Qiang Wang
ABSTRACT
Brain image registration is a key part of brain image processing, so the research of brain image registration technology has important value. This paper proposes a brain MR image registration algorithm based on an improved convolutional neural network (CNN). Firstly, the improved CNN is used to extract the feature points in the brain image. Thereafter, the feature pre-matching is performed by finding the nearest neighbors in the feature space. Finally, the registration result of the brain image is obtained by combining the space transformation and the interpolation function. The extensive experiments show the improved CNN method obtains the better results compared with the classic SIFT algorithm and SURF algorithm. At the same time, compared with the CNN algorithm, the mutual information (MI), normalized cross-correlation coefficient (NCC) and normalized mutual information (NMI) of the improved CNN are improved by 10.55%, 0.62% and 1.84%, respectively, while mean square difference (MSD) decreasing by 0.65%. The results show that the algorithm based on the improved CNN achieves higher quality of registration.
- Xie X, Song Y, Ye F, Improving deformable image registration with point metric and masking technique for postoperative breast cancer radiotherapy[J]. Quantitative Imaging in Medicine and Surgery, 2021, 11(4): 1196.Google Scholar
Cross Ref
- Alam F, Rahman S U, Ullah S, Medical image registration in image guided surgery: issues, challenges and research opportunities[J]. Biocybernetics and Biomedical Engineering, 2018, 38(1): 71-89.Google ScholarCross Ref
- Hipwell J H, Vavourakis V, Han L, A review of biomechanically informed breast image registration[J]. Physics in Medicine & Biology, 2016, 61(2): R1.Google ScholarCross Ref
- D. G. Lowe. Distinctive image features from scale-invariant keypoints[J]. International journal of computer vision, 2004, 60(2): 91-110.Google ScholarDigital Library
- Bay H. SURF: Speeded Up Robust Features[J]. Computer Vision & Image Understanding, 2006, 110(3):404-417.Google Scholar
- Alom M Z, Taha T M, Yakopcic C, The history began from alexnet: A comprehensive survey on deep learning approaches[J]. arXiv preprint arXiv:1803.01164, 2018.Google Scholar
- Ren S, He K, Girshick R, Faster r-cnn: Towards real-time object detection with region proposal networks[J]. Advances in neural information processing systems, 2015, 28: 91-99.Google Scholar
- He K, Zhang X, Ren S, Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778.Google Scholar
- Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation[C]//International Conference on Medical image computing and computer-assisted intervention. Springer, Cham, 2015: 234-241.Google Scholar
- Yang Q, Yan P, Zhang Y, Low-dose CT image denoising using a generative adversarial network with Wasserstein distance and perceptual loss[J]. IEEE transactions on medical imaging, 2018, 37(6): 1348-1357.Google ScholarCross Ref
- Yao R, Ochoa M, Intes X, Deep compressive macroscopic fluorescence lifetime imaging[C]//2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018). IEEE, 2018: 908-911.Google Scholar
- Wu G, Kim M, Wang Q, Scalable high-performance image registration framework by unsupervised deep feature representations learning[J]. IEEE transactions on biomedical engineering, 2015, 63(7): 1505-1516.Google Scholar
- Eppenhof K A J, Pluim J P W. Error estimation of deformable image registration of pulmonary CT scans using convolutional neural networks[J]. Journal of medical imaging, 2018, 5(2): 024003.Google Scholar
- Haskins G, Kruecker J, Kruger U, Learning deep similarity metric for 3D MR–TRUS image registration[J]. International journal of computer assisted radiology and surgery, 2019, 14(3): 417-425.Google ScholarCross Ref
- Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint arXiv:1409.1556, 2014.Google Scholar
- Deng J, Dong W, Socher R, Imagenet: A large-scale hierarchical image database[C]//2009 IEEE conference on computer vision and pattern recognition. Ieee, 2009: 248-255.Google Scholar
- Yang Z, Dan T, Yang Y. Multi-temporal remote sensing image registration using deep convolutional features[J]. Ieee Access, 2018, 6: 38544-38555.Google ScholarCross Ref
- Shumway R H, Stoffer D S. An approach to time series smoothing and forecasting using the EM algorithm[J]. Journal of time series analysis, 1982, 3(4): 253-264.Google Scholar
- Viola P, Iii W M W. Alignment by Maximization of Mutual Information[J]. international journal of computer vision, 1997.Google Scholar
- Studholme C, Hill D L G, Hawkes D J. An Overlap Invariant Entropy Measure of 3D Medical Image Alignment[J]. Pattern Recognition, 1999, 32(1): 71–86.Google Scholar
- Sarvaiya J N, Patnaik S, Bombaywala S. Image Registration by Template Matching Using Normalized Cross-Correlation[M]. IEEE, 2009.Google ScholarDigital Library
- Zitova B, Flusser J. Image registration methods: a survey[J]. Image and vision computing, 2003, 21(11): 977-1000.Google Scholar
- Ge P, Chen Q, GU Y. Remote sensing image matching algorithm based on Harris corner and SURF feature [J]. Application research of computers,2014,31(7): 2205-2208Google Scholar
Recommendations
Unsupervised Deformable Image Registration Using Cycle-Consistent CNN
Medical Image Computing and Computer Assisted Intervention – MICCAI 2019AbstractMedical image registration is one of the key processing steps for biomedical image analysis such as cancer diagnosis. Recently, deep learning based supervised and unsupervised image registration methods have been extensively studied due to its ...
Comments