Towards Accurate Segmentation of Retinal Vessels and the Optic Disc in Fundoscopic Images with Generative Adversarial Networks.
Automatic segmentation of the retinal vasculature and the optic disc is a crucial task for accurate geometric analysis and reliable automated diagnosis. In recent years, Convolutional Neural Networks (CNN) have shown outstanding performance compared to the conventional approaches in the segmentation...
| Publicado en: | Journal of Digital Imaging Vol. 32; no. 3; pp. 499 - 513 |
|---|---|
| Autores principales: | , , |
| Formato: | equations & formulas research tables/charts Journal Article |
| Publicado: |
Springer Nature
Jun2019
|
| 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=136223479&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 136223479 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 08971889 DOQ jtl: Journal of Digital Imaging issn: 08971889 maglogo: N pubinfo: dt: Jun2019 vid: 32 iid: 3 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 136223479 136223479 136223479 10.1007/s10278-018-0126-3 136223479 ppf: 499 ppct: 14 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: Towards Accurate Segmentation of Retinal Vessels and the Optic Disc in Fundoscopic Images with Generative Adversarial Networks. aug: au: Son, Jaemin Jung, Kyu-Hwan Park, Sang Jun affil: VUNO Inc., 6F, 507, Gangnam-daero, Seocho-gu, Seoul, Republic of Korea sug: subj: Optic Nerve Pathology Retina Pathology Ophthalmoscopy Methods Neural Networks (Computer) Human ROC Curve Image Processing, Computer Assisted Descriptive Statistics ab: Automatic segmentation of the retinal vasculature and the optic disc is a crucial task for accurate geometric analysis and reliable automated diagnosis. In recent years, Convolutional Neural Networks (CNN) have shown outstanding performance compared to the conventional approaches in the segmentation tasks. In this paper, we experimentally measure the performance gain for Generative Adversarial Networks (GAN) framework when applied to the segmentation tasks. We show that GAN achieves statistically significant improvement in area under the receiver operating characteristic (AU-ROC) and area under the precision and recall curve (AU-PR) on two public datasets (DRIVE, STARE) by segmenting fine vessels. Also, we found a model that surpassed the current state-of-the-art method by 0.2 − 1.0% in AU-ROC and 0.8 − 1.2% in AU-PR and 0.5 − 0.7% in dice coefficient. In contrast, significant improvements were not observed in the optic disc segmentation task on DRIONS-DB, RIM-ONE (r3) and Drishti-GS datasets in AU-ROC and AU-PR. pubtype: Academic Journal doctype: equations & formulas research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|