Measuring the Performance of Image Contrast Enhancement Technique

Asamoah, Dominic; Oppong, Emmanuel Ofori; Oppong, Stephen Opoku; Danso, Juliana

doi:10.5120/ijca2018917899

Cited by 44 publications

(24 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Finally, the differences between the used original images whose holograms to be created and the reconstructed images by using the phase information of the hologram have been revealed by the mean squared error (MSE), mean absolute error (MAE) and peak signal-to-noise ratio (PSNR) which are the most common predictors of image quality measurement and calculated by using the equations given in Eqs. (4-6) respectively [40][41][42].…”

Section: Simulation Resultsmentioning

confidence: 99%

Reconstruction with In-Line Digital Holography Quantitative Phase Imaging for Tissue-Mimicking Phantom Samples

Kaya

Onur

2021

Balkan Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

Optical imaging has attracted recent attention as a non-invasive medical imaging method in biomedical and clinical applications. In optical imaging, a light beam is transmitted through an under-test tissue by using an optical source. The beams which are gone through the tissue and/or reflected from the tissue surfaces are received by an array sensor. Based on the light intensity of these received beams on the sensor, sub-tissue maps are generated to scan large tissue areas so that any further biopsy is not required. Although the large tissue areas in pathological images can be scanned by using various methods, nonlinear deformations occur. To overcome this problem, the reconstruction process is frequently used.In this study, we propose an application of biomedical imaging based on performing the reconstruction of a phantom image via an in-line digital holography technique. Hence, many different sub-tissues can be imaged at the same time without the storage problem of the reconstructed image. To neglect the biopsy process required in medical imaging, the phantom image is obtained by using a linear array transducer for this study. We present the performance evaluation of the simulation results for the proposed technique by calculating the error metrics such as mean squared error (MSE), mean absolute error (MAE) and peak signal-to-noise ratio (PSNR). The obtained results reveal that the reconstructed images are well-matched to the original images, which are desired to be displayed by the holography technique.

show abstract

Section: Simulation Resultsmentioning

confidence: 99%

Reconstruction with In-Line Digital Holography Quantitative Phase Imaging for Tissue-Mimicking Phantom Samples

Kaya

Onur

2021

Balkan Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

show abstract

“…The greater the PSNR value is, the better the image quality becomes, while the smaller the MSE value is, the less noisy the image will be [25], [29], [30]. These can be seen from the 1200×1200 pixels image.…”

Section: Resultsmentioning

confidence: 99%

Planar Scintigraphy Image De-Noising Using Coiflet Wavelet

Puspitasari

Ningsih

Ridwan

et al. 2021

gnd

View full text Add to dashboard Cite

The planar scintigraphic image usually has poor resolution and contains noise. This noise can be removed using the coiflet wavelet method so that the image quality gets better. This coiflet wavelet method is a noise reduction method based on frequency analysis. The planar scintigraphy image is the reconstructed image of the gamma radiation count data (phantom with the Cs-137 source in it). The original image is 15×15 pixel. Before the de-noising process, the image went through an interpolation process, which is to increase the pixel size of the image. The original image enlarged to 70×70, 480×480, and 1200×1200 pixel. After de-noising with coiflet wavelet, the image quality is measured based on MSE and PSNR parameters. The resulting images are quite good, with MSE values are close to zero and PSNR values of more than 60 dB. The smaller the MSE and the bigger the PSNR, is getting the better the image quality. In this study, the results show that the 1200×1200 pixel image has the best quality. It means that the image enlargement process has a good effect on the de-noising process, especially if the original image has a low resolution.

show abstract

“…| is the absolute value of the difference between the two Area Under the Curve (AUC). We now proceed with the second error calculated using the following 2D Mean Square Error (MSE; (Asamoah, Ofori, Opoku, & Danso, 2018)): Where M and N=2 are the number of data points and coordinates points respectively. Again, a spline interpolation was used on the cohort’s data point to the M length of the reference data point prior to error calculation.…”

Section: Methodsmentioning

confidence: 99%

Section: Clinical Assessments Of Motor Symptomsmentioning

confidence: 99%

Intra-individual reproducibility as essential determinant of clinical utility of smartphone-based neurological disability tests

Lkt

Harris

et al. 2021

Preprint

View full text Add to dashboard Cite

Technological advances, lack of medical professionals, high cost of face-to face encounters and disasters such as COVID19 pandemic, fuel the telemedicine revolution. Numerous smartphone apps have been developed to measure neurological functions. However, their psychometric properties are seldom determined. Lacking such data, it is unclear which designs underlie eventual clinical utility of the smartphone tests. We have developed the smartphone Neurological Function Tests Suite (NeuFun-TS) and are systematically evaluating their psychometric properties against the gold-standard of complete neurological examination digitalized into NeurExTM App. This paper examines the fifth, and thus far the most complex NeuFun-TS test, the "Spiral tracing". We generated 40 features in the training cohort (22 healthy donors [HD] and 105 multiple sclerosis [MS] patients) and compared their intraclass correlation coefficient, fold-change between HD and MS and correlations with relevant clinical and imaging outcomes. We assembled the best features into machine-learning models and examined their performance in the independent validation cohort (56 MS patients). We show that by aggregating multiple neurological functions, complex tests such as spiral tracing are susceptible to intra-individual variations, decreasing their reproducibility and thus, clinical utility. Simple tests, reproducibly measuring single function(s) that can be aggregated to increase sensitivity are preferable in app design.

show abstract

Measuring the Performance of Image Contrast Enhancement Technique

Cited by 44 publications

References 8 publications

Reconstruction with In-Line Digital Holography Quantitative Phase Imaging for Tissue-Mimicking Phantom Samples

Reconstruction with In-Line Digital Holography Quantitative Phase Imaging for Tissue-Mimicking Phantom Samples

Planar Scintigraphy Image De-Noising Using Coiflet Wavelet

Intra-individual reproducibility as essential determinant of clinical utility of smartphone-based neurological disability tests

Contact Info

Product

Resources

About