Sun Fuhai
ABSTRACT
In magnetic resonance image (MRI) analysis, it is often necessary and beneficial to analyze multi-modal MRIs. However, it is typically costly to acquire images of multiple modalities. In this context, cross-modality MRI synthesization has a great potential, for which task the generative adversarial network (GAN) technique has been identified to be useful. The main limitation of GAN is that it can only transfer between two modalities and will not work if more than one modalities need to be generated from another single one. In this work, we propose to use StarGAN for multi-modal MRI synthesization. In other words, StarGAN is used to generate MRIs of multiple modalities from a single modality at one shot. In our experiment, we show that StarGAN is more time-saving than multiple GANs and also more accurate.
- Spyridon Bakas, Hamed Akbari, Aristeidis Sotiras, Michel Bilello, Martin Rozycki, Justin S Kirby, John B Freymann, Keyvan Farahani, and Christos Davatzikos. 2017. Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features. Scientific data 4, 1 (2017), 1–13.Google Scholar
- Spyridon Bakas, Mauricio Reyes, Andras Jakab, Stefan Bauer, Markus Rempfler, Alessandro Crimi, Russell Takeshi Shinohara, Christoph Berger, Sung Min Ha, Martin Rozycki, 2018. Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the BRATS challenge. arXiv preprint arXiv:1811.02629(2018).Google Scholar
- Yunjey Choi, Minje Choi, Munyoung Kim, Jung-Woo Ha, Sunghun Kim, and Jaegul Choo. 2018. Stargan: Unified generative adversarial networks for multi-domain image-to-image translation. In Proceedings of the IEEE conference on computer vision and pattern recognition. 8789–8797.Google ScholarCross Ref
- I Goodfellow, J Pouget-Abadie, M Mirza, B Xu, D Warde-Farley, S Ozair, A Courville, and Y Bengio. 2014. Generative adversarial nets In: Advances in Neural Information Processing Systems (NIPS). (2014).Google Scholar
- Yacine Kabir, Michel Dojat, Benoît Scherrer, Florence Forbes, and Catherine Garbay. 2007. Multimodal MRI segmentation of ischemic stroke lesions. In 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE, 1595–1598.Google ScholarCross Ref
- Fayao Liu, Luping Zhou, Chunhua Shen, and Jianping Yin. 2013. Multiple kernel learning in the primal for multimodal Alzheimer’s disease classification. IEEE journal of biomedical and health informatics 18, 3(2013), 984–990.Google Scholar
- Bjoern H Menze, Andras Jakab, Stefan Bauer, Jayashree Kalpathy-Cramer, Keyvan Farahani, Justin Kirby, Yuliya Burren, Nicole Porz, Johannes Slotboom, Roland Wiest, 2014. The multimodal brain tumor image segmentation benchmark (BRATS). IEEE transactions on medical imaging 34, 10 (2014), 1993–2024.Google Scholar
- Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing 13, 4 (2004), 600–612.Google ScholarDigital Library
- Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A Efros. 2017. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE international conference on computer vision. 2223–2232.Google ScholarCross Ref
Recommendations
Adversarial Uni- and Multi-modal Stream Networks for Multimodal Image Registration
Medical Image Computing and Computer Assisted Intervention – MICCAI 2020AbstractDeformable image registration between Computed Tomography (CT) images and Magnetic Resonance (MR) imaging is essential for many image-guided therapies. In this paper, we propose a novel translation-based unsupervised deformable image registration ...
Segmentation of inflamed synovia in multi-modal 3D MRI
ISBI'09: Proceedings of the Sixth IEEE international conference on Symposium on Biomedical Imaging: From Nano to MacroWe address the difficult problem of segmenting the inflamed synovial tissue in multi-modal 3D MR sequences of the wrist. The complex morphology of the structures to segment, the dimensionality of the images, and the multiple modalities all contributes ...
3D Brain MRI GAN-Based Synthesis Conditioned on Partial Volume Maps
Simulation and Synthesis in Medical ImagingAbstractIn this paper, we propose a framework for synthesising 3D brain T1-weighted (T1-w) MRI images from Partial Volume (PV) maps for the purpose of generating synthetic MRI volumes with more accurate tissue borders. Synthetic MRIs are required to ...
Comments