CoChat
Sign Up
PreprintCited by 6Generative Adversarial Networks and Image SynthesisExplainable Artificial Intelligence (XAI)Artificial Intelligence in Healthcare and Education

The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.

Review of Disentanglement Approaches for Medical Applications: Towards Solving the Gordian Knot of Generative Models in Healthcare

Open access
Fragemann, Jana, Ardizzone, Lynton, Egger, Jan, Kleesiek, Jens, Workshop, Mad·2022
DOI 10.36227/techrxiv.19364897.v1
Open this paper in CoChat — free accountOpen PDF

Abstract

Deep neural networks are commonly used for medical purposes such as image generation, segmentation, or classification. Besides this, they are often criticized as black boxes as their decision process is often not human interpretable. Encouraging the latent representation of a generative model to be disentangled offers new perspectives of control and interpretability. Understanding the data generation process could help to create artificial medical data sets without violating patient privacy, synthesizing different data modalities, or discovering data generating characteristics. These characteristics might unravel novel relationships that can be related to genetic traits or patient outcomes. In this paper, we give a comprehensive overview of popular generative models, like Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and Flow-based Models. Furthermore, we summarize the different notions of disentanglement, review approaches to disentangle latent space representations and metrics to evaluate the degree of disentanglement. After introducing the theoretical frameworks, we give an overview of recent medical applications and discuss the impact and importance of disentanglement approaches for medical applications. Keywords: Generative Models, Disentanglement, Representation Learning, Medical Applications

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.36227/techrxiv.19364897.v1

Cites

9 of 9 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • The development of disentanglement learning enables a more interpretable and controllable understanding and generating of biomedical datasets.

    “Moreover, the development of disentanglement learning enables a more interpretable and controllable understanding and generating of biomedical datasets [57].”

    From Challenges in AI-driven Biomedical Multimodal Data Fusion and Analysis (2025) · cites this paper as [57]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 101

