Appropriateness of a donor liver with respect to macrosteatosis: application of artificial neural networks to US images--initial experience

PURPOSE: To retrospectively compare performance of artificial neural networks (ANNs) applied to ultrasonographic (US) images with that of radiologists for prediction of appropriateness of a donor liver with respect to macrosteatosis before liver transplantation. MATERIALS AND METHODS: Institutional ethics committee approved study; written informed consent was obtained. ANNs, constructed with three-layered 15-neuron back-propagation algorithm, were trained to predict appropriateness of a donor liver with respect to macrosteatosis by using statistically significant laboratory and US parameters derived from univariate analyses, together with correct diagnosis. Input variables for ANNs were alkaline phosphatase, glutamic oxaloacetic transaminase, glutamic pyruvate transaminase, gamma-glutamyltransferase, hepatorenal ratio of echogenicity, and tail area ratio and tail length of portal vein wall echogenicity. Three radiologists graded US images in 94 potential donors (71 men and 23 women) on the basis of four degrees of hepatic steatosis. After training and testing of ANNs, performance of ANNs and radiologists in predicting appropriateness of potential donors was evaluated with receiver operating characteristic (ROC) analysis and compared by means of univariate z score test. RESULTS: Among 94 potential donor livers, 76 were normal or had mild steatosis, and 18 had moderate or severe macrosteatosis at histopathologic examination. Area under ROC curve (Az) of ANNs (Az=0.9673) was significantly greater than that of radiologists (faculty, Az=0.9106, P=.048; fellow, Az= 0.9038, P=.044; resident, Az=0.8931, P=.038). No statistically significant difference in sensitivity for predicting appropriateness as a liver donor with respect to macrosteatosis was found between ANNs (88.9%) and radiologists (P >.05). However, specificity of ANNs (96.1%) was significantly better than that of radiologists (P <.003). CONCLUSION: ANNs might be a useful tool to categorize whether a donor liver is appropriate for transplantation with respect to macrosteatosis on the basis of multiple variables related to laboratory and US features. Further study is needed.     

Pulmonary nodules at chest CT: effect of computer-aided diagnosis on radiologists' detection performance

PURPOSE: To evaluate the effect of computer-aided diagnosis (CAD) on radiologists' detection of pulmonary nodules. MATERIALS AND METHODS: Fifty chest computed tomographic (CT) examination cases were used. The mean nodule size was 0.81 cm +/- 0.60 (SD) (range, 0.3-2.9 cm). Alternative free-response receiver operating characteristic (ROC) analysis with a continuous rating scale was used to compare the observers' performance in detecting nodules with and without use of CAD. Five board-certified radiologists and five radiology residents participated in an observer performance study. First they were asked to rate the probability of nodule presence without using CAD; then they were asked to rate the probability of nodule presence by using CAD. RESULTS: For all radiologists, the mean areas under the best-fit alternative free-response ROC curves (Az) without and with CAD were 0.64 +/- 0.08 and 0.67 +/- 0.09, respectively, indicating a significant difference (P <.01). For the five board-certified radiologists, the mean Az values without and with CAD were 0.63 +/- 0.08 and 0.66 +/- 0.09, respectively, indicating a significant difference (P <.01). For the five resident radiologists, the mean Az values without and with CAD were 0.66 +/- 0.04 and 0.68 +/- 0.04, respectively, indicating a significant difference (P =.02). At observer performance analyses, there were no significant differences in Az values obtained either without (P =.61) or with (P =.88) CAD between the board-certified radiologists and the residents. For all radiologists, in the detection of pulmonary nodules 1.0 cm in diameter or smaller, the mean Az values without and with CAD were 0.60 +/- 0.11 and 0.64 +/- 0.11, respectively, indicating a significant difference (P <.01). CONCLUSION: Use of the CAD system improved the board-certified radiologists' and residents' detection of pulmonary nodules at chest CT.     

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.     

