{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T16:11:35Z","timestamp":1780589495471,"version":"3.54.1"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031537660","type":"print"},{"value":"9783031537677","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-53767-7_7","type":"book-chapter","created":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T06:02:12Z","timestamp":1708322532000},"page":"66-76","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["ViT-DAE: Transformer-Driven Diffusion Autoencoder for\u00a0Histopathology Image Analysis"],"prefix":"10.1007","author":[{"given":"Xuan","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saarthak","family":"Kapse","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rajarsi","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prateek","family":"Prasanna","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,2,20]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Boyd, J., Liashuha, M., Deutsch, E., Paragios, N., Christodoulidis, S., Vakalopoulou, M.: Self-supervised representation learning using visual field expansion on digital pathology. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCVW54120.2021.00077"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"7_CR3","unstructured":"Dahan, C., Christodoulidis, S., Vakalopoulou, M., Boyd, J.: Artifact removal in histopathology images. arXiv preprint arXiv:2211.16161 (2022)"},{"key":"7_CR4","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"7_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"7_CR7","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"7_CR8","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"1","key":"7_CR9","doi-asserted-by":"publisher","first-page":"43","DOI":"10.4103\/jpi.jpi_103_20","volume":"12","author":"L Jose","year":"2021","unstructured":"Jose, L., Liu, S., Russo, C., Nadort, A., Di Ieva, A.: Generative adversarial networks in digital pathology and histopathological image processing: a review. J. Pathol. Inf. 12(1), 43 (2021)","journal-title":"J. Pathol. Inf."},{"key":"7_CR10","doi-asserted-by":"publisher","first-page":"58821","DOI":"10.1109\/ACCESS.2022.3176091","volume":"10","author":"N Kanwal","year":"2022","unstructured":"Kanwal, N., P\u00e9rez-Bueno, F., Schmidt, A., Engan, K., Molina, R.: The devil is in the details: whole slide image acquisition and processing for artifacts detection, color variation, and data augmentation: a review. IEEE Access 10, 58821\u201358844 (2022)","journal-title":"IEEE Access"},{"key":"7_CR11","unstructured":"Kather, J.N., Halama, N., Marx, A.: 100,000 histological images of human colorectal cancer and healthy tissue. Zenodo10 (2018)"},{"issue":"7","key":"7_CR12","doi-asserted-by":"publisher","first-page":"1054","DOI":"10.1038\/s41591-019-0462-y","volume":"25","author":"JN Kather","year":"2019","unstructured":"Kather, J.N., et al.: Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer. Nat. Med. 25(7), 1054\u20131056 (2019)","journal-title":"Nat. Med."},{"key":"7_CR13","unstructured":"Kynk\u00e4\u00e4nniemi, T., Karras, T., Aittala, M., Aila, T., Lehtinen, J.: The role of imagenet classes in fr$$\\backslash $$\u2019echet inception distance. arXiv preprint arXiv:2203.06026 (2022)"},{"key":"7_CR14","unstructured":"Kynk\u00e4\u00e4nniemi, T., Karras, T., Laine, S., Lehtinen, J., Aila, T.: Improved precision and recall metric for assessing generative models. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Moghadam, P.A., et al.: A morphology focused diffusion probabilistic model for synthesis of histopathology images. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2000\u20132009 (2023)","DOI":"10.1109\/WACV56688.2023.00204"},{"key":"7_CR16","first-page":"23296","volume":"34","author":"MM Naseer","year":"2021","unstructured":"Naseer, M.M., Ranasinghe, K., Khan, S.H., Hayat, M., Shahbaz Khan, F., Yang, M.H.: Intriguing properties of vision transformers. Adv. Neural. Inf. Process. Syst. 34, 23296\u201323308 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Preechakul, K., Chatthee, N., Wizadwongsa, S., Suwajanakorn, S.: Diffusion autoencoders: toward a meaningful and decodable representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10619\u201310629 (2022)","DOI":"10.1109\/CVPR52688.2022.01036"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"7_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015, Part III. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"issue":"1","key":"7_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13000-021-01126-y","volume":"16","author":"M Runz","year":"2021","unstructured":"Runz, M., Rusche, D., Schmidt, S., Weihrauch, M.R., Hesser, J., Weis, C.A.: Normalization of he-stained histological images using cycle consistent generative adversarial networks. Diagn. Pathol. 16(1), 1\u201310 (2021)","journal-title":"Diagn. Pathol."},{"key":"7_CR21","unstructured":"Seitzer, M.: pytorch-fid: FID Score for PyTorch. https:\/\/github.com\/mseitzer\/pytorch-fid (August 2020), version 0.3.0"},{"key":"7_CR22","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"7_CR23","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)"},{"key":"7_CR24","doi-asserted-by":"publisher","first-page":"101544","DOI":"10.1016\/j.media.2019.101544","volume":"58","author":"D Tellez","year":"2019","unstructured":"Tellez, D., et al.: Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathology. Med. Image Anal. 58, 101544 (2019)","journal-title":"Med. Image Anal."},{"key":"7_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"7_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1007\/978-3-030-00934-2_24","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2018","author":"BS Veeling","year":"2018","unstructured":"Veeling, B.S., Linmans, J., Winkens, J., Cohen, T., Welling, M.: Rotation equivariant CNNs for digital pathology. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-L\u00f3pez, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11071, pp. 210\u2013218. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-00934-2_24"},{"key":"7_CR27","first-page":"10","volume":"116","author":"J Wei","year":"2019","unstructured":"Wei, J., et al.: Generative image translation for data augmentation in colorectal histopathology images. Proc. Mach. Learn. Res. 116, 10 (2019)","journal-title":"Proc. Mach. Learn. Res."},{"key":"7_CR28","unstructured":"Xiao, Z., Kreis, K., Vahdat, A.: Tackling the generative learning trilemma with denoising diffusion GANs. arXiv preprint arXiv:2112.07804 (2021)"},{"key":"7_CR29","doi-asserted-by":"publisher","first-page":"101816","DOI":"10.1016\/j.media.2020.101816","volume":"67","author":"Y Xue","year":"2021","unstructured":"Xue, Y., et al.: Selective synthetic augmentation with histogan for improved histopathology image classification. Med. Image Anal. 67, 101816 (2021)","journal-title":"Med. Image Anal."},{"issue":"4","key":"7_CR30","doi-asserted-by":"publisher","first-page":"881","DOI":"10.1109\/TMI.2021.3125459","volume":"41","author":"C Zhu","year":"2021","unstructured":"Zhu, C., Chen, W., Peng, T., Wang, Y., Jin, M.: Hard sample aware noise robust learning for histopathology image classification. IEEE Trans. Med. Imaging 41(4), 881\u2013894 (2021)","journal-title":"IEEE Trans. Med. Imaging"}],"container-title":["Lecture Notes in Computer Science","Deep Generative Models"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-53767-7_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T06:03:22Z","timestamp":1708322602000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-53767-7_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031537660","9783031537677"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-53767-7_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"20 February 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vancouver, BC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2023\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2250","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"730","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"32% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}