OBJECTIVE: The purpose of this study was to assess the features of breast lesion texture on sonographic images of patients submitted to breast-conserving surgery, with or without tumor recurrence. MATERIALS AND METHODS: Sonographic images of 36 patients submitted to conservative surgery for breast cancer, 12 of them with, and 24 without local recurrence, included 3 contralateral malignant lesions, 7 benign lumps (3 cysts and 4 fibroadenomas), 5 atypical hyperplasias and 9 fibrocystic changes. The quantification of features of breast lesion texture was based on ten parameters calculated from gray-level co-occurrence matrix and complexity curve. Linear discriminant analysis was applied to the texture parameters for differentiating between breast lesions in women submitted to conservative surgery with and without tumor recurrence. RESULTS: The assessment of performance of texture parameters in distinguishing lesion recurrences in a group including benign lumps and atypical hyperplasias demonstrated specificity of 100%, and accuracy and sensitivity > 91%. Another test demonstrated that texture parameters were useful in the differentiation between atypical hyperplasias and benign lumps. CONCLUSION: Despite the limited number of cases, the present results can be considered as promising, suggesting that texture parameters may help in the differentiation among benign lumps, atypical hyperplasias and recurrent malignant lesions.

Keywords: Computer-assisted image processing, Computer-assisted image interpretation, Computer-assisted decision making, Recurrence, Breast ultrasonography

Objective: To assess the performance of morphometric parameters calculated from breast lesion contours at ultrasonography, in the quantification of morphological features and in the distinction among BI-RADS categories 2, 3, 4 and 5. Materials and Methods: The present casuistry included 40 cases, with orthogonal imaging of patients submitted to surgery. Based on the lesions segmentation, the following five morphometric parameters were calculated: area ratio, overlap ratio, normalized residual value, circularity and depth-to-width ratio. Linear discriminant analysis was applied to select the best parameters, and ROC curve was utilized as figure of merit. Results: Overlap ratio was able to statistically distinguish breast lesions classified as BI-RADS 3 from others classified as BI-RADS 4 (α = 5%; p = 0.015). Additionally, such parameter presented the best performance in the differentiation between malignant and benign breast lesions. Conclusion: These results indicate that morphometric analysis of breast lesions at ultrasonography seems to be helpful in distinguishing patients who should undergo biopsy from those to be followed-up only with imaging methods.

Keywords: Breast ultrasonography; BI-RADS; Computer-assisted image processing; Computer-assisted image interpretation.

Mammography is the best method for early detection of breast cancer. Nevertheless, approximately 10% to 30% of breast lesions are missed at screening due to limitations of human observers. Computer-aided detection (CAD) is a relatively new technology that has been implemented in some mammography services to allow a double reading of mammograms. Clinical studies have demonstrated that CAD increases the sensitivity by up to 21% in the detection of breast cancer by radiologists. A CAD system is useful in situations where there is a high interobserver variability, lack of trained observers, or impossibility to perform the double reading with two or more radiologists. The objective of the present review is based on the need to get the medical community acquainted with this tool as an auxiliary, quantitative and non-operator-dependent method, to improve the diagnosis of breast cancer.

Keywords: Breast cancer; CAD; Double reading.