Region-based wavelet coding methods for digital mammography

Penedo, Manuel G.; Pearlman, William A.; Tahoces, Pablo G.; Souto, Miguel Abel; Vidal, José Martı́nez

doi:10.1109/tmi.2003.817812

Cited by 82 publications

(44 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additional compression algorithms should be considered in future efforts, especially those focusing on preserving the high-frequency components of the mammographic image [37]. Furthermore, metrics of different computational principles, such as edge-based-measures, spectral distance-based measures, and metrics simulating human visual system [29] should also be tested.…”

Section: Discussionmentioning

confidence: 99%

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%

Quantitative Visually Lossless Compression Ratio Determination of JPEG2000 in Digitized Mammograms

et al. 2012

View full text Add to dashboard Cite

show abstract

“…IWT maps the image which is decomposition of partition into a partitioned wavelet coefficient plane.Thus ROI is obtain. Further these arbitrary shape region"s representations are encoded using a modified SPIHT scheme.This RB-IWT method performs better than SPIHT-based ROI coding according to the experimental results gven by the author.In paper [16] ROI wavelet-based coding methods are given with application to digital mammography. In those methods the region based discrete wavelet transform (RBDWT) [17] is applied, after performing a segmentation of the important region in an image.Then object-based extension of the SPIHT (OB-SPIHT) [10] coding algorithm and an object-based extension of the set partitioned embedded block (OB-SPECK) [18] coding method is used respectively for both the methods.RBDWT it is possible to performs a wavelet subband decomposition of an arbitrary shape region very efficiently.Both OB-SPIHT and OB-SPECK mehods are embedded in nature,which means the method produces an embedded bit stream that can be truncated at any point at a desired quality of the image.The wavelet coefficients consist of larger information content have a larger magnitude.…”

Section: Review Of Related Researchmentioning

confidence: 99%

Review on Region of Interest Coding Techniques for Medical Image Compression

Jangbari¹,

Patel²

2016

IJCA

View full text Add to dashboard Cite

Telemedicine is a field of medicine characterized by telecommunication for clinical health care and transmission of medical images and videos. For transmission, a huge bandwidth is required over the internet. The size of the images that belongs to a single patient is very large which contains resolution factor and diagnostic images. So there is a need for efficient compression techniques for compressing these medical images.The regions which are considered to be more important than others in medical images is known as a Region of Interest (ROI) e.g. tumor is ROI in brain MRI. In this work, the ROI is detected by the saliency map technique, after that targets or ROIs be coded at available bits while the remainder of the background or non-ROI part is coded using fewer bits.By this method, the target regions within the video frame or image will be well preserved while the number of bits needed to code the video sequence or images is reduced.Thus, the transmission bandwidth and storage requirements are reduced.

show abstract

“…Therefore, in the field of the medical image pre-processing, method of de-noising plays a very important role. It is often done before the image is to be analyzed [2]. De-noising is mainly used to remove noise that is present and retains the significant information, regardless of the frequency contents of the signal [3].…”

Section: Introductionmentioning

confidence: 99%

“…Both pixel size and pixel depth are factors that critically affect the visibility of small-low contrast objects or signals, which often are relevant information for diagnosis [5]. Therefore, digital image recording systems for medical imaging must provide high spatial resolution and high contrast sensitivity [2].…”

Section: Introductionmentioning

confidence: 99%

An Efficient Approach to De-noising Mammogram Images

Rajurkar¹,

Singnapure²

2014

International Journal of Advanced Research in Computer and Comm

View full text Add to dashboard Cite

Abstract:The noisy nature of digital mammograms and low contrast of doubtful areas which make medical images denoising a challenging problem. In the field of image processing, different types of denoising algorithm are used to remove the unnecessary noise such as additive white Gaussian noise, salt and pepper noise, impulsive noise, as well used to smoothen the image. In the existing work, a novel gradient histogram preservation (GHP) algorithm was developed to improve the texture which exhibits the reduced quality in recognition of human image experiments. To remove the noise, Discrete Wavelet Transform (DWT) algorithm is used to eliminate the noisiness present in the medical image to preserve the texture structures. Proposed approach will efficiently calculate peak signal noise ratio (PSNR) parameters and make the enhanced image without noise and obtains the quality of image without any loss of data.

show abstract

Region-based wavelet coding methods for digital mammography

Cited by 82 publications

References 33 publications

Quantitative Visually Lossless Compression Ratio Determination of JPEG2000 in Digitized Mammograms

Quantitative Visually Lossless Compression Ratio Determination of JPEG2000 in Digitized Mammograms

Review on Region of Interest Coding Techniques for Medical Image Compression

An Efficient Approach to De-noising Mammogram Images

Contact Info

Product

Resources

About