Computer-aided classification of mammographic masses and normal tissue: linear discriminant analysis in texture feature space

Computerized analysis of mammographic microcalcifications in morphological and texture feature spaces

We are developing computerized feature extraction and classification methods to analyze malignant and benign microcalcifications on digitized mammograms. Morphological features that described the size, contrast, and shape of microcalcifications and their variations within a cluster were designed to characterize microcalcifications segmented from the mammographic background. Texture features were derived from the spatial gray-level dependence (SGLD) matrices constructed at multiple distances and directions from tissue regions containing microcalcifications. A genetic algorithm (GA) based feature selection technique was used to select the best feature subset from the multi-dimensional feature spaces. The GA-based method was compared to the commonly used feature selection method based on the stepwise linear discriminant analysis (LDA) procedure. Linear discriminant classifiers using the selected features as input predictor variables were formulated for the classification task. The discriminant scores output from the classifiers were analyzed by receiver operating characteristic (ROC) methodology and the classification accuracy was quantified by the area, Az, under the ROC curve. We analyzed a data set of 145 mammographic microcalcification clusters in this study. It was found that the feature subsets selected by the GA-based method are comparable to or slightly better than those selected by the stepwise LDA method. The texture features (Az = 0.84) were more effective than morphological features (Az = 0.79) in distinguishing malignant and benign microcalcifications. The highest classification accuracy (Az = 0.89) was obtained in the combined texture and morphological feature space. The improvement was statistically significant in comparison to classification in either the morphological (p = 0.002) or the texture (p = 0.04) feature space alone. The classifier using the best feature subset from the combined feature space and an appropriate decision threshold could correctly identify 35% of the benign clusters without missing a malignant cluster. When the average discriminant score from all views of the same cluster was used for classification, the Az value increased to 0.93 and the classifier could identify 50% of the benign clusters at 100% sensitivity for malignancy. Alternatively, if the minimum discriminant score from all views of the same cluster was used, the Az value would be 0.90 and a specificity of 32% would be obtained at 100% sensitivity. The results of this study indicate the potential of using combined morphological and texture features for computer-aided classification of microcalcifications.

Design of a high-sensitivity classifier based on a genetic algorithm: application to computer-aided diagnosis

A genetic algorithm (GA) based feature selection method was developed for the design of high-sensitivity classifiers, which were tailored to yield high sensitivity with high specificity. The fitness function of the GA was based on the receiver operating characteristic (ROC) partial area index, which is defined as the average specificity above a given sensitivity threshold. The designed GA evolved towards the selection of feature combinations which yielded high specificity in the high-sensitivity region of the ROC curve, regardless of the performance at low sensitivity. This is a desirable quality of a classifier used for breast lesion characterization, since the focus in breast lesion characterization is to diagnose correctly as many benign lesions as possible without missing malignancies. The high-sensitivity classifier, formulated as the Fisher's linear discriminant using GA-selected feature variables, was employed to classify 255 biopsy-proven mammographic masses as malignant or benign. The mammograms were digitized at a pixel size of 0.1 mm x 0.1 mm, and regions of interest (ROIs) containing the biopsied masses were extracted by an experienced radiologist. A recently developed image transformation technique, referred to as the rubber-band straightening transform, was applied to the ROIs. Texture features extracted from the spatial grey-level dependence and run-length statistics matrices of the transformed ROIs were used to distinguish malignant and benign masses. The classification accuracy of the high-sensitivity classifier was compared with that of linear discriminant analysis with stepwise feature selection (LDAsfs). With proper GA training, the ROC partial area of the high-sensitivity classifier above a true-positive fraction of 0.95 was significantly larger than that of LDAsfs, although the latter provided a higher total area (Az) under the ROC curve. By setting an appropriate decision threshold, the high-sensitivity classifier and LDAsfs correctly identified 61% and 34% of the benign masses respectively without missing any malignant masses. Our results show that the choice of the feature selection technique is important in computer-aided diagnosis, and that the GA may be a useful tool for designing classifiers for lesion characterization.

