Using deep learning to generate synthetic B-mode musculoskeletal ultrasound images

Computer Methods and Programs in Biomedicine - Tập 196 - Trang 105583 - 2020
Neil J. Cronin1,2,3, Taija Finni1, Olivier Seynnes4
1Neuromuscular Research Centre, Faculty of Sport and Health Sciences, University of Jyvaskyla, Finland
2Department for Health, Bath University, UK
3School of Sport & Exercise, University of Gloucestershire, Gloucestershire, UK
4Norwegian School of Sport Sciences, Oslo, Norway

Tài liệu tham khảo

Topol, 2019, High-performance medicine: the convergence of human and artificial intelligence, Nat. Med., 25, 44, 10.1038/s41591-018-0300-7 M. Frid-Adar, I. Diamant, E. Klang, M. Amitai, J. Goldberger, H. Greenspan, GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification, (2018). https://doi.org/10.1016/j.neucom.2018.09.013. Greenspan, 2016, Guest editorial deep learning in medical imaging: overview and future promise of an exciting new technique, IEEE Trans. Med. Imaging., 35, 1153, 10.1109/TMI.2016.2553401 Krizhevsky, 2012, ImageNet classification with deep convolutional neural networks, 1097 I.J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, Y. Bengio, Generative Adversarial Networks, (2014). http://arxiv.org/abs/1406.2661 (Accessed 14 November 2019). P. Costa, A. Galdran, M.I. Meyer, M.D. Abràmoff, M. Niemeijer, A.M. Mendonça, A. Campilho, Towards Adversarial Retinal Image Synthesis, n.d.. Armanious, 2020, MedGAN: medical image translation using GANs, Comput. Med. Imaging Graph., 79, 10.1016/j.compmedimag.2019.101684 Shin, 2018, Medical image synthesis for data augmentation and anonymization using generative adversarial networks, 1 You, 2020, CT super-resolution GAN constrained by the identical, residual, and cycle learning ensemble (GAN-CIRCLE), IEEE Trans. Med. Imaging., 39, 188, 10.1109/TMI.2019.2922960 Yi, 2019, Generative adversarial network in medical imaging: a review, Med. Image Anal., 58, 10.1016/j.media.2019.101552 Cronin, 2013, The use of ultrasound to study muscle–tendon function in human posture and locomotion, Gait Posture, 37, 305, 10.1016/j.gaitpost.2012.07.024 Seynnes, 2020, Simple Muscle Architecture Analysis (SMA): an ImageJ macro tool to automate measurements in B-mode ultrasound scans, PLoS ONE, 15, 10.1371/journal.pone.0229034 Caresio, 2017, Fully automated Muscle Ultrasound Analysis (MUSA): robust and accurate muscle thickness measurement, Ultrasound Med. Biol., 43, 195, 10.1016/j.ultrasmedbio.2016.08.032 Hu, 2017, Freehand ultrasound image simulation with spatially-conditioned generative adversarial networks, 105 Tom, 2018, Simulating patho-realistic ultrasound images using deep generative networks with adversarial learning, 1174 Wang, 2019, High-resolution image reconstruction for portable ultrasound imaging devices, EURASIP J. Adv. Signal Process., 2019, 1, 10.1186/s13634-019-0649-x Ihle, 2019, Unsupervised data to content transformation with histogram-matching cycle-consistent generative adversarial networks, Nat. Mach. Intell., 1, 461, 10.1038/s42256-019-0096-2 Narici, 1996, In vivo human gastrocnemius architecture with changing joint angle at rest and during graded isometric contraction, J. Physiol., 496, 287, 10.1113/jphysiol.1996.sp021685 J.-.Y. Zhu, T. Park, P. Isola, A.A. Efros, Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks, (2017). http://arxiv.org/abs/1703.10593 (Accessed 14 November 2019). T. Karras, S. Laine, T. Aila, A Style-Based Generator Architecture for Generative Adversarial Networks, (2018). http://arxiv.org/abs/1812.04948 (Accessed 14 November 2019). K. He, X. Zhang, S. Ren, J. Sun, Deep Residual Learning for Image Recognition, ArXiv. (2015). https://arxiv.org/abs/1512.03385v1 (Accessed 15 November 2018). D. Ulyanov, A. Vedaldi, V. Lempitsky, Instance Normalization: the Missing Ingredient for Fast Stylization, ArXiv. (2016). http://arxiv.org/abs/1607.08022v3 (Accessed 16 April 2020). P. Isola, J.-.Y. Zhu, T. Zhou, A.A. Efros, Image-to-Image Translation with Conditional Adversarial Networks, ArXiv. (2016). http://arxiv.org/abs/1611.07004v3 (Accessed 16 April 2020). Schindelin, 2012, Fiji: an open-source platform for biological-image analysis, Nat. Methods, 9, 676, 10.1038/nmeth.2019 Bland, 1986, Statistical methods for assessing agreement between two methods of clinical measurement, Lancet, 1, 307, 10.1016/S0140-6736(86)90837-8 Beaulieu-Jones, 2019, Privacy-preserving generative deep neural networks support clinical data sharing, Circ. Cardiovasc. Qual. Outcomes, 12, 10.1161/CIRCOUTCOMES.118.005122 T. Salimans, I. Goodfellow, W. Zaremba, V. Cheung, A. Radford, X. Chen, Improved Techniques for Training GANs, ArXiv. 1606.03498 (2016). https://arxiv.org/abs/1606.03498 (Accessed 15 November 2019).