Weijie Chen

Volumetric texture analysis of breast lesions on contrast‐enhanced magnetic resonance images

Automated image analysis aims to extract relevant information from contrast‐enhanced magnetic resonance images (CE‐MRI) of the breast and improve the accuracy and consistency of image interpretation. In this work, we extend the traditional 2D gray‐level co‐occurrence matrix (GLCM) method to investigate a volumetric texture analysis approach and apply it for the characterization of breast MR lesions. Our database of breast MR images was obtained using a T1‐weighted 3D spoiled gradient echo sequence and consists of 121 biopsy‐proven lesions (77 malignant and 44 benign). A fuzzy c‐means clustering (FCM) based method is employed to automatically segment 3D breast lesions on CE‐MR images. For each 3D lesion, a nondirectional GLCM is then computed on the first postcontrast frame by summing 13 directional GLCMs. Texture features are extracted from the nondirectional GLCMs and the performance of each texture feature in the task of distinguishing between malignant and benign breast lesions is assessed by receiver operating characteristics (ROC) analysis. Our results show that the classification performance of volumetric texture features is significantly better than that based on 2D analysis. Our investigations of the effects of various of parameters on the diagnostic accuracy provided means for the optimal use of the approach. Magn Reson Med 58:562–571, 2007.

Automatic identification and classification of characteristic kinetic curves of breast lesions on DCE‐MRI

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) of the breast is being used increasingly in the detection and diagnosis of breast cancer as a complementary modality to mammography and sonography. Although the potential diagnostic value of kinetic curves in DCE-MRI is established, the method for generating kinetic curves is not standardized. The inherent reason that curve identification is needed is that the uptake of contrast agent in a breast lesion is often heterogeneous, especially in malignant lesions. It is accepted that manual region of interest selection in 4D breast magnetic resonance (MR) images to generate the kinetic curve is a time-consuming process and suffers from significant inter- and intraobserver variability. We investigated and developed a fuzzy c-means (FCM) clustering-based technique for automatically identifying characteristic kinetic curves from breast lesions in DCE-MRI of the breast. Dynamic contrast-enhanced MR images were obtained using a T1-weighted 3D spoiled gradient echo sequence with Gd-DTPA dose of 0.2 mmol/kg and temporal resolution of 69 s. FCM clustering was applied to automatically partition the signal-time curves in a segmented 3D breast lesion into a number of classes (i.e., prototypic curves). The prototypic curve with the highest initial enhancement was selected as the representative characteristic kinetic curve (CKC) of the lesion. Four features were then extracted from each characteristic kinetic curve to depict the maximum contrast enhancement, time to peak, uptake rate, and washout rate of the lesion kinetics. The performance of the kinetic features in the task of distinguishing between benign and malignant lesions was assessed by receiver operating characteristic analysis. With a database of 121 breast lesions (77 malignant and 44 benign cases), the classification performance of the FCM-identified CKCs was found to be better than that from the curves obtained by averaging over the entire lesion and similar to kinetic curves generated from regions drawn within the lesion by a radiologist experienced in breast MRI.

Computerized interpretation of breast MRI: Investigation of enhancement‐variance dynamics

