Abstract
Generative models such as generative adversarial networks and autoencoders have gained a great deal of attention in the medical field due to their excellent data generation capability. This article provides a comprehensive survey of generative models for 3D volumes, focusing on the brain and heart. A new and elaborate taxonomy of unconditional and conditional generative models is proposed to cover diverse medical tasks for the brain and heart: unconditional synthesis, classification, conditional synthesis, segmentation, denoising, detection, and registration. We provide relevant background, examine each task, and also suggest potential future directions. A list of the latest publications will be updated on GitHub to keep up with the rapid influx of papers at https://github.com/csyanbin/3D-Medical-Generative-Survey.
- [1] . 2021. Medical image denoising system based on stacked convolutional autoencoder for enhancing 2-dimensional gel electrophoresis noise reduction. Biomedical Signal Processing and Control 69 (2021), 102842.Google Scholar
- [2] . 2022. COCA—Coronary Calcium and Chest CT’s Dataset. Retrieved December 22, 2023 from https://stanfordaimi.azurewebsites.net/datasets/e8ca74dc-8dd4-4340-815a-60b41f6cb2aaGoogle Scholar
- [3] . 2017. Deep learning for brain MRI segmentation: State of the art and future directions. Journal of Digital Imaging 30, 4 (2017), 449–459.Google ScholarCross Ref
- [4] . 2022. The role of generative adversarial network in medical image analysis: An in-depth survey. ACM Computing Surveys 55, 5 (2022), Article 96, 36 pages.Google Scholar
- [5] . 2022. The role of generative adversarial networks in brain MRI: A scoping review. Insights into Imaging 13, 1 (2022), 1–15.Google Scholar
- [6] . 2020. XCAT-GAN for synthesizing 3D consistent labeled cardiac MR images on anatomically variable XCAT phantoms. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. 128–137.Google ScholarDigital Library
- [7] . 2008. Efficient and generalizable statistical models of shape and appearance for analysis of cardiac MRI. Medical Image Analysis 12, 3 (2008), 335–357.Google ScholarCross Ref
- [8] . 2017. Wasserstein generative adversarial networks. In Proceedings of the International Conference on Machine Learning.214–223.Google Scholar
- [9] . 2017. Advancing the Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features. Scientific Data 4, 1 (2017), 1–13.Google ScholarCross Ref
- [10] . 2018. An unsupervised learning model for deformable medical image registration. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 9252–9260.Google ScholarCross Ref
- [11] . 2019. VoxelMorph: A learning framework for deformable medical image registration. IEEE Transactions on Medical Imaging 38, 8 (2019), 1788–1800.Google ScholarCross Ref
- [12] . 2022. Subject-specific lesion generation and pseudo-healthy synthesis for multiple sclerosis brain images. In Proceedings of the International Workshop on Simulation and Synthesis in Medical Imaging. 1–11.Google ScholarDigital Library
- [13] . 2018. Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: Is the problem solved? IEEE Transactions on Medical Imaging 37, 11 (2018), 2514–2525.Google ScholarCross Ref
- [14] . 2018. Learning interpretable anatomical features through deep generative models: Application to cardiac remodeling. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. 464–471.Google ScholarDigital Library
- [15] . 2019. Pros and cons of GAN evaluation measures. Computer Vision and Image Understanding 179 (2019), 41–65.Google ScholarDigital Library
- [16] . 1988. Auto-association by multilayer perceptrons and singular value decomposition. Biological Cybernetics 59, 4 (1988), 291–294.Google ScholarDigital Library
- [17] . 2023. Automatic time-resolved cardiovascular segmentation of 4D flow MRI using deep learning. Journal of Magnetic Resonance Imaging 57, 1 (2023), 191–203.Google ScholarCross Ref
- [18] . 2019. Med3D: Transfer learning for 3D medical image analysis. arXiv preprint arXiv:1904.00625 (2019).Google Scholar
- [19] . 2018. S3D-UNet: Separable 3D U-net for brain tumor segmentation. In Proceedings of the International MICCAI Brainlesion Workshop. 358–368.Google Scholar
- [20] . 2020. QSMGAN: Improved quantitative susceptibility mapping using 3D generative adversarial networks with increased receptive field. NeuroImage 207 (2020), 116389.Google ScholarCross Ref
- [21] . 2022. Generative adversarial networks in medical image augmentation: A review. Computers in Biology and Medicine 144 (2022), 105382.Google Scholar
- [22] . 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP ’14).Google ScholarCross Ref
- [23] . 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
- [24] . 2021. Synthesis of 3D MRI brain images with shape and texture generative adversarial deep neural networks. IEEE Access 9 (2021), 64747–64760.Google ScholarCross Ref
- [25] . 2006. Introduction to the Non-rigid Image Registration Evaluation Project (NIREP). In Proceedings of the International Workshop on Biomedical Image Registration. 128–135.Google ScholarDigital Library
- [26] . 2021. Two-stage deep learning for accelerated 3D time-of-flight MRA without matched training data. Medical Image Analysis 71 (2021), 102047.Google ScholarCross Ref
- [27] . 2016. 3D U-Net: Learning dense volumetric segmentation from sparse annotation. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. 424–432.Google Scholar
- [28] . 2020. Vox2Vox: 3D-GAN for brain tumour segmentation. In Proceedings of the International MICCAI Brainlesion Workshop. 274–284.Google Scholar
- [29] . 1997. BrainWeb: Online interface to a 3D MRI simulated brain database. NeuroImage 5, 4 (1997), 425.Google Scholar
- [30] . 2011. Natural language processing (almost) from scratch. Journal of Machine Learning Research 12 (2011), 2493–2537.Google ScholarDigital Library
