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.

Computerized analysis of multiple-mammographic views: potential usefulness of special view mammograms in computer-aided diagnosis.

PURPOSE: To investigate the potential usefulness of special view mammograms in the computer-aided diagnosis of mammographic breast lesions. MATERIALS AND METHODS: Previously, we developed a computerized method for the classification of mammographic mass lesions on standard-view mammograms, i.e., mediolateral oblique (MLO) view and/or cranial caudal (CC) views. In this study, we evaluate the performance of our computerized classification method on an independent database consisting of 70 cases (33 malignant and 37 benign cases), each having CC, MLO, and special view mammograms (spot compression or spot compression magnification views). The mass lesion identified in each of the three mammographic views was analyzed using our previously developed and trained computerized classification method. Performance in the task of distinguishing between malignant and benign lesions was evaluated using receiver operating characteristic analysis. On this independent database, we compared the performance of individual computer-extracted mammographic features, as well as the computer-estimated likelihood of malignancy, for the standard and special views. RESULTS: Computerized analysis of special view mammograms alone in the task of distinguishing between malignant and benign lesions yielded an Az of 0.95, which is significantly higher (p < 0.005) than that obtained from the MLO and CC views (Az values of 0.78 and 0.75, respectively). Use of only the special views correctly classified 19 of 33 benign cases (a specificity of 58%) at 100% sensitivity, whereas use of the CC and MLO views alone correctly classified 4 and 8 of 33 benign cases (specificities of 12% and 24%, respectively). In addition, we found that the average computer output of the three views (Az of 0.95) yielded a significantly better performance than did the maximum computer output from the mammographic views. CONCLUSIONS: Computerized analysis of special view mammograms provides an improved prediction of the benign versus malignant status of mammographic mass lesions.

Computerized classification of benign and malignant masses on digitized mammograms: a study of robustness.

RATIONALE AND OBJECTIVES: The purpose of this study was to evaluate the robustness of a computerized method developed for the classification of benign and malignant masses with respect to variations in both case mix and film digitization. MATERIALS AND METHODS: The classification method included automated segmentation of mass regions, automated feature-extraction, and automated lesion characterization. The method was evaluated independently with a 110-case database consisting of 50 malignant and 60 benign cases. Mammograms were digitized twice with two different digitizers (Konica and Lumisys). Performance of the method in differentiating benign from malignant masses was evaluated with receiver operating characteristic (ROC) analysis. Effects of variations in both case mix and film digitization on performance of the method also were assessed. RESULTS: Categorization of lesions as malignant or benign with an artificial neural network (or a hybrid) classifier achieved an area under the ROC curve, Az, value of 0.90 (0.94 for the hybrid) on the previous training database in a round-robin evaluation and Az values of 0.82 (0.81) and 0.81 (0.82) on the independent database for the Konica and Lumisys formats, respectively. These differences, however, were not statistically significant (P > .10). CONCLUSION: The computerized method for the classification of lesions on mammograms was robust with respect to variations in case mix and film digitization.

Computer-aided detection and diagnosis of breast cancer.

The limitations of radiologists when interpreting mammogram examinations provides a reasonable, if not compelling, basis for application of computer techniques that have the potential to improve diagnostic performance. Computer algorithms, at their present state of development, show great promise for clinical use. It can be expected that such use will only improve as computer technology and computer methods continue to become more formidable. The eventual role of computers in mammographic detection and diagnosis has not been fully defined, but their effect on practice may one day be very significant.

Automated registration of frontal and lateral radionuclide lung scans with digital chest radiographs.

RATIONALE AND OBJECTIVES: The purpose of this study was to develop and evaluate a fully automated method that spatially registers anterior, posterior, and lateral ventilation/perfusion (V/Q) images with posteroanterior and lateral digital chest radiographs to retrospectively combine the physiologic information contained in the V/Q scans with the anatomic detail in the chest radiographs. MATERIALS AND METHODS: Gray-level thresholding techniques were used to segment the aerated lung regions in the radiographic images. A variable-thresholding technique combined with an analysis of image noise was used to segment the adequately perfused or ventilated lung regions in the scintigraphic images. The physical dimensions of the segmented lung regions in images from both modalities were used to properly scale the radiographic images relative to the radionuclide images. Computer-determined locations of anatomic landmarks were then used to rotate and translate the images to achieve registration. Pairs of corresponding radionuclide and radiographic images were enhanced with color and then merged to create superimposed images. RESULTS: Five observers used a five-point rating scale to subjectively evaluate four image combinations for each of 50 cases. Of these ratings, 95.5% reflected very good, good, or fair registration. CONCLUSION: The automated method for the registration of radionuclide lung scans with digital chest radiographs to produce images that combine functional and structural information should benefit nuclear medicine physicians and radiologists, who must visually correlate images that differ greatly in physical size, resolution properties, and information content.

