Ophthalmology is one of the major imaging-intensive fields of medicine and thus has potential for extensive applications of artificial intelligence (AI) to advance diagnosis, drug efficacy, and other ...treatment-related aspects of ocular disease. AI has made impressive progress in ophthalmology within the past few years and two autonomous AI-enabled systems have received US regulatory approvals for autonomously screening for mid-level or advanced diabetic retinopathy and macular edema. While no autonomous AI-enabled system for glaucoma screening has yet received US regulatory approval, numerous assistive AI-enabled software tools are already employed in commercialized instruments for quantifying retinal images and visual fields to augment glaucoma research and clinical practice. In this literature review (non-systematic), we provide an overview of AI applications in glaucoma, and highlight some limitations and considerations for AI integration and adoption into clinical practice.
To evaluate the association between vessel density measurements using optical coherence tomography angiography (OCT-A) and severity of visual field loss in primary open-angle glaucoma.
Observational, ...cross-sectional study.
A total of 153 eyes from 31 healthy participants, 48 glaucoma suspects, and 74 glaucoma patients enrolled in the Diagnostic Innovations in Glaucoma Study.
All eyes underwent imaging using OCT-A (Angiovue; Optovue, Fremont, CA), spectral-domain OCT (Avanti; Optovue), and standard automated perimetry (SAP). Retinal vasculature information was summarized as vessel density, the percentage of area occupied by flowing blood vessels in the selected region. Two measurements from the retinal nerve fiber layer (RNFL) were used: circumpapillary vessel density (cpVD) (750-μm-wide elliptical annulus around the optic disc) and whole-image vessel density (wiVD) (entire 4.5×4.5-mm scan field).
Associations between the severity of visual field loss, reported as SAP mean deviation (MD), and OCT-A vessel density.
Compared with glaucoma eyes, normal eyes demonstrated a denser microvascular network within the RNFL. Vessel density was higher in normal eyes followed by glaucoma suspects, mild glaucoma, and moderate to severe glaucoma eyes for wiVD (55.5%, 51.3%, 48.3%, and 41.7%, respectively) and for cpVD (62.8%, 61.0%, 57.5%, 49.6%, respectively) (P < 0.001 for both). The association between SAP MD with cpVD and wiVD was stronger (R
= 0.54 and R
= 0.51, respectively) than the association between SAP MD with RNFL (R
= 0.36) and rim area (R
= 0.19) (P < 0.05 for all). Multivariate regression analysis showed that each 1% decrease in wiVD was associated with 0.66 decibel (dB) loss in MD and each 1% decrease in cpVD was associated with 0.64 dB loss in MD. In addition, the association between vessel density and severity of visual field damage was found to be significant even after controlling for the effect of structural loss.
Decreased vessel density was significantly associated with the severity of visual field damage independent of the structural loss. Optical coherence tomography angiography is a promising technology in glaucoma management, potentially enhancing the understanding of the role of vasculature in the pathophysiology of the disease.