Computerized analysis of the likelihood of malignancy in solitary pulmonary nodules with use of artificial neural networks

PURPOSE: To develop a computer-aided diagnostic scheme by using an artificial neural network (ANN) to assist radiologists in the distinction of benign and malignant pulmonary nodules. MATERIALS AND METHODS: Fifty-six chest radiographs of 34 primary lung cancers and 22 benign nodules were digitized with a 0.175-mm pixel size and a 10-bit gray scale. Eight subjective image features were evaluated and recorded by radiologists in each case. A computerized method was developed to extract objective features that could be correlated with the subjective features. An ANN was used to distinguish benign from malignant nodules on the basis of subjective or objective features. The performance of the ANN was compared with that of the radiologists by means of receiver operating characteristic (ROC) analysis. RESULTS: Performance of the ANN was considerably greater with objective features (area under the ROC curve, Az = 0.854) than with subjective features (Az = 0.761). Performance of the ANN was also greater than that of the radiologists (Az = 0.752). CONCLUSION: The computerized scheme has the potential to improve the diagnostic accuracy of radiologists in the distinction of benign and malignant solitary pulmonary nodules.     

A comparison of diagnostic accuracy of a newly developed photofluorographic panoramic system with conventional panoramic radiography.

OBJECTIVES: To compare the diagnostic accuracy of a prototype photofluorographic panoramic system with that of a conventional panoramic system. METHODS: We used 14 human skulls with four artificial apical bone defects in each and 13 clinical cases with 21 periapical lesions. Six dental radiologists and six senior dental students rated the presence of defects on each image on a five-point scale. Receiver Operating Characteristic (ROC) analysis was performed and the area under each curve (Az) was compared as an index of accuracy. Statistical significance was set at P<0.05. RESULTS: There were no significant differences between the photofluorographic and the conventional panoramic systems (P=0.074) in detecting artificial apical defects. However, there were significant differences (P=0.03) in detecting natural defects. CONCLUSIONS: The diagnostic accuracy of the prototype photofluorographic panoramic system appears comparable with that of the conventional panoramic system. However, variability may arise from the observers' diagnostic experience and training.     

Improvement of radiologists' characterization of mammographic masses by using computer-aided diagnosis: an ROC study.

PURPOSE: To evaluate the effects of computer-aided diagnosis (CAD) on radiologists' classification of malignant and benign masses seen on mammograms. MATERIALS AND METHODS: The authors previously developed an automated computer program for estimation of the relative malignancy rating of masses. In the present study, the authors conducted observer performance experiments with receiver operating characteristic (ROC) methodology to evaluate the effects of computer estimates on radiologists' confidence ratings. Six radiologists assessed biopsy-proved masses with and without CAD. Two experiments, one with a single view and the other with two views, were conducted. The classification accuracy was quantified by using the area under the ROC curve, Az. RESULTS: For the reading of 238 images, the Az value for the computer classifier was 0.92. The radiologists' Az values ranged from 0.79 to 0.92 without CAD and improved to 0.87-0.96 with CAD. For the reading of a subset of 76 paired views, the radiologists' Az values ranged from 0.88 to 0.95 without CAD and improved to 0.93-0.97 with CAD. Improvements in the reading of the two sets of images were statistically significant (P = .022 and .007, respectively). An improved positive predictive value as a function of the false-negative fraction was predicted from the improved ROC curves. CONCLUSION: CAD may be useful for assisting radiologists in classification of masses and thereby potentially help reduce unnecessary biopsies.     

Variability in the interpretation of ultrasonography in patients with palpable noncalcified breast tumors

PURPOSE: To analyze interobserver variability of ultrasonography (US) as an adjunct to mammography in patients with palpable noncalcified breast tumors. MATERIAL AND METHODS: Mammographic, US, and combined reading of 200 patients with palpable noncalcified breast masses were performed independently by four experienced radiologists. Nonneoplastic abnormalities and mammographically obvious cancers were excluded. Receiver operating characteristic (ROC) analysis based on 115 tumors was carried out for mammography, US, and both combined for each radiologist. The US diagnoses of the 45 cancers excluded from ROC analysis and the 55 cancers included were compared. RESULTS: One radiologist revealed a significantly higher diagnostic performance with US than with mammography. Combined reading showed the highest performance for all observers, but the improvement as compared with mammography was significant for only two. Higher accuracy on combined reading was mainly caused by correct upgrading of tumors with benign or indeterminate mammographic findings. One radiologist had benefit of US for downgrading of tumors. All four radiologists made a malignant US diagnosis twice as often in mammographically obvious cancers than in mammographically nonconclusive tumors. CONCLUSION: Radiologists differ substantially in interpretation of breast imaging. Combined reading offers the highest diagnostic accuracy mainly by correct upgrading of tumors on US. The role of US for downgrading tumors is operator-dependent.     