Breast cancer: importance of spiculation in computer-aided detection.

PURPOSE: To determine the prevalence of spiculation in a large series of screening-detected breast cancers appearing as masses on mammograms and to assess the sensitivity of a computer-aided detection (CAD) algorithm that uses spiculation measures in the detection of such lesions. MATERIALS AND METHODS: Six hundred seventy-seven consecutive cases of breast cancers detected as masses on mammograms were independently reviewed by three radiologists who determined if the lesions were spiculated. All cancers were then analyzed by the CAD system. RESULTS: All three radiologists interpreted 375 (55%) of the 677 masses as being spiculated on at least one view. The CAD algorithm correctly marked 322 (86%) of the 375 clearly spiculated masses, with a mean of 0.24 additional mass mark per image. With a looser definition of spiculation, 585 (86%) of the 677 masses were called spiculated by at least one radiologist on one view. The algorithm correctly marked 464 (79%) of the 585 lesions that were spiculated or possibly spiculated. CONCLUSION: Spiculation was clearly present in a majority (55%) of consecutive screening-detected breast cancer masses found on mammograms in a large clinical trial. Incorporation of spiculation measures is, therefore, an important strategy in the detection of breast cancer with CAD. A present-generation CAD algorithm correctly identified a large proportion (86%) of spiculated breast cancers.

Potential contribution of computer-aided detection to the sensitivity of screening mammography.

PURPOSE: To determine the false-negative rate in screening mammography, the capability of computer-aided detection (CAD) to identify these missed lesions, and whether or not CAD increases the radiologists' recall rate. MATERIALS AND METHODS: All available screening mammograms that led to the detection of biopsy-proved cancer (n = 1,083) and the most recent corresponding prior mammograms (n = 427) were collected from 13 facilities. Panels of radiologists evaluated the retrospectively visible prior mammograms by means of blinded review. All mammograms were analyzed by a CAD system that marks features associated with cancer. The recall rates of 14 radiologists were prospectively measured before and after installation of the CAD system. RESULTS: At retrospective review, 67% (286 of 427) of screening mammography-detected breast cancers were visible on the prior mammograms. At independent, blinded review by panels of radiologists, 27% (115 of 427) were interpreted as warranting recall on the basis of a statistical evaluation index; and the CAD system correctly marked 77% (89 of 115) of these cases. The original attending radiologists' sensitivity was 79% (427 of [427 + 115]). There was no statistically significant increase in the radiologists' recall rate when comparing the values before (8.3%) with those after (7.6%) installation of the CAD system. CONCLUSION: The original attending radiologists had a false-negative rate of 21% (115 of [427 + 115]). CAD prompting could have potentially helped reduce this false-negative rate by 77% (89 of 115) without an increase in the recall rate.

Effect of an artificial neural network on radiologists' performance in the differential diagnosis of interstitial lung disease using chest radiographs.

OBJECTIVE: We developed a new method to distinguish between various interstitial lung diseases that uses an artificial neural network. This network is based on features extracted from chest radiographs and clinical parameters. The aim of our study was to evaluate the effect of the output from the artificial neural network on radiologists' diagnostic accuracy. MATERIALS AND METHODS: The artificial neural network was designed to differentiate among 11 interstitial lung diseases using 10 clinical parameters and 16 radiologic findings. Thirty-three clinical cases (three cases for each lung disease) were selected. In the observer test, chest radiographs were viewed by eight radiologists (four attending physicians and four residents) with and without network output, which indicated the likelihood of each of the 11 possible diagnoses in each case. The radiologists' performance in distinguishing among the 11 interstitial lung diseases was evaluated by receiver operating characteristic (ROC) analysis with a continuous rating scale. RESULTS: When chest radiographs were viewed in conjunction with network output, a statistically significant improvement in diagnostic accuracy was achieved (p < .0001). The average area under the ROC curve was .826 without network output and .911 with network output. CONCLUSION: An artificial neural network can provide a useful "second opinion" to assist radiologists in the differential diagnosis of interstitial lung disease using chest radiographs.

Artificial neural networks in chest radiography: application to the differential diagnosis of interstitial lung disease.