- [31] . 2016. MSSEG challenge proceedings: Multiple sclerosis lesions segmentation challenge using a data management and processing infrastructure. In Proceedings of the 24th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI ’16). 126.Google Scholar
- [32] . 2012. The ADHD-200 consortium: A model to advance the translational potential of neuroimaging in clinical neuroscience. Frontiers in Systems Neuroscience 6 (2012), 62.Google ScholarCross Ref
- [33] . 2017. Harvard aging brain study: Dataset and accessibility. NeuroImage 144 (2017), 255–258.Google ScholarCross Ref
- [34] . 2021. ResViT: Residual vision transformers for multi-modal medical image synthesis. arXiv preprint arXiv:2106.16031 (2021).Google Scholar
- [35] . 2019. Image synthesis in multi-contrast MRI with conditional generative adversarial networks. IEEE Transactions on Medical Imaging 38, 10 (2019), 2375–2388.Google ScholarCross Ref
- [36] . 2010. IXI Brain Development Home Page. Retrieved December 22, 2023 from https://brain-development.org/ixi-dataset/Google Scholar
- [37] . 2016. Submillisievert coronary calcium quantification using model-based iterative reconstruction: A within-patient analysis. European Journal of Radiology 85, 11 (2016), 2152–2159.Google ScholarCross Ref
- [38] . 2009. ImageNet: A large-scale hierarchical image database. In Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, Los Alamitos, CA, 248–255.Google ScholarCross Ref
- [39] . 2023. Challenges of deep learning in medical image analysis—Improving explainability and trust. IEEE Transactions on Technology and Society 4, 1 (2023), 68–75.Google ScholarCross Ref
- [40] . 2021. Diffusion models beat GANs on image synthesis. Advances in Neural Information Processing Systems 34 (2021), 8780–8794.Google Scholar
- [41] . 2014. The autism brain imaging data exchange: Towards a large-scale evaluation of the intrinsic brain architecture in autism. Molecular Psychiatry 19, 6 (2014), 659–667.Google ScholarCross Ref
- [42] . 2018. VoxelAtlasGAN: 3D left ventricle segmentation on echocardiography with atlas guided generation and voxel-to-voxel discrimination. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. 622–629.Google ScholarDigital Library
- [43] . 2020. Deep complex convolutional network for fast reconstruction of 3D late gadolinium enhancement cardiac MRI. NMR in Biomedicine 33, 7 (2020), e4312.Google ScholarCross Ref
- [44] . 2020. GP-GAN: Brain tumor growth prediction using stacked 3D generative adversarial networks from longitudinal MR Images. Neural Networks 132 (2020), 321–332.Google ScholarCross Ref
- [45] . 2019. Neural architecture search: A survey. Journal of Machine Learning Research 20, 1 (2019), 1997–2017.Google ScholarDigital Library
- [46] . 2018. Automatic liver segmentation using U-Net with Wasserstein GANs. Journal of Image and Graphics 6, 2 (2018), 152–159.Google ScholarCross Ref
- [47] . 2021. Taming transformers for high-resolution image synthesis. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 12873–12883.Google ScholarCross Ref
- [48] . 2020. Do GANs always have Nash equilibria? In Proceedings of the International Conference on Machine Learning. 3029–3039.Google Scholar
- [49] . 2012. FreeSurfer. NeuroImage 62, 2 (2012), 774–781.Google ScholarCross Ref
- [50] . 2016. Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. In Proceedings of the International Conference on Machine Learning. 1050–1059.Google ScholarDigital Library
- [51] . 2010. An improved Sobel edge detection. In Proceedings of the 2010 3rd International Conference on Computer Science and Information Technology, Vol. 5. IEEE, Los Alamitos, CA, 67–71.Google Scholar
- [52] . 2015. Fast R-CNN. In Proceedings of the IEEE International Conference on Computer Vision. 1440–1448.Google ScholarDigital Library
- [53] . 2013. The MCIC collection: A shared repository of multi-modal, multi-site brain image data from a clinical investigation of schizophrenia. Neuroinformatics 11, 3 (2013), 367–388.Google ScholarCross Ref
- [54] . 2016. Medical image denoising using convolutional denoising autoencoders. In Proceedings of the 2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW ’16). IEEE, Los Alamitos, CA, 241–246.Google ScholarCross Ref
- [55] . 2014. Generative adversarial nets. Advances in Neural Information Processing Systems 27 (2014), 1–9.Google Scholar
- [56] . 2021. SlabGAN: A method for generating efficient 3D anisotropic medical volumes using generative adversarial networks. In Medical Imaging 2021: Image Processing, Vol. 11596. SPIE, 329–335.Google Scholar
- [57] . 2013. Speech recognition with deep recurrent neural networks. In Proceedings of the 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing. IEEE, Los Alamitos, CA, 6645–6649.Google ScholarCross Ref
- [58] . 2014. Deep autoregressive networks. In Proceedings of the International Conference on Machine Learning. 1242–1250.Google Scholar
- [59] . 2017. Improved training of Wasserstein GANs. In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS ’17). 5769–5779.Google Scholar
- [60] . 2021. Whole heart segmentation using 3D FM-pre-ResNet encoder–decoder based architecture with variational autoencoder regularization. Applied Sciences 11, 9 (2021), 3912.Google ScholarCross Ref
- [61] . 2021. MADGAN: Unsupervised medical anomaly detection GAN using multiple adjacent brain MRI slice reconstruction. BMC Bioinformatics 22, 2 (2021), 1–20.Google Scholar
- [62] . 2022. Masked autoencoders are scalable vision learners. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 16000–16009.Google ScholarCross Ref
- [63] . 2017. Mask R-CNN. In Proceedings of the IEEE International Conference on Computer Vision. 2961–2969.Google ScholarCross Ref
- [64] . 2016. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 770–778.Google ScholarCross Ref
