Texture analysis of tissue surrounding microcalcifications on mammograms for breast cancer diagnosis.

Diagnosis of microcalcifications (MCs) is challenged by the presence of dense breast parenchyma, resulting in low specificity values and thus in unnecessary biopsies. The current study investigates whether texture properties of the tissue surrounding MCs can contribute to breast cancer diagnosis. A case sample of 100 biopsy-proved MC clusters (46 benign, 54 malignant) from 85 dense mammographic images, included in the Digital Database for Screening Mammography, was analysed. Regions of interest (ROIs) containing the MCs were pre-processed using a wavelet-based contrast enhancement method, followed by local thresholding to segment MCs; the segmented MCs were excluded from original image ROIs, and the remaining area (surrounding tissue) was subjected to texture analysis. Four categories of textural features (first order statistics, co-occurrence matrices features, run length matrices features and Laws' texture energy measures) were extracted from the surrounding tissue. The ability of each feature category in discriminating malignant from benign tissue was investigated using a k-nearest neighbour (kNN) classifier. An additional classification scheme was performed by combining classification outputs of three textural feature categories (the most discriminating ones) with a majority voting rule. Receiver operating characteristic (ROC) analysis was conducted for classifier performance evaluation of the individual textural feature categories and of the combined classification scheme. The best performance was achieved by the combined classification scheme yielding an area under the ROC curve (A(z)) of 0.96 (sensitivity 94.4%, specificity 80.0%). Texture analysis of tissue surrounding MCs shows promising results in computer-aided diagnosis of breast cancer and may contribute to the reduction of unnecessary biopsies.

Evaluating the effect of a wavelet enhancement method in characterization of simulated lesions embedded in dense breast parenchyma.

Presence of dense parenchyma in mammographic images masks lesions resulting in either missed detections or mischaracterizations, thus decreasing mammographic sensitivity and specificity. The aim of this study is evaluating the effect of a wavelet enhancement method on dense parenchyma for a lesion contour characterization task, using simulated lesions. The method is recently introduced, based on a two-stage process, locally adaptive denoising by soft-thresholding and enhancement by linear stretching. Sixty simulated low-contrast lesions of known image characteristics were generated and embedded in dense breast areas of normal mammographic images selected from the DDSM database. Evaluation was carried out by an observer performance comparative study between the processed and initial images. The task for four radiologists was to classify each simulated lesion with respect to contour sharpness/unsharpness. ROC analysis was performed. Combining radiologists' responses, values of the area under ROC curve (Az) were 0.93 (95% CI 0.89, 0.96) and 0.81 (CI 0.75, 0.86) for processed and initial images, respectively. This difference in Az values was statistically significant (Student's t-test, P<0.05), indicating the effectiveness of the enhancement method. The specific wavelet enhancement method should be tested for lesion contour characterization tasks in softcopy-based mammographic display environment using naturally occurring pathological lesions and normal cases.

Visually lossless threshold determination for microcalcification detection in wavelet compressed mammograms.

The aim of this study was to determine the visually lossless threshold of a wavelet-based compression algorithm in case of microcalcification cluster detection in mammography. The threshold was determined by means of observer performance using a set of digitized mammograms. In addition, the transfer characteristics of the compression algorithm were assessed by means of image-quality parameters using computer-generated test images. The observer performance study was based on rating performed by four independent radiologists, who reviewed 68 mammograms, from the Digital Database for Screening Mammography (DDSM), at six different compression ratios. Receiver operating characteristics (ROC) analysis was performed on observers' responses and the area under ROC curve (A(z)) was calculated at each compression ratio for each observer. The parameters used for assessment of transfer characteristics of the compression algorithm were input/output response, noise, high-contrast response, and low-contrast-detail response. The computer-generated test image, used for this assessment, mimicked mammographic image characteristics (pixel size, pixel depth, and noise) as well as microcalcification characteristics (size and contrast). The ROC analysis for microcalcification cluster detection indicated a threshold at compression ratio 40:1, as Student's t-test shows statistically significant differences in A(z) values (p<0.05) for compression ratios 70:1 and 100:1. Observers' grading of mammogram quality lowers this threshold at 25:1. Low-contrast-detail detectability in the transfer characteristics study indicate a threshold of 35:1, whereas non-perceptibility of image-quality-parameters degradation lowers this threshold to 30:1. The ROC and transfer characteristics analysis provided comparable thresholds, indicating the potential use of the latter in limiting the target range of compression ratios for subsequent observer studies.

Simulating the mammographic appearance of circumscribed lesions.

Optimization performance of digital image post-processing techniques in mammography requires controlled conditions of data sets permitting quantitative representation of image characteristics of pathological findings. Digital test objects, although objective and quantitative, do not mimic mammographic appearance and clinical data sets do not provide adequate sets of values of the various pathological finding characteristics. This can be overcome by digital simulation of pathological findings and superimposition on mammographic images. A simple method for simulation of mammographic appearance of radiopaque and/or radiolucent circumscribed lesions is presented. Circumscribed lesions are simulated using grey-level transformation functions which shift and compress the range of the initial pixel grey-level values in a region of interest (ROI) of a digitized mammographic image, according to grey-level analysis in 200 ROIs of real circumscribed lesions from digitized mammographic images. Simulation addresses lesion image characteristics, such as elliptical shape, orientation, halo sign for radiopaque lesions and capsule for radiolucent lesions, and is implemented in a user-driven PC-based interactive application. The appearance of the lesions is evaluated by six radiologists on a sample of 60 real and 60 simulated radiopaque lesions with the use of receiver operating characteristic (ROC) analysis. The area under the ROC curve, pooling the responses of the observers, was 0.55+/-0.03 indicating no statistically significant difference between real and simulated lesions (p>0.05). The method adequately simulates the mammographic appearance of circumscribed lesions and could be used to generate circumscribed lesion data sets for performance evaluation of image processing techniques, as well as education purposes.