Nevine H. Eltonsy

A Concentric Morphology Model for the Detection of Masses in Mammography

We propose a technique for the automated detection of malignant masses in screening mammography. The technique is based on the presence of concentric layers surrounding a focal area with suspicious morphological characteristics and low relative incidence in the breast region. Mammographic locations with high concentration of concentric layers with progressively lower average intensity are considered suspicious deviations from normal parenchyma. The multiple concentric layers (MCLs) technique was trained and tested using the craniocaudal views of 270 mammographic cases with biopsy proven malignant masses from the digital database of screening mammography. One-half of the available cases were used for optimizing the parameters of the detection algorithm. The remaining cases were used for testing. During testing, malignant masses were detected with 92%, 88%, and 81% sensitivity at 5.4, 2.4, and 0.6 false positive marks per image. Testing on 82 normal screening mammograms showed a false positive rate of 5.0, 1.7, and 0.2 marks per image at the previously reported operating points. Furthermore, additional evaluation on 135 benign cases produced a significantly lower detection rate for benign masses (61.6%, 58.3%, and 43.7% at 5.1, 2.8, and 1.2 false positives per image, respectively). Overall, MCL is a promising computer-assisted detection strategy for screening mammograms to identify malignant masses while maintaining the detection rate of benign masses considerably lower.

Feature And Knowledge Based Analysis For Reduction of False Positives in the Computerized Detection of Masses in Screening Mammography

Previously we presented a morphologic concentric layered (MCL) algorithm for the detection of masses in screening mammograms. The algorithm achieved high sensitivity (92%) but it also generated 3.26 false positives (FPs) per image. In the present study we propose a false positive reduction strategy based on using an artificial neural network that merges feature and knowledge-based analysis of suspicious mammographic locations. The ANN integrates two types of information regarding the suspicious candidates: (i) directional and fractal neighborhood analysis features, and (ii) knowledge-based analysis using an information-theoretic similarity metric. The study hypothesis is that the synergistic application of feature and knowledge-based analysis will be an effective strategy to reduce false positives while still maintaining sufficiently the detection rate for true masses. The study was performed using mammograms from the Digital Database of Screening Mammography. Using the fusion ANN decision strategy 56% of the FPs were reduced while maintaining 95% of the true masses

Bilateral Breast Volume Asymmetry in Screening Mammograms as a Potential Marker of Breast Cancer: Preliminary Experience

The biological concept of bilateral symmetry as a marker of developmental stability and good health is well established. Although most individuals deviate slightly from perfect symmetry, humans are essentially considered bilaterally symmetrical. Studies have shown that if an individual is exposed to genetic mutations or environmental stresses, the homeostatic mechanisms that maintain symmetry of paired structures (such as breasts) tend to break down. Consequently, increased fluctuating asymmetry of paired structures could be an indicator of poor health. This preliminary study tested if bilateral morphological breast asymmetry in screening mammograms correlates with the presence of breast cancer. Following the biological definition of breast asymmetry in terms of volume, we applied automated computer algorithms for screening mammograms that segment the breast region and then measure each segmented breasts volume. These parameters were measured separately for each breast in each mammographic view (CC and MLO). Then, the normalized absolute differences of these parameters were investigated as measurements of fluctuating asymmetry (FA). Based on 268 cancer cases and 82 normal cases from the DDSM database, we observed that cancer patients demonstrate statistically significantly higher fluctuating asymmetry in their screening mammograms than patients with normal screening studies. Using an artificial neural network to combine FA measurements from both views along with the patients age and breast parenchymal density resulted in an ROC area of 0.80plusmn0.03. These results suggest that bilateral breast volume asymmetry estimated in screening mammograms should be studied as a risk factor for breast cancer.

