Voxel-Wise Medical Imaging Transformation and Adaption Based on CycleGAN and Score-Based Diffusion...33rd Medical Informatics Europe Conference (MIE2023), May 22-25, 2023, Gothenburg, Sweden.
Supervised methods, such as those utilized in classification, prediction, and segmentation tasks for medical images, experience a decline in performance when the training and testing datasets violate the i.i.d (independent and identically distributed) assumption. Hence we adopted the CycleGAN(Genera...
| Publicado en: | Studies in Health Technology & Informatics Vol. 302; pp. 1027 - 1029 |
|---|---|
| Autores principales: | , , , |
| Formato: | proceedings research Journal Article |
| Publicado: |
Sage Publications Inc.
2023
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=163842356&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 163842356 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 09269630 U1V jtl: Studies in Health Technology & Informatics issn: 09269630 maglogo: N pubinfo: dt: 2023 vid: 302 pid: 344 pub: Sage Publications Inc. place: Thousand Oaks, California artinfo: ui: 163842356 163842356 163842356 10.3233/SHTI230337 163842356 ppf: 1027 ppct: 2 formats: tig: atl: Voxel-Wise Medical Imaging Transformation and Adaption Based on CycleGAN and Score-Based Diffusion...33rd Medical Informatics Europe Conference (MIE2023), May 22-25, 2023, Gothenburg, Sweden. aug: au: Feifei LI SCHÖNECK, Mirjam BEYAN, Oya CALDEIRA, Liliana Lourenco affil: Institut für Biomedizinische Informatik Köln, Germany sug: subj: Diagnostic Imaging Congresses and Conferences Sweden Sweden ab: Supervised methods, such as those utilized in classification, prediction, and segmentation tasks for medical images, experience a decline in performance when the training and testing datasets violate the i.i.d (independent and identically distributed) assumption. Hence we adopted the CycleGAN(Generative Adversarial Networks) method to cycle training the CT(Computer Tomography) data from different terminals/manufacturers, which aims to eliminate the distribution shift from diverse data terminals. But due to the model collapse problem of the GAN-based model, the images we generated suffer serious radiology artifacts. To eliminate the boundary marks and artifacts, we adopted a score-based generative model to refine the images voxel-wisely. This novel combination of two generative models makes the transformation between diverse data providers to a higher fidelity level without sacrificing any significant features. In future works, we will evaluate the original datasets and generative datasets by experimenting with a broader range of supervised methods. pubtype: Academic Journal doctype: proceedings research Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|