Biomedical subjects

B Sahiner

Publications and source records attributed to B Sahiner.

23 records · Page 2Linked to original sources

PubMed1996

Automated detection of breast masses on mammograms using adaptive contrast enhancement and texture classification.

This paper presents segmentation and classification results of an automated algorithm for the detection of breast masses on digitized mammograms. Potential mass regions were first identified using density-weighted contrast enhancement (DWCE) segmentation applied to single-view mammograms. Once the potential mass regions had been identified, multiresolution texture features extracted from wavelet coefficients were calculated, and linear discriminant analysis (LDA) was used to classify the regions as breast masses or normal tissue. In this article the overall detection results for two independent sets of 84 mammograms used alternately for training and test were evaluated by free-response receiver operating characteristics (FROC) analysis. The test results indicate that this new algorithm produced approximately 4.4 false positive per image at a true positive detection rate of 90% and 2.3 false positives per image at a true positive rate of 80%.

Automation↗

PubMed1996

Image feature selection by a genetic algorithm: application to classification of mass and normal breast tissue.

We investigated a new approach to feature selection, and demonstrated its application in the task of differentiating regions of interest (ROIs) on mammograms as either mass or normal tissue. The classifier included a genetic algorithm (GA) for image feature selection, and a linear discriminant classifier or a backpropagation neural network (BPN) for formulation of the classifier outputs. The GA-based feature selection was guided by higher probabilities of survival for fitter combinations of features, where the fitness measure was the area Az under the receiver operating characteristic (ROC) curve. We studied the effect of different GA parameters on classification accuracy, and compared the results to those obtained with stepwise feature selection. The data set used in this study consisted of 168 ROIs containing biopsy-proven masses and 504 ROIs containing normal tissue. From each ROI, a total of 587 features were extracted, of which 572 were texture features and 15 were morphological features. The GA was trained and tested with several different partitionings of the ROIs into training and testing sets. With the best combination of the GA parameters, the average test Az value using a linear discriminant classifier reached 0.90, as compared to 0.89 for stepwise feature selection. Test Az values with a BPN classifier and a more limited feature pool were 0.90 with GA-based feature selection, and 0.89 for stepwise feature selection. The use of a GA in tailoring classifiers with specific design characteristics was also discussed. This study indicates that a GA can provide versatility in the design of linear or nonlinear classifiers without a trade-off in the effectiveness of the selected features.

Algorithms↗

PubMed1995

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

We studied the effectiveness of using texture features derived from spatial grey level dependence (SGLD) matrices for classification of masses and normal breast tissue on mammograms. One hundred and sixty-eight regions of interest (ROIS) containing biopsy-proven masses and 504 ROIS containing normal breast tissue were extracted from digitized mammograms for this study. Eight features were calculated for each ROI. The importance of each feature in distinguishing masses from normal tissue was determined by stepwise linear discriminant analysis. Receiver operating characteristic (ROC) methodology was used to evaluate the classification accuracy. We investigated the dependence of classification accuracy on the input features, and on the pixel distance and bit depth in the construction of the SGLD matrices. It was found that five of the texture features were important for the classification. The dependence of classification accuracy on distance and bit depth was weak for distances greater than 12 pixels and bit depths greater than seven bits. By randomly and equally dividing the data set into two groups, the classifier was trained and tested on independent data sets. The classifier achieved an average area under the ROC curve, Az, of 0.84 during training and 0.82 during testing. The results demonstrate the feasibility of using linear discriminant analysis in the texture feature space for classification of true and false detections of masses on mammograms in a computer-aided diagnosis scheme.

Biophysical Phenomena↗

PubMed1995

Classification of mass and normal breast tissue on digital mammograms: multiresolution texture analysis.

We investigated the feasibility of using multiresolution texture analysis for differentiation of masses from normal breast tissue on mammograms. The wavelet transform was used to decompose regions of interest (ROIs) on digitized mammograms into several scales. Multiresolution texture features were calculated from the spatial gray level dependence matrices of (1) the original images at variable distances between the pixel pairs, (2) the wavelet coefficients at different scales, and (3) the wavelet coefficients up to certain scale and then at variable distances between the pixel pairs. In this study, 168 ROIs containing biopsy-proven masses and 504 ROIs containing normal parenchyma were used as the data set. The mass ROIs were randomly and equally divided into training and test groups along with corresponding normal ROIs from the same film. Stepwise linear discriminant analysis was used to select optimal features from the multiresolution texture feature space to maximize the separation of mass and normal tissue for all ROIs. We found that texture features at large pixel distances are important for the classification task. The wavelet transform can effectively condense the image information into its coefficients. With texture features based on the wavelet coefficients and variable distances, the area Az under the receiver operating characteristic curve reached 0.89 and 0.86 for the training and test groups, respectively. The results demonstrate that a linear discriminant classifier using the multiresolution texture features can effectively classify masses from normal tissue on mammograms.

Biopsy↗

PubMed1995

Computer-aided detection of mammographic microcalcifications: pattern recognition with an artificial neural network.

We are developing a computer program for automated detection of clustered microcalcifications on mammograms. In this study, we investigated the effectiveness of a signal classifier based on a convolution neural network (CNN) approach for improvement of the accuracy of the detection program. Fifty-two mammograms with clustered microcalcifications were selected from patient files. The clusters on the mammograms were ranked by experienced mammographers and divided into an obvious group, an average group, and a subtle group. The average and subtle groups were combined and randomly divided into two sets, each of which was used as training or test set alternately. The obvious group served as an additional independent test set. Regions of interest (ROIs) containing potential individual microcalcifications were first located on each mammogram by the automated detection program. The ROIs from one set of the mammograms were used to train CNNs of different configurations with a back-propagation method. The generalization capability of the trained CNNs was then examined by their accuracy of classifying the ROIs from the other set and from the obvious group. The classification accuracy of the CNNs for the ROIs was evaluated by receiver operating characteristic (ROC) analysis. It was found that CNNs of many different configurations can reach approximately the same performance level, with the area under the ROC curve (Az) of 0.9. We incorporated a trained CNN into the detection program and evaluated the improvement of the detection accuracy by the CNN using free response ROC analysis. Our results indicated that, over a wide range of true-positive (TP) cluster detection rate, the CNN classifier could reduce the number of false-positive (FP) clusters per image by more than 70%. For the obvious cases, at a TP rate of 100%, the FP rate reduced from 0.35 cluster per image to 0.1 cluster per image. For the average and subtle cases, the detection accuracy improved from a TP rate of 87% at an FP rate of four clusters per image to a TP rate of 90% at an FP rate of 1.5 clusters per image.

Automation↗