Volume measurement of the retina by OCT based on the ETDRS grid

Abstract

A method for performing retinal volume measurements based on the Early Treatment Diabetic Retinopathy Study (ETDRS) grid is presented. The method includes receiving an optical coherence tomography (OCT) image of a patient's retina and ETDRS mapping information identifying one or more subfields of the ETDRS grid, and segmenting the OCT image of the retina to identify one or more layer features corresponding to the layers of the retina and one or more disease-related features associated with the one or more layer features. The method further includes determining one or more volume measurements of the one or more disease-related features based on the segmented OCT image. The one or more volume measurements correspond to the ETDRS mapping information. The method further includes generating a report based on the one or more volume measurements.

Description

Cross - reference to related applications

[0001] This application claims the benefit of U.S. Provisional Application No. 63 / 355,467, filed on June 24, 2022, the entire content of which is incorporated herein by reference in its entirety.

Technical Field

[0002] This application generally relates to diabetic retinopathy, and more particularly to performing volume measurements of the retina by optical coherence tomography (OCT) based on the Early Treatment Diabetic Retinopathy Study (ETDRS) grid.

Background Art

[0003] Diabetic retinopathy (DR) is a common complication of diabetes mellitus ( "diabetes") in both type 1 and type 2 diabetic patients. DR can occur when high blood glucose levels cause damage to the blood vessels in the retina and can include several progressive stages. For example, the stages of DR can include mild non - proliferative diabetic retinopathy (NPDR), moderate NPDR, severe NPDR, and proliferative diabetic retinopathy (PDR). Each stage of DR can occur at various locations (e.g., within the retina, sub - retinal, and sub - retinal pigment epithelium (under the RPE)) and can include specific disease - related features that can further lead to retinal detachment. For example, complications in the NPDR stage of DR can include weakening of the blood vessel walls that can be observed as small bulges of blood vessels that can leak fluid and blood into the retina. Similarly, in the PDR stage of DR, new fragile blood vessels can form across the retina. These newly formed blood vessels often rupture, and as a result, blood can leak into the vitreous humor, damage the optic nerve, or both. Untreated PDR can lead to severe vision loss and even blindness in diabetic patients. Furthermore, fluid leakage at any stage of DR can cause diabetic macular edema (DME) (e.g., swelling and thickening of the macula of the retina), although DME is most likely to occur during the progressive stages of DR.

[0004] DR progression, DME, and / or vascular changes can be visualized, for example, using color fundus photography (CFP) images or optical coherence tomography (OCT) images. For example, CFP imaging uses a fundus camera to record an image of the inner surface of the eye, capturing the retina, optic nerve head, macula, retinal blood vessels, and posterior pole (e.g., the fundus). By imaging the inner surface of the eye, a clinician (e.g., an ophthalmologist, optometrist, or other retinal specialist) may be able to observe the presence of DR and the potential progression of DR. OCT imaging also involves non-invasively capturing the eye using light waves, the reflections of which are used to generate cross-sectional two-dimensional (2D) images of the retina and retinal layers. For example, OCT imaging can distinguish retinal layers, as well as any fluid or other deposits within or surrounding the retinal layers. OCT imaging can further depict biomarkers present in various retinal layers, including hard lipid exudates (e.g., hard lipid deposits left by leaking blood vessels), drusen (e.g., deposits not removed due to reduced waste removal ability), abnormal blood vessels (e.g., irregular narrowing and dilation of blood vessels), blood leakage or hemorrhage, and hyperreflective material (HRM).

[0005] The treatment of DR can vary based on the severity of DR and / or whether DR progresses to DME. For example, a clinician (e.g., an ophthalmologist, optometrist, or other retinal specialist) may generally discontinue treatment for mild NPDR in a diabetic patient and instead simply observe mild NPDR over time through frequent OCT scans. In contrast, moderate NPDR, severe NPDR, and / or DME can be treated with anti-vascular endothelial growth factor (anti-VEGF) antibodies, anti-angiopoietin-2 (anti-Ang-2) antibodies, or some combination thereof.

[0006] Vision is one characteristic that can be studied or tested by medical practitioners to detect the presence or progression of DR. The current standard for vision testing is known as the Early Treatment Diabetic Retinopathy Study (ETDRS) vision test. The ETDRS scale ranges from 10 (no retinopathy) to 85 (advanced PDR). The ETDRS vision test often requires highly trained evaluators to accurately interpret 2D CFP images of 3D structures including the retina. Additionally, CFP images can make it difficult to observe abnormalities due to the lack of depth perception. Thus, the results of CFP images can be inaccurate, rater-dependent, and time-consuming.

Summary of the Invention

[0007] Embodiments of the present disclosure are directed to one or more computing devices, methods, and non-transitory computer-readable media for performing optical coherence tomography (OCT) volume measurements of a retina based on an Early Treatment Diabetic Retinopathy Study (ETDRS) grid. In certain embodiments, one or more computing devices may receive an optical coherence tomography (OCT) image of a patient's retina and ETDRS mapping information that identifies one or more subfields of an ETDRS grid. In certain embodiments, one or more computing devices may segment an OCT image of the retina to identify one or more layer features corresponding to layers of the retina and one or more disease-related features associated with the one or more layer features. In certain embodiments, one or more computing devices may determine one or more volume measurements of the one or more disease-related features based on the segmented OCT image, wherein the one or more volume measurements correspond to the ETDRS mapping information. In certain embodiments, one or more computing devices may then generate a report based on the one or more volume measurements.