Breast segmentation in screening mammograms using multiscale analysis and self-organizing maps

Previously we presented an unsupervised self-organizing map (SOM) for segmentation of the breast region in screening mammograms. This study improves upon our earlier technique by (1) enhancing the detection of the breast region near the skin line, as well as (2) reducing the computational complexity. Contrary to the initial technique, the improved one exploits global image properties extracted at different scales. These properties were used to both generate the SOM training samples and obtain a preliminary segmentation. Subsequently, a multi-step strategy was implemented to automatically outline a wide band around the skin line for further analysis. This additional step reduces the computational complexity by focusing the analysis on the set of pixels that creates clinically the highest ambiguity. Specifically, the same (already trained) SOM was applied to classify the ambiguous pixels around the skin line. The study was performed on 400 screening mammograms from the digital database for screening mammography (DDSM). Visual examination of the segmentation results confirmed an improvement in the detection of the low-contrast region near the skin line. The performance was consistent regardless of mammographic view and/or breast density. Furthermore, the computational cost of processing can be reduced by up to 80% of the original value.

Morphological concentric layer analysis for automated detection of suspicious masses in screening mammograms

Computer assisted detection systems (CAD) in mammography incorporate two critical stages: (i) prescreening to localize suspicious regions and (ii) detailed analysis of the regions for false positive reduction. In this work, we present a new technique for automatic detection of suspicious masses for prescreening mammograms. The hypothesis of the proposed technique is that malignant masses manifestate as superimposed concentric layers. Morphological characterization of these layers can form the foundation of an automated scheme for detection of suspicious masses. The study was based on fifty nine screening mammograms from the digital database of screening mammography (DDSM). Overall, the proposed scheme performs at 85.7% sensitivity with an average of 0.53 false positives per image. The scheme targets malignant masses and, thus it can provide a second opinion to radiologists without sending benign masses to unnecessary biopsy.

DNA: directional neighborhood analysis for detection of breast masses in screening mammograms

We introduce a computer-assisted detection (CAD) system for the automated detection of breast masses in screening mammograms. The system targets the directional behavior of the neighborhood pixels surrounding a reference image pixel. The underlying hypothesis is that in the presence of a mass the directional properties of the breast tissue surrounding the mass should be altered. The hypothesis was tested using a database of 1,337 mammographic regions of interest (ROIs) extracted from DDSM mammograms. There were 681 ROIs containing a biopsy-proven mass centered in the ROI (340 malignant, 341 benign) and 656 ROIs depicting normal breast parenchyma. Initially, eight main directional propagations were identified and modeled given the center of the ROI as the reference pixel. Subsequently, eight novel morphological features were extracted for each direction. The features were designed to characterize the disturbance occurring in normal breast parenchyma due to the presence of a mass. Finally, the extracted features were merged using a back propagation neural network (BPANN). The network served as a non linear classifier trained to determine the presence of a mass centered at the reference image pixel. The BPANN was trained and tested using a leave-one-out sampling scheme. Its performance was evaluated with Receiver Operating Characteristics (ROC) analysis. Our CAD system showed an ROC area index of Az=0.88±0.01 for discriminating mass vs. normal ROIs. Detection performance was robust for both malignant (Az=0.88±0.01) and benign masses (Az=0.87±0.01). Thus, the proposed directional neighborhood analysis (DNA) can be applied effectively to identify suspicious masses in screening mammograms.

Significance of MPEG-7 Textural Features for Improved Mass Detection in Mammography

The purpose of the study is to investigate the significance of MPEG-7 textural features for improving the detection of masses in screening mammograms. The detection scheme was originally based on morphological directional neighborhood features extracted from mammographic regions of interest (ROIs). Receiver operating characteristics (ROC) was performed to evaluate the performance of each set of features independently and merged into a back-propagation artificial neural network (BPANN) using the leave-one-out sampling scheme (LOOSS). The study was based on a database of 668 mammographic ROIs (340 depicting cancer regions and 328 depicting normal parenchyma). Overall, the ROC area index of the BPANN using the directional morphological features was Az=0.85plusmn0.01. The MPEG-7 edge histogram descriptor-based BPNN showed an ROC area index of Az=0.71plusmn0.01 while homogeneous textural descriptors using 30 and 120 channels helped the BPNN achieve similar ROC area indexes of Az=0.882plusmn0.02 and Az=0.877plusmn0.01 respectively. After merging the MPEG-7 homogeneous textural features with the directional neighborhood features the performance of the BPANN increased providing an ROC area index of Az=0.91plusmn0.01. MPEG-7 homogeneous textural descriptor significantly improved the morphology-based detection scheme

