MR imaging

Contact Info

Product

Resources

About