[0008] In fact, by generating a three-dimensional (3D) volume measurement derivable from a two-dimensional (2D) OCT B-scan of a patient's retinal cross-section and further leveraging an ETDRS grid constructed with known dimensions and subfields corresponding to a 2D image of the patient's fovea, volume measurements (e.g., volume, thickness, area, extent, area of disruption, presence or absence of one or more disease-related features, number of one or more disease-related features) of one or more layer features or disease-related features of the patient's retina can be appropriately mapped to 2D images (e.g., frontal images, retinal thickness maps) of the patient's retina suitable for various clinical applications. The volume measurements and ETDRS mapping information can then be provided as a report to one or more clinicians (e.g., ophthalmologists, optometrists, or other retinal specialists) to improve and facilitate the diagnosis, prognosis, and treatment of, for example, diabetic retinopathy (DR), progression of DR, and / or diabetic macular edema (DME).

[0009] In certain embodiments, one or more layer features can include Bruch's membrane (BM), the boundary between the choroid and the inner segment of the ellipsoid (BMEIS), the ganglion cell layer - inner plexiform layer (GCL-IPL), the inner border outer photoreceptor (IB-OPR) layer, the outer border outer photoreceptor (OB-OPR) layer, the inner border retinal pigment epithelium (IB-RPE) layer, the outer border retinal pigment epithelium (OB-RPE) layer, the inner limiting membrane (ILM), the inner plexiform layer - inner nuclear layer (IPL-INL), the inner plexiform layer - outer nuclear layer (IPL-ONL), the inner segment / outer segment junction (ISJ-OSJ) layer, the outer plexiform layer - Henle fiber layer (OPL-HFL), or the retinal nerve fiber layer - ganglion cell layer (RNFL-GCL).

[0010] In certain embodiments, one or more computing devices, one or more disease-related features may include one or more fluid features, and the one or more fluid features may include one or more of the fluids corresponding to intraretinal fluid (IRF), subretinal fluid (SRF), or pigment epithelial detachment (PED). In certain embodiments, one or more disease-related features may include one or more deposition features, and the one or more deposition features may include subretinal hyperreflective material (SHRM), intraretinal hyperreflective material (IHRM), or hyperreflective retinal foci (HRF). In certain embodiments, one or more computing devices may identify one or more biomarkers based on one or more volume measurements. In certain embodiments, one or more computing devices may receive a frontal image of a patient's retina, and the frontal image is associated with an OCT image. In certain embodiments, prior to generating a report, one or more computing devices may map one or more volume measurements and ETDRS mapping information to the frontal image. For example, in some embodiments, mapping one or more volume measurements and ETDRS mapping information to the frontal image may include associating one or more volume measurement criteria with the frontal image with respect to one or more identified subfields.

[0011] In certain embodiments, determining one or more volume measurements can include determining the total volume of one or more disease-related features related to at least one of one or more identified subfields. In certain embodiments, determining one or more volume measurements can include determining the fluid volume of one or more fluid features related to at least one of one or more identified subfields. In certain embodiments, determining one or more volume measurements can include determining the deposition volume of one or more deposition features related to at least one of one or more identified subfields. In certain embodiments, determining one or more volume measurements can include determining the thickness of one or more of the individual layers of the retina related to at least one of one or more identified subfields. In certain embodiments, determining one or more volume measurements can include determining the fluid extent of one or more fluid features related to at least one of one or more identified subfields.

[0012] In certain embodiments, determining one or more volume measurements can include determining the number of one or more deposition features related to at least one of one or more identified subfields. In certain embodiments, determining one or more volume measurements can include determining the area of one or more disease-related features related to at least one of one or more identified subfields. In certain embodiments, determining one or more volume measurements can include determining the presence or absence of one or more disease-related features related to at least one of one or more identified subfields. In certain embodiments, determining one or more volume measurements can include determining the disrupted area of one or more disease-related features related to at least one of one or more identified subfields.

[0013] In certain embodiments, one or more computing devices may classify a patient as having diabetic retinopathy (DR) based on one or more volume measurements. In certain embodiments, classifying a patient as having DR may further include classifying the patient as having mild non-proliferative diabetic retinopathy (NPDR), moderate NPDR, severe NPDR, or proliferative diabetic retinopathy (PDR) based on one or more volume measurements.

[0014] In certain embodiments, one or more computing devices may receive a second OCT image of a patient's retina and second ETDRS mapping information identifying one or more subfields of an ETDRS grid, and segment the second OCT image of the retina to identify one or more second layer features corresponding to individual retinal layers and one or more second disease-related features associated with the one or more second layer features. In certain embodiments, one or more computing devices may determine one or more second volume measurements of one or more second disease-related features corresponding to the second ETDRS mapping information based on the second segmented OCT image, and may determine the progression of the patient's diabetic retinopathy (DR) based on the one or more second volume measurements.

[0015] In certain embodiments, one or more computing devices may classify a patient as having diabetic macular edema (DME) based on one or more volume measurements. In certain embodiments, one or more computing devices may generate treatment recommendations for a patient based on one or more volume measurements or one or more second volume measurements. In certain embodiments, the treatment may include an anti-vascular endothelial growth factor (anti-VEGF) antibody, an anti-vascular endothelial growth factor A (anti-VEGF-A) antibody, or an anti-angiopoietin-2 (anti-Ang-2) antibody. In certain embodiments, the anti-VEGF-A antibody may include faricimab-svoa. In certain embodiments, the anti-Ang-2 antibody may include faricimab-svoa. In certain embodiments, the anti-VEGF antibody is selected from the group consisting of ranibizumab, aflibercept, brolucizumab, bevacizumab, and pegaptanib sodium. In certain embodiments, one or more computing devices may determine whether a patient is responsive to treatment based on one or more volume measurements or one or more second volume measurements. In certain embodiments, one or more computing devices may identify a precision cohort associated with a patient based on one or more volume measurements or one or more second volume measurements. For example, in some embodiments, the precision cohort may include a group of patients identified as clinically similar to the patient based on one or more volume measurements or one or more second volume measurements.

[0016] In certain embodiments, the OCT image may include a time-domain optical coherence tomography (TD-OCT) image or a spectral-domain optical coherence tomography (SD-OCT) image. In certain embodiments, the OCT image may include an image of the fovea of a patient captured by an OCT ophthalmoscope, and the image of the fovea is further divided into three concentric circles having diameters of approximately 1 millimeter (mm), approximately 3 mm, and approximately 6 mm, respectively, according to an ETDRS grid.

[0017] In certain embodiments, one or more computing devices may receive optical coherence tomography angiography (OCT-A) images of a patient's retina and generate a 3D map of the retinal blood vessels of the retina based on the OCT-A images and one or more volume measurements. In certain embodiments, one or more computing devices may receive color fundus photography (CFP) images of a patient's retina and generate a composite image of the retina based on the CFP images and one or more volume measurements. In certain embodiments, a report may include a table, chart, extensible markup language (XML) file, hypertext markup language (HTML) file, spreadsheet, text file, image file, graphic file, hyperlink, web page, or any combination thereof. In certain embodiments, one or more computing devices may send the report to a computing device associated with a clinician. In certain embodiments, one or more computing devices may send the report to an electronic device associated with a patient.

Brief Description of the Drawings

[0018]

Figure 1

[0019]

Figure 2A

[0020]

Figure 2B

[0021]

Figure 3A

Figure 3B

Figure 3C

[0022]

Figure 4A

Figure 4B

Figure 4C

[0023]

Figure 5A

Figure 5B

Figure 5C

[0024]

Figure 6

Best Mode for Carrying Out the Invention

[0025] Embodiments of the present disclosure are directed to one or more computing devices, methods, and non - transitory computer - readable media for performing volume measurements of an optical coherence tomography (OCT) retina based on an Early Treatment Diabetic Retinopathy Study (ETDRS) grid. In certain embodiments, one or more computing devices may receive an optical coherence tomography (OCT) image of a patient's retina and ETDRS mapping information that identifies one or more sub - fields of the ETDRS grid. In certain embodiments, one or more computing devices may segment an OCT image of the retina to identify one or more layer features corresponding to layers of the retina and one or more disease - related features associated with the one or more layer features. In certain embodiments, one or more computing devices may determine one or more volume measurements of the one or more disease - related features based on the segmented OCT image, and the one or more volume measurements correspond to the ETDRS mapping information. In certain embodiments, one or more computing devices may then generate a report based on the one or more volume measurements.

[0026] In fact, by generating three-dimensional (3D) volume measurements derivable from two-dimensional (2D) OCT B-scans of a patient's retinal cross-section, and further leveraging an ETDRS grid constructed with known dimensions and subfields and corresponding to a 2D image of the patient's fovea, volume measurements (e.g., volume, thickness, area, extent, area of disruption, presence or absence of one or more disease-related features, number of one or more disease-related features) of one or more layer features or disease-related features of the patient's retina can be appropriately mapped to 2D images (e.g., frontal images, retinal thickness maps) of the patient's retina suitable for various clinical applications. The volume measurements and ETDRS mapping information can then be provided as a report to, for example, one or more clinicians (e.g., ophthalmologists, optometrists, or other retinal specialists) to improve and facilitate the diagnosis, prognosis, and treatment of DR, progression of DR, and / or DME.

[0027] FIG. 1 shows an ophthalmic analysis and measurement system 100 for performing OCT retinal volume measurements based on an ETDRS grid and generating a report therefrom, according to an embodiment of the present disclosure. The ophthalmic analysis and measurement system 100 can include, according to an embodiment of the present disclosure, a computing platform 102, a data storage 104, an OCT imaging device 106 (e.g., an OCT ophthalmoscope) that can be associated with ETDRS mapping information 108 and an ETDRS grid 110, and a computing device 112 that can be associated with one or more clinicians 114 (e.g., ophthalmologists, optometrists, or other retinal specialists). In some embodiments, the computing platform 102 can include one or more cloud computing platforms, one or more mobile computing platforms (e.g., smartphones, tablets), or a combination thereof. In certain embodiments, the data storage 104, the OCT imaging device 106 (e.g., an OCT ophthalmoscope), and the computing device 112 can each communicate with the computing platform 102.

[0028] In certain embodiments, an OCT imaging device 106 (e.g., an OCT ophthalmoscope) can include one or more non-invasive imaging devices that can scan a patient's retina and generate one or more two-dimensional (2D) cross-sectional OCT images 116 of the patient's retina (e.g., time-domain - OCT (TD - OCT) B - scans, spectral-domain - OCT (SD - OCT) B - scans). For example, in some embodiments, the OCT images 116 can include a number of OCT B - scans that can be used to capture and render the depth of retinal layers. Specifically, in some embodiments, when capturing an image of a patient's retina, the OCT imaging device 106 can perform a series of one - dimensional (1D) scans (e.g., amplitude scans or "A - scans") at different depth positions and utilize the series of A - scans to generate a 2D cross - sectional image (e.g., intensity scan or "B - scan") of the patient's three - dimensional (3D) retina.

