Development of an automated detection algorithm for patient motion blur in digital mammograms

Hill, Melissa L.; Whelehan, Patsy; Vinnicombe, Sarah; Tromans, Christopher; Evans, Andrew; Warwick, Violet; Brady, J. Michael; Highnam, Ralph

doi:10.1117/12.2318225

Cited by 1 publication

(3 citation statements)

References 10 publications

(13 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The algorithm was based on detecting image unsharpness by interpreting the normalized image Wiener Spectrum. 8 Despite the method's potential, there were few limitations to the study. A small number of images were used that had a limited range of breast characteristics, and there was no control over the blur magnitude in the mammograms, reducing the variety of blur presentations in the sample that the algorithm was tested on.…”

Section: Introductionmentioning

confidence: 99%

“…Most recently, Hill et al developed an automated method to detect motion blur in mammograms with the intention of facilitating immediate re‐take of blurred images during a mammography screening session. The algorithm was based on detecting image unsharpness by interpreting the normalized image Wiener Spectrum . Despite the method's potential, there were few limitations to the study.…”

Section: Introductionmentioning

confidence: 99%

“…Often blur fails to be detected at the time of imaging, and it might not be detected until it reaches the reporting room for diagnostic examination . While there have been studies investigating radiologists' ability to detect blur visually in mammograms, as of this date there is no work done on detecting blur automatically in mammograms except the work presented by Hill et al In addition, there has been no effort to use machine‐learning algorithms to automatically detect blurry mammograms. Instead of relying on the radiologists' subjective assessments of the presence or absence of blur in mammograms, we propose the use of quantitative mathematical features that quantify blur objectively in digital mammograms.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automatic detection of simulated motion blur in mammograms

Kamona

Loew

2020

Medical Physics

View full text Add to dashboard Cite

Purpose: To use machine-learning algorithms and blur measure (BM) operators to automatically detect motion blur in mammograms. Motion blur has been reported to reduce lesion detection performance and mask small abnormalities, resulting in failure to detect them until they reach more advanced stages. Automatic detection of blur could support the clinical decision-making process during the mammography exam by allowing for an immediate retake, thereby preventing unnecessary expense, time, and patient anxiety. Methods: Blur was simulated mathematically to mimic the real blur seen in clinical practice. The blur point-spread-function (PSF) mask is generated by distributing pixel intensity of an image pixel moving under random motion within the range of blur effect (the maximum amount of tissue motion allowed). The random motion trajectory vector is generated on a super-sampled image frame to accommodate smaller substeps; the vector was then sampled on a regular pixel grid using subpixel linear interpolation to generate the blur PSF mask. This randomly generated motion trajectory is constrained by several factors: the effects of variations in tissue elasticity, imaging exposure time, and size of blur effect (motion boundary in millimeters) were examined. The blur mask is convolved with a mammogram to create blur. Five motion blur magnitudes (0.1, 0.25, 0.5, 1.0, and 1.5 mm) were simulated on 244 and 434 mammograms from the INbreast and DDSM databases, respectively. Blur was quantified using nine BM operators for each mammogram and at each blur level. The mammograms were assigned to training (70%) and testing (30%) datasets to train three machine-learning classifiers: Ensemble Bagged Trees, fine Gaussian SVM, and weighted KNN, to distinguish five levels of blurred from unblurred mammograms, using six-way classification. Results: For the INbreast mammograms, the average classification accuracies were 87.7%, 85.7%, and 85.7% for Ensemble Bagged Trees, fine Gaussian SVM, and weighted KNN, respectively, and the average classification accuracies for DDSM were 93.5%, 93.6%, and 92.7% for Ensemble Bagged Trees, fine Gaussian SVM, and weighted KNN, respectively. Conclusions: Preliminary results show the potential to detect simulated blur automatically using those methods. Although limited work has been done to quantify the effects of motion blur on radiologists' performance, there is evidence that motion blur might not be detected visually by a human observer and could negatively affect radiologists' lesion detection performance. As of this date, no other study has investigated the ability of machine-learning classifiers and BM operators to detect motion blur in mammograms.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation