Almen Laboratories has developed a computer-aided tool for breast ultrasound image analysis that operates with the physician in the loop. The system compares a breast mass in question to a database of patient lesion images with verified known findings, displays those most similar to it and then computes CAD assessment of the lesion in question following the American College of Radiologists and FDA approved BI-RADS Lexicon, Classification and method. The computed assessment is based on confirmed findings of the retrieved similar cases. Our approach has considerable appeal and may be more readily acceptable to radiologists because it does clearly show which factors have led to the recommendation or classification. This allows the radiologist the option to consider the findings with higher confidence and to apply her/his own threshold for a decision. In the future, development of the proposed system may advance the application into the diagnostic area, for detection of suspicious masses, for more accurate disease diagnosis following interpretive guidelines and a validated clinical database, even to other imaging problems.
The accuracy of decision making and interpretation of breast ultrasound can be significantly improved by following implementation of a structured method for breast lesion description and interpretation through application of a computer-aided imaging system based on BI-RADS lexicon guidelines. The system also provides a computerized assessment of lesion (CLA) in question (also in some publications referred as as Level of Suspicion (LOS) for cancer) using these same guidelines. Our approach applies a database of verified known findings to which an unknown may be compared and evaluated. Storage and retrieval of these images is accomplished through identification of key information content of the breast masses themselves (case-based reasoning). We suggest that lesions of lower suspicion level such as intra-cystic masse (complex cysts) and fibroadenoma may be ruled out as candidates for biopsy with higher degree of confidence when image interpretation is made with support of this computer-aided imaging system.
For more information about the company please