[0029] In certain embodiments, one or more OCT images 116 (e.g., one or more B-scans) may be associated with ETDRS mapping information 108 and an ETDRS grid 110. For example, according to embodiments of the present disclosure, one or more OCT images 116 (e.g., one or more B-scans) may be generated together with, for example, one or more 2D images (e.g., a frontal image, an infrared image, a thickness map) that each correspond to an anatomical center of a patient's macula (e.g., the patient's fovea). Thus, an ETDRS grid 110 constructed to correspond to a 2D image of the patient's fovea may be overlaid on one or more 2D images (e.g., a frontal image, an infrared image, a thickness map), and the ETDRS mapping information 108 may identify the location of one or more features of interest or regions of interest with respect to nine sub-fields of the ETDRS grid 110, including, for example, the following. "Center" = the center point of the fovea; Inner ring: ISS = "Inner superior sub-field"; INS = "Inner nasal sub-field"; "Inner inner sub-field"; IIS = "Inner inferior sub-field"; ITS = "Inner temporal sub-field"; Outer ring: OSS = "Outer superior sub-field"; ONS = "Outer nasal sub-field"; OIS = "Outer inferior sub-field"; OTS = "Outer temporal sub-field".

[0030] In certain embodiments, the ETDRS mapping information 108 and the ETDRS grid 110 are utilized to determine one or more volumetric measurements (e.g., volume, thickness, area, extent, area of disruption, presence or absence of one or more disease-related features, number of disease-related features) for identifying and quantifying diabetic retinopathy (DR) or other disease-related features regarding an anatomical center of a patient's macula (e.g., the patient's fovea) from one or more OCT images 116 (e.g., one or more B-scans). For example, as described above and further detailed below, one or more OCT images 116 (e.g., one or more B-scans) may be generated together with, for example, one or more 2D images (e.g., a frontal image, an infrared image, a thickness map) that each correspond to an anatomical center of a patient's macula (e.g., the patient's fovea).

[0031] In certain embodiments, in order to identify retinal layers and any disease-related features (e.g., fluid, deposited material) of a patient's retina, when one or more OCT images 116 (e.g., one or more B-scans) are segmented and annotated, computing platform 102 may determine one or more volume measurements (e.g., volume, thickness, area, extent, disrupted area, presence or absence of one or more disease-related features, number of disease-related features) of the retinal layers and disease-related features (e.g., fluid, deposited material). Further, since one or more OCT images 116 (e.g., one or more B-scans) and one or more 2D images (e.g., frontal image, infrared image, thickness map) may each be known to correspond to the patient's fovea, one or more volume measurements determined from one or more OCT images 116 (e.g., one or more B-scans) may then be appropriately mapped to one or more 2D images (e.g., frontal image, infrared image, thickness map) according to the ETDRS mapping information 108 and ETDRS grid 110.

[0032] In certain embodiments, as further shown by FIG. 1, the ETDRS grid 110 may be bounded by a circular region having a diameter of 6 millimeters (mm). The center point of the ETDRS grid 110 may be the center of the circle. The ETDRS grid 110 may be divided into nine standard subfields. The central subfield may be a circle with a diameter of 1 mm. The ETDRS grid 110 may be further divided into four inner subfields and four outer subfields by a circle concentric with the center having a diameter of 3 mm. The inner and outer subfields may each extend from the central circle to the outermost circle, e.g., at 45°, 135°, 225°, and 315°, and may be divided by four radial lines that cross the 3 mm circle at four locations.

[0033] In certain embodiments, each of the four inner subfields and the four outer subfields can be labeled by their orientation relative to the position of the center of the patient's macula, "superior", "nasal", "inferior", and "temporal". For example, in some embodiments, the superior inner subfield may be the area enclosed by the central circle, the 3 mm circle, the 315° radial line, and the 45° radial line. The nasal subfield may, for example, be directed towards the midline of the patient's face and be the one closest to the optic nerve head. In some embodiments, the ETDRS grids 110 for the left and right eyes may be inverted with respect to the positions of the nasal and temporal subfields.

[0034] In certain embodiments, as described above, the ETDRS mapping information 108 can include information for identifying and / or quantifying one or more features of interest or regions of interest within one or more 2D images (e.g., a frontal image, an infrared image, a thickness map) associated with one or more OCT images 116 (e.g., one or more B-scans) with respect to, for example, nine sub-fields of the ETDRS grid 110 (e.g., "center" = the center point of the fovea; inner ring: ISS = "inner upper sub-field"; INS = "nasal inner sub-field"; "inner inner sub-field"; IIS = "inner lower sub-field"; ITS = "inner temporal sub-field"; outer ring: OSS = "outer upper sub-field"; ONS = "nasal outer sub-field"; OIS = "outer lower sub-field"; OTS = "outer temporal sub-field"). For example, as further understood with respect to FIGS. 3, 4, and 5, the ETDRS mapping information 108 can identify the location of one or more features of interest or regions of interest with respect to the ETDRS grid 110 (e.g., within one or more of the nine individual sub-fields, within the outer ring including the OSS, ONS, OIS, and OTS sub-fields, within the inner ring including the ISS, INS, IIS, and ITS sub-fields, a disk or partial disk including the center, ITS, and OTS sub-fields, a disk or partial disk including the center, ITS, and OTS sub-fields, a disk or partial disk including the center, ISS, and OSS sub-fields, a disk or partial disk including the center, INS, and ONS sub-fields, a disk or partial disk including the center, ITS, and OTS sub-fields, or any of their various combinations).

