Computer-aided classification of BI-RADS category 3 breast lesions

Application of computer-aided diagnosis to predict malignancy in BI-RADS 3 breast lesions

Purpose

To evaluate the ability of computer-aided diagnosis (CAD) system (S-Detect) to identify malignancy in ultrasound (US) -detected BI-RADS 3 breast lesions.

Materials and methods

148 patients with 148 breast lesions categorized as BI-RADS 3 were included in the study between January 2021 and September 2022. The malignancy rate, accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and area under the curve (AUC) were calculated.

Results

In this study, 143 breast lesions were found to be benign, and 5 breast lesions were malignant (malignancy rate, 3.4 %, 95 % confidence interval (CI): 0.5-6.3). The malignancy rate rose significantly to 18.2 % (4/22, 95 % CI: 2.1-34.3) in the high-risk group with a "possibly malignant" CAD result (p = 0.017). With a "possibly benign" CAD result, the malignancy rate decreased to 0.8 % (1/126, 95 % CI: 0-2.2) in the low-risk group (p = 0.297). The AUC, sensitivity, specificity, accuracy, PPV, and NPV of the CAD system in BI-RADS 3 breast lesions were 0.837 (95 % CI: 77.7-89.6), 80.0 % (95 % CI: 73.6-86.4), 87.4 % (95 % CI: 82.0-92.7), 87.2 % (95 % CI: 81.8-92.6), 18.2 % (95 % CI: 2.1-34.3) and 99.2 % (95 % CI: 97.8-100.0), respectively.

Conclusions

CAD system (S-Detect) enables radiologists to distinguish a high-risk group and a low-risk group among US-detected BI-RADS 3 breast lesions, so that patients in the low-risk group can receive follow-up without anxiety, while those in the high-risk group with a significantly increased malignancy rate should actively receive biopsy to avoid delayed diagnosis of breast cancer.

An AI model of sonographer’s evaluation+ S-Detect + elastography + clinical information improves the preoperative identification of benign and malignant breast masses

Purpose

The purpose of the study was to build an AI model with selected preoperative clinical features to further improve the accuracy of the assessment of benign and malignant breast nodules.

Methods

Patients who underwent ultrasound, strain elastography, and S-Detect before ultrasound-guided biopsy or surgical excision were enrolled. The diagnosis model was built using a logistic regression model. The diagnostic performances of different models were evaluated and compared.

Results

A total of 179 lesions (101 benign and 78 malignant) were included. The whole dataset consisted of a training set (145 patients) and an independent test set (34 patients). The AI models constructed based on clinical features, ultrasound features, and strain elastography to predict and classify benign and malignant breast nodules had ROC AUCs of 0.87, 0.81, and 0.79 in the test set. The AUCs of the sonographer and S-Detect were 0.75 and 0.82, respectively, in the test set. The AUC of the combined AI model with the best performance was 0.89 in the test set. The combined AI model showed a better specificity of 0.92 than the other models. The sonographer’s assessment showed better sensitivity (0.97 in the test set).

Conclusion

The combined AI model could improve the preoperative identification of benign and malignant breast masses and may reduce unnecessary breast biopsies.

A computer-aided diagnosis system using artificial intelligence for the diagnosis and characterization of breast masses on ultrasound: Added value for the inexperienced breast radiologist

To evaluate the value of the computer-aided diagnosis (CAD) program applied to diagnostic breast ultrasonography (US) based on operator experience.US images of 100 breast masses from 91 women over 2 months (from May to June 2015) were collected and retrospectively analyzed. Three less experienced and 2 experienced breast imaging radiologists analyzed the US features of the breast masses without and with CAD according to the Breast Imaging Reporting and Data System (BI-RADS) lexicon and categories. We then compared the diagnostic performance between the experienced and less experienced radiologists and analyzed the interobserver agreement among the radiologists.Of the 100 breast masses, 41 (41%) were malignant and 59 (59%) were benign. Compared with the experienced radiologists, the less experienced radiologists had significantly improved negative predictive value (86.7%-94.7% vs 53.3%-76.2%, respectively) and area under receiver operating characteristics curve (0.823-0.839 vs 0.623-0.759, respectively) with CAD assistance (all P < .05). In contrast, experienced radiologists had significantly improved specificity (52.5% and 54.2% vs 66.1% and 66.1%) and positive predictive value (55.6% and 58.5% vs 64.9% and 64.9%, respectively) with CAD assistance (all P < .05). Interobserver variability of US features and final assessment by categories were significantly improved and moderate agreement was seen in the final assessment after CAD combination regardless of the radiologist's experience.CAD is a useful additional diagnostic tool for breast US in all radiologists, with benefits differing depending on the radiologist's level of experience. In this study, CAD improved the interobserver agreement and showed acceptable agreement in the characterization of breast masses.

