Computer-aided detection of clustered microcalcifications in digital breast tomosynthesis: A 3D approach

Abstract

Purpose: To design a computer-aided detection (CADe) system for clustered microcalcifications in reconstructed digital breast tomosynthesis (DBT) volumes and to perform a preliminary evaluation of the CADe system. Methods: IRB approval and informed consent were obtained in this study. A data set of two-view DBT of 72 breasts containing microcalcification clusters was collected from 72 subjects who were scheduled to undergo breast biopsy. Based on tissue sampling results, 17 cases had breast cancer and 55 were benign. A separate data set of two-view DBT of 38 breasts free of clustered microcalcifications from 38 subjects was collected to independently estimate the number of false-positives (FPs) generated by the CADe system. A radiologist experienced in breast imaging marked the biopsied cluster of microcalcifications with a 3D bounding box using all available clinical and imaging information. A CADe system was designed to detect microcalcification clusters in the reconstructed volume. The system consisted of prescreening, clustering, and false-positive reduction stages. In the prescreening stage, the conspicuity of microcalcification-like objects was increased by an enhancement-modulated 3D calcification response function. An iterative thresholding and 3D object growing method was used to detect cluster seed objects, which were used as potential centers of microcalcification clusters. In the cluster detection stage, microcalcification candidates were identified using a second iterative thresholding procedure, which was applied to the signal-to-noise ratio (SNR) enhanced image voxels with a positive calcification response. Starting with each cluster seed object as the initial cluster center, a dynamic clustering algorithm formed a cluster candidate by including microcalcification candidates within a 3D neighborhood of the cluster seed object that satisfied the clustering criteria. The number, size, and SNR of the microcalcifications in a cluster candidate and the cluster shape were used to reduce the number of FPs. Results: The prescreening stage detected a cluster seed object in 94% of the biopsied microcalcification clusters at a threshold of 100 cluster seed objects per DBT volume. After clustering, the detection sensitivity was 90% at 15 marks per DBT volume. After FP reduction, at 85% sensitivity, the average number of FPs estimated using the data set containing microcalcification clusters was 3.8 per DBT volume, and that estimated using the data set free of microcalcification clusters was 3.4. The detection performance for malignant microcalcification clusters was superior to that for benign clusters. Conclusions: Our study indicates the feasibility of the 3D approach to the detection of clustered microcalcifications in DBT and that the newly designed enhancement-modulated 3D calcification response function is promising for prescreening. Further work is needed to assess the generalizability of our approach and to improve its performance.

3D Computer-Aided Detection for Digital Breast Tomosynthesis: Comparison with 2D Computer-Aided Detection for Digital Mammography in the Detection of Calcifications

“…to 90% with false-positive rates of 0.65 to 1.55 per DBT volume (6,9,10). In the present study, we observed same case-based sensitivities [100% (31/31)] for malignant calcifications with a 0.52 false-positive mark rate per DBT volume, which is better than the results of previous studies.…”

Improvement of subtle microcalcifications detection in DBT slices

“…To overcome aforementioned problems, preprocessing is performed to enhance microcalcifications. In our work, SNR enhancement [3] and 3D Laplacian of Gaussian filtering was incorporated. 3D Laplacian of Gaussian filtering response…”

“…Sahiner et al [3] proposed a system for detecting clustered microcalcifications from 3D volumes in a 3D approach. In another study, Bernard et al [4] proposed a method for microcalcification detection from filtered back-projection reconstructed slices with a Mexican hat wavelet based enhancement.…”

“…In another study, Bernard et al [4] proposed a method for microcalcification detection from filtered back-projection reconstructed slices with a Mexican hat wavelet based enhancement. Though, many research efforts have been made for efficiently detecting microcalcifications in DBT, false-positive (FP) rate is still high to be useful in clinical practice [3].…”

Spectral correlation analysis for microcalcification detection in digital mammogram images

“…Salama et al [11] used iterative thresholding and adaptive region growing to detect microcalcification clusters while Sahiner et al [12] followed a 3D approach to achieve the same purpose through iterative thresholding and a 3D object growing method.…”