[0035] In certain embodiments, the ophthalmic analysis and measurement system 100 can include one or more processors 118 that can be implemented using hardware, software, firmware, or combinations thereof. In some embodiments, the one or more processors 118 may be included as part of the computing platform 102 and may be further utilized, for example, to assist the retinal segmentation and volume measurement system 120 utilized to segment and annotate one or more OCT images 116 (e.g., one or more B-scans) to label one or more of the layers of the patient's retina, one or more of the fluids associated with one or more of the layers of the patient's retina, or one or more of the materials associated with one or more of the layers of the patient's retina. In certain embodiments, the retinal segmentation and volume measurement system 120 can include one or more deep neural networks (DNNs) 122 or other similar machine learning models suitable for performing image segmentation (e.g., semantic image segmentation), feature extraction and selection, and classification of one or more OCT images 116 (e.g., one or more B-scans).

[0036] In certain embodiments, one or more deep learning models 122 may include, for example, deep residual neural network (ResNet) image classification networks (e.g., ResNet-50, ResNet-101, ResNet-152), full-resolution residual networks (FRRNs), fully convolutional networks (FCNs) (e.g., U-Net), pyramid scene parsing networks (PSPNets), fully convolutional dense neural networks (FCDenseNets), multipath refinement networks (RefineNets), atrous convolutional networks (e.g., DeepLabV3, DeepLabV+), semantic segmentation networks (SegNets), or other deep convolutional neural networks (DCNNs) suitable for performing semantic segmentation and feature extraction and selection to segment and annotate one or more layer features (e.g., retinal layers) and one or more fluid features or deposition features detectable from OCT images 116 (e.g., one or more B-scans). For example, in certain embodiments, the retinal segmentation and volume measurement system 120 may receive one or more OCT images 116 (e.g., one or more B-scans) for processing. In some embodiments, one or more OCT images 116 may include images of the retina of a patient having a diabetes-related eye disease such as DR or DME.

[0037] In certain embodiments, as further shown, the retinal segmentation and volume measurement system 120 may include a layer identification module 120 and a feature segmentation module 130, each of which may be implemented using software, firmware, hardware, or combinations thereof. In certain embodiments, the layer identification module 120 and the feature segmentation module 130 are utilized together to annotate one or more OCT images 116 (e.g., one or more B-scans) to assign class labels to one or more of the retinal layers and disease-related features (e.g., fluid, reflective material) that may be associated with the retinal layers.

[0038] For example, in certain embodiments, the layer identification module 120 may generate a layer map 125 that includes a set 126 of layer indicators. The set 126 of layer indicators identifies one or more retinal layers. In some embodiments, the set 126 of layer indicators may include one or more layer features where each layer feature may correspond to one or more of the boundaries (e.g., inner boundary and / or outer boundary) of the corresponding retinal layer of the retina. For example, in some embodiments, the one or more layer features may be Bruch's membrane (BM), the boundary between the choroid and the inner segment of the ellipsoid (BMEIS), the ganglion cell layer - inner plexiform layer (GCL - IPL), the inner boundary outer photoreceptor (IB - OPR) layer, the outer boundary outer photoreceptor (OB - OPR) layer, the inner boundary retinal pigment epithelium (IB - RPE) layer, the outer boundary retinal pigment epithelium (OB - RPE) layer, the inner limiting membrane (ILM), the inner plexiform layer - inner nuclear layer (IPL - INL), the inner plexiform layer - outer nuclear layer (IPL - ONL), the inner segment / outer segment junction (ISJ - OSJ) layer, the outer plexiform layer - Henle fiber layer (OPL - HFL), or the retinal nerve fiber layer - ganglion cell layer (RNFL - GCL).

[0039] In certain embodiments, the set 126 of layer indicators may include a set of layer segments, where each layer segment is a region that identifies the thickness of a corresponding retinal layer. In one embodiment, the layer segments can be continuous or discontinuous regions. In certain embodiments, the feature segmentation module 130 may generate an initial feature segmented image 135 that includes a set 136 of initial feature segments. In certain embodiments, the initial feature segmented image 135 that includes the set 136 of initial feature segments and the layer map 125 that includes the set 126 of layer indicators may be combined, for example, into a refined feature segmented image 140 that includes a set 141 of refined feature segments. In certain embodiments, the refined feature segmented image 140 and the set 141 of refined feature segments may include one or more OCT images 116 (e.g., one or more B-scans) that include annotations of one or more retinal layers and a set of disease-related features (e.g., fluid, deposited material). For example, the one or more disease-related features may include fluid features that may include one or more of the fluids corresponding to intraretinal fluid (IRF), subretinal fluid (SRF), or pigment epithelial detachment (PED). Further, the one or more disease-related features may include deposited materials that may include subretinal hyperreflective material (SHRM), intraretinal hyperreflective material (IHRM), or hyperreflective retinal foci (HRF).

