Yue Wu

University of Washington

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Developing a deep learning classifier for uveitis scoring on mouse OCT images

Investigative Ophthalmology & Visual Science (2021)

Sarah John Jessica Jeni Na Shreya Swaminathan Leslie Wilson Yue Wu

Source

Cite

Citations (0)

Convolutional neural network-based classification of glaucoma using optic radiation tissue properties

Communications Medicine (2024)

John Kruper Adam Richie-Halford Noah C. Benson Sendy Caffarra Julia P. Owen

Abstract Background Sensory changes due to aging or disease can impact brain tissue. This study aims to investigate the link between glaucoma, a leading cause of blindness, and alterations in brain connections. Methods We analyzed diffusion MRI measurements of white matter tissue in a large group, consisting of 905 glaucoma patients (aged 49-80) and 5292 healthy individuals (aged 45-80) from the UK Biobank. Confounds due to group differences were mitigated by matching a sub-sample of controls to glaucoma subjects. We compared classification of glaucoma using convolutional neural networks (CNNs) focusing on the optic radiations, which are the primary visual connection to the cortex, against those analyzing non-visual brain connections. As a control, we evaluated the performance of regularized linear regression models. Results We showed that CNNs using information from the optic radiations exhibited higher accuracy in classifying subjects with glaucoma when contrasted with CNNs relying on information from non-visual brain connections. Regularized linear regression models were also tested, and showed significantly weaker classification performance. Additionally, the CNN was unable to generalize to the classification of age-group or of age-related macular degeneration. Conclusions Our findings indicate a distinct and potentially non-linear signature of glaucoma in the tissue properties of optic radiations. This study enhances our understanding of how glaucoma affects brain tissue and opens avenues for further research into how diseases that affect sensory input may also affect brain aging.

Optic radiation

10.1038/s43856-024-00496-w

Cite

Citations (6)

Multi-omic spatial effects on high-resolution AI-derived retinal thickness

medRxiv (Cold Spring Harbor Laboratory) (2023)

Victoria E. Jackson Yue Wu Roberto Bonelli Julia P. Owen Samaneh Farashi

Abstract Retinal thickness is a marker of retinal health and more broadly, is seen as a promising biomarker for many systemic diseases. Retinal thickness measurements are procured from optical coherence tomography (OCT) as part of routine clinical eyecare. We processed the UK Biobank OCT images using a convolutional neural network to produce fine-scale retinal thickness measurements across >29,000 points in the macula, the part of the retina responsible for human central vision. The macula is disproportionately affected by high disease burden retinal disorders such as age-related macular degeneration and diabetic retinopathy, which both involve metabolic dysregulation. Analysis of common genomic variants, metabolomic, blood and immune biomarkers, ICD10 codes and polygenic risk scores across a fine-scale macular thickness grid, reveals multiple novel genetic loci-including four on the X chromosome; retinal thinning associated with many systemic disorders including multiple sclerosis; and multiple associations to correlated metabolites that cluster spatially in the retina. We highlight parafoveal thickness to be particularly susceptible to systemic insults. These results demonstrate the gains in discovery power and resolution achievable with AI-leveraged analysis. Results are accessible using a bespoke web interface that gives full control to pursue findings. Graphical Abstract

10.1101/2023.07.31.23293176

Cite

Citations (1)

Exploring a Structural Basis for Delayed Rod-Mediated Dark Adaptation in Age-Related Macular Degeneration Via Deep Learning

Translational Vision Science & Technology (2020)

Aaron Lee Cecilia S. Lee Marian Blazes Julia P. Owen Yelena Bagdasarova

Delayed rod-mediated dark adaptation (RMDA) is a functional biomarker for incipient age-related macular degeneration (AMD). We used anatomically restricted spectral domain optical coherence tomography (SD-OCT) imaging data to localize de novo imaging features associated with and to test hypotheses about delayed RMDA.Rod intercept time (RIT) was measured in participants with and without AMD at 5 degrees from the fovea, and macular SD-OCT images were obtained. A deep learning model was trained with anatomically restricted information using a single representative B-scan through the fovea of each eye. Mean-occlusion masking was utilized to isolate the relevant imaging features.The model identified hyporeflective outer retinal bands on macular SD-OCT associated with delayed RMDA. The validation mean standard error (MSE) registered to the foveal B-scan localized the lowest error to 0.5 mm temporal to the fovea center, within an overall low-error region across the rod-free zone and adjoining parafovea. Mean absolute error (MAE) on the test set was 4.71 minutes (8.8% of the dynamic range).We report a novel framework for imaging biomarker discovery using deep learning and demonstrate its ability to identify and localize a previously undescribed biomarker in retinal imaging. The hyporeflective outer retinal bands in central macula on SD-OCT demonstrate a structural basis for dysfunctional rod vision that correlates to published histopathologic findings.This agnostic approach to anatomic biomarker discovery strengthens the rationale for RMDA as an outcome measure in early AMD clinical trials, and also expands the utility of deep learning beyond automated diagnosis to fundamental discovery.

