Dror Lederman

Computerized Prediction of Risk for Developing Breast Cancer Based on Bilateral Mammographic Breast Tissue Asymmetry

This study developed and assessed a computerized scheme to detect breast abnormalities and predict the risk of developing cancer based on bilateral mammographic tissue asymmetry. A digital mammography database of 100 randomly selected negative cases and 100 positive cases for having high-risk of developing breast cancer was established. Each case includes four images of cranio-caudal (CC) and medio-lateral oblique (MLO) views of the left and right breast. To detect bilateral mammographic tissue asymmetry, a pool of 20 computed features was assembled. A genetic algorithm was applied to select optimal features and build an artificial neural network based classifier to predict the likelihood of a test case being positive. The leave-one-case-out validation method was used to evaluate the classifier performance. Several approaches were investigated to improve the classification performance including extracting asymmetrical tissue features from either selected regions of interests or the entire segmented breast area depicted on bilateral images in one view, and the fusion of classification results from two views. The results showed that (1) using the features computed from the entire breast area, the classifier yielded the higher performance than using ROIs, and (2) using a weighted average fusion method, the classifier achieved the highest performance with the area under ROC curve of 0.781±0.023. At 90% specificity, the scheme detected 58.3% of high-risk cases in which cancers developed and verified 6-18 months later. The study demonstrated the feasibility of applying a computerized scheme to detect cases with high risk of developing breast cancer based on computer-detected bilateral mammographic tissue asymmetry.

Computer-aided detection of early interstitial lung diseases using low-dose CT images

This study aims to develop a new computer-aided detection (CAD) scheme to detect early interstitial lung disease (ILD) using low-dose computed tomography (CT) examinations. The CAD scheme classifies each pixel depicted on the segmented lung areas into positive or negative groups for ILD using a mesh-grid-based region growth method and a multi-feature-based artificial neural network (ANN). A genetic algorithm was applied to select optimal image features and the ANN structure. In testing each CT examination, only pixels selected by the mesh-grid region growth method were analyzed and classified by the ANN to improve computational efficiency. All unselected pixels were classified as negative for ILD. After classifying all pixels into the positive and negative groups, CAD computed a detection score based on the ratio of the number of positive pixels to all pixels in the segmented lung areas, which indicates the likelihood of the test case being positive for ILD. When applying to an independent testing dataset of 15 positive and 15 negative cases, the CAD scheme yielded the area under receiver operating characteristic curve (AUC = 0.884 ± 0.064) and 80.0% sensitivity at 85.7% specificity. The results demonstrated the feasibility of applying the CAD scheme to automatically detect early ILD using low-dose CT examinations.

Classification of cries of infants with cleft-palate using parallel hidden Markov models

This paper addresses the problem of classification of infants with cleft palate. A hidden Markov model (HMM)-based cry classification algorithm is presented. A parallel HMM (PHMM) for coping with age masking, based on a maximum-likelihood decision rule, is introduced. The performance of the proposed algorithm under different model parameters and different feature sets is studied using a database of cries of infants with cleft palate (CLP). The proposed algorithm yields an average of 91% correct classification rate in a subject- and age-dependent experiment. In addition, it is shown that the PHMM significantly outperforms the HMM performance in classification of cries of CLP infants of different ages.

Improving Breast Cancer Risk Stratification Using Resonance-Frequency Electrical Impedance Spectroscopy Through Fusion of Multiple Classifiers

This study aims to improve breast cancer risk stratification. A seven-probe resonance-frequency-based electrical impedance spectroscopy (REIS) system was designed, assembled, and utilized to establish a data set of examinations from 174 women. Three classifiers, including artificial neural network (ANN), support vector machine (SVM), and Gaussian mixture model (GMM), were independently developed to predict the likelihood of each woman to be recommended for biopsy. The performances of these classifiers were compared, and seven fusion methods for integrating these classifiers were investigated. The results showed that among the three classifiers, the ANN yielded the highest performance with an area under the curve (AUC) of 0.81 for the receiver operating characteristic (ROC), while SVM and GMM achieved AUCs of 0.80 and 0.78, respectively. Improvements of up to 3% were obtained using fusion of the three classifiers, with the largest improvement obtained using either a “minimum score” rule or a “weighted sum” rule. Comparing different combinations of two out of the three classifiers, the weighted sum rule provided the most robust and consistent results, with AUCs of 0.81, 0.83, and 0.82 for the different combinations of ANN and SVM, ANN and GMM, and SVM and GMM, respectively. Furthermore, at 90% specificity, the ANN, the weighted sum- and min rule-based classifiers, all detected 67% of the verified cancer cases as compared with 50, 50, and 60% detection of the high risk cases, respectively. The study demonstrated that REIS examinations provide relevant information for developing breast cancer risk stratification tools and that using fusion of several not-fully-correlated classifiers can improve classification performance.

