Attention-Guided 3D-CNN Framework for Glaucoma Detection and Structural-Functional Association Using Volumetric Images

George, Yasmeen; Antony, Bhavna J.; Ishikawa, Hiroshi; Wollstein, Gadi; Schuman, Joel S.; Garnavi, Rahil

doi:10.1109/jbhi.2020.3001019

Cited by 44 publications

(13 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a work from the same group of authors, George et al showed a similar performance to estimate SAP VFI from ONH centered volumes, although the main goal of their work was to detect glaucomatous VF defect. 8 While the studies presented above showed complex DL models, using different types of inputs, the work done by Huang et al showed a model that predicted SAP MD from the RNFL thickness averaged into 64 sectors. 9 Although they use a simpler model, its performance in their internal test set was comparable to those of the previous studies, with a MAE of 4.0, a root mean squared error (RMSE) of 5.2, and a median absolute error of 3.1 dB.…”

Section: Prediction Of Visual Field Summary Metricsmentioning

confidence: 99%

A review of deep learning in structure and function in glaucoma

Mariottoni¹,

Medeiros²,

Costa³

2022

MAIO

View full text Add to dashboard Cite

The relationship between structural damage and functional loss in glaucoma is of great importance for its diagnosis and management. The functional status is usually assessed through visual field examination, a subjective test that is burdensome and time-consuming. Moreover, it depends on patients’ answers and there is a learning curve until accurate and reliable measurements are possible. Structural assessment, on the other hand, has remarkably improved since the development of optical coherence tomography, a fast test that allows for objective and quantitative analysis of retinal layers. The relationship between the two tests, however, is complex and nonlinear, and is influenced by interindividual variability. Thus, qualitative evaluation or the use of conventional statistics might not be appropriate. In recent years, we have seen a remarkable evolution of artificial intelligence algorithms and deep learning models. These techniques have proved adequate to model such complicated relationships. In this review, we summarize studies that investigate the structure and function relationship in glaucoma making use of artificial intelligence and deep learning, the challenges associated with predicting visual field information from structural measurements, and the strategies adopted to improve their accuracy.

show abstract

Section: Prediction Of Visual Field Summary Metricsmentioning

confidence: 99%

A review of deep learning in structure and function in glaucoma

Mariottoni¹,

Medeiros²,

Costa³

2022

MAIO

View full text Add to dashboard Cite

show abstract

“…Zhang et al [10] incorporate medical and imaging prior knowledge with deep learning to address the challenging issue of the segmentation and visualization of choroid in OCT. A biomarker infused global-to-local network is designed to regularize the segmentation via predicted choroid thickness, simultaneously, leverage a global-to-local segmentation strategy to provide global structure information and suppress overfitting. George et al [11] proposes an end-to-end attention guided 3D deep learning model for glaucoma detection and estimating visual function from retinal structures. The model is trained directly 2168-2194 © 2020 IEEE.…”

Section: Guest Editorial Ophthalmic Image Analysis and Informaticsmentioning

confidence: 99%

Guest Editorial Ophthalmic Image Analysis and Informatics

Cheng¹,

Fu²,

DeBuc³

et al. 2020

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

“…Convolutional neural networks (CNNs) have been used for image processing to analyze the results of a few optical imaging methods, such as optical coherence tomography, photoacoustic imaging, and fluorescence imaging, to realize vessel segmentation and classification, 11 – 16 cell morphometry, 17 , 18 and ocular disease analysis and diagnosis. 19 – 25 Further, CNNs have been used in combination with abiotic optical imaging methods to reconstruct image information by analyzing optical properties. Zhu et al.…”

Section: Introductionmentioning

confidence: 99%

Spatiotemporal absorption fluctuation imaging based on U-Net

et al. 2022

J. Biomed. Opt.

View full text Add to dashboard Cite

. Significance: Full-field optical angiography is critical for vascular disease research and clinical diagnosis. Existing methods struggle to improve the temporal and spatial resolutions simultaneously. Aim: Spatiotemporal absorption fluctuation imaging (ST-AFI) is proposed to achieve dynamic blood flow imaging with high spatial and temporal resolutions. Approach: ST-AFI is a dynamic optical angiography based on a low-coherence imaging system and U-Net. The system was used to acquire a series of dynamic red blood cell (RBC) signals and static background tissue signals, and U-Net is used to predict optical absorption properties and spatiotemporal fluctuation information. U-Net was generally used in two-dimensional blood flow segmentation as an image processing algorithm for biomedical imaging. In the proposed approach, the network simultaneously analyzes the spatial absorption coefficient differences and the temporal dynamic absorption fluctuation. Results: The spatial resolution of ST-AFI is up to , and the temporal resolution is up to 0.032 s. In vivo experiments on 2.5-day-old chicken embryos were conducted. The results demonstrate that intermittent RBCs flow in capillaries can be resolved, and the blood vessels without blood flow can be suppressed. Conclusions: Using ST-AFI to achieve convolutional neural network (CNN)-based dynamic angiography is a novel approach that may be useful for several clinical applications. Owing to their strong feature extraction ability, CNNs exhibit the potential to be expanded to other blood flow imaging methods for the prediction of the spatiotemporal optical properties with improved temporal and spatial resolutions.

show abstract

Attention-Guided 3D-CNN Framework for Glaucoma Detection and Structural-Functional Association Using Volumetric Images

Cited by 44 publications

References 38 publications

A review of deep learning in structure and function in glaucoma

A review of deep learning in structure and function in glaucoma

Guest Editorial Ophthalmic Image Analysis and Informatics

Spatiotemporal absorption fluctuation imaging based on U-Net

Contact Info

Product

Resources

About