  1. Abbasi, A., Monadjemi, A., Fang, L., Rabbani, H., 2018. Optical coherence tomography retinal image reconstruction via nonlocal weighted sparse rep- resentation. Journal of Biomedical Optics 23, 1. doi:10.1117/1.JBO.23.3.036011. · DOI
  2. Arjovsky, M., Chintala, S., Bottou, L., 2017. Wasser- stein generative adversarial networks, in: Interna- tional conference on machine learning, PMLR. pp. 214-223.
  3. Armato III, S.G., McLennan, G., Bidaut, L., McNitt- Gray, M.F., et. al., 2011. The lung image database consortium (lidc) and image database resource initiative (idri): a completed reference database of lung nodules on ct scans. Medical Physics, 38(2):915-931 .
  4. Athanasiadis, E., et al., 2017. Single-cell rna- sequencing uncovers transcriptional states and fate decisions in haematopoiesis. Nature com- munications 8, 2045, https://doi.org/10.1038/ s41467-017-02305-6. · DOI
  5. Bastidas-Ponce, A., Tritschler, S., Dony, L., Scheib- ner, K., Tarquis-Medina, M., Salinno, C., Schirge, S., Burtscher, I., Böttcher, A., Theis, F.J., Lick- ert, H., Bakhti, M., Klein, A., Treutlein, B., 2019. Comprehensive single cell mRNA pro- filing reveals a detailed roadmap for pancre- atic endocrinogenesis. Development 146. URL: https://doi.org/10.1242/dev.173849, doi:10.1242/dev.173849. dev173849. · DOI
  6. Behrmann, J., Grathwohl, W., Chen, R.T.Q., Duve- naud, D., Jacobsen, J., 2019. Invertible residual networks, in: Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA, pp. 573-582, http://proceedings.mlr.press/v97/ behrmann19a.html.
  7. Ben-Cohen, A., Mechrez, R., Yedidia, N., Greenspan, H., 2019. Improving cnn training using disentan- glement for liver lesion classification in ct. in: Proc. IEEE Engineering in Medicine and Biology Society (EMBC), pp. 886-889.
  8. Bepler, T., Zhong, E., Kelley, K., Brignole, E., Berger, B., 2019. Explicitly disentangling image content from translation and rotation with spatial-vae. Ad- vances in Neural Information Processing Systems 2019, 15409-15419.
  9. Bica, I., Andrés-Terré, H., Cvejic, A., et al., 2020. Unsupervised generative and graph representation learning for modelling cell differentiation. Sci Rep 10, 9790. https: //doi.org/10.1038/s41598-020-66166-8. · DOI
  10. Bousquet, O., Gelly, S., Tolstikhin, I., Simon-Gabriel, C.J., Schoelkopf, B., 2017. From optimal trans- port to generative modeling: the vegan cookbook. arXiv:1705.07642 . · arXiv
  11. Chen, J., Batmanghelich, K., 2020. Weakly supervised disentanglement by pairwise similarities. Proc Conf AAAI Artif Intell. 2020 Feb;34(4). doi:10.1609/ aaai.v34i04.5754. · DOI
  12. Chen, R.T., Rubanova, Y., Bettencourt, J., Duvenaud, D.K., 2018a. Neural ordinary differential equa- tions. Advances in neural information processing systems 31.
  13. Chen, T.Q., Li, X., Grosse, R.B., Duvenaud, D., 2018b. Isolating sources of disentanglement in variational autoencoders. CoRR abs/1802.04942. URL: http: //arxiv.org/abs/1802.04942, arXiv:1802.04942. · arXiv
  14. Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P., 2016. Infogan: Inter- pretable representation learning by informa- tion maximizing generative adversarial nets. arXiv:1606.03657. · arXiv
  15. Christ, P., Ettlinger, F., Grün, F., Lipkova, J., Kaissis, G., 2017. Lits-liver tumor segmentation challenge. ISBI and MICCAI.
  16. Dinh, L., Krueger, D., Bengio, Y., 2015. Nice: Non-linear independent components estimation. arXiv:1410.8516. · arXiv
  17. Dinh, L., Sohl-Dickstein, J., Bengio, S., 2016. Density estimation using real nvp. arXiv:1605.08803. · arXiv
  18. Do, K., Tran, T., 2021. Theory and evaluatin metrics for learning disentangled representations. arXiv:1908.09961. · arXiv