Comparison of LCD and CRT monitors for detection of pulmonary nodules and interstitial lung diseases on digital chest radiographs by using receiver operating characteristic analysis

Soft copy reading of digital images has been practiced commonly in the PACS environment. In this study, we compared liquid-crystal display (LCD) and cathode-ray tube (CRT) monitors for detection of pulmonary nodules and interstitial lung diseases on digital chest radiographs by using receiver operating characteristic (ROC) analysis. Digital chest images with a 1000x1000 matrix size and a 8 bit grayscale were displayed on LCD/CRT monitor with 2M pixels in each observer test. Eight and ten radiologists participated in the observer tests for detection of nodules and interstitial diseases, respectively. In each observer test, radiologists marked their confidence levels for diagnosis of pulmonary nodules or interstitial diseases. The detection performance of radiologists was evaluated by ROC analyses. The average Az values (area under the ROC curve) in detecting pulmonary nodules with LCD and CRT monitors were 0.792 and 0.814, respectively. In addition, the average Az values in detecting interstitial diseases with LCD and CRT monitors were 0.951 and 0.953, respectively. There was no statistically significant difference between LCD and CRT for both detection of pulmonary nodules (P=0.522) and interstitial lung diseases (P=0.869). Therefore, we believe that the LCD monitor instead of the CRT monitor can be used for the diagnosis of pulmonary nodules and interstitial lung diseases in digital chest images.     

Breast cancer: effectiveness of computer-aided diagnosis observer study with independent database of mammograms

PURPOSE: To evaluate the effectiveness of a computerized classification method as an aid to radiologists reviewing clinical mammograms for which the diagnoses were unknown to both the radiologists and the computer. MATERIALS AND METHODS: Six mammographers and six community radiologists participated in an observer study. These 12 radiologists interpreted, with and without the computer aid, 110 cases that were unknown to both the 12 radiologist observers and the trained computer classification scheme. The radiologists' performances in differentiating between benign and malignant masses without and with the computer aid were evaluated with receiver operating characteristic (ROC) analysis. Two-tailed P values were calculated for the Student t test to indicate the statistical significance of the differences in performances with and without the computer aid. RESULTS: When the computer aid was used, the average performance of the 12 radiologists improved, as indicated by an increase in the area under the ROC curve (A(z)) from 0.93 to 0.96 (P <.001), by an increase in partial area under the ROC curve ((0.90)A(')(z)) from 0.56 to 0.72 (P <.001), and by an increase in sensitivity from 94% to 98% (P =.022). No statistically significant difference in specificity was found between readings with and those without computer aid (Delta = -0.014; P =.46; 95% CI: -0.054, 0.026), where Delta is difference in specificity. When we analyzed results from the mammographers and community radiologists as separate groups, a larger improvement was demonstrated for the community radiologists. CONCLUSION: Computer-aided diagnosis can potentially help radiologists improve their diagnostic accuracy in the task of differentiating between benign and malignant masses seen on mammograms.     

Real-time US elastography in the differentiation of suspicious microcalcifications on mammography

The purpose of this study was to retrospectively evaluate the use of US elastography in the differentiation of mammographically detected suspicious microcalcifications, using histology as the reference standard. Between May 2006 and April 2007, real-time US elasticity images were obtained in 77 patients (age range, 24–67 years; mean, 46 years) with 77 mammographically detected areas of microcalcifications (42 benign and 35 malignant lesions) prior to needle biopsy. Two experienced radiologists reviewed cine clips of elasticity and B-mode images and assigned an elasticity score of 1 to 3 in consensus, based on the degree of strain in the hypoechoic lesion without information of mammography and histology. For the elasticity score, the mean ± standard deviation was 1.5 ± 0.7 for benign and 2.7 ± 0.7 for malignant lesions (P < 0.001). When a cutoff point between elasticity scores of 1 and 2 was used, US elastography showed 97% (34/35) sensitivity, 62% (26/42) specificity, 68% (34/50) PPV, and 96% (26/27) NPV with an Az value of 0.852 (0.753–0.923, 95% confidence interval) in the differentiation of benign and malignant microcalcifications. Our results suggest that US elastography has the potential to differentiate benign and malignant lesions associated with microcalcifications detected at screening mammography.     