- [65] . 2014. Gauss–Newton inspired preconditioned optimization in large deformation diffeomorphic metric mapping. Physics in Medicine & Biology 59, 20 (2014), 6085.Google ScholarCross Ref
- [66] . 2017. GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS ’17). 6629–6640.Google Scholar
- [67] . 1993. Autoencoders, minimum description length, and Helmholtz free energy. In Proceedings of the 6th International Conference on Neural Information Processing Systems (NIPS ’93). 3–10.Google Scholar
- [68] . 2012. Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Processing Magazine 29, 6 (2012), 82–97.Google ScholarCross Ref
- [69] . 2021. Improved techniques for training single-image GANs. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 1300–1309.Google ScholarCross Ref
- [70] . 2020. Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems 33 (2020), 6840–6851.Google Scholar
- [71] . 2022. Cascaded diffusion models for high fidelity image generation. Journal of Machine Learning Research 23 (2022), 47–51.Google Scholar
- [72] . 2009. CANDIShare: A resource for pediatric neuroimaging data. Neuroinformatics 10, 3 (2009), 319–322.Google Scholar
- [73] . 2015. Brain Genomics Superstruct Project initial data release with structural, functional, and behavioral measures. Scientific Data 2, 1 (2015), 1–16.Google ScholarCross Ref
- [74] . 2021. 3D-StyleGAN: A style-based generative adversarial network for generative modeling of three-dimensional medical images. In Deep Generative Models, and Data Augmentation, Labelling, and Imperfections. Springer, 24–34.Google ScholarDigital Library
- [75] . 2020. 3D brain MRI reconstruction based on 2D super-resolution technology. In Proceedings of the 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC ’20). IEEE, Los Alamitos, CA, 18–23.Google ScholarDigital Library
- [76] . 2009. Prospective study on the mismatch concept in acute stroke patients within the first 24 h after symptom onset—1000Plus study. BMC Neurology 9, 1 (2009), 1–8.Google ScholarCross Ref
- [77] . 2021. Few-shot learning for multi-label intent detection. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 13036–13044.Google ScholarCross Ref
- [78] . 2020. MCMT-GAN: Multi-task coherent modality transferable GAN for 3D brain image synthesis. IEEE Transactions on Image Processing 29 (2020), 8187–8198.Google ScholarCross Ref
- [79] . 2022. Generative adversarial networks and its applications in the biomedical image segmentation: A comprehensive survey. International Journal of Multimedia Information Retrieval 11 (2022), 333–368.Google ScholarCross Ref
- [80] . 2022. 6-Month Infant MRI Brain Segmentation. Retrieved December 22, 2023 from https://iseg2017.web.unc.edu/reference/Google Scholar
- [81] . 2017. Image-to-image translation with conditional adversarial networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1125–1134.Google ScholarCross Ref
- [82] . 2015. Spatial transformer networks. Advances in Neural Information Processing Systems 28 (2015), 1–9.Google Scholar
- [83] . 2022. Systematic review of generative adversarial networks (GANs) for medical image classification and segmentation. Journal of Digital Imaging35, 2 (2022), 137–152.Google ScholarCross Ref
- [84] . 2012. 3D convolutional neural networks for human action recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 35, 1 (2012), 221–231.Google ScholarDigital Library
- [85] . 2019. 3D medical image synthesis by factorised representation and deformable model learning. In Proceedings of the International Workshop on Simulation and Synthesis in Medical Imaging. 110–119.Google ScholarDigital Library
- [86] . 2017. Progressive growing of GANs for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196 (2017).Google Scholar
- [87] . 2019. A style-based generator architecture for generative adversarial networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 4401–4410.Google ScholarCross Ref
- [88] . 2020. Analyzing and improving the image quality of StyleGAN. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 8110–8119.Google ScholarCross Ref
- [89] . 2020. GANs for medical image analysis. Artificial Intelligence in Medicine 109 (2020), 101938.Google ScholarCross Ref
- [90] . 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT. 4171–4186.Google Scholar
- [91] . 2022. Diffusion deformable model for 4D temporal medical image generation. arXiv preprint arXiv:2206.13295 (2022).Google Scholar
- [92] . 2013. Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114 (2013).Google Scholar
- [93] . 2017. Mindboggling morphometry of human brains. PLoS Computational Biology 13, 2 (2017), e1005350.Google ScholarCross Ref
- [94] . 2021. Planar 3D transfer learning for end to end unimodal MRI unbalanced data segmentation. In Proceedings of the 2020 25th International Conference on Pattern Recognition (ICPR ’21). IEEE, Los Alamitos, CA, 6051–6058.Google ScholarCross Ref
- [95] . 2019. Resource efficient 3D convolutional neural networks. In Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops.Google ScholarCross Ref
- [96] . 2021. Learning a generative motion model from image sequences based on a latent motion matrix. IEEE Transactions on Medical Imaging 40, 5 (2021), 1405–1416.Google ScholarCross Ref
- [97] . 2012. ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems 25 (2012), 1–9.Google Scholar
- [98] . 2019. CBIR system using Capsule Networks and 3D CNN for Alzheimer’s disease diagnosis. Informatics in Medicine Unlocked 14 (2019), 59–68.Google ScholarCross Ref
- [99] . 2019. Standardized assessment of automatic segmentation of white matter hyperintensities and results of the WMH segmentation challenge. IEEE Transactions on Medical Imaging 38, 11 (2019), 2556–2568.Google ScholarCross Ref
