Browsing by Subject "Glaucoma"

Glaucoma is a group of chronic eye diseases characterized by optic neuropathy, which causes irreversible vision loss. It is caused by progressive degeneration of the optic nerve, leading to gradual loss of the visual field from the periphery to the center, resulting in blindness if left untreated. Since the changes are gradual and the damage progresses generally slowly, glaucoma development is insidious and often diagnosed until it reaches an advanced stage. Early detection of glaucoma progression is necessary to monitor the atrophy and formulate treatment strategies to halt progressive functional vision impairments. The availability of data centric methods have made it possible for researchers to develop computer-aided algorithms for the clinical diagnosis of glaucoma and capture accurate disease characteristics. In this research, we use deep learning models, one such forefront, to identify complex disease characteristics and progression criteria, enabling the detection of subtle changes indicative of glaucoma progression.

To this end, we investigate the structure-function relationship of glaucoma progression and explore the possibility of predicting functional impairment from structural eye deterioration. We also analyze various statistical and machine-learning methods that have aided previous attempts to estimate progression, including emerging deep-learning techniques that use structural features like optical coherence tomography (OCT) scans to predict glaucoma progression accurately. We show through our investigations that these methods are still prone to confounding risk factors, especially variability due to age, data imbalances, potential noisy labels, lack of gold standard criteria, etc. We developed novel semi-supervised time-series algorithms to overcome these multifaceted challenges using unique data-driven approaches:

Weakly-Supervised Time-Series Learning: We develop a convolutional neural network-long short-term memory (CNN-LSTM) base model to encode the spatiotemporal features from the OCT scan sequence taken over a fixed follow-up. We model the rest of the deep learning architecture on the fact that original OCT sequences exhibit age-related progression, and reshuffling the sequence order, along with the knowledge of healthy eyes from a positive-unlabeled dataset, can establish robust pseudo-progression criteria for glaucoma. This circumvents the need for gold standard labels for disease progression.

Semi-supervised Time-Series Learning: We extend the above notion to a labeled case where labels are obtained from Guided Progression Analysis (GPA), a well-known, stable, and accurate functional assessment for glaucoma progression, but might be prone to noisy labels due to nuances in data acquisition. We model the age-related structural progression as a pseudo-identifier for glaucoma progression. We use this knowledge in a contrastive learning scheme where the foundational CNN-LSTM base learns accurate spatiotemporal characteristics from potentially mislabeled data and improves predictions.

Finally, we compare and show that these methods outperform conventional and state-of-the-art techniques.

Purpose of review

Recent findings

Summary

Purpose

Design

Participants

Methods

Main outcome measures

Results

Conclusions

Introduction

Methods

Results

Conclusions

Purpose

Design

Participants

Methods

Main outcome measures

Results

Conclusions

Primary OAG (POAG) is the second leading cause of irreversible blindness in the US and its prevalence is expected to worsen in the coming years. Major pathological changes have been attributed to the Juxtacanicular Tissue (JCT) and Inner Wall (IW) of Schlemm’s Canal (SC) within the human conventional outflow pathway. Biological tissues like the JCT/IW are viscoelastic in nature with both intra-cellular and extra-cellular mechanisms by which to store and dissipate applied forces. How these events contribute towards regulation of the local mechanobiology in the dynamic reciprocitybetween cells, their extracellular matrix (ECM), and in ultimately regulating outflow resistance, is poorly understood. Furthermore, the viscoelastic properties of the human trabecular meshwork (hTM) tissue are poorly understood. As a first step to develop more insight into the role of viscoelasticity, it was our goal to determine the localized dynamic mechanical properties of different regions of the hTM as a function of dexamethasone treatment. To explore the viscoelastic properties of the different tissue regions in the hTM comprising the hTM, we applied our co-located AFM-based rheometer/CLSM method to frontal sections of hTM under control and early ocular hypertensive conditions across a broad frequency range (1 Hz-1 kHz). We specifically considered the storage and loss moduli in the ocular pulse-relevant frequency range (1-10 Hz) and their changes across regions under dex treatment for two donors.

Background

Methods/design

Discussion

The trabecular meshwork (TM) is comparable to a bioactive filter that plays a major role in regulating outflow of aqueous humor of the eye and setting intraocular pressure (IOP). TM dysfunction may lead to ocular hypertension which is the major risk factor in glaucoma. Although the outflow properties of the TM have been assessed over the last sixty years, very little work has been done assessing its mechanical properties. Therefore, the major goals of these studies were two-fold: (1) to determine the relationship between mechanical properties of TM, specifically the bulk Young's modulus, and outflow function in normal and glaucomatous eyes, and (2) to establish a method and possible animal model for future testing of this relationship.

Outflow function was assessed by constant pressure perfusion in enucleated eyes at four pressure levels (10, 20, 30, and 40 mmHg) to determine outflow facilities and variability in outflow resistance with pressure elevation. A micro-strain analyzer (MSA) was used to determine the circumferential bulk Young's modulus of the TM post-perfusion. Based on their relative ease of availability, pigs and rats were explored as possible animal models. Due to the small size of rat eyes, atomic force microscopy (AFM) was used to assess the Young's modulus of TM rather than with a MSA.

We found that there was a relationship with better outflow function and a stiffer TM in normal eyes. Additionally, glaucomatous TM was found to be much softer and more variable than normal TM. Unfortunately, porcine TM did not serve as a good model for the bulk Young's modulus of human TM, presumably due to anatomical difference in its outflow pathway. Lastly, we were able to establish a new method for measuring the Young's modulus of rat TM for future work to determine potential mechanism for evaluating stiffness changes that may be associated with glaucoma.

Purpose

Design

Methods

Results

Conclusions