Kurt Rossmann Laboratories

or Radiologic Image Research


ROC Software
Contact Us




Breast Imaging with Ultrasound and MRI

1. Computerized Analysis of Breast Lesions using Dynamic MRI

Contrast-enhanced MRI of the breast is known to reveal breast cancer with higher sensitivity than mammography alone.  The specificity is, however, compromised by the observation that several benign masses take up contrast agent in addition to malignant lesions.  The aim of this study was to increase the objectivity of breast cancer diagnosis in contrast-enhanced MRI by developing automated methods for CAD.  Our database consisted of 27 MR studies from 27 patients.  In each study, at least four MR series of both breasts were obtained using FLASH 3D acquisition at 90 s time intervals after injection of Gd-DTPA contrast agent.  Each series consists of 64 coronal slices with a typical thickness of 2 mm, and a pixel size of 1.25 mm.  The study contained 13 benign and 15 malignant lesions from which features were automatically extracted in 3D.  These features included margin descriptors and radial gradient analysis as a function of time and space.  Stepwise multiple regressions were employed to obtain an effective subset of combined features.  A final estimate of likelihood of malignancy was determined by linear discriminant analysis and the performance of classification by round-robin testing and ROC analysis.  To assess the efficacy of 3D analysis, the study was repeated in 2D using a representative slice through the middle of the lesion.  In 2D and 3D, radial gradient analysis and analysis of margin sharpness were found to be an effective combination to distinguish between benign and malignant masses (Az of 0.96).  Feature analysis in 3D was found to result in higher performance of lesion characterization than 2D feature analysis for the majority of single and combined features.  In conclusion, automated feature extraction and classification has the potential to complement the interpretation of radiologists in an objective, consistent, and accurate way.  (599, 600)


2. Computerized Analysis of Lesions in US Images of the Breast

Breast sonography is not routinely used to distinguish benign from malignant solid masses because of considerable overlap in their sonographic appearances.  The purpose of this study was to investigate the computerized analyses of breast lesions in ultrasonographic (US) images in order to ultimately aid in the task of discriminating between malignant and benign lesions.  Features related to lesion margin, shape, homogeneity (texture), and posterior acoustic attenuation pattern in US images of the breast were extracted and calculated.  The study database contained 184 digitized US images from 58 patients with 78 lesions.  Benign lesions were confirmed at biopsy or cyst aspiration or with image interpretation alone; malignant lesions were confirmed at biopsy.  Performance of the various individual features and output from linear discriminant analysis in distinguishing benign from malignant lesions was studied by using ROC analysis.  The feature characterizing the margin yielded Az values of 0.85 and 0.75 in distinguishing between benign and malignant lesions for the entire database and for an “equivocal” database, respectively.  The equivocal database contained lesions that were proved to be benign or malignant at cyst aspiration or biopsy.  Linear discriminant analysis by round-robin runs yielded Az values of 0.94 and 0.87 in distinguishing benign from malignant lesions for the entire database and for the equivocal database, respectively.  Computerized analysis of US images has the potential to increase the specificity of breast sonography.  (656, 759, 799, 800, 808, 809, 810, 861, 862)


3. Automatic Segmentation of Breast Lesions on Ultrasound

We developed a computationally efficient segmentation algorithm for breast masses on sonography that was based on maximizing a utility function over partition margins defined through gray-value thresholding of a preprocessed image.  The performance of the segmentation algorithm was 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 CAD 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.  (760)


4. Effect of CAD in the Interpretation of Breast Lesions on Ultrasound Images

The purpose of this study was to investigate the potential usefulness of computer-aided diagnosis to radiologists in the characterization and classification of mass lesions on ultrasound.  We evaluated 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 in terms of biopsy recommendation.  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 biopsy feedback, and then interpreted 110 additional ultrasound cases. During the interpretation, observers gave their likelihood 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 likelihood that the lesion was malignant and also their patient management recommendation.  For the expert mammographers and for the community radiologists, the Az increased from 0.83 to 0.87 (P=0.02) and from 0.80 to 0.84 (P=0.04), respectively, when the computer aid was used in the interpretation of the ultrasound images.  In addition, the performance level of the community radiologists with aid was similar to that of the expert mammographers without aid.  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 recommending cases for biopsy. (920)


5. 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. (799)


6. Computerized Analysis of Shadowing on Breast Ultrasound for Improved Lesion Detection

Sonography is being considered for the screening of women at high risk for breast cancer. We are developing computerized detection methods to aid in the localization of lesions on breast ultrasound images. The detection scheme presented here is based on the analysis of posterior acoustic shadowing, since posterior acoustic shadowing is observed for many malignant lesions. The method uses a nonlinear filtering technique based on the skewness of the gray level distribution within a kernel of image data. The database used in this study included 400 breast ultrasound cases (757 images) consisting of complicated cysts, solid benign lesions, and malignant lesions. At a false-positive rate of 0.25 false positives per image, a detection sensitivity of 80% by case (66% by image) was achieved for malignant lesions. The performance for the overall database (at 0.25 false positives per image) was less at 42% sensitivity by case (30% by image) due to the more limited presence of posterior acoustic shadowing for benign solid lesions and the presence of posterior acoustic enhancement for cysts. Our computerized method for the detection of lesion shadows alerts radiologists to lesions that exhibit posterior acoustic shadowing. While this is not a characterization method, its performance is best for lesions that exhibit posterior acoustic shadowing such as malignant and, to a lesser extent, benign solid lesions. This method, in combination with other computerized sonographic detection methods, may ultimately help facilitate the use of ultrasound for breast cancer screening. (861)


Home | Up | History | ROC Software | Publications | Contact Us

This site was last updated 11/24/04