[0040] In certain embodiments, after one or more OCT images 116 (e.g., one or more B-scans) are segmented and annotated to include class labels for retinal layers and disease-related features (e.g., fluid, deposited material), computing platform 102 may then determine one or more volume measurements 142 (e.g., volume measurement, thickness measurement, area measurement, extent measurement, disrupted area measurement) from the one or more OCT images 116 (e.g., one or more B-scans). Specifically, in certain embodiments, to identify the retinal layers and any disease-related features (e.g., fluid, deposited material) of a patient's retina, when one or more OCT images 116 (e.g., one or more B-scans) are segmented and annotated, computing platform 102 may determine one or more volume measurements 142 (e.g., volume, thickness, area, extent, disrupted area, presence or absence of one or more disease-related features, number of one or more disease-related features) of the retinal layers and disease-related features (e.g., fluid, deposited material) from the one or more OCT images 116 (e.g., one or more B-scans).

[0041] For example, in some embodiments, computing platform 102 may determine one or more volume measurements 142 (e.g., volume, thickness, area, extent, disrupted area, presence or absence of one or more disease-related features, number of one or more disease-related features) from the one or more OCT images 116 (e.g., one or more B-scans) based on the ETDRS mapping information 108 and the ETDRS grid 110. As described above, each of the one or more OCT images 116 (e.g., one or more B-scans) may be captured and generated together with one or more 2D images (e.g., frontal image, infrared image, thickness map), and each of the one or more OCT images 116 (e.g., one or more B-scans) and the one or more 2D images (e.g., frontal image, infrared image, thickness map) may be known to correspond to the patient's fovea.

[0042] Thus, in certain embodiments, based on the ETDRS mapping information 108, as well as the known measurements and dimensions of the ETDRS grid 110 (e.g., three concentric circles having diameters of 1 mm, 3 mm, and 6 mm respectively, and four radial lines extending from the central circle to the outermost circle and crossing the 3 mm circle at four locations), and the knowledge of one or more OCT images 116 (e.g., one or more B-scans) regarding depth information (e.g., the depth of the retinal layers), the computing platform 102 can utilize one or more image processing techniques (e.g., morphological image processing) to estimate one or more volume measurements 142. For example, in some embodiments, the computing platform 102 can derive some subspace constraints (e.g., the representation of 3D subspaces such as the intraretinal subspace and the subretinal subspace where disease-related features can occur) based on layer features (e.g., BM, BMEIS, GCL-IPL, IB-OPR, OB-OPR layers, IB-RPE, OB-RPE, ILM, IPL-INL, IPL-ONL, ISJ-OSJ, OPL-HFL, RNFL-GCL), and the derived some subspace constraints can then be mapped and / or masked with respect to nine subfields of the ETDRS grid 110. Next, the computing platform 102 can determine one or more volume measurements 142 (e.g., volume, thickness, area, degree, disrupted area, presence or absence of one or more disease-related features, number of one or more disease-related features) by, for example, counting the number of pixels per subfield of the ETDRS grid 110 and converting the determined number of pixels per subfield of the ETDRS grid 110 to microns for thickness, square microns for area, cubic microns for volume, etc.

[0043] In certain embodiments, the volume measurement 142 may include, for example, the total volume of one or more disease-related features (e.g., the total volume in cubic microns between various layers of the retina) for one or more of the nine subfields of the ETDRS grid 110, the total volume of the fluid volume of one or more fluid features (e.g., the total volume in cubic microns of various fluids) for one or more of the nine subfields of the ETDRS grid 110, the total volume of the deposition volume of one or more deposition features (e.g., the total volume in cubic microns of various deposition materials) for one or more of the nine subfields of the ETDRS grid 110, the thickness of one or more of the layers of the retina (e.g., measurement of the thickness in microns of all layers of the retina, measurement of the thickness in microns for one or more specific layers of the retina, or measurement of the thickness in microns of a "slab" or space between layers of the retina) for one or more of the nine subfields of the ETDRS grid 110, the extent of the fluid of one or more fluid features (e.g., measurement of the volume in microns for various fluids) for one or more of the nine subfields of the ETDRS grid 110, or the number of one or more deposition features (e.g., a numerical value representing the total number of identified deposition materials) for one or more of the nine subfields of the ETDRS grid 110.

[0044] In certain embodiments, one or more volume measurements 142 may include, for example, areas of one or more disease - related features for one or more of the nine sub - fields of the ETDRS grid 110 (e.g., frontal image area measurements in square microns for various fluids or deposited materials), indications of the presence or absence of one or more disease - related features for one or more of the nine sub - fields of the ETDRS grid 110 (e.g., binary values indicating the presence or absence of various fluids and deposited materials), disrupted areas of one or more disease - related features for one or more of the nine sub - fields of the ETDRS grid 110 (e.g., frontal images of disrupted areas in square microns for various fluids or deposited materials), or one or more other volume measurements that may be utilized by one or more clinicians 114 (e.g., ophthalmologists, optometrists, or other retinal specialists) to identify and quantify DR - related features, DME - related features, or other disease - related features with respect to, for example, the anatomical center of the patient's macula (e.g., the patient's fovea).

[0045] In some embodiments, as further shown by FIG. 1, after one or more volume measurements 142 are determined, the one or more volume measurements 142 and the corresponding one or more segmented and annotated OCT images 116 (e.g., one or more B - scans) may be stored in the data storage 104 by the computing platform 102. In other embodiments, as further shown by FIG. 1, after one or more volume measurements 142 are determined, the one or more volume measurements 142 and the corresponding one or more segmented and annotated OCT images 116 (e.g., one or more B - scans) may be included in one or more clinical reports 144 and then transmitted by the computing platform 102 to a computing device 112 associated with one or more clinicians 114 (e.g., ophthalmologists, optometrists, or other retinal specialists) for analysis and examination.