Computerized characterization of masses on mammograms: the rubber band straightening transform and texture analysis

A new rubber band straightening transform (RBST) is introduced for characterization of mammographic masses as malignant or benign. The RBST transforms a band of pixels surrounding a segmented mass onto the Cartesian plane (the RBST image). The border of a mammographic mass appears approximately as a horizontal line, and possible speculations resemble vertical lines in the RBST image. In this study, the effectiveness of a set of directional textures extracted from the images before the RBST. A database of 168 mammograms containing biopsy-proven malignant and benign breast masses was digitized at a pixel size of 100 microns x 100 microns. Regions of interest (ROIs) containing the biopsied mass were extracted from each mammogram by an experienced radiologist. A clustering algorithm was employed for automated segmentation of each ROI into a mass object and background tissue. Texture features extracted from spatial gray-level dependence matrices and run-length statistics matrices were evaluated for three different regions and representations: (i) the entire ROI; (ii) a band of pixels surrounding the segmented mass object in the ROI; and (iii) the RBST image. Linear discriminant analysis was used for classification, and receiver operating characteristic (ROC) analysis was used to evaluate the classification accuracy. Using the ROC curves as the performance measure, features extracted from the RBST images were found to be significantly more effective than those extracted from the original images. Features extracted from the RBST images yielded an area (Az) of 0.94 under the ROC curve for classification of mammographic masses as malignant and benign.

Incorporation of a set enumeration trees-based classifier into a hybrid computer-assisted diagnosis scheme for mass detection

RATIONALE AND OBJECTIVES

The authors evaluated whether a hybrid classifier of two independent computer-aided diagnosis (CAD) schemes, the set enumeration (SE) trees approach and an artificial neural network (ANN), could improve the detection of masses on digitized mammograms. The potential benefits resulting from the interpretability of the SE trees model was also explored.

MATERIALS AND METHODS

Two hundred thirty verified mass regions and 230 negative but suspicious regions were randomly selected from 618 digitized mammograms. Each region was represented by a 24-parameter feature vector. These features were used as input data for the SE trees and ANN-based schemes. After the positive and negative regions were randomly segmented into five exclusive partitions, a fivefold cross-validation method was applied to evaluate and compare the performance of the SE trees, ANN, and hybrid system in the identification of masses.

RESULTS

The performance of the SE trees approach was comparable to that of the ANN. The average area under the receiver operating characteristic (ROC) curves for all five partitions was 0.88 (standard deviation, 0.04). Owing to the relatively low correlation between the region-based results of the SE trees and ANN methods, the hybrid classifier yielded a significantly improved performance, with an area under the ROC curve of 0.94 (standard deviation, 0.02; P < .05).

CONCLUSION

The hybrid CAD scheme significantly improved performance. The amenability of the SE trees models to interpretation may aid in the assessment of the importance of specific features.

Automated detection of clustered microcalcifications on mammograms: CAD system application to MIAS database

To investigate the detection performance of our automated detection scheme for clustered microcalcifications on mammograms, we applied our computer-aided diagnosis (CAD) system to the database of the Mammographic Image Analysis Society (MIAS) in the UK. Forty-three mammograms from this database were used in this study. In our scheme, the breast regions were firstly extracted by determining the skinline. Histograms of the original images were used to extract the high-density area within the breast region as the segmentation from the fatty area around the skinline. Then the contrast correction technique was employed. Gradient vectors of the image density were calculated on the contrast corrected images. To extract the specific features of the pattern of the microcalcifications, triple-ring filter analysis was employed. A variable-ring filter was used for more accurate detection after the triple-ring filter. The features of the detected candidate areas were then characterized by feature analysis. The areas which satisfied the characteristics and specific terms were classified and displayed as clusters. As a result, the sensitivity was 95.8% with the false-positive rate at 1.8 clusters per image. This demonstrates that the automated detection of clustered microcalcifications in our CAD system is reliable as an aid to radiologists.

Digital mammography: computer-assisted diagnosis method for mass detection with multiorientation and multiresolution wavelet transforms

RATIONALE AND OBJECTIVES

The authors evaluated a modular computer-assisted diagnosis (CAD) method for mass detection that uses computation of features in three domains (gray level, morphology, and directional texture). Their objectives were to improve the sensitivity of detection and reduce the false-positive (FP) detection rate.

MATERIALS AND METHODS

The directional wavelet transform (DWT) method, which uses both multiorientation and multiresolution wavelet transforms to improve image preprocessing and segmentation of suspicious areas and to extract both morphologic and directional texture features, was evaluated with a previously reported image database containing 50 normal and 45 abnormal digitized screen-film mammograms. The mammograms contained all mass types and included 16 minimal cancers. This method was compared with the Markov random field (MRF) method to avoid issues related to case selection criteria. Free-response receiver operating characteristic curves were compared for both DWT and MRF methods.

RESULTS

For the DWT method, the sensitivity was 98% and the FP detection rate was 1.8 FP findings per image. For the MRF method, the sensitivity was 90% and the FP detection rate was 2.0 FP findings per image.