Computer-aided diagnosis program for classifying the risk of hepatocellular carcinoma on MR images following liver imaging reporting and data system (LI-RADS)

PURPOSE

To develop and evaluate a computer-aided diagnosis (CAD) program for liver lesions on magnetic resonance (MR) images for classification of the risk of hepatocellular carcinoma (HCC) following the liver imaging reporting and data system (LI-RADS).

MATERIALS AND METHODS

Liver MR images from 41 patients with hyperenhancing liver lesions categorized as LR 3, 4, and 5 were evaluated by two radiologists. The major LI-RADS features of each index liver lesion were recorded, including size (maximum transverse diameter), presence of hyperenhancement, washout appearance, and capsule appearance. A CAD program was implemented to register MR images at different contrast-enhancement phases, segment liver lesions, extract lesion features, and classify lesions according to LI-RADS. The LI-RADS features quantified by CAD were compared with those assessed by radiologists using the intraclass correlation coefficient (ICC) and receiver operator curve (ROC) analyses. The LI-RADS categorization between CAD and radiologists was evaluated using the weighted Cohen's kappa coefficient.

RESULTS

The mean and standard deviation of the lesion diameters were 21 ± 11 mm (range, 7-70 mm) by radiologists and 22 ± 11 mm (range, 8-72 mm) by CAD (ICC, 0.96-0.97). The area under the curve (AUC) for the washout assessment by CAD was 0.79-0.93 with sensitivity 0.69-0.82 and specificity 0.79-1. The AUC for the capsule assessment by CAD was 0.79-0.9 with sensitivity 0.75-0.9 and specificity 0.82-0.96. The classifications by the radiologists and CAD coincided in 76-83% lesions (k = 0.57-0.71), while the agreements between radiologists were in 78% lesions (k = 0.59).

CONCLUSION

We developed a CAD program for liver lesions on MR images and showed a substantial agreement in the LI-RADS-based classification of the risk of HCCs between the CAD and radiologists.

LEVEL OF EVIDENCE

1 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2018;47:710-722.

Downgrading BIRADS 3 to BIRADS 2 category using a computer-aided microcalcification analysis and risk assessment system for early breast cancer

This paper explores the potential of a computer-aided diagnosis system to discriminate the real benign microcalcifications among a specific subset of 109 patients with BIRADS 3 mammograms who had undergone biopsy, thus making it possible to downgrade them to BIRADS 2 category. The system detected and quantified critical features of microcalcifications and classified them on a risk percentage scale for malignancy. The system successfully detected all cancers. Nevertheless, it suggested biopsy for 11/15 atypical lesions. Finally, the system characterized as definitely benign (BIRADS 2) 29/88 benign lesions, previously assigned to BIRADS 3, and thus achieved a reduction of 33% in unnecessary biopsies.

Probabilistic computer model developed from clinical data in national mammography database format to classify mammographic findings

PURPOSE

To determine whether a Bayesian network trained on a large database of patient demographic risk factors and radiologist-observed findings from consecutive clinical mammography examinations can exceed radiologist performance in the classification of mammographic findings as benign or malignant.

MATERIALS AND METHODS

The institutional review board exempted this HIPAA-compliant retrospective study from requiring informed consent. Structured reports from 48 744 consecutive pooled screening and diagnostic mammography examinations in 18 269 patients from April 5, 1999 to February 9, 2004 were collected. Mammographic findings were matched with a state cancer registry, which served as the reference standard. By using 10-fold cross validation, the Bayesian network was tested and trained to estimate breast cancer risk by using demographic risk factors (age, family and personal history of breast cancer, and use of hormone replacement therapy) and mammographic findings recorded in the Breast Imaging Reporting and Data System lexicon. The performance of radiologists compared with the Bayesian network was evaluated by using area under the receiver operating characteristic curve (AUC), sensitivity, and specificity.

RESULTS

The Bayesian network significantly exceeded the performance of interpreting radiologists in terms of AUC (0.960 vs 0.939, P = .002), sensitivity (90.0% vs 85.3%, P < .001), and specificity (93.0% vs 88.1%, P < .001).

CONCLUSION

On the basis of prospectively collected variables, the evaluated Bayesian network can predict the probability of breast cancer and exceed interpreting radiologist performance. Bayesian networks may help radiologists improve mammographic interpretation.

