PMID- 38405807
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20240301
DP  - 2024 Feb 13
TI  - Recurrent and Concurrent Prediction of Longitudinal Progression of Stargardt 
      Atrophy and Geographic Atrophy.
LID - 2024.02.11.24302670 [pii]
LID - 10.1101/2024.02.11.24302670 [doi]
AB  - Stargardt disease and age-related macular degeneration are the leading causes of 
      blindness in the juvenile and geriatric populations, respectively. The formation 
      of atrophic regions of the macula is a hallmark of the end-stages of both 
      diseases. The progression of these diseases is tracked using various imaging 
      modalities, two of the most common being fundus autofluorescence (FAF) imaging 
      and spectral-domain optical coherence tomography (SD-OCT). This study seeks to 
      investigate the use of longitudinal FAF and SD-OCT imaging (month 0, month 6, 
      month 12, and month 18) data for the predictive modelling of future atrophy in 
      Stargardt and geographic atrophy. To achieve such an objective, we develop a set 
      of novel deep convolutional neural networks enhanced with recurrent network units 
      for longitudinal prediction and concurrent learning of ensemble network units 
      (termed ReConNet) which take advantage of improved retinal layer features beyond 
      the mean intensity features. Using FAF images, the neural network presented in 
      this paper achieved mean (+/- standard deviation, SD) and median Dice coefficients 
      of 0.895 (+/- 0.086) and 0.922 for Stargardt atrophy, and 0.864 (+/- 0.113) and 0.893 
      for geographic atrophy. Using SD-OCT images for Stargardt atrophy, the neural 
      network achieved mean and median Dice coefficients of 0.882 (+/- 0.101) and 0.906, 
      respectively. When predicting only the interval growth of the atrophic lesions 
      with FAF images, mean (+/- SD) and median Dice coefficients of 0.557 (+/- 0.094) and 
      0.559 were achieved for Stargardt atrophy, and 0.612 (+/- 0.089) and 0.601 for 
      geographic atrophy. The prediction performance in OCT images is comparably good 
      to that using FAF which opens a new, more efficient, and practical door in the 
      assessment of atrophy progression for clinical trials and retina clinics, beyond 
      widely used FAF. These results are highly encouraging for a high-performance 
      interval growth prediction when more frequent or longer-term longitudinal data 
      are available in our clinics. This is a pressing task for our next step in 
      ongoing research.
FAU - Mishra, Zubin
AU  - Mishra Z
AD  - Doheny Image Analysis Laboratory, Doheny Eye Institute, Pasadena, CA, 91103, USA.
AD  - Case Western Reserve University School of Medicine, Cleveland, OH, 44106, USA.
FAU - Wang, Ziyuan
AU  - Wang Z
AD  - Doheny Image Analysis Laboratory, Doheny Eye Institute, Pasadena, CA, 91103, USA.
AD  - The University of California, Los Angeles, CA, 90095, USA.
FAU - Xu, Emily
AU  - Xu E
AD  - Doheny Image Analysis Laboratory, Doheny Eye Institute, Pasadena, CA, 91103, USA.
FAU - Xu, Sophia
AU  - Xu S
AD  - Doheny Image Analysis Laboratory, Doheny Eye Institute, Pasadena, CA, 91103, USA.
FAU - Majid, Iyad
AU  - Majid I
AD  - Doheny Image Analysis Laboratory, Doheny Eye Institute, Pasadena, CA, 91103, USA.
FAU - Sadda, SriniVas R
AU  - Sadda SR
AD  - Doheny Image Analysis Laboratory, Doheny Eye Institute, Pasadena, CA, 91103, USA.
AD  - The University of California, Los Angeles, CA, 90095, USA.
FAU - Hu, Zhihong Jewel
AU  - Hu ZJ
AUID- ORCID: 0000-0001-8307-0298
AD  - Doheny Image Analysis Laboratory, Doheny Eye Institute, Pasadena, CA, 91103, USA.
LA  - eng
GR  - R21 EY029839/EY/NEI NIH HHS/United States
PT  - Preprint
DEP - 20240213
PL  - United States
TA  - medRxiv
JT  - medRxiv : the preprint server for health sciences
JID - 101767986
PMC - PMC10888984
COIS- Competing Interests The authors declare no competing interests.
EDAT- 2024/02/26 06:44
MHDA- 2024/02/26 06:45
PMCR- 2024/02/23
CRDT- 2024/02/26 04:50
PHST- 2024/02/26 06:44 [pubmed]
PHST- 2024/02/26 06:45 [medline]
PHST- 2024/02/26 04:50 [entrez]
PHST- 2024/02/23 00:00 [pmc-release]
AID - 2024.02.11.24302670 [pii]
AID - 10.1101/2024.02.11.24302670 [doi]
PST - epublish
SO  - medRxiv [Preprint]. 2024 Feb 13:2024.02.11.24302670. doi: 
      10.1101/2024.02.11.24302670.