Rene Vargas-Voracek

Computer‐assisted detection of mammographic masses: A template matching scheme based on mutual information

The purpose of this study was to develop a knowledge-based scheme for the detection of masses on digitized screening mammograms. The computer-assisted detection (CAD) scheme utilizes a knowledge databank of mammographic regions of interest (ROIs) with known ground truth. Each ROI in the databank serves as a template. The CAD system follows a template matching approach with mutual information as the similarity metric to determine if a query mammographic ROI depicts a true mass. Based on their information content, all similar ROIs in the databank are retrieved and rank-ordered. Then, a decision index is calculated based on the querys best matches. The decision index effectively combines the similarity indices and ground truth of the best-matched templates into a prediction regarding the presence of a mass in the query mammographic ROI. The system was developed and evaluated using a database of 1465 ROIs extracted from the Digital Database for Screening Mammography. There were 809 ROIs with confirmed masses (455 malignant and 354 benign) and 656 normal ROIs. CAD performance was assessed using a leave-one-out sampling scheme and Receiver Operating Characteristics analysis. Depending on the formulation of the decision index, CAD performance as high as A(zeta) = 0.87 +/- 0.01 was achieved. The CAD detection rate was consistent for both malignant and benign masses. In addition, the impact of certain implementation parameters on the detection accuracy and speed of the proposed CAD scheme was studied in more detail.

Segmentation of suspicious clustered microcalcifications in mammograms

We have developed a multistage computer-aided diagnosis (CAD) scheme for the automated segmentation of suspicious microcalcification clusters in digital mammograms. The scheme consisted of three main processing steps. First, the breast region was segmented and its high-frequency content was enhanced using unsharp masking. In the second step, individual microcalcifications were segmented using local histogram analysis on overlapping subimages. For this step, eight histogram features were extracted for each subimage and were used as input to a fuzzy rule-based classifier that identified subimages containing microcalcifications and assigned the appropriate thresholds to segment any microcalcifications within them. The final step clustered the segmented microcalcifications and extracted the following features for each cluster: the number of microcalcifications, the average distance between microcalcifications, and the average number of times pixels in the cluster were segmented in the second step. Fuzzy logic rules incorporating the cluster features were designed to remove nonsuspicious clusters, defined as those with typically benign characteristics. A database of 98 images, with 48 images containing one or more microcalcification clusters, provided training and testing sets to optimize the parameters and evaluate the CAD scheme, respectively. The results showed a true positive rate of 93.2% and an average of 0.73 false positive clusters per image. A comparison of our results with other reported segmentation results on the same database showed comparable sensitivity and at the same time an improved false positive rate. The performance of the CAD scheme is encouraging for its use as an automatic tool for efficient and accurate diagnosis of breast cancer.

Identification of lung regions in chest radiographs using Markov random field modeling

The authors present an algorithm utilizing Markov random field modeling for identifying lung regions in a digitized chest radiograph (DCR). Let x represent the classifications of each pixel in a DCR as either lung or nonlung. We model x as a realization of a spatially varying Markov random field. This model is developed utilizing spatial and textural information extracted from samples of lung and nonlung region-types in a training set of DCRs. With this model, the technique of Iterated Conditional Modes is used to determine the optimal classification of each pixel in a DCR. The algorithms ability to identify lung regions is evaluated on a testing set of DCRs. The algorithm performs well yielding a sensitivity of 90.7% +/- 4.4%, a specificity of 97.2% +/- 2.0%, and an accuracy of 94.8% +/- 1.6%. In an attempt to gain insight into the meaning and level of the algorithms performance numbers, the results are compared to those of some easily implemented classification algorithms.

Markov random field modeling in posteroanterior chest radiograph segmentation.

Previously, the authors presented an algorithm that identifies lung regions in a digitized posteroanterior chest radiograph (DCR) by labeling each pixel as either lung or nonlung. In this manuscript, the inherent flexibility of this algorithm is demonstrated as the algorithm is generalized to identify multiple anatomical regions in a DCR. Specifically, each pixel is classified as belonging to one of six anatomical region types: lung, subdiaphragm, heart, mediastinum, body, or background. The algorithm determines the optimal set of pixel classifications, xOPT, for a given set of DCR pixel gray level values y via a probabilistic approach that defines xOPT as the particular segmentation that maximizes the conditional distribution P(x/y). A spatially varying Markov random field (MRF) model is used that incorporates spatial and textural information of each possible region type. MRF modeling provides the form of P(x/y), and Iterated Conditional Modes is used to converge to the distribution maximum of P(x/y) thus obtaining the optimal segmentation for a given DCR. Results show the algorithm being able to correctly classify 90.0% +/- 3.4% of the pixels in a DCR.

Bi-plane correlation imaging for improved detection of lung nodules

Bi-plane correlation imaging (BCI) is a new imaging approach that utilizes angular information from a bi-plane digital acquisition in conjunction with computer assisted detection (CAD) to reduce the degrading influence of anatomical noise in the detection of subtle lesions in planar images. An anthropomorphic chest phantom, supplemented with added nodule phantoms (5-13 mm at the image plane), was imaged from different posterior projections within a ±12° range by moving the x-ray tube vertically and horizontally with respect to the detector. Each image was analyzed using a basic front-end single-view CAD algorithm. The correlation of the suspect lesions from the PA view with those from each of the oblique views was examined using a priori knowledge of the acquisition geometry. The correlated suspect lesions were registered as positive. Using an optimum --3° vertical geometry and processing parameters, BCI resulted in 62.5% sensitivity, 1.5 FP/image, and 0.885 PPV. The corresponding values from the observer experiment were 56% sensitivity, 10.8 FP/image, and 0.45 PPV, respectively. Compared to single-view CAD results, the BCI reduced sensitivity by 20%. However, the corresponding reduction in FPs was notably higher (94%) leading to 140% improvement in the PPV. Changes in processing parameters could result in higher PPV and lower FP/image at the expense of lower sensitivity. Similar findings were indicated for small (5-9 mm) and large (9-13 mm) nodules, but the relative improvement was significantly higher for smaller nodules. (The research was supported by a grant from the NIH, R21CA91806.)

