머신러닝을 이용한 에너지 선택적 유방촬영의 진단 정확도 향상에 관한 연구
A Feasibility Study on the Improvement of Diagnostic Accuracy for Energy-selective Digital Mammography using Machine Learning
2
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
Although digital mammography is a representative method for breast cancer detection. It has a limitation in detecting and classifying breast tumor due to superimposed structures. Machine learning, which is a part of artificial intelligence fields, is a method for analysing a large amount of data using complex algorithms, recognizing patterns and making prediction. In this study, we proposed a technique to improve the diagnostic accuracy of energy-selective mammography by training data using the machine learning algorithm and using dual-energy measurements. A dual-energy images obtained from a photon-counting detector were used for the input data of machine learning algorithms, and we analyzed the accuracy of predicted tumor thickness for verifying the machine learning algorithms. The results showed that the classification accuracy of tumor thickness was above 95% and was improved with an increase of imput data. Therefore, we expect that the diagnostic accuracy of energy-selective mammography can be improved by using machine learning.
Abstract
Although digital mammography is a representative method for breast cancer detection. It has a limitation in detecting and classifying breast tumor due to superimposed structures. Machine learning, which is a part of artificial intelligence fields, is a method for analysing a large amount of data using complex algorithms, recognizing patterns and making prediction. In this study, we proposed a technique to improve the diagnostic accuracy of energy-selective mammography by training data using the machine learning algorithm and using dual-energy measurements. A dual-energy images obtained from a photon-counting detector were used for the input data of machine learning algorithms, and we analyzed the accuracy of predicted tumor thickness for verifying the machine learning algorithms. The results showed that the classification accuracy of tumor thickness was above 95% and was improved with an increase of imput data. Therefore, we expect that the diagnostic accuracy of energy-selective mammography can be improved by using machine learning.
참고문헌 (24)
- Korean Breast Cancer, "Breast Cancer Facts & Figures 2018", Korean Breast Cancer Society, ~ (2018)
- Wu T, "Tomographic Mammography using a Limited Number of Low-dose Cone-beam Projection Images", Medical Physics, 30(3), pp.365~380 (2003)
- Leschka S, "Low Kilovoltage Cardiac Dual-source CT: Attenuation, Noise, and Radiation Dose", European Radiology, 18(9), pp.1809~1817 (2008)
- Lewin JM, "Dual-energy Contrast-enhanced Digital Subtraction Mammography : Feasibility", Radiology, 229(1), pp.261~268 (2003)
- Takahashi T, "Recent Progress in CdTe and CdZnTe Detectors", IEEE Transactions on Nuclear Science, 48(4), pp.950~959 (2001)
- Laidevant AD, "Compositional Breast Imaging using a Dual-energy Mammography Protocol", Medical Physics, 37(1), pp.164~174 (2010)
- 최유나, "Material Decomposition in Contrast-enhanced Digital Mammography Based on Photon Counting: Monte Carlo Simulation Studies", Journal of the Korean Physical Society, 59(1), pp.161~168 (2011), 한국물리학회
- Miyajima S, "CdZnTe detector in Mammographic X-ray Spectroscopy", Physics in Medicine and Biology, 47(22), pp.3959~ (2002)
- Barber WC, "Characterization of a Novel Photon Counting Detector for Clinical CT: Count Rate, Energy Resolution. and Noise Performance. In Medical Imaging 2009", In Medical Imaging 2009: Physics of Medical Imaging, 7258, pp.725824~ (2009)
- Géron A, "Hands-on Machine Learning with Scikit-learn & Tensorflow" (2016), Hanbit Media Inc
- Subasi A, "EEG Signal Classification using PCA, ICA, LDA and Support Vector Machines", Expert Systems with Applications, 37(12), pp.8659~8666 (2010)
- Zhang H, "SVM-KNN:Discriminative Nearest Neighbor Classification for Visual Category Recognition", Computer Vision and Patten Recognition, 2006 IEEE Computer Society Conference o, 2, pp.2126~2136 (2006)
- Jan S, "GATE V6: a Major Enhancement of the GATE Simulation Platform Enabling Modelling of CT and Radiotherapy", Physics in Medicine and Biology, 56(4), pp.881~ (2011)
- 이창래, "다양한 팬텀 모양 및 재질에 따른 전산화단층촬영장치 선량 평가", 방사선기술과학, 40(1), pp.13~18 (2017), 대한방사선과학회[DOI]
- 안수정, "GATE6를 이용한 Varian 21EX Clinac 선형가속기의 6 MV X-선 특성모사", 방사선기술과학, 39(4), pp.571~575 (2016), 대한방사선과학회[DOI]
- 윤인영, "Mammographic Breast Density Evaluation in Korean Women Using Fully Automated Volumetric Assessment", Journal of Korean Medical Science, 31(3), pp.457~462 (2016), 대한의학회
- Castronovo A, "Evidence that Breast Cancer Associated Microcalcifications are Mineralized Malignant Cell", International Journal of Oncology, 12(2), pp.305~313 (1998)
- Catalogue of Diagnostic X-ray Spectra and Other Data, "Carney K.", Institute of Physics and Engineering in Medicine, ~, pp.Report No 78 (1997)
- Desai N, "Practical Evaluation of Image Quality in Computed Radiographic (CR) Imaging Systems", Medical Imaging 2010: Physics of Medical Imaging, 7622, pp.76224~ (2010), International Society for Optic and Photonics[DOI]
- Bengio Y, "No Unbiased Estimator of the Variance of K-fold Cross Validation", Journal of Machine Learning Research, 5, pp.1089~1105 (2004)
- Stehman SV, "Selecting and Interpreting Measures of Thematic Classification Accuracy", Remote Sensing of Environment, 62(1), pp.77~89 (1997)
- Buades A, "Non-local Algorithm for Image Denoising", Ciboyter Vision and PAttern Recognition 2005 IEEE Computer Society Conference on, 2, pp.60~65 (2005)
- Kourou K, "Machine Learning Applications in Cancer Prognosis and Prediction", Computational and Structural Biotechnology Journal, 13, pp.8~17 (2015)
- Taguchi K, "version 20", 20 : Single Photon counting X-ray Detectors in Medical Imaging, 2013, pp.40(10), 100901~