The advantages of breast MRI using contrast agent Gd-DTPA in the diagnosis of breast cancer have been well established. The variation of interpretation criteria and absence of interpretation guidelines, however, is a major obstacle for applications of MRI in the routine clinical practice of breast imaging. Our study aims to increase the objectivity and reproducibility of breast MRI interpretation by developing an automated interpretation approach for ultimate use in computer-aided diagnosis. The database in this study contains 121 cases: 77 malignant and 44 benign masses as revealed by biopsy. Images were obtained using a T1-weighted 3D spoiled gradient echo sequence. After the acquisition of the precontrast series, Gd-DTPA contrast agent was injected intravenously by power injection with a dose of 0.2 mmol/kg. Five postcontrast series were then taken with a time interval of 60 s. Each series contained 64 coronal slices with a matrix of 128 x 256 pixels and an in-plane resolution of 1.25 x 1.25 mm2. Slice thickness ranged from 2 to 3 mm depending on breast size. The lesions were delineated by an experienced radiologist as well as independently by computer using an automatic volume-growing algorithm. Fourteen features that were extracted automatically from the lesions could be grouped into three categories based on (I) morphology, (II) enhancement kinetics, and (III) time course of enhancement-variation over the lesion. A stepwise feature selection procedure was employed to select an effective subset of features, which were then combined by linear discriminant analysis (LDA) into a discriminant score, related to the likelihood of malignancy. The classification performances of individual features and the combined discriminant score were evaluated with receiver operating characteristic (ROC) analysis. With the radiologist-delineated lesion contours, stepwise feature selection yielded four features and an Az value of 0.80 for the LDA in leave-one-out cross-validation testing. With the computer-segmented lesion volumes, it yielded six features and an Az value of 0.86 for the LDA in the leave-one-out testing.

Evaluation of Computer-aided Diagnosis on a Large Clinical Full-field Digital Mammographic Dataset

RATIONALE AND OBJECTIVES To convert and optimize our previously developed computerized analysis methods for use with images from full-field digital mammography (FFDM) for breast mass classification to aid in the diagnosis of breast cancer. MATERIALS AND METHODS An institutional review board approved protocol was obtained, with waiver of consent for retrospective use of mammograms and pathology data. Seven hundred thirty-nine FFDM images, which contained 287 biopsy-proven breast mass lesions, of which 148 lesions were malignant and 139 lesions were benign, were retrospectively collected. Lesion margins were delineated by an expert breast radiologist and were used as the truth for lesion-segmentation evaluation. Our computerized image analysis method consisted of several steps: 1) identified lesions were automatically extracted from the parenchymal background using computerized segmentation methods; 2) a set of image characteristics (mathematic descriptors) were automatically extracted from image data of the lesions and surrounding tissues; and 3) selected features were merged into an estimate of the probability of malignancy using a Bayesian artificial neural network classifier. Performance of the analyses was evaluated at various stages of the conversion using receiver-operating characteristic analysis. RESULTS An area under the curve value of 0.81 was obtained in the task of distinguishing between malignant and benign mass lesions in a round-robin by case evaluation on the entire FFDM dataset. We failed to show a statistically significant difference (P = .83) compared to results from our previous study in which the computerized classification was performed on digitized screen-film mammograms. CONCLUSIONS Our computerized analysis methods developed on digitized screen-film mammography can be converted for use with FFDM. Results show that the computerized analysis methods for the diagnosis of breast mass lesions on FFDM are promising, and can potentially be used to aid clinicians in the diagnostic interpretation of FFDM.

A fuzzy c-means (FCM) based algorithm for intensity inhomogeneity correction and segmentation of MR images

Magnetic resonance images are often corrupted by intensity inhomogeneity, which manifests itself as slow intensity variations of the same tissue over the image domain. Such shading artifacts must be corrected before doing computerized analysis such as intensity-based segmentation and quantitative analysis. In this paper, we present a fuzzy c-means (FCM) based algorithm that simultaneously estimates the shading effect while segmenting the image. A multiplier field term that models the intensity variation is incorporated into the FCM objective function which is minimized iteratively. In each iteration, the bias field is estimated based on the current tissue class centroids and the membership values of the voxels and then smoothed by an iterative low-pass filter. The efficacy of the algorithm is demonstrated on clinical breast MR images.

