RATIONALE AND OBJECTIVES: The authors evaluated the effect of optimal neural network architecture selection on the performance of a computer-aided diagnostic system designed to detect microcalcification clusters on digitized mammograms. MATERIALS AND METHODS: The authors developed a computer program to detect microcalcification clusters automatically on digitized mammograms. Previously, they found that a properly selected and trained convolution neural network (CNN) could reduce false-positive (FP) findings and therefore improve the accuracy of microcalcification detection. In the current study, they evaluated the effectiveness of the CNN optimized with an automated optimization technique in improving the accuracy of the microcalcification detection program, comparing it with the manually selected CNN. An independent test data set was used, which included 472 mammograms selected from the University of South Florida public database and contained 253 biopsy-proved malignant clusters. RESULTS: At an FP rate of 0.7 cluster per image, the film-based sensitivity was 84.6% for the optimized CNN, compared with 77.2% for the manually selected CNN. For clusters imaged on both craniocaudal and mediolateral oblique views, a cluster could be considered detected when it was detected on one or both views. For this case-based approach, at an FP rate of 0.7 per image, the sensitivity was 93.3% for the optimized and 87.0% for the manually selected CNN. CONCLUSION: The classification of true and false signals is an important step in the microcalcification detection program. An optimized CNN can effectively reduce FP findings and improve the accuracy of the computer-aided detection system.
RATIONALE AND OBJECTIVES: The authors evaluated the effect of optimal neural network architecture selection on the performance of a computer-aided diagnostic system designed to detect microcalcification clusters on digitized mammograms. MATERIALS AND METHODS: The authors developed a computer program to detect microcalcification clusters automatically on digitized mammograms. Previously, they found that a properly selected and trained convolution neural network (CNN) could reduce false-positive (FP) findings and therefore improve the accuracy of microcalcification detection. In the current study, they evaluated the effectiveness of the CNN optimized with an automated optimization technique in improving the accuracy of the microcalcification detection program, comparing it with the manually selected CNN. An independent test data set was used, which included 472 mammograms selected from the University of South Florida public database and contained 253 biopsy-proved malignant clusters. RESULTS: At an FP rate of 0.7 cluster per image, the film-based sensitivity was 84.6% for the optimized CNN, compared with 77.2% for the manually selected CNN. For clusters imaged on both craniocaudal and mediolateral oblique views, a cluster could be considered detected when it was detected on one or both views. For this case-based approach, at an FP rate of 0.7 per image, the sensitivity was 93.3% for the optimized and 87.0% for the manually selected CNN. CONCLUSION: The classification of true and false signals is an important step in the microcalcification detection program. An optimized CNN can effectively reduce FP findings and improve the accuracy of the computer-aided detection system.
Authors: Ravi K Samala; Heang-Ping Chan; Yao Lu; Lubomir M Hadjiiski; Jun Wei; Mark A Helvie Journal: Phys Med Biol Date: 2014-11-13 Impact factor: 3.609
Authors: Jun Ge; Lubomir M Hadjiiski; Berkman Sahiner; Jun Wei; Mark A Helvie; Chuan Zhou; Heang-Ping Chan Journal: Phys Med Biol Date: 2007-01-23 Impact factor: 3.609
Authors: Ravi K Samala; Heang-Ping Chan; Yao Lu; Lubomir M Hadjiiski; Jun Wei; Mark A Helvie Journal: Phys Med Biol Date: 2015-10-14 Impact factor: 3.609
Authors: Marshall N Gordon; Lubomir M Hadjiiski; Kenny H Cha; Ravi K Samala; Heang-Ping Chan; Richard H Cohan; Elaine M Caoili Journal: Med Phys Date: 2019-01-04 Impact factor: 4.071