We developed an unsupervised machine learning algorithm and applied it to big corneal parameters to identify and monitor keratoconus stages. A big dataset of corneal swept source optical coherence ...tomography (OCT) images of 12,242 eyes acquired from SS-1000 CASIA OCT Imaging Systems in multiple centers across Japan was assembled. A total of 3,156 eyes with valid Ectasia Status Index (ESI) between zero and 100% were selected for the downstream analysis. Four hundred and twenty corneal topography, elevation, and pachymetry parameters (excluding ESI Keratoconus indices) were selected. The algorithm included three major steps. 1) Principal component analysis (PCA) was used to linearly reduce the dimensionality of the input data from 420 to eight significant principal components. 2) Manifold learning was used to further reducing the selected principal components nonlinearly to two eigen-parameters. 3) Finally, a density-based clustering was applied to the eigen-parameters to identify eyes with keratoconus. Visualization of clusters in 2-D space was used to validate the quality of learning subjectively and ESI was used to assess the accuracy of the identified clusters objectively. The proposed method identified four clusters; I: a cluster composed of mostly normal eyes (224 eyes with ESI equal to zero, 23 eyes with ESI between five and 29, and nine eyes with ESI greater than 29), II: a cluster composed of mostly healthy eyes and eyes with forme fruste keratoconus (1772 eyes with ESI equal to zero, 698 eyes with ESI between five and 29, and 117 eyes with ESI greater than 29), III: a cluster composed of mostly eyes with mild keratoconus stage (184 eyes with ESI greater than 29, 74 eyes with ESI between five and 29, and 6 eyes with ESI equal to zero), and IV: a cluster composed of eyes with mostly advanced keratoconus stage (80 eyes had ESI greater than 29 and 1 eye had ESI between five and 29). We found that keratoconus status and severity can be well identified using unsupervised machine learning algorithms along with linear and non-linear corneal data transformation. The proposed method can better identify and visualize the keratoconus stages.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
The purpose of this study was to compare retinal nerve fiber layer (RNFL) thickness and optical coherence tomography angiography (OCT-A) retinal vasculature measurements in healthy, glaucoma suspect, ...and glaucoma patients.
Two hundred sixty-one eyes of 164 healthy, glaucoma suspect, and open-angle glaucoma (OAG) participants from the Diagnostic Innovations in Glaucoma Study with good quality OCT-A images were included. Retinal vasculature information was summarized as a vessel density map and as vessel density (%), which is the proportion of flowing vessel area over the total area evaluated. Two vessel density measurements extracted from the RNFL were analyzed: (1) circumpapillary vessel density (cpVD) measured in a 750-μm-wide elliptical annulus around the disc and (2) whole image vessel density (wiVD) measured over the entire image. Areas under the receiver operating characteristic curves (AUROC) were used to evaluate diagnostic accuracy.
Age-adjusted mean vessel density was significantly lower in OAG eyes compared with glaucoma suspects and healthy eyes. (cpVD: 55.1 ± 7%, 60.3 ± 5%, and 64.2 ± 3%, respectively; P < 0.001; and wiVD: 46.2 ± 6%, 51.3 ± 5%, and 56.6 ± 3%, respectively; P < 0.001). For differentiating between glaucoma and healthy eyes, the age-adjusted AUROC was highest for wiVD (0.94), followed by RNFL thickness (0.92) and cpVD (0.83). The AUROCs for differentiating between healthy and glaucoma suspect eyes were highest for wiVD (0.70), followed by cpVD (0.65) and RNFL thickness (0.65).
Optical coherence tomography angiography vessel density had similar diagnostic accuracy to RNFL thickness measurements for differentiating between healthy and glaucoma eyes. These results suggest that OCT-A measurements reflect damage to tissues relevant to the pathophysiology of OAG.
Global indices of standard automated perimerty are insensitive to localized losses, while point-wise indices are sensitive but highly variable. Region-wise indices sit in between. This study ...introduces a machine learning–based index for glaucoma progression detection that outperforms global, region-wise, and point-wise indices.
Development and comparison of a prognostic index.
Visual fields from 2085 eyes of 1214 subjects were used to identify glaucoma progression patterns using machine learning. Visual fields from 133 eyes of 71 glaucoma patients were collected 10 times over 10 weeks to provide a no-change, test-retest dataset. The parameters of all methods were identified using visual field sequences in the test-retest dataset to meet fixed 95% specificity. An independent dataset of 270 eyes of 136 glaucoma patients and survival analysis were used to compare methods.