  19. Donahue, J., Simonyan, K., 2019. Large scale adversarial representation learning, in: Wal- lach, H., Larochelle, H., Beygelzimer, A., d'Alché-Buc, F., Fox, E., Garnett, R. (Eds.), Advances in Neural Information Process- ing Systems, Curran Associates, Inc., https: //proceedings.neurips.cc/paper/2019/file/ 18cdf49ea54eec029238fcc95f76ce41-Paper.pdf.
  20. Duan, S., Matthey, L., Saraiva, A., Watters, N., Burgess, C., Lerchner, A., Higgins, I., 2019. Unsupervised model selection for variational disentangled repre- sentation learning, in: International Conference on Learning Representations.
  21. Eastwood, C., Williams, C.K.I., 2018. A framework for the quantitative evaluation of disentan- gled representations, in: International Con- ference on Learning Representations,https: //openreview.net/forum?id=By-7dz-AZ.
  22. Esser, P., Rombach, R., Ommer, B., 2020. A disentan- gling invertible interpretation network for explain- ing latent representations. arXiv:2004.13166. · arXiv
  23. Fei, Y., Zhan, B., Hong, M., Wu, X., Zhou, J., Wang, Y., 2021. Deep learning-based multi-modal com- puting with feature disentanglement for mri im- age synthesis. Med Phys. 2021 Jul;48(7):3778-3789. doi: 10.1002/mp.14929. Epub 2021 Jun 7. PMID: 33959965. · DOI
  24. Gillies, R.J., Kinahan, P.E., Hricak, H., 2016. Ra- diomics: Images are more than pictures, they are data. Radiology 278, 563-577. URL: https://doi.org/10.1148/radiol. 2015151169, doi:10.1148/radiol.2015151169, arXiv:https://doi.org/10.1148/radiol.2015151169. pMID: 26579733. · DOI · Paper page
  25. Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Ben- gio, Y., 2014. Generative adversarial networks. arXiv:1406.2661. · arXiv
  26. Grathwohl, W., Chen, R.T., Bettencourt, J., Sutskever, I., Duvenaud, D., 2018. Ffjord: Free-form contin- uous dynamics for scalable reversible generative models, in: International Conference on Learning Representations.
  27. Griffiths, T.L., Ghahramani, Z., 2011. The indian buf- fet process: An introduction and review. Journal of Machine Learning Research 12, 1185-1224, http: //jmlr.org/papers/v12/griffiths11a.html.
  28. Gyawali, P., Murkute, J., Toloubidokhti, M., Jiang, X., Horacek, B., Sapp, J., Wang, L., 2021. Learning to disentangle inter-subject anatomical variations in electrocardiographic data. IEEE Trans Biomed Eng. 2021 Aug 30;PP. doi: 10.1109/TBME.2021.3108164. Epub ahead of print. PMID: 34460360. · DOI
  29. Gyawali, P.K., Horacek, B.M., Sapp, J.L., Wang, L., 2019. Sequential factorized autoencoder for lo- calizing the origin of ventricular activation from 12-lead electrocardiograms. IEEE Transactions on Biomedical Engineering 67, 1505-1516.
  30. Higgins, I., Amos, D., Pfau, D., Racaniere, S., Matthey, L., Rezende, D., Lerchner, A., 2018. Towards a definition of disentangled representations. arXiv:1812.02230. · arXiv
  31. Higgins, I., Matthey, L., Pal, A., Burgess, C.P., Glo- rot, X., Botvinick, M., Mohamed, S., Lerchner, A., 2017. beta-vae: Learning basic visual concepts with a constrained variational framework, in: ICLR.
  32. Howell, B., et al., 2019. "the unc/umn baby connec- tome project (bcp): an overview of the study design and protocol development,". NeuroImage, vol. 185, pp. 891-905, 2019. [PubMed: 29578031] .
  33. Hu, D., Wang, F., Zhang, H., Wu, Z., Wang, L., Lin, W., Li, G., Shen, D., Consortium, U.B.C.P., et al., 2020. Disentangled intensive triplet autoencoder for in- fant functional connectome fingerprinting, in: In- ternational Conference on Medical Image Comput- ing and Computer-Assisted Intervention, Springer. pp. 72-82.
  34. Hu, D., Zhang, H., Wu, Z., Wang, F., Wang, L., Smith, J.K., Lin, W., Li, G., Shen, D., 2021. Disentangled-multimodal adversarial autoen- coder: Application to infant age prediction with incomplete multimodal neuroimages. IEEE Trans Med Imaging. 2020 Dec;39(12):4137-4149. doi: 10.1109/TMI.2020.3013825. Epub 2020 Nov 30. PMID: 32746154; PMCID: PMC7773223. · DOI