Fovea centralis

10.1167/tvst.9.2.62

Cite

Citations (27)

De Novo Identification and Visualization of Important Cell Populations for Classic Hodgkin Lymphoma Using Flow Cytometry and Machine Learning

American Journal of Clinical Pathology (2021)

Paul D. Simonson Yue Wu David Wu Jonathan R. Fromm Aaron Lee

Abstract Objectives Automated classification of flow cytometry data has the potential to reduce errors and accelerate flow cytometry interpretation. We desired a machine learning approach that is accurate, is intuitively easy to understand, and highlights the cells that are most important in the algorithm’s prediction for a given case. Methods We developed an ensemble of convolutional neural networks for classification and visualization of impactful cell populations in detecting classic Hodgkin lymphoma using two-dimensional (2D) histograms. Data from 977 and 245 clinical flow cytometry cases were used for training and testing, respectively. Seventy-eight nongated 2D histograms were created per flow cytometry file. Shapley additive explanation (SHAP) values were calculated to determine the most impactful 2D histograms and regions within histograms. SHAP values from all 78 histograms were then projected back to the original cell data for gating and visualization using standard flow cytometry software. Results The algorithm achieved 67.7% recall (sensitivity), 82.4% precision, and 0.92 area under the receiver operating characteristic. Visualization of the important cell populations for individual predictions demonstrated correlations with known biology. Conclusions The method presented enables model explainability while highlighting important cell populations in individual flow cytometry specimens, with potential applications in both diagnosis and discovery of previously overlooked key cell populations.

Identification

10.1093/ajcp/aqab076

Cite

Citations (15)

Fully automated artificial intelligence (AI) pipeline for feature-based segmentation and classification of diabetic retinopathy in fundus photographs

Investigative Ophthalmology & Visual Science (2019)

Yue Wu Fenghua Wang Sa Xiao Yuka Kihara Ted Spaide

Fundus (uterus)

Feature (linguistics)

Source

Cite

Citations (0)

Contributed Session I: Specific and non-linear effects of glaucoma on optic radiation tissue properties

Journal of Vision (2023)

John Kruper Adam Richie-Halford Noah C. Benson Sendy Caffarra Julia P. Owen

Changes in sensory input with aging and disease affect brain tissue properties. To establish the link between glaucoma, the most prevalent cause of irreversible blindness, and changes in major brain connections, we characterized white matter tissue properties in diffusion MRI measurements in a large sample of subjects with glaucoma (N=905; age 49-80) and healthy controls (N=5,292; age 45-80) from the UK Biobank. Confounds due to group differences were mitigated by matching a sub-sample of controls to glaucoma subjects. A convolutional neural network (CNN) accurately classified whether a subject has glaucoma using information from the primary visual connection to cortex (the optic radiations, OR), but not from non-visual brain connections. On the other hand, regularized linear regression could not classify glaucoma, and the CNN did not generalize to classification of age-group or of age-related macular degeneration. This suggests a unique non-linear signature of glaucoma in OR tissue properties.

Optic radiation

10.1167/jov.23.15.73

Cite

Citations (0)

Automated Machine Learning Pipeline for Predicting Retinal Sensitivity from Optical Coherence Tomography in Macular Telangiectasia Type 2

Investigative Ophthalmology & Visual Science (2019)

Yuka Kihara Tjebo Heeren Yue Wu Ted Spaide Sa Xiao

Macular telangiectasia

Source

Cite

Citations (0)

Forecasting Future Humphrey Visual Fields Using Deep Learning

bioRxiv (Cold Spring Harbor Laboratory) (2018)

Joanne C. Wen Cecilia S. Lee Pearse A. Keane Sa Xiao Yue Wu

ABSTRACT Purpose To determine if deep learning networks could be trained to forecast a future 24-2 Humphrey Visual Field (HVF). Design Retrospective database study. Participants All patients who obtained a HVF 24-2 at the University of Washington. Methods All datapoints from consecutive 24-2 HVFs from 1998 to 2018 were extracted from a University of Washington database. Ten-fold cross validation with a held out test set was used to develop the three main phases of model development: model architecture selection, dataset combination selection, and time-interval model training with transfer learning, to train a deep learning artificial neural network capable of generating a point-wise visual field prediction. Main outcome measures Mean absolute error (MAE) and difference in Mean Deviation (MD) between predicted and actual future HVF. Results More than 1.7 million perimetry points were extracted to the hundredth decibel from 32,443 24-2 HVFs. The best performing model with 20 million trainable parameters, CascadeNet-5, was selected. The overall MAE for the test set was 2.47 dB (95% CI: 2.45 dB to 2.48 dB). The 100 fully trained models were able to successfully predict progressive field loss in glaucomatous eyes up to 5.5 years in the future with a correlation of 0.92 between the MD of predicted and actual future HVF (p < 2.2 = 10 −16 ) and an average difference of 0.41 dB. Conclusions Using unfiltered real-world datasets, deep learning networks show an impressive ability to not only learn spatio-temporal HVF changes but also to generate predictions for future HVFs up to 5.5 years, given only a single HVF.

Decibel

Absolute deviation

Mean absolute error

10.1101/293621

Cite

Citations (11)

Using Fixed-Force Goldmann Applanation Tonometry to measure the Ocular Pulse Amplitude

Investigative Ophthalmology & Visual Science (2021)

Joanne C. Wen Theodore Spaide Yue Wu Aaron Lee

Applanation tonometry

Source

Cite

Citations (0)