- [100] . 2019. Generation of 3D brain MRI using auto-encoding generative adversarial networks. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. 118–126.Google ScholarDigital Library
- [101] . 2019. OASIS-3: Longitudinal neuroimaging, clinical, and cognitive dataset for normal aging and Alzheimer disease. MedRxiv 2019 (2019), 1–37.Google Scholar
- [102] . 2020. SC-GAN: 3D self-attention conditional GAN with spectral normalization for multi-modal neuroimaging synthesis. bioRxiv 2020 (2020), 1–35.Google Scholar
- [103] . 2011. The neural autoregressive distribution estimator. In Proceedings of the 14th International Conference on Artificial Intelligence and Statistics. 29–37.Google Scholar
- [104] . 1987. Modeles connexionnistes de l’apprentissage (Connectionist Learning Models). Ph.D. Dissertation. Laboratoire de Dynamique des Reseaux.Google Scholar
- [105] . 1998. Gradient-based learning applied to document recognition. Proceedings of the IEEE 86, 11 (1998), 2278–2324.Google ScholarCross Ref
- [106] . 2022. Pop-out motion: 3D-aware image deformation via learning the shape Laplacian. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 18532–18541.Google ScholarCross Ref
- [107] . 2020. Recent and upcoming technological developments in computed tomography: High speed, low dose, deep learning, multienergy. Investigative Radiology 55, 1 (2020), 8–19.Google ScholarCross Ref
- [108] . 2018. A novel public MR image dataset of multiple sclerosis patients with lesion segmentations based on multi-rater consensus. Neuroinformatics 16, 1 (2018), 51–63.Google ScholarCross Ref
- [109] . 2016. Precomputed real-time texture synthesis with Markovian generative adversarial networks. In Proceedings of the European Conference on Computer Vision. 702–716.Google ScholarCross Ref
- [110] . 2020. Shape-aware semi-supervised 3D semantic segmentation for medical images. In Proceedings of the International Conference on Medical Image Computing, and Computer-Assisted Intervention. 552–561.Google ScholarDigital Library
- [111] . 2018. More knowledge is better: Cross-modality volume completion and 3D+2D segmentation for intracardiac echocardiography contouring. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. 535–543.Google ScholarDigital Library
- [112] . 2018. A large, open source dataset of stroke anatomical brain images and manual lesion segmentations. Scientific Data 5, 1 (2018), 1–11.Google ScholarCross Ref
- [113] . 2020. Synthesizing missing data using 3D reversible GAN for Alzheimer’s disease. In Proceedings of the 2020 International Symposium on Artificial Intelligence in Medical Sciences. 208–213.Google ScholarDigital Library
- [114] . 2021. Bidirectional mapping of brain MRI and PET with 3D reversible GAN for the diagnosis of Alzheimer’s disease. Frontiers in Neuroscience 15 (2021), 646013.Google ScholarCross Ref
- [115] . 2019. Glioma subregions segmentation with a discriminative adversarial regularized 3D Unet. In Proceedings of the 3rd International Symposium on Image Computing and Digital Medicine. 269–273.Google ScholarDigital Library
- [116] . 2019. Few-shot unsupervised image-to-image translation. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 10551–10560.Google ScholarCross Ref
- [117] . 2019. Deep learning in medical ultrasound analysis: A review. Engineering 5, 2 (2019), 261–275.Google ScholarCross Ref
- [118] . 2023. Self-supervised learning: Generative or contrastive. IEEE Transactions on Knowledge and Data Engineering 35, 1 (2023), 857–876.Google Scholar
- [119] . 2023. Inflating 2D convolution weights for efficient generation of 3D medical images. Computer Methods and Programs in Biomedicine 240 (2023), 107685.Google Scholar
- [120] . 2019. Learning to propagate labels: Transductive propagation network for few-shot learning. In Proceedings of the 7th International Conference on Learning Representations (ICLR ’19).Google Scholar
- [121] . 2020. A 3D fully convolutional neural network with top-down attention-guided refinement for accurate and robust automatic segmentation of amygdala and its subnuclei. Frontiers in Neuroscience 14 (2020), 260.Google ScholarCross Ref
- [122] . 2022. Deep learning based brain tumor segmentation: A survey. Complex & Intelligent Systems 94, 4 (2022), 1–26.Google Scholar
- [123] . 2019. An overview of deep learning in medical imaging focusing on MRI. Zeitschrift für Medizinische Physik 29, 2 (2019), 102–127.Google ScholarCross Ref
- [124] . 2017. ISLES 2015—A public evaluation benchmark for ischemic stroke lesion segmentation from multispectral MRI. Medical Image Analysis 35 (2017), 250–269.Google ScholarCross Ref
- [125] . 2007. Open Access Series of Imaging Studies (OASIS): Cross-sectional MRI data in young, middle aged, nondemented, and demented older adults. Journal of Cognitive Neuroscience 19, 9 (2007), 1498–1507.Google ScholarDigital Library
- [126] . 2011. The Parkinson Progression Marker Initiative (PPMI). Progress in Neurobiology 95, 4 (2011), 629–635.Google ScholarCross Ref
- [127] . 2015. MRBrainS challenge: Online evaluation framework for brain image segmentation in 3T MRI scans. Computational Intelligence and Neuroscience 2015 (2015), 813696.Google ScholarDigital Library
- [128] . 2011. Strategies for training large scale neural network language models. In Proceedings of the 2011 IEEE Workshop on Automatic Speech Recognition and Understanding. IEEE, Los Alamitos, CA, 196–201.Google ScholarCross Ref
- [129] . 2016. V-Net: Fully convolutional neural networks for volumetric medical image segmentation. In Proceedings of the 2016 4th International Conference on 3D Vision (3DV ’16). IEEE, Los Alamitos, CA, 565–571.Google ScholarCross Ref
- [130] . 2014. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014).Google Scholar
- [131] . 2012. Making a “completely blind” image quality analyzer. IEEE Signal Processing Letters 20, 3 (2012), 209–212.Google ScholarCross Ref
