Purpose: Accurate and early detection of breast cancer using effective imaging modalities is an active area of research in medical image analysis. Computeraided diagnosis (CAD) of breast cancer using digital mammograms may help in early diagnosis and can assist in maintaining patient health. The breast imaging reporting and data system (BIRADS) is widely used for risk assessment and classification grading in breast cancer screening. It contains seven different grading systems for breast cancer risk assessment. These range from grade 0 (incomplete) to grade 6 (proven malignancy). All other intermediate stages state the progression of risk. Methods: The current research results have shown that two-dimensional synthesized mammogram (2DSM) imaging and conventional full-field digital mammography (FFDM) are two important imaging modalities which can be used for screening breast cancer. To the best of our knowledge, there is no study which has yet compared the BIRADS discrimination power of 2DSM and FFDM imaging modalities. In this paper we present a novel CAD-based comparative study, using texton and gist for the characterization of breast cancer with 2DSM and FFDM imagery. Results: The developed method achieved an average performance of 92.9% accuracy using a probabilistic neural network classifier for FFDM images with tenfold crossvalidation. Hence, our proposed model showed that FFDM images are more effective than the 2DSM imaging modality in discriminating BIRADS grades. Conclusion: The obtained results confirmed that our method performed well in the early detection of breast cancer. Consequently, it can be used as a distinct system in rural hospitals.
All Science Journal Classification (ASJC) codes
- Control and Systems Engineering
- Theoretical Computer Science
- Computational Theory and Mathematics
- Artificial Intelligence