Artery vein classification in fundus images using serially connected U-Nets.

BACKGROUND AND OBJECTIVE: Retinal vessels provide valuable information when diagnosing or monitoring various diseases affecting the retina and disorders affecting the cardiovascular or central nervous systems. Automated retinal vessel segmentation can assist clinicians and researchers when interpreting retinal images. As there are differences in both the structure and function of retinal arteries and veins, separating these two vessel types is essential. As manual segmentation of retinal images is impractical, an accurate automated method is required. METHODS: In this paper, we propose a convolutional neural network based on serially connected U-nets that simultaneously segment the retinal vessels and classify them as arteries or veins. Detailed ablation experiments are performed to understand how the major components contribute to the overall system's performance. The proposed method is trained and tested on the public DRIVE and HRF datasets and a proprietary dataset. RESULTS: The proposed convolutional neural network achieves an F1 score of 0.829 for vessel segmentation on the DRIVE dataset and an F1 score of 0.814 on the HRF dataset, consistent with the state-of-the-art methods on the former and outperforming the state-of-the-art on the latter. On the task of classifying the vessels into arteries and veins, the method achieves an F1 score of 0.952 for the DRIVE dataset exceeding the state-of-the-art performance. On the HRF dataset, the method achieves an F1 score of 0.966, which is consistent with the state-of-the-art. CONCLUSIONS: The proposed method demonstrates competitive performance on both vessel segmentation and artery vein classification compared with state-of-the-art methods. The method outperforms human experts on the DRIVE dataset when classifying retinal images into arteries, veins, and background simultaneously. The method segments the vasculature on the proprietary dataset and classifies the retinal vessels accurately, even on challenging pathological images. The ablation experiments which utilize repeated runs for each configuration provide statistical evidence for the appropriateness of the proposed solution. Connecting several simple U-nets significantly improved artery vein classification performance. The proposed way of serially connecting base networks is not limited to the proposed base network or segmenting the retinal vessels and could be applied to other tasks.

Automation improves repeatability of retinal oximetry measurements.

PURPOSE: Retinal oximetry is a technique based on spectrophotometry where images are analyzed with software capable of calculating vessel oxygen saturation and vessel diameter. In this study, the effect of automation of measurements of retinal vessel oxygen saturation and vessel diameter is explored. METHODS: Until now, operators have had to choose each vessel segment to be measured explicitly. A new, automatic version of the software automatically selects the vessels once the operator defines a measurement area. Five operators analyzed image pairs from the right eye of 23 healthy subjects with semiautomated retinal oximetry analysis software, Oxymap Analyzer (v2.5.1), and an automated version (v3.0). Inter- and intra-operator variability was investigated using the intraclass correlation coefficient (ICC) between oxygen saturation measurements of vessel segments in the same area of the retina. RESULTS: For semiautomated saturation measurements, the inter-rater ICC was 0.80 for arterioles and venules. For automated saturation measurements, the inter-rater ICC was 0.97 for arterioles and 0.96 for venules. For semiautomated diameter measurements, the inter-rater ICC was 0.71 for arterioles and venules. For automated diameter measurements the inter-rater ICC was 0.97 for arterioles and 0.95 for venules. The inter-rater ICCs were different (p < 0.01) between the semiautomated and automated version in all instances. CONCLUSION: Automated measurements of retinal oximetry values are more repeatable compared to measurements where vessels are selected manually.

Retinal oximetry: Metabolic imaging for diseases of the retina and brain.

Retinal oximetry imaging of retinal blood vessels measures oxygen saturation of hemoglobin. The imaging technology is non-invasive and reproducible with remarkably low variability on test-retest studies and in healthy cohorts. Pathophysiological principles and novel biomarkers in several retinal diseases have been discovered, as well as possible applications for systemic and brain disease. In diabetic retinopathy, retinal venous oxygen saturation is elevated and arteriovenous difference progressively reduced in advanced stages of retinopathy compared with healthy persons. This correlates with pathophysiology of diabetic retinopathy where hypoxia stimulates VEGF production. Laser treatment and vitrectomy both improve retinal oximetry values, which correlate with clinical outcome. The oximetry biomarker may allow automatic measurement of severity of diabetic retinopathy and predict its response to treatment. Central retinal vein occlusion is characterized by retinal hypoxia, which is evident in retinal oximetry. The retinal hypoxia seen on oximetry correlates with the extent of peripheral ischemia, visual acuity and thickness of macular edema. This biomarker may help diagnose and measure severity of vein occlusion and degree of retinal ischemia. Glaucomatous retinal atrophy is associated with reduced oxygen consumption resulting in reduced arteriovenous difference and higher retinal venous saturation. The oximetry findings correlate with worse visual field, thinner nerve fiber layer and smaller optic disc rim. This provides an objective biomarker for glaucomatous damage. In retinitis pigmentosa, an association exists between advanced atrophy, worse visual field and higher retinal venous oxygen saturation, lower arteriovenous difference. This biomarker may allow measurement of severity and progression of retinitis pigmentosa and other atrophic retinal diseases. Retinal oximetry offers visible light imaging of systemic and central nervous system vessels. It senses hypoxia in cardiac and pulmonary diseases. Oximetry biomarkers have been discovered in Alzheimer's disease and multiple sclerosis and oxygen levels in the retina correspond well with brain.

Retinal oxygen metabolism in patients with mild cognitive impairment.