[0046] For example, in some embodiments, the clinical report 144 may include, for example, tables, charts, Extensible Markup Language (XML) files, Hypertext Markup Language (HTML) files, spreadsheets, text files, image files, graphic files, hyperlinks, web pages, or other files that may be accessible and viewable by a computing device 112 by one or more clinicians 114 (e.g., ophthalmologists, optometrists, or other retinal specialists). In one embodiment, one or more clinical reports 144 may also be transmitted by the computing platform 102 to a computing device associated with the patient or one or more additional scientific or medical experts (e.g., biomarker scientists, data scientists) for further analysis and / or clinical application.

[0047] In certain embodiments, because one or more volume measurements 142 may be associated with the ETDRS mapping information 108 and the ETDRS grid 110, one or more clinicians 114 (e.g., ophthalmologists, optometrists, or other retinal specialists) may utilize the clinical report 144 to accurately and efficiently identify and quantify DR-related features, DME-related features, or other disease-related features with respect to the anatomical center of the patient's macula (e.g., the patient's fovea). For example, in one embodiment, as further understood with respect to examples 300, 400, and 500 respectively shown by FIGS. 3, 4, and 5, the clinical report 144 may include volume measurements of the retina for each of the nine subfields of the ETDRS grid 110. In certain embodiments, one or more clinicians 114 (e.g., ophthalmologists, optometrists, or other retinal specialists) may then utilize the volume measurements of the retina to determine, for example, whether one or more of the volume measurements of the retina are outside of a reference range for determining a diagnosis of DR and / or DME, one or more treatments of DR and / or DME, and / or the progression of DR and / or DME.

[0048] In certain embodiments, based on one or more volume measurements 142, computing platform 102 classifies a patient as having DR and / or DME, generates recommendations for one or more appropriate treatments for the patient (e.g., an anti-vascular endothelial growth factor (anti-VEGF) antibody, an anti-vascular endothelial growth factor A (anti-VEGF-A) antibody, or an anti-angiopoietin-2 (anti-Ang-2) antibody), and includes this data in a clinical report 144 provided to one or more clinicians 114 (e.g., an ophthalmologist, an optometrist, or other retinal specialist). For example, in some embodiments, the anti-VEGF-A antibody may include faricimab-svoa, and the anti-Ang-2 antibody may include faricimab-svoa. In some embodiments, the anti-VEGF antibody may be selected from the group consisting of ranibizumab, aflibercept, brolucizumab, bevacizumab, and pegaptanib sodium.

[0049] In certain embodiments, computing platform 102 may identify a precision cohort associated with a patient based on one or more volume measurements 142. For example, in some embodiments, the precision cohort may include a group of patients identified as being clinically similar to the patient based on one or more volume measurements 142. For example, in one embodiment, the precision cohort may be identified as having the same stage of DR or other similar retinal disease as the patient and / or as most responsive to one or more particular treatment regimens such that the patient may be recommended to receive the same or a similar treatment regimen as the precision cohort.

[0050] FIG. 2A shows a flowchart of a method 200A for performing OCT retinal volume measurements based on an ETDRS grid and generating a report therefrom, according to the disclosed embodiments. Method 200A may be implemented using one or more processing devices (e.g., the computing platform 102 described above with respect to FIG. 1) that may include hardware (e.g., a general-purpose processor, a graphics processing unit (GPU), an application-specific integrated circuit (ASIC), a system-on-chip (SoC), a microcontroller, a field-programmable gate array (FPGA), a central processing unit (CPU), an application processor (AP), a vision processing unit (VPU), a neural processing unit (NPU), a neural decision processor (NDP), a deep learning processor (DLP), a tensor processing unit (TPU), a neuromorphic processing unit (NPU), or any other processing device that may be suitable for processing retinal data and making one or more decisions based thereon), firmware (e.g., microcode), or some combination thereof.

[0051] Method 200A may begin in block 202 where one or more processing devices receive an optical coherence tomography (OCT) image of a patient's retina and ETDRS mapping information identifying one or more subfields of an ETDRS grid. For example, in some embodiments, computing platform 102 may receive one or more OCT B-scans of a patient's retina. Next, method 200A may proceed to block 204 where one or more processing devices segment an OCT image of the retina to identify one or more layer features corresponding to layers of the retina and one or more disease-related features associated with the one or more layer features. For example, in some embodiments, computing platform 102 may segment OCT image 116 (e.g., one or more B-scans), identify and annotate a set of one or more retinal layers and disease-related features (e.g., fluid, deposited material). One or more disease-related features may include, for example, fluid features (e.g., IRF, SRF, PED, etc.) and deposited materials (e.g., SHRM, IHRM, HRF, etc.).

[0052] Next, method 200A may proceed to block 206 where one or more processing devices determine one or more volume measurements of one or more disease-related features based on the segmented OCT image, and the one or more volume measurements correspond to the ETDRS mapping information. For example, as previously described above with respect to FIG. 1, based on ETDRS mapping information 108, as well as the known measurements and dimensions of ETDRS grid 110 (e.g., three concentric circles each having a diameter of 1 mm, 3 mm, and 6 mm respectively, and four radial lines extending from the central circle to the outermost circle and crossing the 3 mm circle at four locations), and knowledge of one or more OCT images 116 (e.g., one or more B-scans) regarding depth information (e.g., depth of retinal layers), computing platform 102 may utilize one or more image processing techniques (e.g., morphological image processing) to determine the number of volume measurements 142.