RATIONALE AND OBJECTIVES: The authors evaluated the usefulness of artificial neural networks (ANNs) in the differential diagnosis of interstitial lung disease. MATERIALS AND METHODS: The authors used three-layer, feed-forward ANNs with a back-propagation algorithm. The ANNs were designed to distinguish between 11 interstitial lung diseases on the basis of 10 clinical parameters and 16 radiologic findings extracted by chest radiologists. Thus, the ANNs consisted of 26 input units and 11 output units. One hundred fifty actual clinical cases, 110 cases from previously published articles, and 110 hypothetical cases were used for training and testing the ANNs by using a round-robin (or leave-one-out) technique. ANN performance was evaluated with receiver operating characteristic (ROC) analysis. RESULTS: The Az (area under the ROC curve) obtained with actual clinical cases was 0.947, and both the sensitivity and specificity of the ANNs were approximately 90% in terms of indicating the correct diagnosis with the two largest output values among the 11 diseases. CONCLUSION: ANNs using clinical parameters and radiologic findings may be useful for making the differential diagnosis of interstitial lung disease on chest radiographs.

Automated computerized classification of malignant and benign masses on digitized mammograms.

RATIONALE AND OBJECTIVES: To develop a method for differentiating malignant from benign masses in which a computer automatically extracts lesion features and merges them into an estimated likelihood of malignancy. MATERIALS AND METHODS: Ninety-five mammograms depicting masses in 65 patients were digitized. Various features related to the margin and density of each mass were extracted automatically from the neighborhoods of the computer-identified mass regions. Selected features were merged into an estimated likelihood of malignancy by, using three different automated classifiers. The performance of the three classifiers in distinguishing between benign and malignant masses was evaluated by receiver operating characteristic analysis and compared with the performance of an experienced mammographer and that of five less experienced mammographers. RESULTS: Our computer classification scheme yielded an area under the receiver operating characteristic curve (Az) value of 0.94, which was similar to that for an experienced mammographer (Az = 0.91) and was statistically significantly higher than the average performance of the radiologists with less mammographic experience (Az = 0.81) (P = .013). With the database used, the computer scheme achieved, at 100% sensitivity, a positive predictive value of 83%, which was 12% higher than that for the performance of the experienced mammographer and 21% higher than that for the average performance of the less experienced mammographers (P < .0001). CONCLUSION: Automated computerized classification schemes may be useful in helping radiologists distinguish between benign and malignant masses and thus reducing the number of unnecessary biopsies.

Image quality and the clinical radiographic examination.

Image quality considerations in medical radiography are as diverse and complex as are the types of anatomy and pathologic conditions encountered in clinical practice. Nevertheless, certain basic concepts are central to the discussion of image quality in any radiographic examination. These concepts include the types of significant, or target, findings that are expected to occur and the anatomic background on which they are likely to appear. Physical parameters of radiographic systems, such as contrast, sharpness, and noise, act in unison in determining the final appearance of a radiograph and affect not only the portrayal of the expected pathologic condition but also that of the normal anatomy. Basic radiographic approaches in different clinical radiographic examinations can be derived from anticipated targets and backgrounds as well as from known physical determinants of image quality in radiography.

Automated registration of ventilation-perfusion images with digital chest radiographs.

RATIONALE AND OBJECTIVES: The authors have developed an automated computerized technique for registering radionuclide lung scan images with digital chest radiographs. METHODS: Threshold analysis was used to construct contours around the high-activity regions of radionuclide ventilation-perfusion images. Analogous contours were constructed around the lung regions of the corresponding digitized radiographs. Contour dimensions and anatomic landmark locations were then used to superimpose the radiographic, ventilation, and perfusion images. RESULTS: Evaluation of 25 sets of images indicated that the scheme provided adequate to excellent registration in 91% of the pairwise combinations. CONCLUSION: This automated scheme for registering ventilation-perfusion images with digital chest radiographs has the potential to aid radiologists in the interpretation of these images.

Malignant and benign clustered microcalcifications: automated feature analysis and classification.

PURPOSE: To develop a method for differentiating malignant from benign clustered microcalcifications in which image features are both extracted and analyzed by a computer. MATERIALS AND METHODS: One hundred mammograms from 53 patients who had undergone biopsy for suspicious clustered microcalcifications were analyzed by a computer. Eight computer-extracted features of clustered microcalcifications were merged by an artificial neural network. Human input was limited to initial identification of the microcalcifications. RESULTS: Computer analysis allowed identification of 100% of the patients with breast cancer and 82% of the patients with benign conditions. The accuracy of computer analysis was statistically significantly better than that of five radiologists (P = .03). CONCLUSION: Quantitative features can be extracted and analyzed by a computer to distinguish malignant from benign clustered microcalcifications. This technique may help radiologists reduce the number of false-positive biopsy findings.

Analysis of spiculation in the computerized classification of mammographic masses.

