Globally optimal OCT surface segmentation using a constrained IPM optimization
Segmentation of multiple surfaces in optical coherence tomography (OCT) images is a challenging problem, further complicated by the frequent presence of weak boundaries, varying layer thicknesses, and mutual influence between adjacent surfaces. The traditional graph-based optimal surface segmentatio...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
11 Jan 2022
|
| In: |
Optics express
Year: 2022, Jahrgang: 30, Heft: 2, Pages: 2453-2471 |
| ISSN: | 1094-4087 |
| DOI: | 10.1364/OE.444369 |
| Online-Zugang: | Verlag, kostenfrei, Volltext: https://doi.org/10.1364/OE.444369 Verlag, kostenfrei, Volltext: https://opg.optica.org/oe/abstract.cfm?uri=oe-30-2-2453 
|
| Verfasserangaben: | Hui Xie, Zhe Pan, Leixin Zhou, Fahim A. Zaman, Danny Z. Chen, Jost B. Jonas, Weiyu Xu, Ya Xing Wang and Xiaodong Wu |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 185263538X | ||
| 003 | DE-627 | ||
| 005 | 20240307090335.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 230713s2022 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1364/OE.444369 |2 doi | |
| 035 | |a (DE-627)185263538X | ||
| 035 | |a (DE-599)KXP185263538X | ||
| 035 | |a (OCoLC)1425217319 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 33 |2 sdnb | ||
| 100 | 1 | |a Xie, Hui |e VerfasserIn |0 (DE-588)1295944073 |0 (DE-627)185263698X |4 aut | |
| 245 | 1 | 0 | |a Globally optimal OCT surface segmentation using a constrained IPM optimization |c Hui Xie, Zhe Pan, Leixin Zhou, Fahim A. Zaman, Danny Z. Chen, Jost B. Jonas, Weiyu Xu, Ya Xing Wang and Xiaodong Wu |
| 264 | 1 | |c 11 Jan 2022 | |
| 300 | |a 19 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Gesehen am 13.07.2022 | ||
| 520 | |a Segmentation of multiple surfaces in optical coherence tomography (OCT) images is a challenging problem, further complicated by the frequent presence of weak boundaries, varying layer thicknesses, and mutual influence between adjacent surfaces. The traditional graph-based optimal surface segmentation method has proven its effectiveness with its ability to capture various surface priors in a uniform graph model. However, its efficacy heavily relies on handcrafted features that are used to define the surface cost for the “goodness” of a surface. Recently, deep learning (DL) is emerging as a powerful tool for medical image segmentation thanks to its superior feature learning capability. Unfortunately, due to the scarcity of training data in medical imaging, it is nontrivial for DL networks to implicitly learn the global structure of the target surfaces, including surface interactions. This study proposes to parameterize the surface cost functions in the graph model and leverage DL to learn those parameters. The multiple optimal surfaces are then simultaneously detected by minimizing the total surface cost while explicitly enforcing the mutual surface interaction constraints. The optimization problem is solved by the primal-dual interior-point method (IPM), which can be implemented by a layer of neural networks, enabling efficient end-to-end training of the whole network. Experiments on spectral-domain optical coherence tomography (SD-OCT) retinal layer segmentation demonstrated promising segmentation results with sub-pixel accuracy. | ||
| 650 | 4 | |a Medical image processing | |
| 650 | 4 | |a Medical imaging | |
| 650 | 4 | |a Neural networks | |
| 650 | 4 | |a Optical surfaces | |
| 650 | 4 | |a Retinal nerve fiber layer | |
| 650 | 4 | |a Spectral domain optical coherence tomography | |
| 700 | 1 | |a Pan, Zhe |e VerfasserIn |4 aut | |
| 700 | 1 | |a Zhou, Leixin |e VerfasserIn |4 aut | |
| 700 | 1 | |a Zaman, Fahim A. |e VerfasserIn |4 aut | |