  35. Huang, Y., Xia, W., Lu, Z., Liu, Y., Chen, H., Zhou, J., Fang, L., Zhang, Y., 2021. Noise-powered disentan- gled representation for unsupervised speckle re- duction of optical coherence tomography images. IEEE Trans Med Imaging. 2021 Oct;40(10):2600- 2614. doi: 10.1109/TMI.2020.3045207. Epub 2021 Sep 30. PMID: 33326376. · DOI
  36. Hyvärinen, A., Oja, E., 2000. Independent compo- nent analysis: algorithms and applications. Neural Netw. 2000 May-Jun;13(4-5):411-30. doi:doi:10. 1016/s0893-6080(00)00026-5.PMID:10946390. · DOI
  37. Justusson, B.I., 1981. Median Filtering: Statistical Properties. Springer Berlin Heidelberg, Berlin, Hei- delberg. pp. 161-196. URL: https://doi.org/10. 1007/BFb0057597, doi:10.1007/BFb0057597. · DOI
  38. Jutten, C., Herault, J., 1991. Blind separation of sources, part i: An adaptive algorithm based on neuromimetic architecture. Signal Processing 24, 1-10. URL: https://www.sciencedirect. com/science/article/pii/016516849190079X, doi:https://doi.org/10.1016/0165-1684(91) 90079-X. · DOI
  39. Kalinin, S.V., Zhang, S., Valleti, M., Pyles, H., Baker, D., Yoreo, J.J.D., Ziatdinov, M., 2021. Disentangling rotational dynamics and ordering transitions in a system of self-organizing protein nanorods via rotationally invariant latent representations. ACS Nano. 2021 Apr 27;15(4):6471-6480. doi: 10.1021/acsnano.0c08914. Epub 2021 Apr 16. PMID: 33861068. · DOI
  40. Karras, T., Laine, S., Aila, T., 2019. A style-based gen- erator architecture for generative adversarial net- works, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 4401-4410.
  41. Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T., 2020. Analyzing and improving the image quality of stylegan. arXiv:1912.04958. · arXiv
  42. Khemakhem, I., Kingma, D.P., Monti, R.P., Hyvärinen, A., 2020. Variational autoencoders and nonlinear ica: A unifying framework. arXiv:1907.04809. · arXiv
  43. Kim, H., Mnih, A., 2019. Disentangling by factorising. arXiv:1802.05983. · arXiv
  44. Kim, M., Wang, Y., Sahu, P., Pavlovic, V., 2019. Rele- vance factor vae: Learning and identifying disen- tangled factors. arXiv:1902.01568. · arXiv
  45. Kingma, D.P., Dhariwal, P., 2018. Glow: Gen- erative flow with invertible 1x1 convolutions. arXiv:1807.03039. · arXiv
  46. Kingma, D.P., Welling, M., 2014. Auto-encoding vari- ational bayes. arXiv:1312.6114. · arXiv
  47. Kleesiek, J., Kersjes, B., Ueltzhöffer, K., Murray, J.M., Rother, C., Köthe, U., Schlemmer, H.P., 2021. Discovering digital tumor signatures-using latent code representations to manipulate and classify liver lesions. Cancers 13. URL: https://www.mdpi.com/2072-6694/13/13/3108, doi:10.3390/cancers13133108. · DOI
  48. Kompa, B., Coker, B., 2020. Learning a latent space of highly multidimensional cancer data. Pacific Sym- posium on Biocomputing. Pacific Symposium on Biocomputing vol. 25 (2020): 379-390.
  49. Kumar, A., Sattigeri, P., Balakrishnan, A., 2018. Vari- ational inference of disentangled latent concepts from unlabeled observations, in: International Conference on Learning Representations.
  50. Lang, O., Gandelsman, Y., Yarom, M., Wald, Y., Elidan, G., Hassidim, A., Freeman, W.T., Isola, P., Glober- son, A., Irani, M., Mosseri, I., 2021. Explaining in style: Training a gan to explain a classifier in stylespace. arXiv:2104.13369. · arXiv
  51. Lee, J., Gu, J., Ye, J.C., 2021. Unsupervised ct metal artifact learning using attention-guided -cyclegan. IEEE Transactions on Medical Imaging 40, 3932- 3944. doi:10.1109/TMI.2021.3101363. · DOI
  52. Li, J., Pimentel, P., Szengel, A., Ehlke, M., Lamecker, H., Zachow, S., Estacio, L., Doenitz, C., Ramm, H., Shi, H., et al., 2021. Autoimplant 2020-first mic- cai challenge on automatic cranial implant design. IEEE transactions on medical imaging 40, 2329- 2342.
