Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 2 de 2
Filter
Add more filters










Database
Language
Publication year range
1.
J Optom ; 15 Suppl 1: S58-S69, 2022.
Article in English | MEDLINE | ID: mdl-36396540

ABSTRACT

BACKGROUND: Retinal and optic disc images are used to assess changes in the retinal vasculature. These can be changes associated with diseases such as diabetic retinopathy and glaucoma or induced using ophthalmodynamometry to measure arterial and venous pressure. Key steps toward automating the assessment of these changes are the segmentation and classification of the veins and arteries. However, such segmentation and classification are still required to be manually labelled by experts. Such automated labelling is challenging because of the complex morphology, anatomical variations, alterations due to disease and scarcity of labelled data for algorithm development. We present a deep machine learning solution called the multiscale guided attention network for retinal artery and vein segmentation and classification (MSGANet-RAV). METHODS: MSGANet-RAV was developed and tested on 383 colour clinical optic disc images from LEI-CENTRAL, constructed in-house and 40 colour fundus images from the AV-DRIVE public dataset. The datasets have a mean optic disc occupancy per image of 60.6% and 2.18%, respectively. MSGANet-RAV is a U-shaped encoder-decoder network, where the encoder extracts multiscale features, and the decoder includes a sequence of self-attention modules. The self-attention modules explore, guide and incorporate vessel-specific structural and contextual feature information to segment and classify central optic disc and retinal vessel pixels. RESULTS: MSGANet-RAV achieved a pixel classification accuracy of 93.15%, sensitivity of 92.19%, and specificity of 94.13% on LEI-CENTRAL, outperforming several reference models. It similarly performed highly on AV-DRIVE with an accuracy, sensitivity and specificity of 95.48%, 93.59% and 97.27%, respectively. CONCLUSION: The results show the efficacy of MSGANet-RAV for identifying central optic disc and retinal arteries and veins. The method can be used in automated systems designed to assess vascular changes in retinal and optic disc images quantitatively.


Subject(s)
Glaucoma , Optic Disk , Humans , Optic Disk/diagnostic imaging , Arteries , Retinal Vessels/diagnostic imaging , Retina , Glaucoma/diagnosis
2.
Br J Ophthalmol ; 94(7): 854-7, 2010 Jul.
Article in English | MEDLINE | ID: mdl-19846411

ABSTRACT

AIMS: Central retinal vein pulsation is affected by intracranial pressure (ICP), glaucoma and venous pathology. Its genesis is poorly understood with most models suggesting that intraocular pressure (IOP) fluctuation dominates the rhythm of venous pulsation; however, this has not been explored experimentally. This study planned to measure the timing of central retinal vein pulsation with respect to IOP pulse. METHODS: Video recording of the optic disc vessels and movement of Goldmann applanation mires while recording the cardiac cycle with a pulse oximeter probe was undertaken in 10 subjects from a general ophthalmic clinic. The timing of the variation in IOP and retinal vein diameter from the onset of the oximeter signal were expressed as a percentage of the cardiac cycle and also in degrees of the cycle. RESULTS: Minimum vein diameter occurred at a mean 40 ms (SD 47) after minimum IOP in 10 subjects with mean cardiac cycle length of 866 ms (SD 132), the delay representing 4% or 14 degrees (SD 5.1, 95% CI 0.3% to 8%) of the mean cardiac cycle. Maximum vein diameter occurred an average of 5 ms after maximum IOP (SD 57) representing 1% or 4 degrees (SD 6.9, 95% CI -4% to 6%) of the mean cardiac cycle. CONCLUSION: During venous pulsation, venous collapse occurred in time with ocular diastole and dilatation in time with systole. This is contrary to earlier conceptual understanding. The results suggest that the intracranial pulse pressure may be of equal importance to intraocular pulse pressure in producing venous pulsation.


Subject(s)
Eye Diseases/physiopathology , Intraocular Pressure/physiology , Retinal Vein/physiopathology , Adult , Aged , Diabetic Retinopathy/physiopathology , Female , Glaucoma/physiopathology , Humans , Intracranial Pressure/physiology , Male , Middle Aged , Pulsatile Flow/physiology , Video Recording
SELECTION OF CITATIONS
SEARCH DETAIL
...