Prevalence of rupture of silicone gel breast implants revealed on MR imaging in a population of women in Birmingham, Alabama

OBJECTIVE. Silicone gel breast implants have been reported to rupture, but the prevalence of implant rupture in an unreferred population of women is not known. The objective of this study was to assess the prevalence of implant rupture and the presence of extracapsular silicone gel in an unreferred population of women without regard to the absence or presence of any local or systemic symptoms. SUBJECTS AND METHODS. Women identified as part of a National Cancer Institute cohort study on breast implants, living in the Birmingham, AL, area were invited to undergo MR imaging of their current silicone gel breast implants at the Kirklin Clinic at the University of Alabama at Birmingham. Three radiologists independently examined and rated all MR images for signs of implant rupture and extracapsular silicone. RESULTS. A total of 344 women with silicone gel breast implants underwent MR imaging. Breast implant rupture was reported by at least two of three radiologists for 378 (55.0%) of the 687 implants in this study. Another 50 implants (7.2%) were rated as indeterminate (suspicious) for rupture. A majority of women in this study, 265 (77.0%) of 344, had at least one breast implant that was rated as ruptured or indeterminate. Radiologists also agreed that silicone gel could be seen outside the fibrous capsule that forms around the implant in 85 (12.4%) of the 687 implants affecting 73 women (21.2%). Factors that affected implant rupture were implant age and location (submuscular or subglandular). The median implant age at rupture was estimated to be 10.8 years with a 95% confidence interval of 8.4-13.9 years. CONCLUSION. The prevalence of silent or occult silicone gel breast implant rupture is higher than was previously suspected. Most women in this study had MR imaging evidence of at least one ruptured silicone gel breast implant.     

胸部双能减影与常规数字X线摄影对信号检出效能的比较

目的比较双能减影(DES)与常规数字X线摄影(CDR)对信号的检出效能。方法将200个直径为4mm塑料小球作为信号分别置于塑料板和健康志愿者右胸上部摄取CDR和DES片。由3位放射科医师用5等级判别法各自独立阅片,用ROCkit软件对观察结果进行ROC曲线分析。结果当信号置于塑料板上时,CDR和DES的Az值分别为0.9931和0.9879,P值为0.4851(双尾)>0.05,差异无统计学意义。当信号置于右胸上部时,CDR和DES的Az值分别为0.7276和0.8561,P值为0.0002(双尾)<0.01,差异有统计学意义。结论DES可以去除肋骨对胸部信号的遮挡,使DES对胸部信号的检出能力明显高于CDR,提示DES在胸部的应用具有良好的前景。     

Computer-aided diagnosis to distinguish benign from malignant solitary pulmonary nodules on radiographs: ROC analysis of radiologists' performance--initial experience

PURPOSE: To evaluate radiologists' performance for determining a distinction between benign and malignant pulmonary nodules on chest radiographs without and with use of a computer-aided diagnosis scheme. MATERIALS AND METHODS: Fifty-three chest radiographs that depicted 31 primary lung cancers and 22 benign nodules were used. The likelihood measure of malignancy for each nodule was determined by using an automated computerized scheme. Sixteen radiologists (nine attending radiologists and seven radiology residents) participated in an observer study in which cases were interpreted first without and then with use of the scheme. The radiologists' performance was evaluated with receiver operating characteristic analysis. RESULTS: The mean area under the best-fit binormal receiver operating characteristic curve plotted in the unit square (Az) values of radiologists who interpreted images without and with the scheme were 0.743 and 0.817, respectively. The performance of radiologists was improved significantly when the scheme was used (P =.002). However, the performance (Az = 0.889) of the computer alone exceeded these results by a substantial margin. The average change in radiologists' confidence level for interpretation without and with the scheme was highly correlated (r = 0.845) with the likelihood measure of malignancy, which was presented as computer output. CONCLUSION: This scheme for computer-aided diagnosis has the potential to improve the accuracy of radiologists' performance in the classification of benign and malignant solitary pulmonary nodules.     