  53. Li, J., Yang, S., Huang, X., Da, Q., Yang, X., Hu, Z., Duan, Q., Wang, C., Li, H., 2019. Signet ring cell detection with a semi-supervised learning frame- work, in: International conference on information processing in medical imaging, Springer. pp. 842- 854.
  54. Liao, H., Lin, W.A., Zhou, S.K., Luo, J., 2020. Adn: Artifact disentanglement network for unsu- pervised metal artifact reduction. IEEE Trans Med Imaging. 2020 Mar;39(3):634-643. doi: 10.1109/TMI.2019.2933425. Epub 2019 Aug 5. PMID: 31395543. · DOI
  55. Lin, Z., Thekumparampil, K.K., Fanti, G., Oh, S., 2020. Infogan-cr and modelcentrality: Self-supervised model training and selection for disentangling gans. arXiv:1906.06034. · arXiv
  56. Liu, A., Liu, Y.C., Yeh, Y.Y., Wang, Y.C., 2014. A unified feature disentangler for multi-domain image trans- lation and manipulation. in Advances in Neural Information Processing Systems 31, eds.
  57. Bengio S, Wallach H, Larochelle H, Grauman K, Cesa-Bianchi N and Garnett R (Curran Associates, Inc., 2018) pp. 2595-2604.
  58. Liu, X., Sanchez, P., Thermos, S., O'Neil, A.Q., Tsaf- taris, S.A., 2021a. Learning disentangled represen- tations in the imaging domain. arXiv:2108.12043. · arXiv
  59. Liu, X., Xing, F., Fakhri, G.E., Woo, J., 2021b. A unified conditional disentanglement framework for multimodal brain mr image translation. Proc IEEE Int Symp Biomed Imaging. 2021 Apr;2021:10.1109/isbi48211.2021.9433897. doi: 10.1109/isbi48211.2021.9433897. PMID: 34567419; PMCID: PMC8460116. · DOI
  60. Locatello, F., Bauer, S., Lucic, M., Gelly, S., Schölkopf, B., Bachem, O., 2018. Challenging common assumptions in the unsupervised learning of dis- entangled representations. CoRR abs/1811.12359. URL: http://arxiv.org/abs/1811.12359, arXiv:1811.12359. · arXiv
  61. Locatello, F., Bauer, S., Lucic, M., Raetsch, G., Gelly, S., Schölkopf, B., Bachem, O., 2020. A sober look at the unsupervised learning of disentangled rep- resentations and their evaluation. Journal of Ma- chine Learning Research 21, 1-62. URL: http:// jmlr.org/papers/v21/19-976.html.
  62. Makhzani, A., 2019. Implicit autoencoders. arXiv:1805.09804. · arXiv
  63. Makhzani, A., Shlens, J., Jaitly, N., Goodfellow, I., Frey, B., 2016. Adversarial autoencoders. arXiv:1511.05644. · arXiv
  64. Mathieu, E., Rainforth, T., Siddharth, N., Teh, Y.W., 2019. Disentangling disentanglement in varia- tional autoencoders. arXiv:1812.02833. · arXiv
  65. Menze, B., et al., 2014. The multimodal brain tu- mor image segmentation benchmark (brats). IEEE transactions on medical imaging 34, 1993-2024.
  66. Menze, B., et al., 2015. The multimodal brain tu- mor image segmentation benchmark (brats). IEEE transactions on medical imaging 34, 1993-2024.
  67. Mitchell, G.F., Hwang, S.J., Vasan, R.S., Larson, M.G., Pencina, M.J., Hamburg, N.M., Vita, J.A., Levy, D., Benjamin, E.J., 2010. Arterial stiffness and cardio- vascular events: the framingham heart study. Cir- culation 121(4): 505.
  68. Montero, M.L., Ludwig, C.J., Costa, R.P., Malhotra, G., Bowers, J., 2021. The role of disentangle- ment in generalisation, in: International Confer- ence on Learning Representations. URL: https: //openreview.net/forum?id=qbH974jKUVy.
  69. Moody, G.B., Mark, R.G., 2001. The impact of the mitbih arrhythmia database. IEE Engineering in Medicine and Biology Magazine, vol.20, no. 3, pp. 45-50.
  70. Nensa, F., Demircioglu, A., Rischpler, C., 2019. Arti- ficial intelligence in nuclear medicine. Journal of Nuclear Medicine 60, 29S-37S. URL: https://jnm. snmjournals.org/content/60/Supplement_2/29S, doi:10.2967/jnumed.118.220590. · DOI
  71. Ouyang, J., Adeli, E., Pohl, K.M., Zhao, Q., Zaharchuk, G., 2021. Representation disentanglement for multi-modal brain mri analysis, in: International Conference on Information Processing in Medical Imaging, Springer. pp. 321-333.