Acoustic monitoring of double-lumen ventilated lungs for the detection of selective unilateral lung ventilation.

One-lung intubation (OLI) is among the most common complications of endotracheal intubation. None of the monitoring tools now available has proved effective for its early detection. In this study we investigated the efficacy of acoustic analysis for the detection of OLI. We collected lung sounds from 11 patients undergoing thoracic surgery requiring the placement of a double-lumen tube. Recordings of separate lung ventilation were performed after induction and confirmation of adequate tube positioning, before surgery. Samples of lung sounds were collected by three piezoelectric microphones, one on each side of the chest and one on the right forearm, for background noise sampling. The samples were filtered, the signals’ energy envelopes were calculated, and segmentation to breath and rest periods was performed. Each respiration was classified into one of the three categories: bilateral ventilation, selective right-lung ventilation, or selective left-lung ventilation, on the basis of the ratio between the energy signals of each lung. OLI was accurately identified in 10 of the 11 patients during right OLI and in all 11 patients during left OLI. This study suggests that acoustic monitoring is effective for the detection of selective lung ventilation and may be useful for early diagnosis of OLI.

Classification of multichannel EEG patterns using parallel hidden Markov models

In this paper, a parallel hidden-Markov-model (PHMM)-based approach is proposed for the problem of multichannel electroencephalogram (EEG) patterns classification. The approach is based on multi-channel representation of the EEG signals using a parallel combination of HMMs, where each model represents a particular channel. The performance of the proposed algorithm is studied using an artificial EEG database, and two real EEG databases: a database of two classes of EEGs elicited during a task of imagery of hand upward and downward movements of a computer screen cursor (db Ia), and a database of two classes of sensorimotor EEGs elicited during a feedback-regulated left–right motor imagery task (db III). The results show that the proposed algorithm outperforms other commonly used methods with classification rate improvement of 2 and 10% for db Ia and db III, respectively. In addition, the proposed method outperforms a support vector machine classifier with a linear kernel, when both classifiers utilize the same feature set. The results also show that a model architecture which includes a left-to-right scheme with no skips, five states and three Gaussians, outperforms the other tested architectures due to the fact that it allows a better modeling of the temporal sequencing of the EEG components.

Improving Performance of Computer-aided Detection of Masses by Incorporating Bilateral Mammographic Density Asymmetry: An Assessment

RATIONALE AND OBJECTIVES Bilateral mammographic density asymmetry is a promising indicator in assessing risk of having or developing breast cancer. This study aims to assess the performance improvement of a computer-aided detection (CAD) scheme in detecting masses by incorporating bilateral mammographic density asymmetrical information. MATERIALS AND METHODS A testing dataset containing 2400 full-field digital mammograms (FFDM) acquired from 600 examination cases was established. Among them, 300 were positive cases with verified cancer associated with malignant masses and 300 were negative cases. Two computerized schemes were applied to process images of each case. The first single-image based CAD scheme detected suspicious mass regions and the second scheme computed average and difference of mammographic tissue density depicted between the left and right breast. A fusion method based on rotation of the CAD scoring projection reference axis was then applied to combine CAD-generated mass detection scores and either the computed average or difference (asymmetry) of bilateral mammographic density scores. The CAD performance levels with and without incorporating mammographic density information were evaluated and compared using a free-response receiver operating characteristic type data analysis method. RESULTS CAD achieved a case-based mass detection sensitivity of 0.74 and a region-based sensitivity of 0.56 at a false-positive rate of 0.25 per image. By fusing the CAD and bilateral mammographic density asymmetry scores, the case-based and region-based sensitivity levels of the CAD scheme were increased to 0.84 and 0.69, respectively, at the same false-positive rate. Fusion with average mammographic density only slightly increased CAD sensitivity to 0.75 (case-based) and 0.57 (region-based). CONCLUSIONS This study indicated that 1) bilateral mammographic density asymmetry was a stronger indicator of the case depicting suspicious masses than the average density computed from two breasts and 2) fusion between the conventional CAD scores and bilateral mammographic density asymmetry information could substantially increase CAD performance in mass detection.

An interactive system for computer-aided diagnosis of breast masses.