Computerized Assessment of Breast Lesion Malignancy using DCE-MRI: Robustness Study on Two Independent Clinical Datasets from Two Manufacturers

RATIONALE AND OBJECTIVES To conduct a preclinical evaluation of the robustness of our computerized system for breast lesion characterization on two breast magnetic resonance imaging (MRI) databases that were acquired using scanners from two different manufacturers. MATERIALS AND METHODS Two clinical breast MRI databases were acquired from a Siemens scanner and a GE scanner, which shared similar imaging protocols and retrospectively collected under an institutional review board-approved protocol. In our computerized analysis system, after a breast lesion is identified by the radiologist, the computer performs automatic lesion segmentation and feature extraction and outputs an estimated probability of malignancy. We used a Bayesian neural network with automatic relevance determination for joint feature selection and classification. To evaluate the robustness of our classification system, we first used Database 1 for feature selection and classifier training, and Database 2 to test the trained classifier. Then, we exchanged the two datasets and repeated the process. Area under the receiver operating characteristic curve (AUC) was used as a performance figure of merit in the task of distinguishing between malignant and benign lesions. RESULTS We obtained an AUC of 0.85 (approximate 95% confidence interval [CI] 0.79-0.91) for (a) feature selection and classifier training using Database 1 and testing on Database 2; and an AUC of 0.90 (approximate 95% CI 0.84-0.96) for (b) feature selection and classifier training using Database 2 and testing on Database 1. We failed to observe statistical significance for the difference AUC of 0.05 between the two database conditions (P = .24; 95% confidence interval -0.03, 0.1). CONCLUSION These results demonstrate the robustness of our computerized classification system in the task of distinguishing between malignant and benign breast lesions on dynamic contrast-enhanced (DCE) MRI images from two manufacturers. Our study showed the feasibility of developing a computerized classification system that is robust across different scanners.

A Novel Hybrid Linear/Nonlinear Classifier for Two-Class Classification: Theory, Algorithm, and Applications

Classifier design for a given classification task needs to take into consideration both the complexity of the classifier and the size of the dataset that is available for training the classifier. With limited training data, as often is the situation in computer-aided diagnosis of medical images, a classifier with simple structure (e.g., a linear classifier) is more robust and therefore preferred. We propose a novel two-class classifier, which we call a hybrid linear/nonlinear classifier (HLNLC), that involves two stages: the input features are linearly combined to form a scalar variable in the first stage and then the likelihood ratio of the scalar variable is used as the decision variable for classification. We first develop the theory of HLNLC by assuming that the feature data follow normal distributions. We show that the commonly used Fishers linear discriminant function is generally not the optimal linear function in the first stage of the HLNLC. We formulate an optimization problem to solve for the optimal linear function in the first stage of the HLNLC, i.e., the linear function that maximizes the area under the receiver operating characteristic (ROC) curve of the HLNLC. For practical applications, we propose a robust implementation of the HLNLC by making a loose assumption that the two-class feature data arise from a pair of latent (rather than explicit) multivariate normal distributions. The novel hybrid classifier fills a gap between linear discriminant analysis (LDA) and quadratic discriminant analysis (QDA) in the sense that both its theoretical performance and its complexity lie between those of the LDA and those of the QDA. Simulation studies show that the hybrid linear/nonlinear classifier performs better than LDA without increasing the classifier complexity accordingly. With a finite number of training samples, the HLNLC can perform better than that of the ideal observer due to its simplicity. Finally, we demonstrate the application of the HLNLC in computer-aided diagnosis of breast lesions in ultrasound images.

Joint feature selection and classification using a Bayesian neural network with automatic relevance determination priors: potential use in CAD of medical imaging

