전이학습을 수행한 신경망을 사용한 압축센싱 심장 자기공명영상
Compressed-Sensing Cardiac CINE MRI using Neural Network with Transfer Learning
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
전이학습을 수행한 심층 인공신경망을 압축센싱 심혈관 자기공명영상에 적용하였다. 전이학습은 선행학습 신경망의 구조나 필터 커널, 가중치를 현재의 학습이나 응용에 활용하는 방법이다. 전이학습은 학습 속도를 향상시키고, 학습 데이터가 제한적일 때 신경망의 일반화에 도움이 된다. 8명의 건강한 지원자가 참여한 심장 자기공명영상 실험에서 전이학습을 수행한신경망은 단독학습 신경망에 비해 학습시간이 5배 이상 단축되었다. 시험 데이터에 대해서도 전이학습을 수행한 신경망은 전이학습을 수행하지 않은 신경망에 비하여 낮은 정규화 평균제곱오차와 향상된 재구성 영상화질을 보였다.
Abstract
Deep artificial neural network with transfer learning is applied to compressed sensing cardiovascular MRI. Transferlearning is a method that utilizes structure, filter kernels, and weights of the network used in prior learning for currentlearning or application. The transfer learning is useful in accelerating learning speed, and in generalization of the neuralnetwork when learning data is limited. From a cardiac MRI experiment, with 8 healthy volunteers, the neural networkwith transfer learning was able to reduce learning time by a factor of more than five compared to that with standalonelearning. Using test data set, reconstructed images with transfer learning showed lower normalized mean square errorand better image quality compared to those without transfer learning.
참고문헌 (14)
- Jeffrey Tsao, "MRI temporal acceleration techniques", Journal of Magnetic Resonance Imaging, 36(3), pp.543~560 (2012), Wiley[DOI]
- Hong Jung, "k-t FOCUSS: A general compressed sensing framework for high resolution dynamic MRI", Magnetic Resonance in Medicine, 61(1), pp.103~116 (2009), Wiley[DOI]
- 박진호, "Fast Cardiac CINE MRI by Iterative Truncation of Small Transformed Coefficients", Investigative Magnetic Resonance Imaging, 19(1), pp.19~30 (2015), 대한자기공명의과학회[DOI]
- O. Ronneberger, "U-net:Convolutional networks for biomedical image segmentation", International Conference on Medical computing and computer-assisted intervention (2015), Springer
- Geert Litjens, "A survey on deep learning in medical image analysis", Medical Image Analysis, 42, pp.60~88 (2017), Elsevier BV[DOI]
- C. Hyun, "Deep learning for undersampled MRI reconstruction", Physics in Medicine & Biology, 63, pp.135007~ (2018)[DOI]
- 이두희, "Deep Learning in MR Image Processing", Investigative Magnetic Resonance Imaging, 23(2), pp.81~99 (2019), 대한자기공명의과학회
- Y. Chen, "Brain MRI super resolution using 3D deep densely connected neural networks", 2018 IEEE 15th International Symposium on Biomedical Imaging, pp.739~742 (2018)
- Guotai Wang, "Interactive Medical Image Segmentation Using Deep Learning With Image-Specific Fine Tuning", IEEE Transactions on Medical Imaging, 37(7), pp.1562~1573 (2018), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Alexander Andreopoulos, "Efficient and generalizable statistical models of shape and appearance for analysis of cardiac MRI", Medical Image Analysis, 12(3), pp.335~357 (2008), Elsevier BV[DOI]
- Hoo-Chang Shin, "Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning", IEEE Transactions on Medical Imaging, 35(5), pp.1285~1298 (2016), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Karl Weiss, "A survey of transfer learning", Journal of Big Data, 3(1), pp.9~ (2016), Springer Science and Business Media LLC[DOI]
- 윤종현, "Biases in the Assessment of Left Ventricular Function by Compressed Sensing Cardiovascular Cine MRI", Investigative Magnetic Resonance Imaging, 23(2), pp.114~124 (2019), 대한자기공명의과학회
- X. Glorot, "Understanding the difficulty of training deep feedforward neural networks", Proceedings of the thirteenth international conference on artificial intelligence and statistics, pp.249~256 (2010)