Although mammography is the only clinically accepted imaging modality for screening the general population to detect breast cancer, interpreting mammograms is difficult with lower sensitivity and specificity. To provide radiologists “a visual aid” in interpreting mammograms, we developed and tested an interactive system for computer-aided detection and diagnosis (CAD) of mass-like cancers. Using this system, an observer can view CAD-cued mass regions depicted on one image and then query any suspicious regions (either cued or not cued by CAD). CAD scheme automatically segments the suspicious region or accepts manually defined region and computes a set of image features. Using content-based image retrieval (CBIR) algorithm, CAD searches for a set of reference images depicting “abnormalities” similar to the queried region. Based on image retrieval results and a decision algorithm, a classification score is assigned to the queried region. In this study, a reference database with 1,800 malignant mass regions and 1,800 benign and CAD-generated false-positive regions was used. A modified CBIR algorithm with a new function of stretching the attributes in the multi-dimensional space and decision scheme was optimized using a genetic algorithm. Using a leave-one-out testing method to classify suspicious mass regions, we compared the classification performance using two CBIR algorithms with either equally weighted or optimally stretched attributes. Using the modified CBIR algorithm, the area under receiver operating characteristic curve was significantly increased from 0.865 ± 0.006 to 0.897 ± 0.005 (p < 0.001). This study demonstrated the feasibility of developing an interactive CAD system with a large reference database and achieving improved performance.

Automatic endotracheal tube position confirmation system based on image classification--a preliminary assessment.

Endotracheal intubation is a complex medical procedure in which a ventilating tube is inserted into the human trachea. Improper positioning carries potentially fatal consequences and therefore confirmation of correct positioning is mandatory. This paper introduces a novel system for endotracheal tube position confirmation. The proposed system comprises a miniature complementary metal oxide silicon sensor (CMOS) attached to the tip of a semi rigid stylet and connected to a digital signal processor (DSP) with an integrated video acquisition component. Video signals are acquired and processed by a confirmation algorithm implemented on the processor. The confirmation approach is based on video image classification, i.e., identifying desired expected anatomical structures (upper trachea and main bifurcation of the trachea) and undesired structures (esophagus). The desired and undesired images are indicators of correct or incorrect endotracheal tube positioning. The proposed methodology is comprised of a continuous and probabilistic image representation scheme using Gaussian mixture models (GMMs), estimated using a greedy algorithm. A multi-dimensional feature space, which consists of several textural-based features, is utilized to represent the images. The performance of the proposed algorithm was evaluated using two datasets: a dataset of 1600 images extracted from 10 videos recorded during intubations on dead cows, and a dataset of 358 images extracted from 8 videos recorded during intubations performed on human subjects. Each one of the video images was classified by a medical expert into one of three categories: upper tracheal intubation, correct (carina) intubation and esophageal intubation. The results, obtained using a leave-one-case-out method, show that the system correctly classified 1530 out of 1600 (95.6%) of the cow intubations images, and 351 out of the 358 human images (98.0%). Misclassification of an image of the esophagus as carina or upper-trachea, which is potentially fatal, was extremely rare (only one case when in the animal dataset and no cases when in the human intubation dataset). The classification results of the cow intubations dataset compare favorably with a state-of-the-art classification method tested on the same dataset.

Endotracheal Intubation Confirmation Based on Video Image Classification Using a Parallel GMMs Framework: A Preliminary Evaluation

In this paper, the problem of endotracheal intubation confirmation is addressed. Endotracheal intubation is a complex procedure which requires high skills and the use of secondary confirmation devices to ensure correct positioning of the tube. A novel confirmation approach, based on video images classification, is introduced. The approach is based on identification of specific anatomical landmarks, including esophagus, upper trachea and main bifurcation of the trachea into the two primary bronchi (“carina”), as indicators of correct or incorrect tube insertion and positioning. Classification of the images is performed using a parallel Gaussian mixture models (GMMs) framework, which is composed of several GMMs, schematically connected in parallel, where each GMM represents a different imaging angle. The performance of the proposed approach was evaluated using a dataset of cow-intubation videos and a dataset of human-intubation videos. Each one of the video images was manually (visually) classified by a medical expert into one of three categories: upper-tracheal intubation, correct (carina) intubation, and esophageal intubation. The image classification algorithm was applied off-line using a leave-one-case-out method. The results show that the system correctly classified 1517 out of 1600 (94.8%) of the cow-intubation images, and 340 out of the 358 human images (95.0%). The classification results compared favorably with a “standard” GMM approach utilizing textural based features, as well as with a state-of-the-art classification method, tested on the cow-intubation dataset.