Detection and Weak Segmentation of Masses in Gray-Scale Breast Mammogram Images Using Deep Learning
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Purpose: In this paper, we propose deep-learning methodology with which to enhance the mass differentiation performance of convolutional neural network (CNN)-based architecture. Materials and Methods: We differentiated breast mass lesions from gray-scale X-ray mammography images based on regions of interest (ROIs). Our dataset comprised breast mammogram images for 150 cases of malignant masses from which we extracted the mass ROI, and we composed a CNN-based deep learning model trained on this dataset to identify ROI mass lesions. The test dataset was created by shifting some of the training data images. Thus, although both datasets were different, they retained a deep structural similarity. We then applied our trained deep-learning model to detect masses on 8-bit mammogram images containing malignant masses. The input images were preprocessed by applying a scaling parameter of intensity before being used to train the CNN model for mass differentiation. Results: The highest area under the receiver operating characteristic curve was 0.897 (Î 20). Conclusion: Our results indicated that the proposed patch-wise detection method can be utilized as a mass detection and segmentation tool.
Abstract
Purpose: In this paper, we propose deep-learning methodology with which to enhance the mass differentiation performance of convolutional neural network (CNN)-based architecture. Materials and Methods: We differentiated breast mass lesions from gray-scale X-ray mammography images based on regions of interest (ROIs). Our dataset comprised breast mammogram images for 150 cases of malignant masses from which we extracted the mass ROI, and we composed a CNN-based deep learning model trained on this dataset to identify ROI mass lesions. The test dataset was created by shifting some of the training data images. Thus, although both datasets were different, they retained a deep structural similarity. We then applied our trained deep-learning model to detect masses on 8-bit mammogram images containing malignant masses. The input images were preprocessed by applying a scaling parameter of intensity before being used to train the CNN model for mass differentiation. Results: The highest area under the receiver operating characteristic curve was 0.897 (Î 20). Conclusion: Our results indicated that the proposed patch-wise detection method can be utilized as a mass detection and segmentation tool.
참고문헌 (37)
- [URL]
- Ferlay J, "Cancer incidence and mortality worldwide : sources, methods and major patterns in GLOBOCAN 2012", Int J Cancer, 136, pp.E359~E386 (2015)
- Cheng HD, "Computer-aided detection and classification of microcalcifications in mammograms : a survey", Pattern Recognit, 36, pp.2967~2991 (2003)
- Cheng HD, "Approaches for automated detection and classification of masses in mammograms", Pattern Recognit, 39, pp.646~668 (2006)
- Zheng B, "Comparison of artificial neural network and Bayesian belief network in a computerassisted diagnosis scheme for mammography", Proceedings of the IJCNN’99. International Joint Conference on Neural Networks, pp.4181~4185 (1999)
- Egan RL, "Breast cancer mammography patterns", Cancer, 40, pp.2087~2090 (1977)
- Wolfe JN, "Breast patterns as an index of risk for developing breast cancer", AJR Am J Roentgenol, 126, pp.1130~1137 (1976)
- Petrick N, "An adaptive density-weighted contrast enhancement filter for mammographic breast mass detection", IEEE Trans Med Imaging, 15, pp.59~67 (1996)
- Li HD, "Markov random field for tumor detection in digital mammography", IEEE Trans Med Imaging, 14, pp.565~576 (1995)
- Rojas Domínguez A, "Detection of masses in mammograms via statistically based enhancement, multilevel-thresholding segmentation, and region selection", Comput Med Imaging Graph, 32, pp.304~315 (2008)
- Martinez VG, "Iterative method for automatic detection of masses in digital mammograms for computer-aided diagnosis", Proceedings of the Medical Imaging 1999 : Image Processing, pp.1086~1093 (1999)
- Kallergi M, "Image segmentation in digital mammography : comparison of local thresholding and region growing algorithms", Comput Med Imaging Graph, 16, pp.323~331 (1992)
- Pappas TN, "An adaptive clustering algorithm for image segmentation", Proc IEEE Int Conf Acoust Speech Signal Process, 3, pp.1667~1670 (1989)
- Lai SM, "On techniques for detecting circumscribed masses in mammograms", IEEE Trans Med Imaging, 8, pp.377~386 (1989)
- Li H, "Nonlinear filtering enhancement and histogram modeling segmentation of masses for digital mammograms", Proceedings of the 18th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp.1045~1046 (1996)
- Sameti M, "Digital mammography", pp.471~474 (1996), Elsevier
- Zheng B, "Computerized detection of masses from digitized mammograms : comparison of single-image segmentation and bilateral-image subtraction", Acad Radiol, 2, pp.1056~1061 (1995)
- Brake GM, "Single and multiscale detection of masses in digital mammograms", IEEE Trans Med Imaging, 18, pp.628~639 (1999)
- Undrill P, "Texture analysis and boundary refinement to outline mammography masses", Proceedings of the IEE Colloquium on Digital Mammography, pp.5 (1996), 1~5[DOI]
- Petrick N, "Automated detection of breast masses on mammograms using adaptive contrast enhancement and texture classification", Med Phys, 23, pp.1685~1696 (1996)
- Bovis K, "Identification of masses in digital mammograms with MLP and RBF nets", Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000, pp.342~347 (2000), IEEE
- Viton JL, "Method for characterizing masses in digital mammograms", Opt Eng, 35, pp.3453~3459 (1996)
- Brzakovic D, "An approach to automated detection of tumors in mammograms", IEEE Trans Med Imaging, 9, pp.233~241 (1990)
- Domingues I, "Mass detection on mammogram images:a first assessment of deep learning techniques", Proceedings of the 19th Portuguese Conference on Pattern Recognition (RECPAD) (2013), APRP
- Dhungel N, "Automated mass detection in mammograms using cascaded deep learning and random forests", Proceedings of the 2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA), pp.1~8 (2015)
- LeCun YA, "Neural networks: tricks of the trade", pp.9~48 (2012), Springer
- Fawzi A, "Adaptive data augmentation for image classification", Proceedings of the 2016 IEEE International Conference on Image Processing (ICIP 2016), pp.3688~3692 (2016), IEEE
- "Very deep convolutional networks for large-scale image recognition" (2014)[URL]
- Lecun Y, "Gradient-based learning applied to document recognition", Proceedings of the IEEE, 86, pp.2278~2324 (1998)
- Srivastava N, "Dropout : a simple way to prevent neural networks from overfitting", J Mach Learn Res, 15, pp.1929~1958 (2014)
- Ester M, "A density-based algorithm for discovering clusters in large spatial databases with noise", Proceedings of the Second International Conference on Knowledge Discovery and Data Mining(KDD-96), pp.226~231 (1996), Association for the Advancement of Artificial Intelligence
- [URL]
- Ertosun MG, "Probabilistic visual search for masses within mammography images using deep learning", Proceedings of the 2015 IEEE International Conference on Bioinformatics and Biomedicine(BIBM), pp.1310~1315 (2015), IEEE
- Li Y, "Mass detection in mammograms by bilateral analysis using convolution neural network", Comput Methods Programs Biomed, 195, pp.105518~ (2020)
- Zeiler MD, "Computer Vision – ECCV 2014", pp.818~833 (2014), Springer
- "Understanding neural networks through deep visualization" (2015)[URL]
- "High-resolution breast cancer screening with multi-view deep convolutional neural networks" (2017)[URL]