Latent diffusion augmentation enhances deep learning analysis of neuro-morphology in limbal stem cell deficiency

David Gibson; Thai Tran; Vidhur Raveendran; Clémence Bonnet; Nathan Siu; Micah Vinet; Theo Stoddard-Bennett; Corey Arnold; Sophie X Deng; William Speier

doi:10.3389/fmed.2023.1270570

Latent diffusion augmentation enhances deep learning analysis of neuro-morphology in limbal stem cell deficiency

Front Med (Lausanne). 2023 Oct 16:10:1270570. doi: 10.3389/fmed.2023.1270570. eCollection 2023.

Authors

David Gibson¹, Thai Tran¹, Vidhur Raveendran², Clémence Bonnet^{3

4}, Nathan Siu^{1

4

5}, Micah Vinet^{2

5}, Theo Stoddard-Bennett⁶, Corey Arnold^{1

2

5}, Sophie X Deng^{4

5

7}, William Speier^{1

2

5}

Affiliations

¹ Medical Informatics Home Area, Graduate Programs in Bioscience, University of California, Los Angeles, Los Angeles, CA, United States.
² Department of Bioengineering, University of California, Los Angeles, Los Angeles, CA, United States.
³ Ophthalmology Department, Cochin Hospital and Paris Cité University, AP-HP, Paris, France.
⁴ Stein Eye Institute, University of California, Los Angeles, Los Angeles, CA, United States.
⁵ Computational Diagnostics Lab, University of California, Los Angeles, Los Angeles, CA, United States.
⁶ David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, CA, United States.
⁷ Molecular Biology Institute, University of California, Los Angeles, Los Angeles, CA, United States.

Abstract

Introduction: Limbal Stem Cell Deficiency (LSCD) is a blinding corneal disease characterized by the loss of function or deficiency in adult stem cells located at the junction between the cornea and the sclera (i.e., the limbus), namely the limbal stem cells (LSCs). Recent advances in in vivo imaging technology have improved disease diagnosis and staging to quantify several biomarkers of in vivo LSC function including epithelial thickness measured by anterior segment optical coherence tomography, and basal epithelial cell density and subbasal nerve plexus by in vivo confocal microscopy. A decrease in central corneal sub-basal nerve density and nerve fiber and branching number has been shown to correlate with the severity of the disease in parallel with increased nerve tortuosity. Yet, image acquisition and manual quantification require a high level of expertise and are time-consuming. Manual quantification presents inevitable interobserver variability.

Methods: The current study employs a novel deep learning approach to classify neuron morphology in various LSCD stages and healthy controls, by integrating images created through latent diffusion augmentation. The proposed model, a residual U-Net, is based in part on the InceptionResNetV2 transfer learning model.

Results: Deep learning was able to determine fiber number, branching, and fiber length with high accuracy (R2 of 0.63, 0.63, and 0.80, respectively). The model trained on images generated through latent diffusion on average outperformed the same model when trained on solely original images. The model was also able to detect LSCD with an AUC of 0.867, which showed slightly higher performance compared to classification using manually assessed metrics.

Discussion: The results suggest that utilizing latent diffusion to supplement training data may be effective in bolstering model performance. The results of the model emphasize the ability as well as the shortcomings of this novel deep learning approach to predict various nerve morphology metrics as well as LSCD disease severity.

Keywords: deep learning; in vivo confocal microscopy; limbal stem cell deficiency; machine learning; ophthalmology.

Abstract

Grants and funding