Content-based image retrieval as a computer aid for the detection of mammographic masses

The purpose of the study was to develop and evaluate a content-based image retrieval (CBIR) approach as a computer aid for the detection of masses in screening mammograms. The study was based on the Digital Database for Screening Mammography (DDSM). Initially, a knowledge database of 1,009 mammographic regions was created. They were all 512x512 pixel ROIs with known pathology. Specifically, there were 340 ROIs depicting a biopsy-proven malignant mass, 341 ROIs with a benign mass, and the remaining 328 ROIs were normal. Subsequently, the CBIR algorithm was implemented using mutual information (MI) as the similarity metric for image retrieval. The CBIR algorithm formed the basis of a knowledge-based CAD system. The system operated as follows. Given a databank of mammographic regions with known pathology, a query suspicious mammographic region was evaluated. Based on their information content, all similar cases in the databank were retrieved. The matches were rank-ordered and a decision index was calculated using the querys best matches. Based on a leave-one out sampling scheme, the CBIR-CAD system achieved an ROC area index Az= 0.87±0.01 and a partial ROC area index 0.90Az = 0.45±0.03 for the detection of masses in screening mammograms.

Characteristics of regions suspicious for pulmonary nodules at chest radiography.

RATIONALE AND OBJECTIVES This study was performed to determine physical characteristics of areas on chest radiographs that are suspicious but not definitive for the presence of a pulmonary nodule and the characteristics of areas that contain an obvious nodule. MATERIALS AND METHODS Two groups of patients were identified: those who had an area at plain radiography that was suspicious for a pulmonary nodule and underwent fluoroscopy for further evaluation (138 patients, 142 areas) and those who had an obvious nodule at plain radiography who underwent computed tomography for further evaluation (72 patients, 97 areas). The measured characteristics of the region of interest included size, circularity, compactness, contrast, and location. RESULTS A comparison of the data show that while there was some difference between these groups of patients with regard to location of the nodules, there were essentially no differences with regard to size, circularity, compactness, and contrast of the regions of interest. CONCLUSION Size, circularity, compactness, contrast, and location are not sufficient to distinguish pulmonary nodules from other suspicious regions on the chest radiograph.

Spectral characterization of mammographic tissue for computer aided diagnosis of malignant masses

An approach for the analysis of the spectral properties of digitized mammograms for computer aided diagnosis is presented. The approach is developed using 206 regions of interest (ROIs) extracted from 103 normal and 103 malignant mass cases selected from the Digital Database for Screening Mammography (DDSM) available from the University of South Florida. A spectral definition is proposed in terms of a linear function of the local slope of the modified, circularly averaged periodogram across the entire spectrum. The local slope is estimated in a least squares sense for each point in the spectrum as a function of local neighboring samples. The proposed spectral definition is evaluated for the discrimination of malignant versus normal ROIs. Results are summarized by receiver operating characteristic (ROC) curve analysis. For the cases studied, maximum detection performance is achieved with an area under the ROC curve (AUC) of 0.9223 and a partial AUC at 90% sensitivity of 0.712. These results suggest that the proposed spectral signature is useful as a computationally fast and effective approach for the characterization of malignant masses in digitized mammograms.

Fast search and localization algorithm based on human visual perception modeling: an application for fast localization of structures in mammograms

A computer algorithm for fast identification and localization of structures of interest in images is presented. The algorithm is based on the analysis of a reduced set of image neighborhoods selected randomly by a constrained sampling of an associated image map of much smaller spatial resolution. The general approach is demonstrated by estimating the relative location of the breast tissue on a dataset of 860 digitized mammographic images. The computational times and breast tissue localization error rates are reported for different reduced spatial resolution image maps and three different features used for the corresponding neighborhood analysis. Our results show significant improvement on the error rates and computational times obtained with our approach compared to a pixel intensity thresholding approach. The algorithm implementation is very simple, requires less computation time than the sequential processing of each one of the image elements in a raster pattern and can be easily included into a hierarchical image analysis model.

Hierarchical Markov random field modeling for mammographic structure segmentation using multiple spatial and intensity image resolutions

A hierarchical Markov random field (MRF) model for mammographic structure segmentation using multiple spatial and intensity image resolutions is proposed. The general image model is formed by a sequence of representations at different spatial and intensity scales. Through the hierarchical structure of the MRF model, components at different local spatial resolutions are used to condition the corresponding intensity resolution and the spatial distribution of the intensity components. As a first step, only breast skin edge and non fat breast parenchyma (Coopers ligaments, blood vessels and fibroglandular tissue) have been included into the model and implemented. Three basic priors for the local spatial intensity distribution (texture) are defined. An iterated conditional mode (ICM) optimization procedure is implemented, the lower resolution representations are used sequentially to form the initial image configurations for the ICM procedure. The proposed approach was tested using 100 digitized mammograms (at a resolution of 100 microns and 12 bits per pixel). The mammograms are from three different views and different breast parenchyma densities. Results for breast skin edge and breast parenchyma were obtained and evaluated visually. For all cases, the location of the three possible structures (skin, parenchyma and background) was identified correctly.