Karla Horsch

Computerized diagnosis of breast lesions on ultrasound

We present a computer-aided diagnosis (CAD) method for breast lesions on ultrasound that is based on the automatic segmentation of lesions and the automatic extraction of four features related to the lesion shape, margin, texture, and posterior acoustic behavior. Using a database of 400 cases (94 malignant lesions, 124 complex cysts, and 182 benign solid lesions), we investigate the marginal benefit of each feature in our CAD method and the performance of our CAD method in distinguishing malignant lesions from various classes of benign lesions. Finally, independent validation is performed on our CAD method. Eleven independent trials yielded an average Az value of 0.87 in the task of distinguishing malignant from benign lesions.

Computerized lesion detection on breast ultrasound

We investigated the use of a radial gradient index (RGI) filtering technique to automatically detect lesions on breast ultrasound. After initial RGI filtering, a sensitivity of 87% at 0.76 false-positive detections per image was obtained on a database of 400 patients (757 images). Next, lesion candidates were segmented from the background by maximizing an average radial gradient (ARD) index for regions grown from the detected points. At an overlap of 0.4 with a radiologist lesion outline, 75% of the lesions were correctly detected. Subsequently, round robin analysis was used to assess the quality of the classification of lesion candidates into actual lesions and false-positives by a Bayesian neural network. The round robin analysis yielded an Az value of 0.84, and an overall performance by case of 94% sensitivity at 0.48 false-positives per image. Use of computerized analysis of breast sonograms may ultimately facilitate the use of sonography in breast cancer screening programs.

Automatic segmentation of breast lesions on ultrasound

In this paper we present a computationally efficient segmentation algorithm for breast masses on sonography that is based on maximizing a utility function over partition margins defined through gray-value thresholding of a preprocessed image. The performance of the segmentation algorithm is evaluated on a database of 400 cases in two ways. Of the 400 cases, 124 were complex cysts, 182 were benign solid lesions, and 94 were malignant lesions. In the first evaluation, the computer-delineated margins were compared to manually delineated margins. At an overlap threshold of 0.40, the segmentation algorithm correctly delineated 94% of the lesions. In the second evaluation, the performance of our computer-aided diagnosis method on the computer-delineated margins was compared to the performance of our method on the manually delineated margins. Round robin evaluation yielded Az values of 0.90 and 0.87 on the manually delineated margins and the computer-delineated margins, respectively, in the task of distinguishing between malignant and nonmalignant lesions.

Performance of computer-aided diagnosis in the interpretation of lesions on breast sonography

RATIONALE AND OBJECTIVES To investigate the potential usefulness of computer-aided diagnosis as a tool for radiologists in the characterization and classification of mass lesions on ultrasound. MATERIALS AND METHODS Previously, a computerized method for the automatic classification of breast lesions on ultrasound was developed. The computerized method includes automatic segmentation of the lesion from the ultrasound image background and automatic extraction of four features related to lesion shape, margin, texture, and posterior acoustic behavior. In this study, the effectiveness of the computer output as an aid to radiologists in their ability to distinguish between malignant and benign lesions, and in their patient management decisions in terms of biopsy recommendation are evaluated. Six expert mammographers and six radiologists in private practice at an institution accredited by the American Ultrasound Institute of Medicine participated in the study. Each observer first interpreted 25 training cases with feedback of biopsy results, and then interpreted 110 additional ultrasound cases without feedback. Simulating an actual clinical setting, the 110 cases were unknown to both the observers and the computer. During interpretation, observers gave their confidence that the lesion was malignant and also their patient management recommendation (biopsy or follow-up). The computer output was then displayed, and observers again gave their confidence that the lesion was malignant and theirpatient management recommendation. Statistical analyses included receiver operator characteristic analysis and Student t-test. RESULTS For the expert mammographers and for the community radiologists, the Az (area under the receiver operator characteristic curve) increased from 0.83 to 0.87 (P = .02) and from 0.80 to 0.84 (P = .04), respectively, when the computer aid was used in the interpretation of the ultrasound images. Also, the Az values for the community radiologists with aid and for the expert mammographers without aid are similar to the Az value for the computer alone (Az = 0.83). CONCLUSION Computer analysis of ultrasound images of breast lesions has been shown to improve the diagnostic accuracy of radiologists in the task of distinguishing between malignant and benign breast lesions and in recommending cases for biopsy.

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.