The time to detect progression in 25% of the eyes in the longitudinal dataset using global mean deviation (MD) was 5.2 (95% confidence interval, 4.1–6.5) years; 4.5 (4.0–5.5) years using region-wise, 3.9 (3.5–4.6) years using point-wise, and 3.5 (3.1–4.0) years using machine learning analysis. The time until 25% of eyes showed subsequently confirmed progression after 2 additional visits were included were 6.6 (5.6–7.4) years, 5.7 (4.8–6.7) years, 5.6 (4.7–6.5) years, and 5.1 (4.5–6.0) years for global, region-wise, point-wise, and machine learning analyses, respectively.
Machine learning analysis detects progressing eyes earlier than other methods consistently, with or without confirmation visits. In particular, machine learning detects more slowly progressing eyes than other methods.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK, ZRSKP
To assess the accuracy of deep learning models to predict glaucoma development from fundus photographs several years before disease onset.
Algorithm development for predicting glaucoma using data ...from a prospective longitudinal study.
A total of 66 721 fundus photographs from 3272 eyes of 1636 subjects who participated in the Ocular Hypertension Treatment Study (OHTS) were included.
Accuracy and area under the curve (AUC).
Fundus photographs and visual fields were carefully examined by 2 independent readers from the optic disc and visual field reading centers of the OHTS. When an abnormality was detected by the readers, the subject was recalled for retesting to confirm the abnormality and for further confirmation by an end point committee. By using 66 721 fundus photographs, deep learning models were trained and validated using 85% of the fundus photographs and further retested (validated) on the remaining (held-out) 15% of the fundus photographs.
The AUC of the deep learning model in predicting glaucoma development 4 to 7 years before disease onset was 0.77 (95% confidence interval CI, 0.75-0.79). The accuracy of the model in predicting glaucoma development approximately 1 to 3 years before disease onset was 0.88 (95% CI, 0.86-0.91). The accuracy of the model in detecting glaucoma after onset was 0.95 (95% CI, 0.94-0.96).
Deep learning models can predict glaucoma development before disease onset with reasonable accuracy. Eyes with visual field abnormality but not glaucomatous optic neuropathy had a higher tendency to be missed by deep learning algorithms.
Abstract
The main goal of this study is to identify the association between corneal shape, elevation, and thickness parameters and visual field damage using machine learning. A total of 676 eyes from ...568 patients from the Jichi Medical University in Japan were included in this study. Corneal topography, pachymetry, and elevation images were obtained using anterior segment optical coherence tomography (OCT) and visual field tests were collected using standard automated perimetry with 24-2 Swedish Interactive Threshold Algorithm. The association between corneal structural parameters and visual field damage was investigated using machine learning and evaluated through tenfold cross-validation of the area under the receiver operating characteristic curves (AUC). The average mean deviation was − 8.0 dB and the average central corneal thickness (CCT) was 513.1 µm. Using ensemble machine learning bagged trees classifiers, we detected visual field abnormality from corneal parameters with an AUC of 0.83. Using a tree-based machine learning classifier, we detected four visual field severity levels from corneal parameters with an AUC of 0.74. Although CCT and corneal hysteresis have long been accepted as predictors of glaucoma development and future visual field loss, corneal shape and elevation parameters may also predict glaucoma-induced visual functional loss.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
Employment of ground-based positioning systems has been consistently growing over the past decades due to the growing number of applications that require location information where the conventional ...satellite-based systems have limitations. Such systems have been successfully adopted in the context of wireless emergency services, tactical military operations, and various other applications offering location-based services. In current and previous generation of cellular systems, i.e., 3G, 4G, and LTE, the base stations, which have known locations, have been assumed to be stationary and fixed. However, with the possibility of having mobile relays in 5G networks, there is a demand for novel algorithms that address the challenges that did not exist in the previous generations of localization systems. This paper includes a review of various fundamental techniques, current trends, and state-of-the-art systems and algorithms employed in wireless position estimation using moving receivers. Subsequently, performance criteria comparisons are given for the aforementioned techniques and systems. Moreover, a discussion addressing potential research directions when dealing with moving receivers, e.g., receiver's movement pattern for efficient and accurate localization, non-line-of-sight problem, sensor fusion, and cooperative localization, is briefly given.
