Performance of a Method to Standardize Breast Ultrasound Interpretation Using Image Processing and Case-Based Reasoning
Our computer-aided diagnostic (CADx) tool uses advanced image processing and artificial intelligence to analyze findings on breast sonography images. The goal is to standardize reporting of such findings using well-defined descriptors and to improve accuracy and reproducibility of interpretation of breast ultrasound by radiologists. This study examined several factors that may impact accuracy and reproducibility of the CADx software, which proved to be highly accurate and stabile over several operating conditions.
KeywordsBreast cancer Sonography Computer-aided diagnosis Image processing Relative similarity ROC analysis Segmentation Case-based reasoning
This work was supported in part by grant 2R44CA112858 from the National Institutes of Health, National Cancer Institute, USA and by the Gustavus and Louise Pfeiffer Research Foundation, Denville, NJ, USA.
We gratefully acknowledge the support of Julie Phan, B.S., Paul Feigin, Ph.D., Paul Clopton, M.S. and Janice J. André, M.S. during discussions of the details of this work.
- 1.Stavros, A.T., Thickman, D., Rapp, C.L., Dennis, M.A., Parker, S.H., Sisney, G.A.: Solid breast nodules: Use of sonography to distinguish between benign and malignant lesions. Radiology 196, 123–134 (1995)Google Scholar
- 6.American College of Radiology: ACR Standards 2000–2001. Reston, VA: American College of Radiology (2000)Google Scholar