Progressive lossy to lossless compression of ROI in mammograms: Effects on microcalcification detection

Zyout, Imad; Abdel‐Qader, Ikhlas; Al-Otum, Hazem Munawer

doi:10.3233/ica-2008-15304

Cited by 8 publications

(11 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The quantitative image quality approach of compressed mammograms has been considered as an additional option to observer performance analysis [15,18], as well as in the framework of evaluating image compression schemes utilizing mammographic images [19][20][21], phantom images [34], and computer-generated test objects images [10]. However, the quantitative image quality approach has not been exploited towards the determination of visually or diagnostically lossless CR thresholds in mammography.…”

Section: Discussionmentioning

confidence: 99%

“…MSE and PSNR metrics, accounting for two equivalent measures, are the most commonly adopted in quantitative mammographic image quality evaluation studies [15,19,20], while their incorporation into medical image compression evaluation has been recently highlighted [7]. The use of the recently proposed SSIM metric [32] as a new measure that quantifies structural changes caused by various types of distortions is also suggested in image compression evaluation schemes further being more consistent with the performance of the human visual system [7].…”

Section: Discussionmentioning

confidence: 99%

“…In case of mammographic image compression, metrics such as: SNR, PSNR, MAE, and MSE have been previously exploited [15,[18][19][20], while a linear combination of metrics has been proposed and correlated to diagnostically related image quality [21].…”

Section: Quantitative Image Quality Evaluationmentioning

confidence: 99%

“…Quantitative image quality approaches of compressed mammograms have been considered in the framework of evaluating image compression schemes [18][19][20][21] but have not been exploited toward the determination of visually or diagnostically lossless CR thresholds. Sung et al [15] considered a quantitative approach toward image quality evaluation by means of the peak signal-to-noise ratio (PSNR) metric in addition to observer studies performed for lossy CR threshold determination.…”

Section: Introductionmentioning

confidence: 99%

“…Results demonstrated that digital mammograms compressed in a lossy fashion to 0.015 bits per pixel (bpp), about 80:1 CR, using an embedded wavelet coding scheme result in no significant differences from the analog or digital originals. Zyout et al [19] employed mean square error (MSE) and PSNR metrics for evaluating a wavelet-based progressive lossy to lossless image compression scheme applied on regions of interest (ROIs) of digitized mammograms containing MCs. Kim et al [20] exploited objective metrics such as SNR, PSNR, root mean square error, and mean average error (MAE) for evaluating image quality of digital mammograms compressed by JPEG2000 and JPEG, in case of direct and indirect detectors in FFDM.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Quantitative Visually Lossless Compression Ratio Determination of JPEG2000 in Digitized Mammograms

et al. 2012

View full text Add to dashboard Cite

The current study presents a quantitative approach towards visually lossless compression ratio (CR) threshold determination of JPEG2000 in digitized mammograms. This is achieved by identifying quantitative image quality metrics that reflect radiologists' visual perception in distinguishing between original and wavelet-compressed mammographic regions of interest containing microcalcification clusters (MCs) and normal parenchyma, originating from 68 images from the Digital Database for Screening Mammography. Specifically, image quality of waveletcompressed mammograms (CRs, 10:1, 25:1, 40:1, 70:1, 100:1) is evaluated quantitatively by means of eight image quality metrics of different computational principles and qualitatively by three radiologists employing a five-point rating scale. The accuracy of the objective metrics is investigated in terms of (1) their correlation (r) with qualitative assessment and (2) ROC analysis (A z index), employing pooled radiologists' rating scores as ground truth. The quantitative metrics mean square error, mean absolute error, peak signal-to-noise ratio, and structural similarity demonstrated strong correlation with pooled radiologists' ratings (r, 0.825, 0.823, −0.825, and −0.826, respectively) and the highest area under ROC curve (A z , 0.922, 0.920, 0.922, and 0.922, respectively). For each quantitative metric, the highest accuracy values of corresponding ROC curves were used to define metric cut-off values. The metrics cut-off values were subsequently used to suggest a visually lossless CR threshold, estimated to be between 25:1 and 40:1 for the dataset analyzed. Results indicate the potential of the quantitative metrics approach in predicting visually lossless CRs in case of MCs in mammography.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Quantitative Image Quality Evaluationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Quantitative Visually Lossless Compression Ratio Determination of JPEG2000 in Digitized Mammograms

et al. 2012

View full text Add to dashboard Cite

show abstract

Efficient ROI-based compression of mammography images

Abdellatif

Taha

El-Shanawany

et al. 2022

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

A generalization of quad-trees applied to lossy image coding

Kutil

2012

2012 Picture Coding Symposium

View full text Add to dashboard Cite

Quad-trees are restricted to combined horizontal and vertical decomposition of tiles. If this restriction is dropped, anisotropic rectangular tiles result which can be arranged in a previously developed graph structure called "bush". Although this graph requires more bits to be encoded, the reduction of the number of tiles by a factor of about two more than compensates this, especially when there is a big payload per tile such as polynomial or DCT approximations of image content. Therefore, together with an existing efficient coding scheme for this graph, a lossy coding scheme based on tile-wise rate-distortion optimized quantization of low-frequency DCT coefficients is developed. It is able to compete with JPEG2000, especially for images with smooth regions.

show abstract

Progressive lossy to lossless compression of ROI in mammograms: Effects on microcalcification detection

Cited by 8 publications

References 22 publications

Quantitative Visually Lossless Compression Ratio Determination of JPEG2000 in Digitized Mammograms

Quantitative Visually Lossless Compression Ratio Determination of JPEG2000 in Digitized Mammograms

Efficient ROI-based compression of mammography images

A generalization of quad-trees applied to lossy image coding

Contact Info

Product

Resources

About