- [132] . 2018. Few-shot 3D multi-modal medical image segmentation using generative adversarial learning. arXiv preprint arXiv:1810.12241 (2018).Google Scholar
- [133] NAMIC Multimodality. 2023. NAMIC Multimodality Dataset Download Link. Retrieved December 27, 2023 from https://www.na-mic.org/wiki/DownloadsGoogle Scholar
- [134] . 2014. Clinical evaluation of an arterial-spin-labeling product sequence in steno-occlusive disease of the brain. PLoS One 9, 2 (2014), e87143.Google ScholarCross Ref
- [135] . 2018. 3D MRI brain tumor segmentation using autoencoder regularization. In Proceedings of the International MICCAI Brainlesion Workshop. 311–320.Google Scholar
- [136] . 2022. Data harmonisation for information fusion in digital healthcare: A state-of-the-art systematic review, meta-analysis and future research directions. Information Fusion 82 (2022), 99–122.Google ScholarDigital Library
- [137] . 2022. Medical image segmentation with 3D convolutional neural networks: A survey. Neurocomputing 493 (2022), 397–413.Google ScholarDigital Library
- [138] . 2009. Detection and quantification of left atrial structural remodeling with delayed-enhancement magnetic resonance imaging in patients with atrial fibrillation. Circulation 119, 13 (2009), 1758–1767.Google ScholarCross Ref
- [139] . 2017. Conditional image synthesis with auxiliary classifier GANs. In Proceedings of the International Conference on Machine Learning. 2642–2651.Google Scholar
- [140] . 2021. Few-shot image generation via cross-domain correspondence. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 10743–10752.Google ScholarCross Ref
- [141] . 2022. Self-supervised learning for few-shot medical image segmentation. IEEE Transactions on Medical Imaging 41, 7 (2022), 1837–1848.Google ScholarCross Ref
- [142] . 2020. Three dimensional MR image synthesis with progressive generative adversarial networks. arXiv preprint arXiv:2101.05218 (2020).Google Scholar
- [143] . 2018. Synthesizing missing PET from MRI with cycle-consistent generative adversarial networks for Alzheimer’s disease diagnosis. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. 455–463.Google Scholar
- [144] . 2010. Running experiments on Amazon Mechanical Turk. Judgment and Decision Making 5, 5 (2010), 411–419.Google ScholarCross Ref
- [145] . 2020. Deep structural causal models for tractable counterfactual inference. Advances in Neural Information Processing Systems 33 (2020), 857–869.Google Scholar
- [146] . 2021. Multi-modality MR image synthesis via confidence-guided aggregation and cross-modality refinement. IEEE Journal of Biomedical and Health Informatics 26, 1 (2021), 27–35.Google ScholarCross Ref
- [147] . 2020. Multi-scale 3D U-Nets: An approach to automatic segmentation of brain tumor. International Journal of Imaging Systems and Technology 30, 1 (2020), 5–17.Google ScholarCross Ref
- [148] . 2016. Invertible conditional GANs for image editing. arXiv preprint arXiv:1611.06355 (2016).Google Scholar
- [149] . 2017. Deep learning in robotics: A review of recent research. Advanced Robotics 31, 16 (2017), 821–835.Google ScholarCross Ref
- [150] . 2022. Fast unsupervised brain anomaly detection and segmentation with diffusion models. arXiv preprint arXiv:2206.03461 (2022).Google Scholar
- [151] . 2022. Unsupervised brain imaging 3D anomaly detection and segmentation with transformers. Medical Image Analysis 79 (2022), 102475.Google ScholarCross Ref
- [152] . 2021. Equitable modelling of brain imaging by counterfactual augmentation with morphologically constrained 3D deep generative models. arXiv preprint arXiv:2111.14923 (2021).Google Scholar
- [153] . 2019. Bayesian volumetric autoregressive generative models for better semisupervised learning. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. 429–437.Google ScholarDigital Library
- [154] . 2020. Interpretable deep models for cardiac resynchronisation therapy response prediction. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. 284–293.Google ScholarDigital Library
- [155] . 2021. MVSGAN: Spatial-aware multi-view CMR fusion for accurate 3D left ventricular myocardium segmentation. IEEE Journal of Biomedical and Health Informatics 26, 5 (2021), 2264–2275.Google ScholarCross Ref
- [156] . 2022. Generative modelling of the ageing heart with cross-sectional imaging and clinical data. In Proceedings of the International Workshop on Statistical Atlases and Computational Models of the Heart. 3–12.Google ScholarDigital Library
- [157] . 2023. CHeart: A conditional spatio-temporal generative model for cardiac anatomy. arXiv preprint arXiv:2301.13098 (2023).Google Scholar
- [158] . 2009. Evaluation framework for algorithms segmenting short axis cardiac MRI. MIDAS Journal. Retrieved December 22, 2023 from https:midasjournal.org/browse/publication/658Google Scholar
- [159] . 2022. Learning conditional variational autoencoders with missing covariates. arXiv preprint arXiv:2203.01218 (2022).Google Scholar
- [160] . 2022. LDDMM meets GANs: Generative adversarial networks for diffeomorphic registration. In Proceedings of the International Workshop on Biomedical Image Registration. 18–28.Google ScholarDigital Library
- [161] . 2019. Denoising of 3D magnetic resonance images using a residual encoder-decoder Wasserstein generative adversarial network. Medical Image Analysis 55 (2019), 165–180.Google ScholarCross Ref
- [162] . 2021. Recent advances in trustworthy explainable artificial intelligence: Status, challenges, and perspectives. IEEE Transactions on Artificial Intelligence 3, 6 (2021), 852–866.Google ScholarCross Ref
- [163] . 2020. Deep learning for PET image reconstruction. IEEE Transactions on Radiation and Plasma Medical Sciences 5, 1 (2020), 1–25.Google ScholarCross Ref