INTRODUCTION: We have previously reported that retinal vessel oxygen saturation is increased in mild-to-moderate dementia of Alzheimer's type when compared with healthy individuals. Mild cognitive impairment (MCI) is the predementia stage of the disease. The main purpose was to investigate if these changes are seen in MCI. METHODS: Retinal vessel oxygen saturation was measured in 42 patients with MCI and 42 healthy individuals with a noninvasive retinal oximeter, Oxymap T1. The groups were paired according to age. RESULTS: Arteriolar and venular oxygen saturation was increased in MCI patients compared to healthy individuals (arterioles: 93.1 ± 3.7% vs. 91.1 ± 3.4%, P = .01; venules: 59.6 ± 6.1% vs. 54.9 ± 6.4%, P = .001). Arteriovenous difference was decreased in MCI compared to healthy individuals (33.5 ± 4.5% vs. 36.2 ± 5.2%, P = .01). DISCUSSION: Increased retinal vessel oxygen saturation and decreased arteriovenous difference in MCI could reflect less oxygen extraction by retinal tissue. This indicates that retinal oxygen metabolism may be affected in patients with MCI.

Glaucoma filtration surgery and retinal oxygen saturation.

PURPOSE: Glaucoma may involve disturbances in retinal oxygenation and blood flow. The purpose of this study was to measure the effect of glaucoma filtration surgery on retinal vessel oxygen saturation. METHODS: A noninvasive spectrophotometric retinal oximeter was used to measure hemoglobin oxygen saturation in retinal arterioles and venules before and after glaucoma filtration surgery. Twenty-five consecutive patients were recruited, and 19 had adequate image quality. Fourteen underwent trabeculectomy and five glaucoma tube surgery. Twelve had primary open-angle glaucoma and seven had exfoliative glaucoma. IOP decreased from 23 +/- 7 to 10 +/- 4 mm Hg (mean +/- SD, P = 0.0001). RESULTS: Oxygen saturation increased in retinal arterioles from 97% +/- 4% to 99% +/- 6% (n = 19; P = 0.046) after surgery and was unchanged in venules (63% +/- 5% before surgery and 64% +/- 6% after, P = 0.76). There were no significant changes in saturation in the fellow eyes (P > 0.60). The arteriovenous difference was 34% before and 36% after surgery (P = 0.35). CONCLUSIONS: Glaucoma filtration surgery had almost no effect on retinal vessel oxygen saturation.

Oxygen saturation in human retinal vessels is higher in dark than in light.

PURPOSE: Animal studies have indicated that retinal oxygen consumption is greater in dark than light. In this study, oxygen saturation is measured in retinal vessels of healthy humans during dark and light. METHODS: The oximeter consists of a fundus camera, a beam splitter, a digital camera and software, which calculates hemoglobin oxygen saturation in the retinal vessels. In the first experiment, 18 healthy individuals underwent oximetry measurements after 30 minutes in the dark, followed by alternating 5-minute periods of white light (80 cd/m(2)) and dark. In the second experiment, 23 volunteers underwent oximetry measurements after 30 minutes in the dark, followed by light at 1, 10, and 100 cd/m(2). Three subjects were excluded from analysis in the first experiment and four in the second experiment because of poor image quality. RESULTS: In the first experiment, the arteriolar saturation decreased from 92% +/- 4% (n = 15; mean +/- SD) after 30 minutes in the dark to 89% +/- 5% after 5 minutes in the light (P = 0.008). Corresponding numbers for venules are 60% +/- 5% in the dark and 55% +/- 10% (P = 0.020) in the light. In the second experiment, the arteriolar saturation was 92% +/- 4% in the dark and 88% +/- 7% in 100 cd/m(2) light (n = 19, P = 0.012). The corresponding values for venules were 59% +/- 9% in the dark and 55% +/- 10% in 100 cd/m(2) light (P = 0.065). CONCLUSIONS: Oxygen saturation in retinal blood vessels is higher in dark than in 80 or 100 cd/m(2) light in human retinal arterioles and venules. The authors propose that this is a consequence of increased oxygen demand in the outer retina in the dark.

Automatic retinal oximetry.

PURPOSE: To measure hemoglobin oxygen saturation (SO(2)) in retinal vessels and to test the reproducibility and sensitivity of an automatic spectrophotometric oximeter. METHODS: Specialized software automatically identifies the retinal blood vessels on fundus images, which are obtained with four different wavelengths of light. The software calculates optical density ratios (ODRs) for each vessel. The reproducibility was evaluated by analyzing five repeated measurements of the same vessels. A linear relationship between SO(2) and ODR was assumed and a linear model derived. After calibration, reproducibility and sensitivity were calculated in terms of SO(2). Systemic hyperoxia (n = 16) was induced in healthy volunteers by changing the O(2) concentration in inhaled air from 21% to 100%. RESULTS: The automatic software enhanced reproducibility, and the mean SD for repeated measurements was 3.7% for arterioles and 5.3% venules, in terms of percentage of SO(2) (five repeats, 10 individuals). The model derived for calibration was SO(2) = 125 - 142 . ODR. The arterial SO(2) measured 96% +/- 9% (mean +/- SD) during normoxia and 101% +/- 8% during hyperoxia (n = 16). The difference between normoxia and hyperoxia was significant (P = 0.0027, paired t-test). Corresponding numbers for venules were 55% +/- 14% and 78% +/- 15% (P < 0.0001). SO(2) is displayed as a pseudocolor map drawn on fundus images. CONCLUSIONS: The retinal oximeter is reliable, easy to use, and sensitive to changes in SO(2) when concentration of O(2) in inhaled air is changed.