Joint Motion Correction and 3D Segmentation with Graph-Assisted Neural Networks for Retinal OCT

Wang, Yiqian; Galang, Carlo; Freeman, William R.; Nguyen, Truong Q.; An, Cheolhong

doi:10.1109/icip46576.2022.9898072

Cited by 3 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Segmentation-corrected OCTA may offer better detection of choroidal neovascularization and follow-up of changes in CNV morphology in response to anti-VEGF treatment. The need for improvement of automated software segmentation in eyes with pathology has been recognized and there are methods using neural networks studied by our group to refine the segmentation in OCT and OCTA 15,16 . In our study, we only corrected Bruch's Membrane, as suggested by other authors 12 , although errors in other layers may be present and might not be relevant for this disease, future work could involve full segmentation correction of all layers, but this would be very laborious to do manually and might require AI methods to help with automate this task.…”

Section: Discussionmentioning

confidence: 99%

Effect of manual OCTA segmentation correction to improve image quality and visibility of choroidal neovascularization in AMD

Deussen,

Heinke,

Elsner

et al. 2024

Sci Rep

View full text Add to dashboard Cite

In this retrospective case series on neovascular age-related macular degeneration (nAMD), we aimed to improve Choroidal Neovascularization (CNV) visualization in Optical Coherence Tomography Angiography (OCTA) scans by addressing segmentation errors. Out of 198 eyes, 73 OCTA scans required manual segmentation correction. We compared uncorrected scans to those with minimal (2 corrections), moderate (10 corrections), and detailed (50 corrections) efforts targeting falsely segmented Bruch’s Membrane (BM). Results showed that 55% of corrected OCTAs exhibited improved quality after manual correction. Notably, minimal correction (2 scans) already led to significant improvements, with additional corrections (10 or 50) not further enhancing expert grading. Reduced background noise and improved CNV identification were observed, with the most substantial improvement after two corrections compared to baseline uncorrected images. In conclusion, our approach of correcting segmentation errors effectively enhances image quality in OCTA scans of nAMD. This study demonstrates the efficacy of the method, with 55% of resegmented OCTA images exhibiting enhanced quality, leading to a notable increase in the proportion of high-quality images from 63 to 83%.

show abstract

Section: Discussionmentioning

confidence: 99%

Effect of manual OCTA segmentation correction to improve image quality and visibility of choroidal neovascularization in AMD

Deussen,

Heinke,

Elsner

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Certainly, the novel AI-based segmentation algorithms will be helpful in this matter and could be applied in the future to improve classification performance. 29 The lower success rate of prediction performance in the active and remission CNV category could be also associated with limitations of OCTA as an imaging modality, or the fact that in some patients, the morphology of the CNV vasculature does not change despite lack of leakage. Slow flow or pooling in vessels may potentially cause that the motion is not captured and the vessels are missed.…”

Section: Discussionmentioning

confidence: 99%

“…Certainly, the novel AI-based segmentation algorithms will be helpful in this matter and could be applied in the future to improve classification performance. 29…”

Section: Discussionmentioning

confidence: 99%

Artificial intelligence for OCTA-based disease activity prediction in age-related macular degeneration.

Heinke,

Zhang,

Deussen

et al. 2023

Retina

Self Cite

View full text Add to dashboard Cite

Purpose: We hypothesize that OCTA-visualized vascular morphology may be a predictor of CNV status in AMD. We thus evaluated the use of AI to predict different stages of AMD disease based on OCTA en-face 2D projections scans. Methods: Retrospective cross-sectional study based on collected 2D OCTA data from 310 high-resolution scans. Based on OCT B-scan fluid and clinical status, OCTA was classified as normal, dry AMD, wet AMD active and wet-AMD in remission with no signs of activity. Two human experts graded the same test set and a consensus grading between 2 experts was used for the prediction of 4 categories. Results: The AI can achieve 80.36% accuracy on a four-category grading task with 2D OCTA projections. The sensitivity of prediction by AI was: 0.7857 (active), 0.7142 (remission), 0.9286 (dry AMD), and 0.9286 (normal) and the specificity was 0.9524, 0.9524, 0.9286, and 0.9524, respectively. The sensitivity of prediction by human experts was: 0.4286 active CNV, 0.2143 remission, 0.8571 dry AMD, and 0.8571 normal with specificity of 0.7619, 0.9286, 0.7857, 0.9762 respectively. The overall AI classification prediction was significantly better than the human (odds ratio=1.95, p=0.0021). Conclusion: Our data shows that CNV morphology can be used to predict disease activity by AI; Longitudinal studies are needed to better understand the evolution of CNV and features that predict reactivation. Future studies will be able to evaluate the additional predicative value of OCTA on top of other imaging characteristics (i.e., fluid location on OCT B scans) to help predict response to treatment.

show abstract

Retinal OCT Layer Segmentation via Joint Motion Correction and Graph-Assisted 3D Neural Network

Wang,

Galang,

Freeman

et al. 2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

Optical Coherence Tomography (OCT) is a widely used 3D imaging technology in ophthalmology. Segmentation of retinal layers in OCT is important for diagnosis and evaluation of various retinal and systemic diseases. While 2D segmentation algorithms have been developed, they do not fully utilize contextual information and suffer from inconsistency in 3D. We propose neural networks to combine motion correction and segmentation in 3D. The proposed segmentation network utilizes 3D convolution and a novel graph pyramid structure with graph-inspired building blocks. We also collected one of the largest OCT segmentation dataset with manually corrected segmentation covering both normal examples and various diseases. The experimental results on three datasets with multiple instruments and various diseases show the proposed method can achieve improved segmentation accuracy compared with commercial softwares and conventional or deep learning methods in literature. Specifically, the proposed method reduced the average error from 38.47% to 11.43% compared to clinically available commercial software for severe deformations caused by diseases. The diagnosis and evaluation of diseases with large deformation such as DME, wet AMD and CRVO would greatly benefit from the improved accuracy, which impacts tens of millions of patients.

show abstract

Joint Motion Correction and 3D Segmentation with Graph-Assisted Neural Networks for Retinal OCT

Cited by 3 publications

References 23 publications

Effect of manual OCTA segmentation correction to improve image quality and visibility of choroidal neovascularization in AMD

Effect of manual OCTA segmentation correction to improve image quality and visibility of choroidal neovascularization in AMD

Artificial intelligence for OCTA-based disease activity prediction in age-related macular degeneration.

Retinal OCT Layer Segmentation via Joint Motion Correction and Graph-Assisted 3D Neural Network

Contact Info

Product

Resources

About