Potential Effect of Different Radiologist Reporting Methods on Studies Showing Benefit of CAD

RATIONALE AND OBJECTIVES To investigate the effect of different reporting methods and performance measures on the assessment of the benefit of computer-aided diagnosis (CAD) in characterizing malignant and benign breast lesions on mammography and sonography. MATERIALS AND METHODS In a previous study, 10 observers provided three types of reporting data (probability of malignancy [PM] estimates, Breast Imaging Reporting and Data System [BI-RADS] ratings, and biopsy decisions), both without and with CAD. The current study compares alternative performance measures computed from the three types of reporting data. The area under the receiver operating characteristic curve (AUC) was computed from both the PM estimates and the BI-RADS ratings, whereas sensitivity and specificity were computed from all three data types. Sensitivity and specificity values calculated from either the PM estimates or the BI-RADS ratings were determined by setting both constant and user-dependent thresholds. Students t-tests were used to evaluate the statistical significance of the differences in the performance measures without and with CAD. RESULTS The average AUC values of the 10 observers calculated from either PM estimates or BI-RADS ratings demonstrated statistically significant improvements in performance with CAD, increasing from 0.87 to 0.92 or 0.93, respectively. However, the statistical significance of improvements in sensitivity or specificity depended on the type of reporting data used. CONCLUSIONS Use of different types of reporting data in the computation of sensitivity and specificity may result in different conclusions concerning the benefit of CAD. Meaningful determination of sensitivity and specificity from PM estimates require the use of user-dependent thresholds.

Optimizing feature selection across a multimodality database in computerized classification of breast lesions

Linear step-wise feature selection is performed for computerized analysis methods on a set of mammography features using a database of mammography cases, a set of ultrasound features using a database of ultrasound cases, and a set of mammography and sonography features using a multi- modality database of lesions with both mammograms and sonograms. The large mammography and sonography databases were randomly split 20 times into three subdatabases for feature selection, classifier training and independent validation. The average validation Az value over the 20 random splits for the mammography database was 0.82 +/- 0.04 and for the sonography database was 0.85 +/- 0.03. The average consistency feature selection Az value for the mammography and sonography databases were 0.87 +/- 0.02 and 0.88 +/- 0.02, respectively. For the multi-modality database, the consistency feature selection Az value was 0.93.

PROGRESS IN BREAST CADx

The accuracy of a medical imaging examination depends on both the quality of the image acquisition and the quality of the image interpretation. For more than half a century, computer technology greatly improved image acquisition systems, e.g., with the development of various advanced tomographic imaging modalities. Computer technology is also contributing to the quality of the image interpretation process by incorporation of CAD, i.e., computer-aided detection (CADe) and computer-aided diagnosis (CADx). CADe involves the use of computer analyses to indicate locations of suspect regions in a medical image. The characterization, diagnosis, and patient management are left to the radiologist. CADx involves the use of computer analyses to characterize a region or lesion, initially located by either a human or computer, leaving the final diagnosis and patient management to the radiologist. We present here our progress in CADx for breast cancer using mammography, sonography, and breast MRI

Computer-aided diagnosis of lesions on multimodality images of the breast

We have developed computerized methods for the analysis of lesions that combine results from different imaging modalities, in this case digitized mammograms and sonograms of the breast, for distinguishing between malignant and benign lesions. The computerized classification method -- applied here to mass lesions seen on both digitized mammograms and sonograms, includes: (1) automatic lesion extraction, (2) automated feature extraction, and (3) automatic classification. The results for both modalities are then merged into an estimate of the likelihood of malignancy. For the mammograms, computer-extracted lesion features include degree of spiculation, margin sharpness, lesion density, and lesion texture. For the ultrasound images, lesion features include margin definition, texture, shape, and posterior acoustic attenuation. Malignant and benign lesions are better distinguished when features from both mammograms and ultrasound images are combined.

Correlation of lesions from multiple images for CAD

The object of this research is to investigate a method for determining whether two different imaged presentations of a lesion actually represent the same abnormality. Tasks of this kind are expected to arise in numerous applications, including when interpreting multi-view mammograms or multi-modal images for breast cancer diagnosis and when comparing breast images in longitudinal studies for evaluation of disease prognosis or treatment outcome. Currently, we consider the above-stated discrimination task in two-view breast sonography. We are studying image-based feature(s) and are developing general correlation formulation that uses the identified feature(s). By using a database of 262 actual breast lesions we have obtained promising initial results that yield an Az value of 0.82 in the task of distinguishing between corresponding lesion pairs and non-corresponding lesion pairs.