PMID- 34131181
OWN - NLM
STAT- MEDLINE
DCOM- 20211029
LR  - 20211029
IS  - 2045-2322 (Electronic)
IS  - 2045-2322 (Linking)
VI  - 11
IP  - 1
DP  - 2021 Jun 15
TI  - RetiNerveNet: using recursive deep learning to estimate pointwise 24-2 visual 
      field data based on retinal structure.
PG  - 12562
LID - 10.1038/s41598-021-91493-9 [doi]
LID - 12562
AB  - Glaucoma is the leading cause of irreversible blindness in the world, affecting 
      over 70 million people. The cumbersome Standard Automated Perimetry (SAP) test is 
      most frequently used to detect visual loss due to glaucoma. Due to the SAP test's 
      innate difficulty and its high test-retest variability, we propose the 
      RetiNerveNet, a deep convolutional recursive neural network for obtaining 
      estimates of the SAP visual field. RetiNerveNet uses information from the more 
      objective Spectral-Domain Optical Coherence Tomography (SDOCT). RetiNerveNet 
      attempts to trace-back the arcuate convergence of the retinal nerve fibers, 
      starting from the Retinal Nerve Fiber Layer (RNFL) thickness around the optic 
      disc, to estimate individual age-corrected 24-2 SAP values. Recursive passes 
      through the proposed network sequentially yield estimates of the visual locations 
      progressively farther from the optic disc. While all the methods used for our 
      experiments exhibit lower performance for the advanced disease group (possibly 
      due to the "floor effect" for the SDOCT test), the proposed network is observed 
      to be more accurate than all the baselines for estimating the individual visual 
      field values. We further augment the proposed network to additionally predict the 
      SAP Mean Deviation values and also facilitate the assignment of higher weightage 
      to the underrepresented groups in the data. We then study the resulting 
      performance trade-offs of the RetiNerveNet on the early, moderate and severe 
      disease groups.
FAU - Datta, Shounak
AU  - Datta S
AD  - Department of Electrical and Computer Engineering, Pratt School of Engineering, 
      Duke University, Durham, NC, 27708, USA.
FAU - Mariottoni, Eduardo B
AU  - Mariottoni EB
AD  - Vision, Imaging and Performance (VIP) Laboratory, Duke Eye Center, Duke 
      University, Durham, NC, 27705, USA.
FAU - Dov, David
AU  - Dov D
AD  - Department of Electrical and Computer Engineering, Pratt School of Engineering, 
      Duke University, Durham, NC, 27708, USA.
FAU - Jammal, Alessandro A
AU  - Jammal AA
AD  - Vision, Imaging and Performance (VIP) Laboratory, Duke Eye Center, Duke 
      University, Durham, NC, 27705, USA.
FAU - Carin, Lawrence
AU  - Carin L
AD  - Department of Electrical and Computer Engineering, Pratt School of Engineering, 
      Duke University, Durham, NC, 27708, USA.
FAU - Medeiros, Felipe A
AU  - Medeiros FA
AD  - Department of Electrical and Computer Engineering, Pratt School of Engineering, 
      Duke University, Durham, NC, 27708, USA. felipe.medeiros@duke.edu.
AD  - Vision, Imaging and Performance (VIP) Laboratory, Duke Eye Center, Duke 
      University, Durham, NC, 27705, USA. felipe.medeiros@duke.edu.
LA  - eng
PT  - Journal Article
DEP - 20210615
PL  - England
TA  - Sci Rep
JT  - Scientific reports
JID - 101563288
SB  - IM
MH  - Aged
MH  - Deep Learning
MH  - Glaucoma, Open-Angle/*diagnosis/diagnostic imaging/pathology
MH  - Humans
MH  - Intraocular Pressure/physiology
MH  - Male
MH  - Middle Aged
MH  - Nerve Fibers/pathology
MH  - Neural Networks, Computer
MH  - Optic Disk/diagnostic imaging/pathology
MH  - Retina/*diagnostic imaging/pathology
MH  - Retinal Ganglion Cells/pathology/ultrastructure
MH  - *Tomography, Optical Coherence
MH  - *Visual Field Tests
MH  - Visual Fields/physiology
PMC - PMC8206091
COIS- The authors declare no competing interests.
EDAT- 2021/06/17 06:00
MHDA- 2021/10/30 06:00
PMCR- 2021/06/15
CRDT- 2021/06/16 06:20
PHST- 2020/09/26 00:00 [received]
PHST- 2021/05/27 00:00 [accepted]
PHST- 2021/06/16 06:20 [entrez]
PHST- 2021/06/17 06:00 [pubmed]
PHST- 2021/10/30 06:00 [medline]
PHST- 2021/06/15 00:00 [pmc-release]
AID - 10.1038/s41598-021-91493-9 [pii]
AID - 91493 [pii]
AID - 10.1038/s41598-021-91493-9 [doi]
PST - epublish
SO  - Sci Rep. 2021 Jun 15;11(1):12562. doi: 10.1038/s41598-021-91493-9.