CONCLUSION

The CAD method applied to the full mammographic image is automatic and independent of mass type. The segmentation of masses as performed with this method may potentially allow visual interpretation according to American College of Radiology criteria.

False-positive reduction technique for detection of masses on digital mammograms: global and local multiresolution texture analysis

We investigated the application of multiresolution global and local texture features to reduce false-positive detection in a computerized mass detection program. One hundred and sixty-eight digitized mammograms were randomly and equally divided into training and test groups. From these mammograms, two datasets were formed. The first dataset (manual) contained four regions of interest (ROIs) selected manually from each of the mammograms. One of the four ROIs contained a biopsy-proven mass and the other three contained normal parenchyma, including dense, mixed dense/fatty, and fatty tissues. The second dataset (hybrid) contained the manually extracted mass ROIs, along with normal tissue ROIs extracted by an automated Density-Weighted Contrast Enhancement (DWCE) algorithm as false-positive detections. A wavelet transform was used to decompose an ROI into several scales. Global texture features were derived from the low-pass coefficients in the wavelet transformed images. Local texture features were calculated from the suspicious object and the peripheral subregions. Linear discriminant models using effective features selected from the global, local, or combined feature spaces were established to maximize the separation between masses and normal tissue. Receiver Operating Characteristic (ROC) analysis was conducted to evaluate the classifier performance. The classification accuracy using global features were comparable to that using local features. With both global and local features, the average area, Az, under the test ROC curve, reached 0.92 for the manual dataset and 0.96 for the hybrid dataset, demonstrating statistically significant improvement over those obtained with global or local features alone. The results indicated the effectiveness of the combined global and local features in the classification of masses and normal tissue for false-positive reduction.

Computerized classification of malignant and benign microcalcifications on mammograms: texture analysis using an artificial neural network

We investigated the feasibility of using texture features extracted from mammograms to predict whether the presence of microcalcifications is associated with malignant or benign pathology. Eighty-six mammograms from 54 cases (26 benign and 28 malignant) were used as case samples. All lesions had been recommended for surgical biopsy by specialists in breast imaging. A region of interest (ROI) containing the microcalcifications was first corrected for the low-frequency background density variation. Spatial grey level dependence (SGLD) matrices at ten different pixel distances in both the axial and diagonal directions were constructed from the background-corrected ROI. Thirteen texture measures were extracted from each SGLD matrix. Using a stepwise feature selection technique, which maximized the separation of the two class distributions, subsets of texture features were selected from the multi-dimensional feature space. A backpropagation artificial neural network (ANN) classifier was trained and tested with a leave-one-case-out method to recognize the malignant or benign microcalcification clusters. The performance of the ANN was analysed with receiver operating characteristic (ROC) methodology. It was found that a subset of six texture features provided the highest classification accuracy among the feature sets studied. The ANN classifier achieved an area under the ROC curve of 0.88. By setting an appropriate decision threshold, 11 of the 28 benign cases were correctly identified (39% specificity) without missing any malignant cases (100% sensitivity) for patients who had undergone biopsy. This preliminary result indicates that computerized texture analysis can extract mammographic information that is not apparent by visual inspection. The computer-extracted texture information may be used to assist in mammographic interpretation, with the potential to reduce biopsies of benign cases and improve the positive predictive value of mammography.

Adaptive computer-aided diagnosis scheme of digitized mammograms

RATIONALE AND OBJECTIVES

We investigated an adaptive rule-based computer-aided diagnosis (CAD) scheme for digitized mammograms that can be optimized by using an image difficulty index as determined from global measures of image characteristics.

METHODS

First, we defined an image "difficulty" index based on image feature measurements in both the spatial and frequency domains. The CAD scheme then segmented the database into three groups. An image database of 428 digitized mammograms with 220 verified masses was randomly divided into two subsets, one for training (rule-setting) and the other for testing the adaptive CAD scheme. Each of the image difficulty groups in the training set was optimized independently to achieve a low false-positive detection rate while maintaining high detection sensitivity. Scheme performance was then evaluated with the test set, and the results were compared with a global rule-based system that was optimized without the adaptive method.

RESULTS

In this preliminary study, a relatively simple adaptive scheme reduced false-positive mass detections compared with the nonadaptive scheme from 0.85 to 0.53 per image. At the same time sensitivity was not significantly changed.

CONCLUSION

This adaptive CAD scheme has distinct advantages in improving CAD scheme performance as long as the training database includes a large number of cases in each image difficulty group with a variety of true-positive abnormalities.

Robustness of computerized identification of masses in digitized mammograms. A preliminary assessment

RATIONALE AND OBJECTIVES

The authors assess the robustness of a computer-aided diagnosis (CAD) scheme with five rule-based stages to identify regions suspicious for mass in digitized mammograms.