  72. Peebles, W., Peebles, J., Zhu, J.Y., Efros, A., Torralba, A., 2020. The hessian penalty: A weak prior for un- supervised disentanglement. arXiv:2008.10599. · arXiv
  73. Quan, S.F., V Howard, B., Iber, C., Kiley, J., Nieto, F., O'Connor, G., Rapoport, D., Redline, S., Rob- bins, J., Samet, J.e.a., 1997. "the sleep heart health study: design, rationale, and methods.". Sleep 20(12):1077-1085. .
  74. Ren, X., Yang, T., Wang, Y., Zeng, W., 2021. Do gen- erative models know disentanglement? contrastive learning is all you need. arXiv:2102.10543. · arXiv
  75. Ridgeway, K., Mozer, M.C., 2018. Learning deep disentangled embeddings with the f-statistic loss. arXiv:1802.05312. · arXiv
  76. Sankar, A., Keicher, M., Eisawy, R., Parida, A., Pfister, F., Kim, S.T., Navab, N., 2021. Glowin: A flow-based invertible generative framework for learning disen- tangled feature representations in medical images. arXiv:2103.10868. · arXiv
  77. Sarkar, S., Phillips, P.J., Liu, Z., Vega, I.R., Grother, P., Bowyer, K.W., 2005. "the human id gait chal- lenge problem: Data sets, performance, and anal- ysis,". IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 27, no. 2, pp. 162-177, 2005.
  78. Sepliarskaia, A., Kiseleva, J., de Rijke, M., 2021. How to not measure disentanglement. arXiv:1910.05587. · arXiv
  79. Shen, L., Zhu, W., Wang, X., Xing, L., Pauly, J.M., Turkbey, B., Harmon, S.A., Sanford, T.H., Mehralivand, S., Choyke, P.L., Wood, B.J., Xu, D., 2021. Multi-domain image completion for random missing input data. IEEE Trans Med Imaging. 2021 Apr;40(4):1113-1122. doi: 10.1109/TMI.2020.3046444. Epub 2021 Apr 1. PMID: 33351753; PMCID: PMC8136445. · DOI
  80. Shu, R., Chen, Y., Kumar, A., Ermon, S., Poole, B., 2020. Weakly supervised disentanglement with guaran- tees. arXiv:1910.09772. · arXiv
  81. Simonyan, K., Zisserman, A., 2014. Very deep con- volutional networks for large-scale image recogni- tion. arXiv preprint arXiv:1409.1556 . · arXiv
  82. Simonyan, K., Zisserman, A., 2015. Very deep con- volutional networks for large-scale image recogni- tion. arXiv:1409.1556. · arXiv
  83. Song, J., Shi, J., Dong, D., et al., 2018. A new approach to predict progression-free survival in stage iv egfr-mutant nsclc patients with egfr-tki therapy. Clin Cancer Res. 2018;24(15):3583-3592. doi:10.1158/1078-0432.CCR-17-2507. · DOI
  84. Song, J., Wang, L., Ng, N.N., Zhao, M., Shi, J., Ning Wu, W.L., Liu, Z., Yeom, K.W., Tian, J., 2020. Develop- ment and validation of a machine learning model to explore tyrosine kinase inhibitor response in patients with stage iv egfr variant-positive non- small cell lung cancer. JAMA Netw Open. 2020 Dec 1;3(12):e2030442. doi: 10.1001/jamanet- workopen.2020.30442. Erratum in: JAMA Netw Open. 2021 Feb 1;4(2):e211634. PMID: 33331920; PMCID: PMC7747022. . · DOI
  85. Sorrenson, P., Rother, C., Köthe, U., 2020. Dis- entanglement by nonlinear ica with gen- eral incompressible-flow networks (gin). arXiv:2001.04872. · arXiv
  86. Toda, R., Teramoto, A., Tsujimoto, M., et al., 2021. Syn- thetic ct image generation of shape-controlled lung cancer using semi-conditional infogan and its ap- plicability for type classification. Int J CARS 16, 241-251 (2021).s , 101719doi:https://doi.org/10. 1007/s11548-021-02308-1. · DOI
  87. Van Steenkiste, T., Deschrijver, D., Dhaene, T., 2019. Interpretable ecg beat embedding using disen- tangled variational auto-encoders. Medical Im- age Analysis 32, 101719. doi:10.1109/CBMS.2019. 00081. · DOI
  88. Velten, L., et al., 2017. Human haematopoietic stem cell lineage commitment is a continuous process. Nature cell biology 19, 271 (2017).
  89. Wang, T., Lei, Y., Fu, Y., Curran, W.J., Liu, T., Yang, X., 2020. Medical imaging synthesis using deep learning and its clinical applications: A review. arXiv:2004.10322. · arXiv
