Free-Response Receiver Operating Characteristic Evaluation of Lossy JPEG2000 and Object-based Set Partitioning in Hierarchical Trees Compression of Digitized Mammograms

Penedo, Manuel G.; Souto, Miguel Abel; Tahoces, Pablo G.; Carreira, José M.; Villalón, Justo; Porto, Gerardo; Seoane, C.; Vidal, José Martı́nez; Berbaum, Kevin S.; Chakraborty, Dev P.; Fajardo, Laurie L.

doi:10.1148/radiol.2372040996

Cited by 53 publications

(35 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The free-response receiver operating characteristic (FROC) paradigm (1-6) is being increasingly used in the assessment of medical imaging systems (7,8), particularly in the evaluation of computer aided detection (CAD) (9)(10)(11) algorithms. The paradigm differs from the traditional receiver operating characteristic (ROC) method (12)(13)(14) in that it seeks location information from the observer, rewarding the observer when the reported disease is marked in the appropriate location, and penalizing the observer when it is not.…”

Section: Introductionmentioning

confidence: 99%

Spatial Localization Accuracy of Radiologists in Free-Response Studies: Inferring Perceptual FROC Curves from Mark-Rating Data

2007

View full text Add to dashboard Cite

Free-response data consists of a set of mark-ratings pairs. Prior to analysis the data is classified or "scored" into lesion and non-lesion localizations. The scoring is done by choosing an acceptanceradius and classifying marks within the acceptance-radius of lesion centers as lesion localizations, and all other marks are classified as non-lesion localizations. The scored data is plotted as a freeresponse receiver operating characteristic (FROC) curve, essentially a plot of appropriately normalized numbers of lesion localizations vs. non-lesion localizations. Scored FROC curves are frequently used to compare imaging systems and computer aided detection (CAD) algorithms. However, the choice of acceptance-radius is arbitrary. This makes it difficult to compare curves from different studies and to estimate true performance. To resolve this issue the concept of two types of marks is introduced: perceptual hits and perceptual misses. A perceptual hit is a mark made in response to the observer seeing the lesion. A perceptual miss is a mark made in response to the observer seeing a (lesion-like) non-lesion. A method of estimating the most probable numbers of perceptual hits and misses is described. This allows one to plot a perceptual FROC operating point and by extension a perceptual FROC curve. Unlike a scored FROC operating point, a perceptual point is independent of the choice of acceptance-radius. The method does not allow one to identify individual marks as perceptual hits or misses -only the most probable numbers. It is based on a 3-parameter statistical model of the spatial distributions of perceptual hits and misses relative to lesion centers. The method has been applied to an observer dataset in which mammographers, and residents with different levels of experience were asked to locate lesions in mammograms. The perceptual operating points suggest superior performance for the mammographers and equivalent performance for residents in the first and second mammography rotations. These results and the model validation are preliminary as they are based on a small dataset. The significance of this study is showing that it is possible to probabilistically determine if a mark resulted from seeing a lesion or a nonlesion. Using the method developed in this study one could perform acceptance-radius independent estimation of observer performance.

show abstract

Section: Introductionmentioning

confidence: 99%

Spatial Localization Accuracy of Radiologists in Free-Response Studies: Inferring Perceptual FROC Curves from Mark-Rating Data

2007

View full text Add to dashboard Cite

show abstract

“…Previously reported literature on image quality evaluation of compressed mammograms has focused on the determination of diagnostically lossless CR thresholds [9][10][11][12][13][14] and less on the visually lossless approach [8,15,16], with both approaches employing observer performance analysis methods. 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].…”

Section: Discussionmentioning

confidence: 99%

“…In case of mammographic image compression, most studies have focused on the determination of diagnostically lossless CR thresholds [9][10][11][12][13][14], employing mainly observer performance analyses. These studies have aimed at evaluating the quality of digitized and digital compressed mammograms with respect to lesion detection [9][10][11][12][13] or a lesion diagnosis [14] task.…”

Section: Introductionmentioning

confidence: 99%

“…These studies have aimed at evaluating the quality of digitized and digital compressed mammograms with respect to lesion detection [9][10][11][12][13] or a lesion diagnosis [14] task. Specifically, Good et al [9] evaluated observers' ability in detecting breast masses and MCs on lossy Joint Photographic Experts Group (JPEG) compressed mammograms.…”

Section: Introductionmentioning

confidence: 99%

“…The detection of simulated masses was not affected by compression, while the detection of MCs was significantly reduced for CR greater than 15:1. Penedo et al [12] assessed the effect of two irreversible wavelet-based compression algorithms (a standard JPEG2000 and an object-based set partitioning in hierarchical trees) on the detection of MCs and masses on digitized mammograms. Results suggested that lossy compression of digitized mammograms at 80:1 with both methods considered can be performed without decreasing the rate of detection for either type of lesions.…”

Section: Introductionmentioning

confidence: 99%

See 2 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

Relevance of Biomedical Data Compression

Tanguy¹,

Jallet²,

Bozec³

et al. 2008

Compression of Biomedical Images and Signals

View full text Add to dashboard Cite

Free-Response Receiver Operating Characteristic Evaluation of Lossy JPEG2000 and Object-based Set Partitioning in Hierarchical Trees Compression of Digitized Mammograms

Abstract: To within the accuracy of these measurements, lossy compression of digital mammographic data at 80:1 with JPEG2000 or the object-based SPIHT algorithm can be performed without decreasing the rate of detection of clusters of microcalcifications and masses.

Cited by 53 publications

References 43 publications

Spatial Localization Accuracy of Radiologists in Free-Response Studies: Inferring Perceptual FROC Curves from Mark-Rating Data

Spatial Localization Accuracy of Radiologists in Free-Response Studies: Inferring Perceptual FROC Curves from Mark-Rating Data

Quantitative Visually Lossless Compression Ratio Determination of JPEG2000 in Digitized Mammograms

Relevance of Biomedical Data Compression

Contact Info

Product

Resources

About