Search: onr:"swepub:oai:DiVA.org:liu-201435" > Brain tumor segment...
Fältnamn | Indikatorer | Metadata |
---|---|---|
000 | 04098naa a2200445 4500 | |
001 | oai:DiVA.org:liu-201435 | |
003 | SwePub | |
008 | 240309s2024 | |||||||||||000 ||eng| | |
024 | 7 | a https://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-2014352 URI |
024 | 7 | a https://doi.org/10.1038/s41597-024-03073-x2 DOI |
040 | a (SwePub)liu | |
041 | a engb eng | |
042 | 9 SwePub | |
072 | 7 | a ref2 swepub-contenttype |
072 | 7 | a art2 swepub-publicationtype |
100 | 1 | a Akbar, Muhammad Usman,d 1990-u Linköpings universitet,Avdelningen för medicinsk teknik,Tekniska fakulteten,Centrum för medicinsk bildvetenskap och visualisering, CMIV4 aut0 (Swepub:liu)muhak80 |
245 | 1 0 | a Brain tumor segmentation using synthetic MR images - A comparison of GANs and diffusion models |
264 | 1 | b Nature Publishing Group,c 2024 |
338 | a electronic2 rdacarrier | |
500 | a Funding Agencies|ITEA/VINNOVA project ASSIST [2021-01420]; LiU Cancer; VINNOVA AIDA [M22-0088]; Ake Wiberg foundation; Wallenberg Center for Molecular Medicine as an associated clinical fellow; [2021-01954] | |
520 | a Large annotated datasets are required for training deep learning models, but in medical imaging data sharing is often complicated due to ethics, anonymization and data protection legislation. Generative AI models, such as generative adversarial networks (GANs) and diffusion models, can today produce very realistic synthetic images, and can potentially facilitate data sharing. However, in order to share synthetic medical images it must first be demonstrated that they can be used for training different networks with acceptable performance. Here, we therefore comprehensively evaluate four GANs (progressive GAN, StyleGAN 1–3) and a diffusion model for the task of brain tumor segmentation (using two segmentation networks, U-Net and a Swin transformer). Our results show that segmentation networks trained on synthetic images reach Dice scores that are 80%–90% of Dice scores when training with real images, but that memorization of the training images can be a problem for diffusion models if the original dataset is too small. Our conclusion is that sharing synthetic medical images is a viable option to sharing real images, but that further work is required. The trained generative models and the generated synthetic images are shared on AIDA data hub. | |
650 | 7 | a MEDICIN OCH HÄLSOVETENSKAPx Klinisk medicinx Radiologi och bildbehandling0 (SwePub)302082 hsv//swe |
650 | 7 | a MEDICAL AND HEALTH SCIENCESx Clinical Medicinex Radiology, Nuclear Medicine and Medical Imaging0 (SwePub)302082 hsv//eng |
650 | 7 | a TEKNIK OCH TEKNOLOGIERx Medicinteknikx Medicinsk bildbehandling0 (SwePub)206032 hsv//swe |
650 | 7 | a ENGINEERING AND TECHNOLOGYx Medical Engineeringx Medical Image Processing0 (SwePub)206032 hsv//eng |
653 | a Deep learning | |
653 | a brain tumor | |
653 | a magnetic resonance imaging | |
653 | a synthetic images | |
653 | a generative adversarial networks | |
653 | a diffusion models | |
700 | 1 | a Larsson, Månsu Eigenvision, Malmö, Sweden4 aut |
700 | 1 | a Blystad, Ida,d 1972-u Linköpings universitet,Medicinska fakulteten,Centrum för medicinsk bildvetenskap och visualisering, CMIV,Avdelningen för diagnostik och specialistmedicin,Region Östergötland, Röntgenkliniken i Linköping4 aut0 (Swepub:liu)idabl62 |
700 | 1 | a Eklund, Anders,d 1981-u Linköpings universitet,Avdelningen för medicinsk teknik,Tekniska fakulteten,Centrum för medicinsk bildvetenskap och visualisering, CMIV,Statistik och maskininlärning4 aut0 (Swepub:liu)andek67 |
710 | 2 | a Linköpings universitetb Avdelningen för medicinsk teknik4 org |
773 | 0 | t Scientific Datad : Nature Publishing Groupg 11:1q 11:1x 2052-4463 |
856 | 4 | u https://doi.org/10.1038/s41597-024-03073-xy Fulltext |
856 | 4 | u https://liu.diva-portal.org/smash/get/diva2:1843384/FULLTEXT02.pdfx primaryx Raw objecty fulltext:print |
856 | 4 8 | u https://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-201435 |
856 | 4 8 | u https://doi.org/10.1038/s41597-024-03073-x |
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.