论文信息 - Comparison of BI-RADS Lesion Descriptors and Computer-Extracted Image Features for Automated Classification of Malignant and Benign Breast Lesions

Comparison of BI-RADS Lesion Descriptors and Computer-Extracted Image Features for Automated Classification of Malignant and Benign Breast Lesions

We compared Breast Imaging Report and Data System (BI-RADS) lesion descriptors provided by radiologists and image features extracted by a computer for computer classification of breast lesions as malignant or benign. Our results indicate that combining the BI-RADS lesion descriptors provided by radiologists and the computer-extracted image features produced the best computer classification performance.

[1] M. Giger,et al. Improving breast cancer diagnosis with computer-aided diagnosis. , 1999, Academic radiology.

[2] M. Giger,et al. Breast cancer: effectiveness of computer-aided diagnosis observer study with independent database of mammograms. , 2002, Radiology.

[3] Maryellen L. Giger,et al. Ideal observer approximation using Bayesian classification neural networks , 2001, IEEE Transactions on Medical Imaging.

[4] C. Floyd,et al. Breast imaging reporting and data system standardized mammography lexicon: observer variability in lesion description. , 1996, AJR. American journal of roentgenology.

[5] M. Giger,et al. Automated computerized classification of malignant and benign masses on digitized mammograms. , 1998, Academic radiology.

[6] P. Langenberg,et al. Breast Imaging Reporting and Data System: inter- and intraobserver variability in feature analysis and final assessment. , 2000, AJR. American journal of roentgenology.

[7] M. Giger,et al. Malignant and benign clustered microcalcifications: automated feature analysis and classification. , 1996, Radiology.

[8] C. Floyd,et al. Artificial neural network: improving the quality of breast biopsy recommendations. , 1996, Radiology.