To investigate whether vessel density assessed by optical coherence tomography angiography (OCT-A) is reduced in glaucomatous eyes with focal lamina cribrosa (LC) defects.
Cross-sectional, ...case-control study.
A total of 82 patients with primary open-angle glaucoma (POAG) from the Diagnostic Innovations in Glaucoma Study (DIGS) with and without focal LC defects (41 eyes of 41 patients in each group) matched by severity of visual field (VF) damage.
Optical coherence tomography (OCT) angiography-derived circumpapillary vessel density (cpVD) was calculated as the percentage area occupied by vessels in the measured region extracted from the retinal nerve fiber layer (RNFL) in a 750-μm-wide elliptical annulus around the disc. Focal LC defects were detected using swept-source OCT images.
Comparison of global and sectoral (eight 45-degree sectors) cpVDs and circumpapillary RNFL (cpRNFL) thicknesses in eyes with and without LC defects.
Age, global, and sectoral cpRNFL thicknesses, VF mean deviation (MD) and pattern standard deviation, presence of optic disc hemorrhage, and mean ocular perfusion pressure did not differ between patients with and without LC defects (P > 0.05 for all comparisons). Mean cpVDs of eyes with LC defects were significantly lower than in eyes without a defect globally (52.9%±5.6% vs. 56.8%±7.7%; P = 0.013) and in the inferotemporal (IT) (49.5%±10.3% vs. 56.8%±12.2%; P = 0.004), superotemporal (ST) (54.3%±8.8% vs. 58.8%±9.6%; P = 0.030), and inferonasal (IN) (52.4%±9.0% vs. 57.6%±9.1%; P = 0.009) sectors. Eyes with LC defects in the IT sector (n = 33) had significantly lower cpVDs than eyes without a defect in the corresponding IT and IN sectors (P < 0.05 for all). Eyes with LC defects in the ST sector (n = 19) had lower cpVDs in the ST, IT, and IN sectors (P < 0.05 for all).
In eyes with similar severity of glaucoma, OCT-A-measured vessel density was significantly lower in POAG eyes with focal LC defects than in eyes without an LC defect. Moreover, reduction of vessel density was spatially correlated with the location of the LC defect.
To compare the hemifield asymmetry of visual field (VF) loss in primary open-angle glaucoma (POAG) and primary angle-closure glaucoma (PACG) across all severity levels.
A total of 522 eyes of 327 ...patients with POAG (mean age ± SD, 54.1 ± 12.4 years) and 375 eyes of 204 patients with PACG (67.3 ± 8.9 years) were included. Subjects meeting the definitions of POAG or PACG were included. Means of the total deviation (TD) values (Humphrey 24-2 VF) in the Glaucoma Hemifield Test (GHT) regions were calculated in early (≥ -6 dB), moderate (< -6 dB and ≥ -12 dB), and advanced (< -12 dB) stages of POAG and PACG eyes. Then the differences of the TD values between superior and inferior hemifield GHT regions of POAG and PACG eyes were calculated. Also, the relationship between the values of pattern SD (PSD) and mean TD (mTD) was compared between POAG and PACG.
In POAG eyes in the early stage, three regions (central, paracentral, and peripheral) in the superior hemifield had greater loss than their inferior counterparts; in moderate and advanced stages, all GHT regions in the superior hemifield had greater loss than their inferior counterparts. In PACG eyes, siginificantly fewer regions in the superior hemifield were significantly worse than their inferior counterpart, compared with POAG: one region (central) in early stage, two regions (central and peripheral) in moderate stage, and one region (central) in advanced stage. POAG eyes had greater PSD values than PACG eyes for given mean of TD values.
In both POAG and PACG eyes, VF damage was more pronounced in superior hemifield than inferior hemifield; however, this tendency was more obvious in POAG eyes than in PACG eyes.