Quality evaluation of fast morphing interpolation model for 3D volume reconstruction

The purpose of this study is to evaluate a 3D volume reconstruction model for volume rendering. The model is conducted using brain MRI data of Visible Human Project. Particularly MRI T1 data were used. The quality of the developed model is compared with linear interpolation technique. By applying our morphing technique recursively, taking progressively smaller subregions within a region, a high quality and accuracy interpolation is obtained. The presented algorithm is robust and has 20 adjustable parameters for use with different modalities. The main advantages of this morphing algorithm are: 1) applicability to general configurations of planes in 3D space, 2) automated behavior, 3) applicability to CT scans with no changes in the algorithm and software. Subsequently, to visualize data, a specialized volume rendering card (TeraRecon VolumePro 1000) was used. To represent data in 3D space, special software was developed to convert interpolated CT slices to 3D objects compatible with the VolumePro card. Quantitative and visual comparison between the proposed model and linear interpolation clearly demonstrates the superiority of the proposed model. Evaluation is performed by removing slices from the original stack of 2D images and using them as reference for error comparison among alternative approaches. Error analysis using average Mean Square and Absolute error clearly demonstrates improved performance

Automated detection of mammographic masses: preliminary assessment of an information-theoretic CAD scheme for reduction of false positives

The purpose of this work was to evaluate an information-theoretic computer-aided detection (CAD) scheme for improving the specificity of mass detection in screening mammograms. The study was based on images from the Lumisys set of the Digital Database for Screening Mammography (DDSM). Initially, the craniocaudal views of 49 DDSM mammograms were analyzed using an automated detection algorithm developed to prescreen mammograms. The prescreening algorithm followed a morphological concentric layer analysis and resulted in 319 false positive detections at 92% sensitivity. These 319 suspicious yet normal regions were extracted for further analysis with our information-theoretic CAD scheme. Our scheme follows a knowledge-based decision strategy. The strategy relies on information theoretic principles for similarity assessment between a query case and a knowledge databank of cases with known ground truth. Receiver Operating Characteristic (ROC) analysis was performed to determine how well the CAD scheme can discriminate the false positive regions from 681 true masses. The overall ROC area index of the information-theoretic CAD system was 0.75±0.02. At 97%, 95%, and 90% sensitivity, the system eliminated safely 20%, 30%, and 42% of the previously identified false positives respectively. Thus, information-theoretic CAD analysis can yield a significant reduction in false-positive detections while maintaining reasonable sensitivity.

Detection of architectural distortion in mammograms using fractal analysis

Several studies have demonstrated the fractal properties of screening mammograms. The purpose of this study was to investigate fractal texture analysis for the automated detection of architectural distortion (AD) in screening mammograms. The study was based on the Digital Database for Screening Mammography (DDSM). Initially, a database of 708 mammographic regions with confirmed pathology was created. They were all 512x512 pixel regions of interest (ROIs). The ROI size was determined empirically. Fifty-two regions were extracted around biopsy-proven architectural distortion. The remaining 656 ROIs depicted normal breast parenchyma. Fractal analysis was performed on each ROI at multiple resolutions (512x512, 256x256, 128x128, and 64x64). The fractal dimension of each ROI was calculated using the circular average power spectrum technique. Overall, the average fractal dimension (FD) estimate of the normal ROIs was statistically significantly higher than the average FD of the ROIs with AD. This result was consistent across all resolutions. However, best detection performance was achieved when the fractal dimension was estimated on ROIs subsampled with a factor of 2 (ROC area index Az=0.89±0.02). Specifically, there was perfect performance in fatty breasts (Az=1.0), Az=0.95±0.02 in fibroglandular breasts, Az=0.84±0.05 in heterogeneous breasts, and Az=0.66±0.10 in dense breasts. Overall, the present study demonstrates that the presence of AD disrupts the normal parenchymal structure, thus resulting in a lower fractal dimension. Consequently, fractal texture analysis could play an important role in the development of computer-assisted detection tools tailored towards architectural distortion.