Bayesian neural network (BNN) with automatic relevance determination (ARD) priors has the ability to assess the relevance of each input feature during network training. Our purpose is to investigate the potential use of BNN-with-ARD-priors for joint feature selection and classification in computer-aided diagnosis (CAD) of medical imaging. With ARD priors, each group of weights that connect an input feature to the hidden units is associated with a hyperparameter controlling the magnitudes of the weights. The hyperparameters and the weights are updated simultaneously during neural network training. A smaller hyperparameter will likely result in larger weight values and the corresponding feature will likely be more relevant to the output, and thus, to the classification task. For our study, a multivariate normal feature space is designed to include one feature with high classification performance in terms of both ideal observer and linear observer, two features with high ideal observer performance but low linear observer performance and 7 useless features. An exclusive-OR (XOR) feature space is designed to include 2 XOR features and 8 useless features. Our simulation results show that the ARD-BNN approach has the ability to select the optimal subset of features on the designed nonlinear feature spaces on which the linear approach fails. ARD-BNN has the ability to recognize features that have high ideal observer performance. Stepwise linear discriminant analysis (SWLDA) has the ability to select features that have high linear observer performance but fails to select features that have high ideal observer performance and low linear observer performance. The cross-validation results on clinical breast MRI data show that ARD-BNN yields statistically significant better performance than does the SWLDA-LDA approach. We believe that ARD-BNN is a promising method for pattern recognition in computer-aided diagnosis of medical imaging.

Automated identification of temporal pattern with high initial enhancement in dynamic MR lesions using fuzzy c-means algorithm

In contrast-enhanced (CE) MRI of the breast, signal-intensity time curves have been proven useful in differentiating between benign and malignant lesions. Due to uptake heterogeneity in the breast lesion, however, the signal-intensity time curve obtained from a specific region in the lesion may outperform that from the entire lesion. In this study, we propose the use of fuzzy c-means (FCM) clustering algorithms to reveal different temporal patterns within the breast lesion. The algorithm finds fuzzy cluster centers (i.e., temporal patterns) and assigns membership values to each voxel. The temporal pattern with maximum initial enhancement is selected as the representative curve of the lesion and the thresholded membership map is the identified region of fast enhancement. The approach was applied to the analysis of 121 lesions (77 malignant and 44 benign). The resulting representative curves were classified with linear discriminant analysis (LDA). The differentiation performance of LDA output in leave-one-out cross evaluation was assessed using receiver operating characteristic (ROC) analysis. Our results show that the use of FCM significantly improved the performance of signal-intensity time curves in the task of distinguishing between malignant and benign lesions.

TU‐D‐330A‐01: Computerized Lesion Detection On Breast MR Images

Purpose: To develop a computerized lesion detection method for DCE‐MRI breast images using the fuzzy c‐means clustering algorithm. Method: Contrast‐enhanced MR imaging is increasingly being incorporated into procedures for the screening of women at high risk of developing breast cancer. Such screening programs may potentially benefit from computer prompts that indicate potential lesion sites. In addition, analysis of other enhancing regions in the breast may reduce the number of false detections. Thus, we are developing an automated computerized lesion detection method based on the fuzzy c‐means clustering algorithm. The proposed method consists of four stages: (1) Breast volume segmentation based on a volume growing method; (2) Fuzzy c‐means clusteringanalysis on voxel‐based kinetics within the 4D breast image data (3D over time); (3) Voxel‐by‐voxel membership assignment to the most‐enhancing categories; and (4) Connectivity & size criteria for eliminating some false‐positive detections. Methods were evaluated by calculating detection sensitivity for malignant lesions, detection sensitivity for all lesions, and number of false‐positive detections per breast volume for output from the most‐enhancing kinetic categories. Results: Our preliminary studies are based on 20 MRI cases including 21 lesions (9 biopsy‐proven malignant cases, 5 biopsy‐proven benign cases; 6 cases without pathological proof). Based on computer‐identified regions from the most enhancing membership category, the proposed method correctly detected 16 lesions, including all nine malignant ones. In addition, most of the benign cases fell into either the most‐enhancing or second‐most‐enhancing categories. Preliminary results yielded, on average, 9 false‐positive detections per breast volume, which will subsequently be input to the classifier stage that exams morphological and kinetic characteristics for false positive reduction. Conclusion: The preliminary results with our FCM‐based computerized MRI lesion detection method are promising for potential use in breast cancer screening. Conflict of Interest: M.L.G. is a shareholder in R2 Technology, Inc.