- [164] . 2016. Generative adversarial text to image synthesis. In Proceedings of the International Conference on Machine Learning. 1060–1069.Google Scholar
- [165] . 2018. voxel-GAN: Adversarial framework for learning imbalanced brain tumor segmentation. In Proceedings of the International MICCAI Brainlesion Workshop. 321–333.Google Scholar
- [166] . 2022. RIRE Dataset. Retrieved December 22, 2023 from https://www.insight-journal.org/rire/Google Scholar
- [167] . 2004. Evaluation of atlas selection strategies for atlas-based image segmentation with application to confocal microscopy images of bee brains. NeuroImage 21, 4 (2004), 1428–1442.Google ScholarCross Ref
- [168] . 2015. U-Net: Convolutional networks for biomedical image segmentation. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. 234–241.Google ScholarCross Ref
- [169] . 2017. Variational approaches for auto-encoding generative adversarial networks. arXiv preprint arXiv:1706.04987 (2017).Google Scholar
- [170] . 2017. Dynamic routing between capsules. Advances in Neural Information Processing Systems 30 (2017), 1–11.Google Scholar
- [171] . 2017. Tversky loss function for image segmentation using 3D fully convolutional deep networks. In Proceedings of the International Workshop on Machine Learning in Medical Imaging. 379–387.Google ScholarCross Ref
- [172] . 2016. Improved techniques for training GANs. Advances in Neural Information Processing Systems 29 (2016), 1–11.Google Scholar
- [173] . 2021. Generative adversarial networks (GANs) challenges, solutions, and future directions. ACM Computing Surveys 54, 3 (2021), 1–42.Google ScholarDigital Library
- [174] . 2020. Data augmentation of 3D brain environment using deep convolutional refined auto-encoding alpha GAN. IEEE Transactions on Medical Robotics and Bionics 3, 1 (2020), 269–272.Google ScholarCross Ref
- [175] . 2021. Segmentation of vestibular schwannoma from MRI, an open annotated dataset and baseline algorithm. Scientific Data 8, 1 (2021), 1–6.Google ScholarCross Ref
- [176] . 2008. Construction of a 3D probabilistic atlas of human cortical structures. NeuroImage 39, 3 (2008), 1064–1080.Google ScholarCross Ref
- [177] . 2021. MRI to PET cross-modality translation using globally and locally aware GAN (GLA-GAN) for multi-modal diagnosis of Alzheimer’s disease. arXiv preprint arXiv:2108.02160 (2021).Google Scholar
- [178] . 2019. A large annotated medical image dataset for the development and evaluation of segmentation algorithms. arXiv preprint arXiv:1902.09063 (2019).Google Scholar
- [179] . 2013. Efficient and reproducible high resolution spiral myocardial phase velocity mapping of the entire cardiac cycle. Journal of Cardiovascular Magnetic Resonance 15, 1 (2013), 1–14.Google ScholarCross Ref
- [180] . 2014. Spiral tissue phase velocity mapping in a breath-hold with non-Cartesian SENSE. Magnetic Resonance in Medicine 72, 3 (2014), 659–668.Google ScholarCross Ref
- [181] . 2020. 3D deep learning on medical images: A review. Sensors 20, 18 (2020), 5097.Google ScholarCross Ref
- [182] . 2015. Deep unsupervised learning using nonequilibrium thermodynamics. In Proceedings of the International Conference on Machine Learning. 2256–2265.Google Scholar
- [183] . 2015. Learning structured output representation using deep conditional generative models. Advances in Neural Information Processing Systems 28 (2015), 1–9.Google Scholar
- [184] . 2017. VEEGAN: Reducing mode collapse in GANs using implicit variational learning. Advances in Neural Information Processing Systems 30 (2017), 1–11.Google Scholar
- [185] . 2022. Generating 3D TOF-MRA volumes and segmentation labels using generative adversarial networks. Medical Image Analysis 78 (2022), 102396.Google ScholarCross Ref
- [186] . 2015. UK biobank: An open access resource for identifying the causes of a wide range of complex diseases of middle and old age. PLoS Medicine 12, 3 (2015), e1001779.Google ScholarCross Ref
- [187] . 2014. A collaborative resource to build consensus for automated left ventricular segmentation of cardiac MR images. Medical Image Analysis 18, 1 (2014), 50–62.Google ScholarCross Ref
- [188] . 2022. Hierarchical amortized GAN for 3D high resolution medical image synthesis. IEEE Journal of Biomedical and Health Informatics 26, 8 (2022), 3966–3975.Google ScholarCross Ref
- [189] . 2018. The limits and potentials of deep learning for robotics. International Journal of Robotics Research 37, 4-5 (2018), 405–420.Google ScholarCross Ref
- [190] . 2014. Sequence to sequence learning with neural networks. Advances in Neural Information Processing Systems 27 (2014), 1–9.Google Scholar
- [191] . 2020. Alleviation of gradient exploding in GANs: Fake can be real. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 1191–1200.Google ScholarCross Ref
- [192] . 2020. Catastrophic forgetting and mode collapse in GANs. In Proceedings of the 2020 International Joint Conference on Neural Networks (IJCNN ’20). IEEE, Los Alamitos, CA, 1–10.Google ScholarCross Ref
- [193] . 2015. Efficient object localization using convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 648–656.Google ScholarCross Ref
- [194] . 2022. Quality assessment of anatomical MRI images from generative adversarial networks: Human assessment and image quality metrics. Journal of Neuroscience Methods 374 (2022), 109579.Google ScholarCross Ref
- [195] . 2021. Repurposing GANs for one-shot semantic part segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 4475–4485.Google ScholarCross Ref
- [196] . 2021. Brain MR image enhancement for tumor segmentation using 3D U-Net. Sensors 21, 22 (2021), 7528.Google ScholarCross Ref
- [197] . 2019. Unsupervised pathology detection in medical images using conditional variational autoencoders. International Journal of Computer Assisted Radiology and Surgery 14, 3 (2019), 451–461.Google ScholarCross Ref