Wavelet compression of low-dose chest CT data: effect on lung nodule detection

PURPOSE: To assess the effect of using a lossy Joint Photographic Experts Group standard for wavelet image compression, JPEG2000, on pulmonary nodule detection at low-dose computed tomography (CT). MATERIALS AND METHODS: One hundred sets of lung CT data ("cases") were compressed to 30:1, 20:1, and 10:1 levels by using a wavelet-based JPEG2000 method, resulting in 400 test cases. Each case consisted of nine 1.25-mm sections that had been obtained with 20-40 mAs. Four thoracic radiologists independently interpreted the test case images. Performance was measured by using area under the receiver operating characteristic (ROC) curve (Az) and conventional sensitivity and specificity analyses. RESULTS: There were 51 cases with and 49 without lung nodules. Az values were 0.984, 0.988, 0.972, 0.921, respectively, for original and 10:1, 20:1, and 30:1 compressed images. Az values decreased significantly at 30:1 (P =.014) but not at 10:1 compression, with a trend toward significant decrease at 20:1 (P =.051). Specificity values were unaffected by compression (>98.0% at all compression levels). Sensitivity values were 86.3% (176 of 204 test cases with nodules), 77.9% (159 of 204 cases), 76.5% (156 of 204 cases), and 70.1% (143 of 204 cases), respectively, for original and 10:1, 20:1, and 30:1 compressed images. Results of logistic regression model analysis confirmed the significant effects of compression rate and nodule attenuation, size, and location on sensitivity (P <.05). CONCLUSION: While no reduction in nodule detection at 10:1 compression levels was demonstrated by using ROC analysis, a significant decrease in sensitivity was identified. Further investigation is needed before widespread use of image compression technology in low-dose chest CT can be recommended.     

Diagnosis of gastric cancers: comparison of conventional radiography and digital radiography with a 4 million-pixel charge-coupled device

PURPOSE: To evaluate the differences in accuracy and observer performance at conventional radiography and at digital radiography with a 4 million-pixel charge-coupled device (CCD) for the diagnosis of gastric cancers. MATERIALS AND METHODS: A prospective study was performed of 225 patients with suspected gastric cancer who were referred to our hospital from January 1997 through February 1997. One hundred twelve patients were examined at conventional radiography and 113 were examined at digital radiography, and 24 and 27 patients had gastric cancer, respectively. Six radiologists interpreted the images, with attention to tumor findings. They were blinded to the clinical details, and their interpretations were rated against those of three other radiologists who examined the patients and who were aware of the clinical information such as endoscopic features and/or histopathologic findings in biopsy specimens. Receiver operating characteristic (ROC) analysis was used to compare the differences in observer performance for the diagnosis of gastric cancers at conventional radiography and at digital radiography. RESULTS: The overall sensitivity was 64.6% at conventional radiography versus 75.3% at digital radiography (P =. 287); specificities were 84.5% and 90.5%, respectively (P =.011); and the positive predictive values were 53.1% and 71.3%, respectively (P =.036). ROC analysis clearly showed higher diagnostic performance at digital radiography than at conventional radiography. CONCLUSION: The data demonstrate the high diagnostic value of digital radiography with a 4 million-pixel CCD for gastric cancers. The technique has considerable potential as an alternative to conventional gastrointestinal radiography.     

Optimizing parameters for computer-aided diagnosis of microcalcifications at mammography