| 700 | 1 | |a Chen, Danny Z. |e VerfasserIn |4 aut | |
| 700 | 1 | |a Jonas, Jost B. |d 1958- |e VerfasserIn |0 (DE-588)1028286732 |0 (DE-627)730536823 |0 (DE-576)37578537X |4 aut | |
| 700 | 1 | |a Xu, Weiyu |e VerfasserIn |4 aut | |
| 700 | 1 | |a Wang, Ya Xing |e VerfasserIn |4 aut | |
| 700 | 1 | |a Wu, Xiaodong |e VerfasserIn |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Optics express |d Washington, DC : Optica, 1997 |g 30(2022), 2, Seite 2453-2471 |h Online-Ressource |w (DE-627)302718370 |w (DE-600)1491859-6 |w (DE-576)079876579 |x 1094-4087 |7 nnas |a Globally optimal OCT surface segmentation using a constrained IPM optimization |
| 773 | 1 | 8 | |g volume:30 |g year:2022 |g number:2 |g pages:2453-2471 |g extent:19 |a Globally optimal OCT surface segmentation using a constrained IPM optimization |
| 856 | 4 | 0 | |u https://doi.org/10.1364/OE.444369 |x Verlag |x Resolving-System |z kostenfrei |3 Volltext |
| 856 | 4 | 0 | |u https://opg.optica.org/oe/abstract.cfm?uri=oe-30-2-2453 |x Verlag |z kostenfrei |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20230713 | ||
| 993 | |a Article | ||
| 994 | |a 2022 | ||
| 998 | |g 1028286732 |a Jonas, Jost B. |m 1028286732:Jonas, Jost B. |d 60000 |e 60000PJ1028286732 |k 0/60000/ |p 6 | ||
| 999 | |a KXP-PPN185263538X |e 4353608576 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"person":[{"role":"aut","display":"Xie, Hui","family":"Xie","given":"Hui"},{"role":"aut","display":"Pan, Zhe","family":"Pan","given":"Zhe"},{"given":"Leixin","display":"Zhou, Leixin","family":"Zhou","role":"aut"},{"role":"aut","display":"Zaman, Fahim A.","family":"Zaman","given":"Fahim A."},{"given":"Danny Z.","display":"Chen, Danny Z.","family":"Chen","role":"aut"},{"given":"Jost B.","display":"Jonas, Jost B.","family":"Jonas","role":"aut"},{"role":"aut","display":"Xu, Weiyu","family":"Xu","given":"Weiyu"},{"role":"aut","family":"Wang","display":"Wang, Ya Xing","given":"Ya Xing"},{"role":"aut","display":"Wu, Xiaodong","family":"Wu","given":"Xiaodong"}],"type":{"media":"Online-Ressource","bibl":"article-journal"},"relHost":[{"origin":[{"dateIssuedKey":"1997","publisherPlace":"Washington, DC ; Washington, DC","dateIssuedDisp":"1997-","publisher":"Optica ; Optical Society of America, OSA"}],"id":{"issn":["1094-4087"],"eki":["302718370"],"zdb":["1491859-6"]},"language":["eng"],"title":[{"title_sort":"Optics express","subtitle":"the international electronic journal of optics","title":"Optics express"}],"physDesc":[{"extent":"Online-Ressource"}],"note":["Gesehen am 10.01.2022","Herausgebendes Organ bis 2021: Optical Society of America"],"name":{"displayForm":["Optica"]},"recId":"302718370","type":{"bibl":"periodical","media":"Online-Ressource"},"pubHistory":["1.1997 -"],"corporate":[{"display":"Optica","role":"isb"},{"role":"isb","display":"Optical Society of America"}],"part":{"text":"30(2022), 2, Seite 2453-2471","year":"2022","extent":"19","issue":"2","volume":"30","pages":"2453-2471"},"disp":"Globally optimal OCT surface segmentation using a constrained IPM optimizationOptics express"}],"origin":[{"dateIssuedDisp":"11 Jan 2022","dateIssuedKey":"2022"}],"id":{"eki":["185263538X"],"doi":["10.1364/OE.444369"]},"recId":"185263538X","title":[{"title":"Globally optimal OCT surface segmentation using a constrained IPM optimization","title_sort":"Globally optimal OCT surface segmentation using a constrained IPM optimization"}],"language":["eng"],"physDesc":[{"extent":"19 S."}],"note":["Gesehen am 13.07.2022"],"name":{"displayForm":["Hui Xie, Zhe Pan, Leixin Zhou, Fahim A. Zaman, Danny Z. Chen, Jost B. Jonas, Weiyu Xu, Ya Xing Wang and Xiaodong Wu"]}} | ||
| SRT | |a XIEHUIPANZGLOBALLYOP1120 | ||