- [198] . 2016. Conditional image generation with PixelCNN decoders. Advances in Neural Information Processing Systems 29 (2016), 1–9.Google Scholar
- [199] . 2017. Neural discrete representation learning. Advances in Neural Information Processing Systems 30 (2017), 1–10.Google Scholar
- [200] . 2019. Reversible GANs for memory-efficient image-to-image translation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 4720–4728.Google Scholar
- [201] . 2013. The WU-Minn Human Connectome Project: An overview. NeuroImage 80 (2013), 62–79.Google ScholarCross Ref
- [202] . 2016. Pixel recurrent neural networks. In Proceedings of the International Conference on Machine Learning. 1747–1756.Google Scholar
- [203] . 2017. Attention is all you need. Advances in Neural Information Processing Systems 30 (2017), 1–11.Google Scholar
- [204] . 2020. Fully automated 3D cardiac MRI localisation and segmentation using deep neural networks. Journal of Imaging 6, 7 (2020), 65.Google ScholarCross Ref
- [205] . 2008. Extracting and composing robust features with denoising autoencoders. In Proceedings of the 25th International Conference on Machine Learning. 1096–1103.Google ScholarDigital Library
- [206] . 2010. Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. Journal of Machine Learning Research 11, 12 (2010), 1–38.Google Scholar
- [207] . 2020. Modelling the distribution of 3D brain MRI using a 2D slice VAE. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. 657–666.Google ScholarDigital Library
- [208] . 2019. TPSDicyc: Improved deformation invariant cross-domain medical image synthesis. In Proceedings of the 2nd International Workshop on Machine Learning for Medical Image Reconstruction (MLMIR ’19). 245–254.Google Scholar
- [209] . 2021. DiCyc: GAN-based deformation invariant cross-domain information fusion for medical image synthesis. Information Fusion 67 (2021), 147–160.Google ScholarCross Ref
- [210] . 2019. RP-Net: A 3D convolutional neural network for brain segmentation from magnetic resonance imaging. IEEE Access 7 (2019), 39670–39679.Google ScholarCross Ref
- [211] . 2018. ESRGAN: Enhanced super-resolution generative adversarial networks. In Proceedings of the European Conference on Computer Vision Workshops (ECCV ’18).Google Scholar
- [212] . 2020. Generalizing from a few examples: A survey on few-shot learning. ACM Computing Surveys 53, 3 (2020), 1–34.Google ScholarDigital Library
- [213] . 2018. 3D conditional generative adversarial networks for high-quality PET image estimation at low dose. NeuroImage 174 (2018), 550–562.Google ScholarCross Ref
- [214] . 2018. 3D auto-context-based locality adaptive multi-modality GANs for PET synthesis. IEEE Transactions on Medical Imaging 38, 6 (2018), 1328–1339.Google ScholarCross Ref
- [215] . 2017. The Alzheimer’s Disease Neuroimaging Initiative 3: Continued innovation for clinical trial improvement. Alzheimer’s & Dementia 13, 5 (2017), 561–571.Google ScholarCross Ref
- [216] . 2017. Generative adversarial networks for noise reduction in low-dose CT. IEEE Transactions on Medical Imaging 36, 12 (2017), 2536–2545.Google ScholarCross Ref
- [217] . 2016. Deep learning computed tomography. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. 432–440.Google ScholarDigital Library
- [218] . 2019. Consistent brain ageing synthesis. In Proceedings of the 22nd International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI ’19). 750–758.Google Scholar
- [219] . 2021. A review of deep learning-based three-dimensional medical image registration methods. Quantitative Imaging in Medicine and Surgery 11, 12 (2021), 4895.Google ScholarCross Ref
- [220] . 2023. HDL: Hybrid deep learning for the synthesis of myocardial velocity maps in Digital Twins for cardiac analysis. IEEE Journal of Biomedical and Health Informatics 27, 10 (2023), 5134–5142.Google ScholarCross Ref
- [221] . 2022. CS 2: A controllable and simultaneous synthesizer of images and annotations with minimal human intervention. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. 3–12.Google ScholarDigital Library
- [222] . 2022. Non-imaging medical data synthesis for trustworthy AI: A comprehensive survey. arXiv preprint arXiv:2209.09239 (2022).Google Scholar
- [223] . 2022. Synthetic velocity mapping cardiac MRI coupled with automated left ventricle segmentation. In Medical Imaging 2022: Image Processing, Vol. 12032. SPIE, 781–785.Google Scholar
- [224] . 2022. A cascaded multi-task generative framework for detecting aortic dissection on 3D non-contrast-enhanced computed tomography. IEEE Journal of Biomedical and Health Informatics 26, 10 (2022), 5177–5188.Google ScholarCross Ref
- [225] . 2021. A global benchmark of algorithms for segmenting the left atrium from late gadolinium-enhanced cardiac magnetic resonance imaging. Medical Image Analysis 67 (2021), 101832.Google ScholarCross Ref
- [226] . 2020. Segmentation and quantification of infarction without contrast agents via spatiotemporal generative adversarial learning. Medical Image Analysis 59 (2020), 101568.Google ScholarCross Ref
- [227] . 2018. MuTGAN: Simultaneous segmentation and quantification of myocardial infarction without contrast agents via joint adversarial learning. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. 525–534.Google ScholarDigital Library
- [228] . 2020. Contrast agent-free synthesis and segmentation of ischemic heart disease images using progressive sequential causal GANs. Medical Image Analysis 62 (2020), 101668.Google ScholarCross Ref
- [229] . 2016. Attribute2Image: Conditional image generation from visual attributes. In Proceedings of the European Conference on Computer Vision. 776–791.Google ScholarCross Ref
- [230] . 2018. 3D LV probabilistic segmentation in cardiac MRI using generative adversarial network. In Proceedings of the International Workshop on Statistical Atlases and Computational Models of the Heart. 181–190.Google Scholar
