Show simple item record

dc.contributor.authorHan, Cen
dc.contributor.authorRundo, Leonardoen
dc.contributor.authorAraki, Ren
dc.contributor.authorFurukawa, Yen
dc.contributor.authorMauri, Gen
dc.contributor.authorNakayama, Hen
dc.contributor.authorHayashi, Hen
dc.date.accessioned2021-06-29T14:36:00Z
dc.date.available2021-06-29T14:36:00Z
dc.identifier.isbn978-981-13-8949-8en
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/324568
dc.description.abstractDue to the lack of available annotated medical images, accurate computer-assisted diagnosis requires intensive data augmentation (DA) techniques, such as geometric/intensity transformations of original images; however, those transformed images intrinsically have a similar distribution to the original ones, leading to limited performance improvement. To fill the data lack in the real image distribution, we synthesize brain contrast-enhanced magnetic resonance (MR) images—realistic but completely different from the original ones—using generative adversarial networks (GANs). This study exploits progressive growing of GANs (PGGANs), a multistage generative training method, to generate original-sized 256 × 256 MR images for convolutional neural network-based brain tumor detection, which is challenging via conventional GANs; difficulties arise due to unstable GAN training with high resolution and a variety of tumors in size, location, shape, and contrast. Our preliminary results show that this novel PGGAN-based DA method can achieve a promising performance improvement, when combined with classical DA, in tumor detection and also in other medical imaging tasks.en
dc.publisherSpringeren
dc.titleInfinite Brain MR Images: PGGAN-Based Data Augmentation for Tumor Detectionen
dc.typeBook chapter
prism.endingPage303
prism.publicationNameNeural Approaches to Dynamics of Signal Exchangesen
prism.startingPage291
prism.volume151en
dc.identifier.doi10.17863/CAM.72023
rioxxterms.versionofrecord10.1007/978-981-13-8950-4_27en
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserveden
dc.contributor.orcidRundo, Leonardo [0000-0003-3341-5483]
rioxxterms.typeBook chapteren
cam.issuedOnline2019-09-19en
rioxxterms.freetoread.startdate2021-09-19


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record