  90. Willetts, M., Paige, B., 2021. I don't need u: Iden- tifiable non-linear ica without side information. arXiv:2106.05238. · arXiv
  91. Xia, T., Chartsias, A., Tsaftaris, S.A., 2020. Pseudo- healthy synthesis with pathology disentan- glement and adversarial learning. Medi- cal Image Analysis 64, 101719. URL: http: //dx.doi.org/10.1016/j.media.2020.101719, doi:10.1016/j.media.2020.101719. · DOI
  92. Xiu, Z., Tao, C., Gao, M., Davis, C., Goldstein, B.A., Henao, R., 2021. Variational disentanglement for rare event modeling. arXiv:2009.08541. · arXiv
  93. Yang, J., Dvornek, N.C., Zhang, F., Zhuang, J., Chapiro, J., Lin, M., Duncan, J.S., 2019. Domain-agnostic learning with anatomy-consistent embedding for cross-modality liver segmentation, in: Proceedings of the IEEE/CVF International Conference on Com- puter Vision Workshops, pp. 0-0.
  94. Yao, K., Sun, J., Huang, K., Jing, L., Liu, H., Huang, D., Jude, C., 2022. Analyzing cell-scaffold interaction through unsupervised 3d nuclei segmentation. In- ternational journal of bioprinting 8.
  95. Yu, H., Welch, J., 2021. Michigan: sampling from disentangled representations of single- cell data using generative adversarial net- works. Genome Biol. 2021 May 20;22(1):158. doi:doi:10.1186/s13059-021-02373-4. · DOI · Paper page
  96. Yu, S., Tan, D., Tan, T., 2006. A framework for eval- uating the effect of view angle, clothing and carry- ing condition on gait recognition. in International Conference on Pattern Recognition (ICPR).
  97. Zech, J.R., Badgeley, M.A., Manway Liu, A.B.C., Titano, J.J., Oermann, E.K., 2018. Variable gener- alization performance of a deep learning model to detect pneumonia in chest radiographs: A cross- sectional study. Neural Netw. 2000 May-Jun;13(4- 5):411-30. doi:PLoSMed.2018Nov6;15(11): e1002683.doi:10.1371/journal.pmed.1002683. PMID:30399157;PMCID:PMC6219764. · DOI · Paper page
  98. Zhang, Z., Tran, L., Liu, F., Liu, X., 2020. On learn- ing disentangled representations for gait recogni- tion. IEEE Transactions on Pattern Analysis and Machine Intelligence .
  99. Zhao, Q., Adeli, E., Honnorat, N., Leng, T., Pohl, K.M., 2019. Variational autoencoder for regres- sion: Application to brain aging analysis, in: Inter- national Conference on Medical Image Computing and Computer-Assisted Intervention, Springer. pp. 823-831.
  100. Zhou, S., Zelikman, E., Lu, F., Ng, A.Y., Carlsson, G.E., Ermon, S., 2021. Evaluating the disentanglement of deep generative models through manifold topol- ogy, in: International Conference on Learning Rep- resentations, https://openreview.net/forum?id= djwS0m4Ft_A.
  101. Zhu, J.Y., Park, T., Isola, P., Efros, A., 2017. Un- paired image-to-image translation using cycle con- sistent adversarial networks. In Proceedings of the IEEE international conference on computer vision, pages 2223-2232.

Cited by

Sorted by citations

Metadata

Authors
Fragemann, J., Ardizzone, L., Egger, J., Kleesiek, J., & Workshop, M.
Affiliations
  • Stiftung Universitätsmedizin Essen (DE)
  • Heidelberg University (DE)
ORCID
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2022-03-22
DOI
10.36227/techrxiv.19364897.v1
OpenAlex
W4221054755
Cited by
6
References
9
Citations by year
2024: 2 · 2023: 4
Type
posted content
Language
en
Open access
Licence
Locations
Figshare (submittedVersion, cc-by)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
  • Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
Keywords
latent space disentanglement, generative models, medical applications, interpretability, generative adversarial networks, variational autoencoder, flow-based generative models, representation learning, synthetic health data, privacy-preserving data generation, black-box models

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review