Gu Yunchao
ABSTRACT
In the general process of breast cancer diagnosis, doctors mainly analyze and judge B-mode ultrasound images through vision, which depends heavily on doctors' operational experience and technical level. Artificial intelligence methods represented by machine learning algorithms have made rapid progress in recent years, especially natural image classification, target detection, semantics segmentation based on computer vision technology have been relatively mature, and have been widely used successfully in various fields. So as to improve the automation ability and reduce human errors, etc. By using artificial intelligence technology such as computer vision and in-depth learning, an automated method is established to diagnose breast cancer B-mode ultrasound images. This method can quickly strengthen the correct diagnostic rate of front-line medical staff and reduce the difference of operation level between urban and rural doctors. It has obvious medical needs and wide social significance.
- Ferlay J. GLOBOCAN 2008, cancer incidence and mortality worldwide: IARC Cancer-Base No. 10{J}. http://globocan. iarc. fr, 2010.Google Scholar
- Jackson V. P., Hendrick R. E., Feig S. A., et al. Imaging of the radiographically dense breast.{J}. Radiology, 1993, 188(2):297--301.Google ScholarCross Ref
- Z O., EJ E. Predicting the Future -Big Data, Machine Learning, and Clinical Medicine{J}. N Engl J Med, 2016, 375(13):1216--1219.Google ScholarCross Ref
- Loizou C. P., Pattichis C. S., Christodoulou C. I., et al. Comparative evaluation of despeckle filtering in ultrasound imaging of the carotid artery{J}. IEEE Transactions on Ultrasonics Ferroelectrics & Frequency Control, 2005, 52(10):1653--69.Google ScholarCross Ref
- Gupta, Chauhan, R.C, et al. Locally adaptive wavelet domain Bayesian processor for denoising medical ultrasound images using Speckle modelling based on Rayleigh distribution{J}. Vision, Image and Signal Processing, IEE Proceedings -, 2005, 152(1):129--135.Google Scholar
- Behar V., Adam D., Friedman Z. A new method of spatial compounding imaging{J}. Ultrasonics, 2003, 41(5):377.Google ScholarCross Ref
- Madabhushi A., Metaxas D. N. Combining low-, high-level and empirical domain knowledge for automated segmentation of ultrasonic breast lesions{J}. IEEE Trans Med Imaging, 2003, 22(2):155--169.Google ScholarCross Ref
- Sarti A., Corsi C., Mazzini E., et al. Maximum likelihood segmentation of ultrasound images with Rayleigh distribution.{J}. IEEE Transactions on Ultrasonics Ferroelectrics & Frequency Control, 2005, 52(6):947.Google ScholarCross Ref
- Liu Q.S., He L.Q. Diagnosis Model Based Neutral -network in Galactophore Cancer Cell Identification {J}. Journal of Chongqing University, 2003, 26(4):70--72.Google Scholar
- Giger M. L., Karssemeijer N., Rd A. S. Computer-aided diagnosis in medical imaging.{J}. IEEE Transactions on Medical Imaging, 2001, 20(12):1205--1208.Google ScholarCross Ref
- Doi K. Computer-Aided Diagnosis in Medical Imaging: Achievements and Challenges{J}. IEEE Transactions on Medical Imaging, 2001, 20(12):1205.Google ScholarCross Ref
- Wright E. R. Enter Health Information Technology: Expanding Theories of the Doctor-Patient Relationship for the Twenty-First Century Health Care Delivery System{M}.{S.l.}:Springer New York, 2011: 343--359.Google Scholar
- Bengio Y., Courville A. C., Vincent P. Representation Learning: A Review and New Perspectives{J}. IEEE Trans. Pattern Anal. Mach. Intell., 2013, 35(8):1798--1828. Google ScholarDigital Library
- Dahl J. V., Koch K. C., Kleinhans E., et al. Convolutional networks and applications in vision{A}. IEEE International Symposium on Circuits and Systems {C}. {S.l.}: {s.n.}, 2011:253--256.Google Scholar
- Hubel D. H., Wiesel T. N. Receptive fields, binocular interaction and functional architecture in the cat's visual cortex{J}. Journal of Physiology, 1962, 160(1):106--154.Google ScholarCross Ref
- Jaderberg M., Simonyan K., Zisserman A., et al. Spatial Transformer Networks{J}. 2015:2017--2025. Google ScholarDigital Library
- Worrall D. E., Garbin S. J., Turmukhambetov D., et al. Harmonic Networks: Deep Translation and Rotation Equivariance{J}. CoRR, 2016, abs/1612.04642. http://arxiv.org/abs/1612.04642.Google Scholar