RATIONALE AND OBJECTIVES: The purpose of this study was to optimize selection of the mammographic features most useful in discriminating benign from malignant clustered microcalcifications. MATERIALS AND METHODS: The computer-aided diagnosis (CAD) system automatically extracted from digitized mammograms 13 quantitative features characterizing microcalcification clusters. Archival cases (n = 134; patient age range, 31-77 years; mean age, 56.8 years) with known histopathologic results (79 malignant, 55 benign) were selected. Three radiologists at three facilities independently analyzed the microcalcifications by using the CAD system. Stepwise discriminant analysis selected the features best discriminating benign from malignant microcalcifications. A classification scheme was constructed on the basis of these optimized features, and its performance was evaluated by using receiver operating characteristic (ROC) analysis. RESULTS: Six of the 13 variables extracted by the CAD system were selected by stepwise determinant analysis for generating the classification scheme, which yielded an ROC curve with an area (Az) of 0.98, specificity of 83.64%, positive predictive value of 89.53%, and accuracy of 91.79% for 98% sensitivity. When patient age was an additional variable, the scheme's performance improved, but this was not statistically significant (Az = 0.98). The ROC curve of the classifier (without age as an additional variable) yielded a high Az of 0.96 for patients younger than 50 years and an even higher (P < .02) Az of 0.99 for those 50 years or older. CONCLUSION: Stepwise discriminant analysis optimized performance of a classification scheme for microcalcifications by selecting six optimized features. Scheme performance was significantly (P < .02) higher for women 50 years or older, but the addition of patient age as a variable did not produce a statistically significant increase in performance.     

Quantitative characterization of mass lesions on digitized mammograms for computer-assisted diagnosis

RATIONALE AND OBJECTIVES: To investigate features for discriminating benign from malignant mammographic findings by using computer-aided diagnosis (CAD) and to test the accuracy of CAD interpretations of mass lesions. METHODS: Fifty-five sequential, mammographically detected mass lesions, referred for biopsy, were digitized for computerized reevaluation with a CAD system. Quantitative features that characterize spiculation were automatically extracted by the CAD system. Data generated by 271 known retrospective cases were used to set reference values indicating the range for malignant and benign lesions. After conventional interpretation of the 55 prospective cases, they were evaluated a second time by the radiologist using the extracted features and the reference ranges. In addition, a pattern-recognition scheme based on the extracted features was used to classify the prospective cases. Accuracy of interpretation with and without the CAD system was evaluated using receiver operating characteristic (ROC) curve analysis. RESULTS: Sensitivity of the CAD diagnosis for the prospective cases improved from 92% to 100%. Specificity improved significantly from 26.7% to 66.7%. This was accompanied by a significant increase in the accuracy of diagnosis from 56.4% to 81.8% and in the positive predictive value from 51.1% to 71.4%. The Az for the CAD ROC curve significantly increased from 0.73 to 0.90. The performance of the classification scheme was slightly lower than that of the radiologists' interpretation with the CAD system. CONCLUSIONS: Use of the CAD system significantly improved the accuracy of diagnosis. The findings suggest that the classification scheme may improve the radiologist's ability to differentiate benign from malignant mass lesions in the interpretation of mammograms.     

Incidental findings on sonography of the breast: clinical significance and diagnostic workup.

OBJECTIVE: The purpose of this study was to determine how often physician-performed high-resolution sonography can detect nonpalpable breast lesions not revealed by mammography. A sonographic classification scheme was tested for its accuracy in predicting malignancy of incidentally detected breast lesions. SUBJECTS AND METHODS: Six thousand one hundred thirteen asymptomatic women with breast density grades 2-4 and 687 patients with palpable or mammographically detected breast masses underwent sonography as an adjunct to mammography. All sonographically detected, clinically and mammographically occult breast lesions that were not simple cysts were prospectively classified into benign, indeterminate, or malignant categories. Diagnoses were confirmed by sonographically guided fine-needle aspiration or core needle biopsy. RESULTS: In 6113 asymptomatic women, 23 malignancies in 21 patients were detected with sonography only (prevalence, 0.31%). Five additional malignant lesions were found in patients with a malignant (n = 3) or a benign (n = 2) palpable or mammographically detected index lesion. The mean size of invasive malignancies detected only by sonography was 9.1 mm, which was not significantly different from the mean size of invasive cancers detected by mammography (p = .07). The sensitivity of the prospective sonographic classification for malignancy was 100%, and the specificity was 33.5%. CONCLUSION: The use of high-resolution sonography as an adjunct to mammography in women with dense breasts may lead to detection of a significant number of otherwise occult malignancies that are no different in size from nonpalpable mammographically detected lesions. Prospective classification of these lesions based on sonographic characteristics results in a significant reduction in number of unnecessary biopsies performed.     

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.