Computer aided classification system for breast ultrasound based on Breast Imaging Reporting and Data System (BI-RADS)

Clinically, the ultrasound findings are evaluated by its sonographic characteristics and then assigned to assessment categories according to the definitions of Breast Imaging Reporting and Data System (BI-RADS) developed by the American College of Radiology. In this study, a computer-aided classification (CAC) system was proposed to classify the masses into assessment categories 3, 4 and 5, which simulated the clinical diagnosis of radiologists. Compared with current computer-aided diagnosis systems, the proposed CAC system classifies the indeterminate cases into BI-RADS category 4 for further diagnosis. Six hundred twenty-six cases were collected from three ultrasound systems and confirmed by pathology and retrospectively classified into categories 3, 4 and 5 by radiologists. The multinomial logistic regression model was trained as the CAC system for predicting the assessment category from the computerized BI-RADS features and from a set of machine-dependent factors. By using the machine-dependent factors to indicate the adopted ultrasound systems, the same regression model could be applied for the cases acquired from different ultrasound systems. A basic CAC system was trained by using the classification result of radiologists. A weighted CAC system, to improve the capacity of the basic CAC system in differentiating benign from malignant lesions, was trained by adding the pathologic result. Between the radiologists and the basic CAC system, a substantial agreement was indicated by Cohen's kappa statistic and the differences in either the performance indices or the A(Z) of receiver operating characteristic (ROC) analysis were not statistically significant. For the weighted CAC system, the performance indices accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) were 73.00% (457 of 626), 98.17% (215 of 219), 59.46% (242 of 407), 56.58% (215 of 380) and 98.37% (242 of 246), respectively; the A(Z) was 0.94; and the correlation with the radiologists was also substantial agreement. The indices accuracy and specificity of weighted CAC system, compared with those of the radiologists, were improved by 5.91% and 8.85%, respectively and the indices of sensitivity and NPV, compared with those of a conventional CAD system, were improved by 10.5% and 5.21%, respectively; all improvements were statistically significant. To classify the mass into BI-RADS assessment categories by the CAC system is feasible. Moreover, the proposed CAC system is flexible because it can be used to diagnose the cases acquired from different ultrasound systems.

BI-RADS: Use in the French radiologic community

In the United States, BI-RADS (Breast Imaging Reporting and Data System) has been set up as a quality assurance system for better communication between professionals and for the follow-up of breast screening programs. It has become a reference in the field of mammographic imaging and has been adopted by several countries throughout the world. It has been translated in French. The aim of this article is to discuss the difficulties in using it in the French radiologic communities. There are few problems with vocabulary excepted for microcalcifications. BI-RADS includes a guidance chapter giving some recommendations for using properly the lexicon. Classification of normal breast remains of concern, as it is difficult to evaluate precisely the content of fat and as the final image is also dependant of technical factors. The main difficulties are related to final classification in BI-RADS categories as the lexicon does not explicit which mammographic features should be included in the categories from three to five. In France, a table concerning the classification of mammographic abnormalities has been established by the HAS (former ANAES) which represents the highest scientific health authority in France. There are no major problems for using the BI-RADS for US and MRI. BI-RADS is suitable for different categories of women and for male and training has an important impact on acceptance and proper use of the lexicon.

Abnormal mammographic findings with short-interval follow-up recommendation

An abnormal Breast Imaging and Reporting Data System (BIRADS) category 3 mammogram with a short interval follow-up recommendation is a common finding seen in approximately 40% of women for each decade of screening. Factors associated with category 3 mammograms include mammography examination features, tendencies of the interpreting physician, and features of the country's health care system and the screened population including age, family history, previous biopsies, obesity, and menopausal hormone therapy. Recently, the degree to which a BIRADS category 3 mammographic result provides differential breast cancer risk compared with normal mammographic categories (BIRADS category 1 or 2) has been questioned. The yield of category 3 mammographic results could potentially be increased by more uniform performance of additional imaging workup (additional views and/or ultrasonography). In addition, other strategies to more accurately characterize the risk of breast cancer in women with category 3 mammographic results are under evaluation and including magnetic resonance imaging, computer-aided classification systems, and digital tomosynthesis. Given the potential psychologic impact of abnormal mammographic results, studies attempting to more accurately relate screening mammography findings to breast cancer risk are a priority.

[Mammographic stable lesions and carcinomas]

Stable breast carcinomas at mammography are infrequent and typically correspond to low-grade non-invasive neoplasms. Diagnosis may be delayed by several months to a few years. This time delay to diagnosis may be reduced by using optimal mammographic technique and careful image interpretation. These lesions frequently are misclassified as BIRADS class III lesions. Comparison with prior mammograms is mandatory for accurate diagnosis of these lesions.

Viscoelastic imaging of breast tumor microenvironment with ultrasound

Imaging systems are most effective for detection and classification when they exploit contrast mechanisms specific to particular disease processes. A common example is mammography, where the contrast depends on local changes in cell density and the presence of microcalcifications. Unfortunately the specificity for classifying malignant breast disease is relatively low for many current diagnostic techniques. This paper describes a new ultrasonic technique for imaging the viscoelastic properties of breast tissue. The mechanical properties of glandular breast tissue, like most biopolymers, react to mechanical stimuli in a manner specific to the microenvironment of the tissue. Elastic properties allow noninvasive imaging of desmoplasia while viscous properties describe metabolism-dependent features such as pH. These ultrasonic methods are providing new tools for studying disease mechanisms as well as improving diagnosis.