- Ruderman A., Rabinowitz N. C., Morcos A. S., et al. Learned Deformation Stability in Convolutional Neural Networks{J}. CoRR, 2018, abs/1804.04438. http://arxiv.org/abs/1804.04438.Google Scholar
- Nair V., Hinton G. E. Rectified linear units improve restricted boltzmann machines{A}.International Conference on International Conference on Machine Learning{C}. {S.l.}:{s.n.}, 2010:807--814. Google ScholarDigital Library
- He K., Zhang X., Ren S., et al. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification{J}. 2015:1026--1034. Google ScholarDigital Library
- Lo S. B., Lou S. A., Lin J. S., et al. Artificial convolution neural network techniques and applications for lung nodule detection{J}. IEEE Transactions on Medical Imaging, 1995, 14(4):711.Google ScholarCross Ref
- Szegedy C., Liu W., Jia Y., et al. Going deeper with convolutions{A}. {S.l.}: {s.n.}, 2014:1--9.Google Scholar
- Russakovsky O., Deng J., Su H., et al. ImageNet Large Scale Visual Recognition Challenge{J}. International Journal of Computer Vision, 2015, 115(3):211--252. Google ScholarDigital Library
- Rajkomar A., Lingam S., Taylor A. G., et al. High-Throughput Classification of Radiographs Using Deep Convolutional Neural Networks {J}. J. Digital Imaging, 2017, 30(1):95--101.Google ScholarCross Ref
- Huang G., Liu Z., Maaten L., et al. Densely Connected Convolutional Networks {J}. 2016.Google Scholar
- Wang X., Peng Y., Lu L., et al. ChestX-Ray8: Hospital-Scale Chest X-Ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases{A}. Computer Vision and Pattern Recognition {C}. {S.l.}: {s.n.}, 2017:3462--3471.Google Scholar
- Rajpurkar P., Irvin J., Zhu K., et al. CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning{J}. 2017.Google Scholar
- Yan Z., Zhan Y., Peng Z., et al. Bodypart Recognition Using Multi-stage Deep Learning{A}. Information Processing in Medical Imaging: Conference{C}. {S.l.}: {s.n.}, 2015:449.Google Scholar
- Roth H. R., Lee C. T., Shin H. C., et al. Anatomy-specific classification of medical images using deep convolutional nets{A}. IEEE International Symposium on Biomedical Imaging{C}. {S.l.}: {s.n.}, 2015:101--104.Google Scholar
- Albarqouni S., Baur C., Achilles F., et al. AggNet: Deep Learning From Crowds for Mitosis Detection in Breast Cancer Histology Images{J}. IEEE Trans. Med. Imaging, 2016, 35(5):1313--1321.Google ScholarCross Ref
- Goodfellow I. J., Pouget-Abadie J., Mirza M., et al. Generative Adversarial Networks {J}. CoRR, 2014, abs/1406.2661. http://arxiv.org/abs/1406.2661.Google Scholar
- Hu Y., Gibson E., Lee L.-L., et al. Freehand Ultrasound Image Simulation with Spatially-Conditioned Generative Adversarial Networks {M}., Molecular Imaging, Reconstruction and Analysis of Moving Body Organs, and Stroke Imaging and Treatment{C}..{S.l.}: Springer, 2017:105--115.Google ScholarCross Ref
Index Terms
- Application of Computer Vision and Deep Learning in Breast Cancer Assisted Diagnosis
Recommendations
Deep learning approach for breast cancer diagnosis
ICSIE '19: Proceedings of the 8th International Conference on Software and Information EngineeringBreast cancer is one of the leading fatal disease worldwide with high risk control if early discovered. Conventional method for breast screening is x-ray mammography, which is known to be challenging for early detection of cancer lesions. The dense ...
Breast cancer diagnosis method based on multitask learning and BI-RADS assessments
CAIH2020: Proceedings of the 2020 Conference on Artificial Intelligence and HealthcareBreast cancer is the most common cancer in women, and ultrasound diagnosis is one of the most common diagnostic methods. This paper used the deep transfer learning network to classify breast ultrasound images as benign and malignant. To improve ...
Breast cancer detection using deep learning: Datasets, methods, and challenges ahead
AbstractBreast Cancer (BC) is the most commonly diagnosed cancer and second leading cause of mortality among women. About 1 in 8 US women (about 13%) will develop invasive BC throughout their lifetime. Early detection of this life-threatening ...
Highlights- Various Breast Cancer Imaging modalities including Mammography, Histopathology, Ultrasound, MRI, PET/CT, and Thermography has been discussed briefly with ...
Comments