Spiculation is a primary sign of malignancy for masses detected by mammography. In this study, we developed a technique that analyzes patterns and quantifies the degree of spiculation present. Our current approach involves (1) automatic lesion extraction using region growing and (2) feature extraction using radial edge-gradient analysis. Two spiculation measures are obtained from an analysis of radial edge gradients. These measures are evaluated in four different neighborhoods about the extracted mammographic mass. The performance of each of the two measures of spiculation was tested on a database of 95 mammographic masses using ROC analysis that evaluates their individual ability to determine the likelihood of malignancy of a mass. The dependence of the performance of these measures on the choice of neighborhood was analyzed. We have found that it is only necessary to accurately extract an approximate outline of a mass lesion for the purposes of this analysis since the choice of a neighborhood that accommodates the thin spicules at the margin allows for the assessment of margin spiculation with the radial edge-gradient analysis technique. The two measures performed at their highest level when the surrounding periphery of the extracted region is used for feature extraction, yielding Az values of 0.83 and 0.85, respectively, for the determination of malignancy. These are similar to that achieved when a radiologist's ratings of spiculation (Az = 0.85) are used alone. The maximum value of one of the two spiculation measures (FWHM) from the four neighborhoods yielded an Az of 0.88 in the classification of mammographic mass lesions.

Computerized detection of clustered microcalcifications: evaluation of performance on mammograms from multiple centers.

To investigate the performance of a computerized method for the automated detection of clustered microcalcifications in digitized mammograms from a variety of screening centers, the authors invited 118 radiologists to bring up to five mammograms to their scientific exhibit at the 1993 meeting of the Radiological Society of North America (RSNA). Forty-three mammograms from 14 sites were brought to the exhibit, where they were digitized and analyzed. Results of the analysis on the RSNA cases were compared with those obtained on a standard database of 39 mammograms collected from two centers. The performance of the detection algorithm on the RSNA images was lower than that achieved on the standard database. This lower performance was due in part to the higher fraction of very subtle clustered microcalcifications in the RSNA cases, as well as the apparent dependence of the algorithm on image characteristics (eg, contrast and noise), which varied from center to center. The authors conclude that the algorithm is robust and accurate enough to undergo clinical testing. When it is implemented clinically, the computerized scheme must be customized to the image characteristics at each specific screening center to obtain optimal performance.

Computer-aided detection of clustered microcalcifications on digital mammograms.

A computer-aided diagnosis scheme to assist radiologists in detecting clustered microcalcifications from mammograms is being developed. Starting with a digital mammogram, the scheme consists of three steps. First, the image is filtered so that the signal-to-noise ratio of microcalcifications is increased by suppression of the normal background structure of the breast. Secondly, potential microcalcifications are extracted from the filtered image with a series of three different techniques: a global thresholding based on the grey-level histogram of the full filtered image, an erosion operator for eliminating very small signals, and a local adaptive grey-level thresholding. Thirdly, some false-positive signals are eliminated by means of a texture analysis technique, and a non-linear clustering algorithm is then used for grouping the remaining signals. With this method, the scheme can detect approximately 85% of true clusters, with an average of two false clusters detected per image.

Computer vision and artificial intelligence in mammography.

The revolution in digital computer technology that has made possible new and sophisticated imaging techniques may next influence the interpretation of radiologic images. In mammography, computer vision and artificial intelligence techniques have been used successfully to detect or to characterize abnormalities on digital images. Radiologists supplied with this information often perform better at mammographic detection or characterization tasks in observer studies than do unaided radiologists. This technology therefore could decrease errors in mammographic interpretation that continue to plague human observers.

Computerized detection of masses in digital mammograms: automated alignment of breast images and its effect on bilateral-subtraction technique.

An automated technique for the alignment of right and left breast images has been developed for use in the computerized analysis of bilateral breast images. In this technique, the breast region is first identified in each digital mammogram by use of histogram analysis and morphological filtering operations. The anterior portions of the tracked breast border and computer-identified nipple positions are selected as landmarks for use in image registration. The paired right and left breast images, either from mediolateral oblique or craniocaudal views, are then registered relative to each other by use of a least-squares matching method. This automated alignment technique has been applied to our computerized detection scheme that employs a nonlinear bilateral-subtraction method for the initial identification of possible masses. The effectiveness of using bilateral subtraction in identifying asymmetries between corresponding right and left breast images is examined by comparing detection performances obtained with various computer-simulated misalignments of 40 pairs of clinical mammograms. Based on free-response receiver operating characteristic and regression analyses, the detection performance obtained with the automated alignment technique was found to be higher than that obtained with simulated misalignments. Detection performance decreased gradually as the amount of simulated misalignment increased. These results indicate that automatic alignment of breast images is possible and that mass-detection performance appears to improve with the inclusion of asymmetric anatomic information but is not sensitive to slight misalignment.