METHODS

With a database of 428 mammograms, 234 of which had not been analyzed by this scheme before, the authors evaluated the performance robustness of their CAD scheme. The following four issues were investigated to assess the variability of the scheme's performance due to: (1) the maximum permissible number of "masses" detected at each stage; (2) exclusion of selected individual rule-based stages; (3) added image noise; and (4) repeated digitizations of the same image.

RESULTS

Enabling the CAD scheme to select a maximum of two suspicious mass regions at any one stage increased sensitivity by as much as 4% (from 93% to 97%), but it increased the false-positive detection rate by as much as 1.2 per image (from 1.7 to 2.9). Eliminating any individual stage decreased sensitivity by as much as 6%, but this reduced the false-positive detection rate by as much as 0.4 per image (from 1.7 to 1.3). The addition of reasonable noise levels decreased sensitivity by as much as 4% without substantially affecting the false-positive detections. Repeated digitizations of selected images demonstrated a scheme sensitivity of 93% +/- 1.8% with more than a 90% overlap of the false-positive regions.

CONCLUSIONS

The results of this preliminary study clearly indicate that this scheme is reasonably robust to the variables investigated here.

Microcalcification clustering parameters in breast disease: a morphometric analysis of radiographs of excision specimens

X-ray microradiography of surgically excised breast specimens offers the possibility of morphological characterization of calcifications. When combined with digital imaging techniques there exists added potential for obtaining valuable basic quantitative morphometric information regarding differences between microcalcifications in tissues exhibiting evidence of fibrocystic change, benign and malignant tumours. A total of 157 excised breast specimens from 84 patients were microradiographed using a Softex Super Soft X-ray unit and Kodak AA high resolution industrial film. A Quantimet 570C image analysis system was used to digitize and analyse the microradiographs. Of the 157 microradiographs, 51 (from 30 patients) revealed microcalcification clusters. The existence of significant differences between the three identified categories of tissue were indicated by clustering parameters. These included the number of particles per cluster, area of clusters, maximum distance to nearest neighbour, and geometric mean distance to nearest neighbour. The distribution pattern index (DPI), another of the clustering parameters used in this study, has been observed to be a particularly powerful discriminator. The value for fibrocystic change was found to be significantly smaller (0.514) than that for benign tumour (0.796) whilst that for benign tumour was observed to be significantly larger than that for malignant tumour (0.604) at a p-value of less than 0.05 (Kruskal-Wallis one-way analysis of variance).

Classification of mass and normal breast tissue: a convolution neural network classifier with spatial domain and texture images

The authors investigated the classification of regions of interest (ROI's) on mammograms as either mass or normal tissue using a convolution neural network (CNN). A CNN is a backpropagation neural network with two-dimensional (2-D) weight kernels that operate on images. A generalized, fast and stable implementation of the CNN was developed. The input images to the CNN were obtained from the ROI's using two techniques. The first technique employed averaging and subsampling. The second technique employed texture feature extraction methods applied to small subregions inside the ROI. Features computed over different subregions were arranged as texture images, which were subsequently used as CNN inputs. The effects of CNN architecture and texture feature parameters on classification accuracy were studied. Receiver operating characteristic (ROC) methodology was used to evaluate the classification accuracy. A data set consisting of 168 ROIs containing biopsy-proven masses and 504 ROI's containing normal breast tissue was extracted from 168 mammograms by radiologists experienced in mammography. This data set was used for training and testing the CNN. With the best combination of CNN architecture and texture feature parameters, the area under the test ROC curve reached 0.87, which corresponded to a true-positive fraction of 90% at a false positive fraction of 31%. The authors' results demonstrate the feasibility of using a CNN for classification of masses and normal tissue on mammograms.

An adaptive density-weighted contrast enhancement filter for mammographic breast mass detection

Presents a novel approach for segmentation of suspicious mass regions in digitized mammograms using a new adaptive density-weighted contrast enhancement (DWCE) filter in conjunction with Laplacian-Gaussian (LG) edge detection. The DWCE enhances structures within the digitized mammogram so that a simple edge detection algorithm can be used to define the boundaries of the objects. Once the object boundaries are known, morphological features are extracted and used by a classification algorithm to differentiate regions within the image. This paper introduces the DWCE algorithm and presents results of a preliminary study based on 25 digitized mammograms with biopsy proven masses. It also compares morphological feature classification based on sequential thresholding, linear discriminant analysis, and neural network classifiers for reduction of false-positive detections.