- [231] . 2021. Synthesizing multi-contrast MR images via novel 3D conditional variational auto-encoding GAN. Mobile Networks and Applications 26, 1 (2021), 415–424.Google ScholarCross Ref
- [232] . 2021. MedMNIST v2: A large-scale lightweight benchmark for 2D and 3D biomedical image classification. arXiv preprint arXiv:2110.14795 (2021).Google Scholar
- [233] . 2022. A novel 3D unsupervised domain adaptation framework for cross-modality medical image segmentation. IEEE Journal of Biomedical and Health Informatics 26, 10 (2022), 4976–4986.Google ScholarCross Ref
- [234] . 2019. Generative adversarial network in medical imaging: A review. Medical Image Analysis 58 (2019), 101552.Google ScholarCross Ref
- [235] . 2018. 3D cGAN based cross-modality MR image synthesis for brain tumor segmentation. In Proceedings of the 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI ’18). IEEE, Los Alamitos, CA, 626–630.Google ScholarCross Ref
- [236] . 2019. Ea-GANs: Edge-aware generative adversarial networks for cross-modality MR image synthesis. IEEE Transactions on Medical Imaging 38, 7 (2019), 1750–1762.Google ScholarCross Ref
- [237] . 2020. Sample-adaptive GANs: Linking global and local mappings for cross-modality MR image synthesis. IEEE Transactions on Medical Imaging 39, 7 (2020), 2339–2350.Google ScholarCross Ref
- [238] . 2019. Uncertainty-aware self-ensembling model for semi-supervised 3D left atrium segmentation. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. 605–613.Google ScholarDigital Library
- [239] . 2020. Unified generative adversarial networks for multimodal segmentation from unpaired 3D medical images. Medical Image Analysis 64 (2020), 101731.Google ScholarCross Ref
- [240] . 2022. Progressively volumetrized deep generative models for data-efficient contextual learning of MR image recovery. Medical Image Analysis 78 (2022), 102429.Google ScholarCross Ref
- [241] . 2018. fastMRI: An open dataset and benchmarks for accelerated MRI. arXiv preprint arXiv:1811.08839 (2018).Google Scholar
- [242] . 2021. Cross-modality deep feature learning for brain tumor segmentation. Pattern Recognition 110 (2021), 107562.Google ScholarCross Ref
- [243] . 2017. Stackgan: Text to photo-realistic image synthesis with stacked generative adversarial networks. In Proceedings of the IEEE International Conference on Computer Vision. 5907–5915.Google ScholarCross Ref
- [244] . 2018. StackGAN++: Realistic image synthesis with stacked generative adversarial networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 41, 8 (2018), 1947–1962.Google ScholarCross Ref
- [245] . 2017. Semi-supervised assessment of incomplete LV coverage in cardiac MRI using generative adversarial nets. In Proceedings of the International Workshop on Simulation and Synthesis in Medical Imaging. 61–68.Google ScholarCross Ref
- [246] . 2020. Deform-GAN: An unsupervised learning model for deformable registration. arXiv preprint arXiv:2002.11430 (2020).Google Scholar
- [247] . 2018. Translating and segmenting multimodal medical volumes with cycle-and shape-consistency generative adversarial network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 9242–9251.Google ScholarCross Ref
- [248] . 2021. Improved transformer for high-resolution GANs. Advances in Neural Information Processing Systems 34 (2021), 18367–18380.Google Scholar
- [249] . 2021. MRI-Trans-GAN: 3D MRI cross-modality translation. In Proceedings of the 2021 40th Chinese Control Conference (CCC ’21). IEEE, Los Alamitos, CA, 7229–7234.Google ScholarCross Ref
- [250] . 2019. Unsupervised 3D end-to-end medical image registration with volume tweening network. IEEE Journal of Biomedical and Health Informatics 24, 5 (2019), 1394–1404.Google ScholarCross Ref
- [251] . 2021. Improved consistency regularization for GANs. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 11033–11041.Google ScholarCross Ref
- [252] . 2022. 3D segmentation guided style-based generative adversarial networks for PET synthesis. IEEE Transactions on Medical Imaging 41, 8 (2022), 2092–2104.Google Scholar
- [253] . 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
- [254] . 2022. Non-rigid multi-modal brain image registration based on two-stage generative adversarial nets. Neurocomputing 505 (2022), 44–57.Google ScholarDigital Library
- [255] . 2021. Joint affine and deformable three-dimensional networks for brain MRI registration. Medical Physics 48, 3 (2021), 1182–1196.Google ScholarCross Ref
- [256] . 2016. Multi-scale patch and multi-modality atlases for whole heart segmentation of MRI. Medical Image Analysis 31 (2016), 77–87.Google ScholarCross Ref
Index Terms
- 3D Brain and Heart Volume Generative Models: A Survey
Recommendations
Mixed-membership naive Bayes models
In recent years, mixture models have found widespread usage in discovering latent cluster structure from data. A popular special case of finite mixture models is the family of naive Bayes (NB) models, where the probability of a feature vector factorizes ...
Dynamical Deep Generative Latent Modeling of 3D Skeletal Motion
AbstractIn this paper, we propose a Bayesian switching dynamical model for segmentation of 3D pose data over time that uncovers interpretable patterns in the data and is generative. Our model decomposes highly correlated skeleton data into a set of few ...
A comprehensive survey and analysis of generative models in machine learning
AbstractGenerative models have been in existence for many decades. In the field of machine learning, we come across many scenarios when directly learning a target is intractable through discriminative models, and in such cases the joint ...
Highlights- Generative models generate joint distribution of target and training data.
- ...
Comments