Evaluation of clinical image processing algorithms used in digital mammography.

Screening is the only proven approach to reduce the mortality of breast cancer, but significant numbers of breast cancers remain undetected even when all quality assurance guidelines are implemented. With the increasing adoption of digital mammography systems, image processing may be a key factor in the imaging chain. Although to our knowledge statistically significant effects of manufacturer-recommended image processings have not been previously demonstrated, the subjective experience of our radiologists, that the apparent image quality can vary considerably between different algorithms, motivated this study. This article addresses the impact of five such algorithms on the detection of clusters of microcalcifications. A database of unprocessed (raw) images of 200 normal digital mammograms, acquired with the Siemens Novation DR, was collected retrospectively. Realistic simulated microcalcification clusters were inserted in half of the unprocessed images. All unprocessed images were subsequently processed with five manufacturer-recommended image processing algorithms (Agfa Musica 1, IMS Raffaello Mammo 1.2, Sectra Mamea AB Sigmoid, Siemens OPVIEW v2, and Siemens OPVIEW v1). Four breast imaging radiologists were asked to locate and score the clusters in each image on a five point rating scale. The free-response data were analyzed by the jackknife free-response receiver operating characteristic (JAFROC) method and, for comparison, also with the receiver operating characteristic (ROC) method. JAFROC analysis revealed highly significant differences between the image processings (F = 8.51, p < 0.0001), suggesting that image processing strongly impacts the detectability of clusters. Siemens OPVIEW2 and Siemens OPVIEW1 yielded the highest and lowest performances, respectively. ROC analysis of the data also revealed significant differences between the processing but at lower significance (F = 3.47, p = 0.0305) than JAFROC. Both statistical analysis methods revealed that the same six pairs of modalities were significantly different, but the JAFROC confidence intervals were about 32% smaller than ROC confidence intervals. This study shows that image processing has a significant impact on the detection of microcalcifications in digital mammograms. Objective measurements, such as described here, should be used by the manufacturers to select the optimal image processing algorithm.

[1]  R. Swensson.  Unified measurement of observer performance in detecting and localizing target objects on images. , 1996, Medical physics.

[2]  Stephen L Hillis,et al.  Recent developments in the Dorfman-Berbaum-Metz procedure for multireader ROC study analysis. , 2008, Academic radiology.

[3]  Donglin Zeng,et al.  The effects of gray scale image processing on digital mammography interpretation performance. , 2005, Academic radiology.

[4]  R. Bird,et al.  Analysis of cancers missed at screening mammography. , 1992, Radiology.

[5]  John F. Hamilton,et al.  A Free Response Approach To The Measurement And Characterization Of Radiographic Observer Performance , 1977, Other Conferences.

[6]  Hilde Bosmans,et al.  An improved method for simulating microcalcifications in digital mammograms. , 2008, Medical physics.

[7]  C. D'Orsi,et al.  Diagnostic Performance of Digital Versus Film Mammography for Breast-Cancer Screening , 2005, The New England journal of medicine.

[8]  Ehsan Samei,et al.  Simulation of mammographic lesions. , 2006, Academic radiology.

[9]  D. Blanc,et al.  European guidelines on quality criteria for diagnostic radiographic images , 1998 .

[10]  M J Schell,et al.  Reassessment of breast cancers missed during routine screening mammography: a community-based study. , 2001, AJR. American journal of roentgenology.

[11]  L. Bassett,et al.  Mammography and breast cancer screening. , 1990, The Surgical clinics of North America.

[12]  Stephen L Hillis,et al.  Power estimation for the Dorfman-Berbaum-Metz method. , 2004, Academic radiology.

[13]  Andrew D. A. Maidment,et al.  Quality control for digital mammography in the ACRIN DMIST trial: part I. , 2006, Medical physics.

[14]  Andrew D. A. Maidment,et al.  Image processing algorithms for digital mammography: a pictorial essay. , 2000, Radiographics : a review publication of the Radiological Society of North America, Inc.

[15]  Arthur E. Burgess,et al.  Producing lesions for hybrid mammograms: extracted tumors and simulated microcalcifications , 1999, Medical Imaging.

[16]  N. Obuchowski,et al.  Comparing the performance of mammographic enhancement algorithms: a preference study. , 2000, AJR. American journal of roentgenology.

[17]  Bradley M. Hemminger,et al.  The effect of intensity windowing on the detection of simulated masses embedded in dense portions of digitized mammograms in a laboratory setting , 2009, Journal of Digital Imaging.

[18]  K. Muller,et al.  Improving the detection of simulated masses in mammograms through two different image-processing techniques. , 2001, Academic radiology.

[19]  K. Berbaum,et al.  Receiver operating characteristic rating analysis. Generalization to the population of readers and patients with the jackknife method. , 1992, Investigative radiology.

[20]  N. Obuchowski,et al.  Hypothesis testing of diagnostic accuracy for multiple readers and multiple tests: An anova approach with dependent observations , 1995 .

[21]  N A Obuchowski,et al.  Multireader receiver operating characteristic studies: a comparison of study designs. , 1995, Academic radiology.

[22]  Robert M. Nishikawa,et al.  Radiologists’ Preferences for Digital Mammographic Display , 2000 .

[23]  Dev P Chakraborty,et al.  Validation and statistical power comparison of methods for analyzing free-response observer performance studies. , 2008, Academic radiology.

[24]  Dev P Chakraborty,et al.  Observer studies involving detection and localization: modeling, analysis, and validation. , 2004, Medical physics.

[25]  Constantine A Gatsonis,et al.  American College of Radiology Imaging Network digital mammographic imaging screening trial: objectives and methodology. , 2005, Radiology.

[26]  Andrew D. A. Maidment,et al.  Diagnostic accuracy of digital mammography in patients with dense breasts who underwent problem-solving mammography: effects of image processing and lesion type. , 2003, Radiology.

[27]  D. Ikeda,et al.  Mammographic characteristics of 115 missed cancers later detected with screening mammography and the potential utility of computer-aided detection. , 2001, Radiology.

[28]  N Karssemeijer,et al.  Automated detection of breast carcinomas not detected in a screening program. , 1998, Radiology.

[29]  Nancy A Obuchowski,et al.  A comparison of the Dorfman–Berbaum–Metz and Obuchowski–Rockette methods for receiver operating characteristic (ROC) data , 2005, Statistics in medicine.

[30]  Bradley M. Hemminger,et al.  Does intensity windowing improve the detection of simulated calcifications in dense mammograms? , 2009, Journal of Digital Imaging.

[31]  L. Solin,et al.  Twenty-year incidence and patterns of contralateral breast cancer after breast conservation treatment with radiation. , 2006, International journal of radiation oncology, biology, physics.

[32]  Ann-Katherine Carton,et al.  Quantification of Al-equivalent thickness of just visible microcalcifications in full field digital mammograms. , 2004, Medical physics.