[0053] For example, in some embodiments, the computing platform 102 may derive some subspace constraints (e.g., the display of 3D subspaces such as the intraretinal subspace and the subretinal subspace where disease-related features may occur) based on layer features (e.g., BM, BMEIS, GCL-IPL, IB-OPR, OB-OPR layer, IB-RPE, OB-RPE, ILM, IPL-INL, IPL-ONL, ISJ-OSJ, OPL-HFL, RNFL-GCL), and some of the derived subspace constraints may then be mapped and / or masked with respect to the nine subfields of the ETDRS grid 110. Next, the computing platform 102 may determine one or more volume measurements 142 (e.g., volume, thickness, area, degree, disrupted area, presence or absence of one or more disease-related features, number of one or more disease-related features) by, for example, counting the number of pixels per subfield of the ETDRS grid 110 and converting the determined number of pixels per subfield of the ETDRS grid 110 to microns for thickness, square microns for area, cubic microns for volume, etc.

[0054] For example, the number of volume measurements 142 can include the total volume of one or more disease-related features (e.g., the total volume in cubic microns between various layers of the retina) for one or more of the nine subfields of the ETDRS grid 110, the total fluid volume of one or more fluid features (e.g., the total volume in cubic microns of various fluids) for one or more of the nine subfields of the ETDRS grid 110, the total deposit volume of one or more deposit features (e.g., the total volume in cubic microns of various deposit materials) for one or more of the nine subfields of the ETDRS grid 110, the thickness of one or more of the layers of the retina (e.g., measurement of the thickness in microns of all layers of the retina, measurement of the thickness in microns for one or more specific layers of the retina, or measurement of the thickness in microns of a "slab" or space between layers of the retina) for one or more of the nine subfields of the ETDRS grid 110, the extent of fluid of one or more fluid features (e.g., measurement of the volume in microns for various fluids) for one or more of the nine subfields of the ETDRS grid 110, or the number of one or more deposit features (e.g., a numerical value representing the total number of identified deposit materials) for one or more of the nine subfields of the ETDRS grid 110.

[0055] In certain embodiments, the number of volume measurements 142 can further include, for example, an area of one or more disease-related features for one or more of the nine subfields of the ETDRS grid 110 (e.g., a frontal image area measurement in square microns for various fluids or deposited materials), an indication of the presence or absence of one or more disease-related features for one or more of the nine subfields of the ETDRS grid 110 (e.g., a binary value indicating the presence or absence of various fluids and deposited materials), or a disrupted area of one or more disease-related features for one or more of the nine subfields of the ETDRS grid 110 (e.g., a frontal image of the disrupted area in square microns for various fluids or deposited materials). The method 200A can then end in block 208 when one or more processing devices determine to generate a report based on the one or more volume measurements. For example, as generally described above, the clinical report 144 can include, for example, a table, chart, XML file, HTML file, spreadsheet, text file, image file, graphic file, hyperlink, web page, or other file that can be accessed and viewed by a computing device 112 by one or more clinicians 114 (e.g., an ophthalmologist, optometrist, or other retina specialist).

[0056] FIG. 2B shows a flowchart of a method 200B for performing OCT retinal volume measurements based on an ETDRS grid and mapping the volume measurements and the ETDRS grid to a 2D retinal image, according to the disclosed embodiments. The method 200B may be implemented using one or more processing devices (e.g., the computing platform 102 described above with respect to FIG. 1) that may include hardware (e.g., a general-purpose processor, a graphics processing unit (GPU), an application-specific integrated circuit (ASIC), a system-on-chip (SoC), a microcontroller, a field-programmable gate array (FPGA), a central processing unit (CPU), an application processor (AP), a vision processing unit (VPU), a neural processing unit (NPU), a neural decision processor (NDP), a deep learning processor (DLP), a tensor processing unit (TPU), a neuromorphic processing unit (NPU), or any other processing device suitable for processing retinal data and making one or more decisions based thereon), firmware (e.g., microcode), or some combination thereof.

[0057] Method 200B may begin in block 210 where one or more processing devices receive an optical coherence tomography (OCT) image of a patient's retina, and a frontal image or thickness map, and ETDRS mapping information that identifies one or more subfields of an ETDRS grid. For example, in some embodiments, computing platform 102 may receive one or more OCT images 116 (e.g., one or more B-scans) and one or more 2D images (e.g., frontal image, infrared image, thickness map), each of which is known to correspond to the patient's fovea. Next, following block 212, method 200B may segment the OCT image of the retina in order for one or more processing devices to identify one or more layer features corresponding to layers of the retina, and one or more disease-related features associated with the one or more layer features. For example, in some embodiments, computing platform 102 may segment OCT image 116 (e.g., one or more B-scans), identify, and annotate a set of one or more retinal layers and disease-related features (e.g., fluid, deposited material). The one or more disease-related features may include, for example, fluid features (e.g., IRF, SRF, PED, etc.) and deposited materials (e.g., SHRM, IHRM, HRF, etc.).

[0058] Next, following block 214, method 200B may determine one or more volume measurements of one or more disease-related features based on the segmented OCT image, and the one or more volume measurements correspond to ETDRS mapping information. For example, as previously described above with respect to FIG. 1, based on the ETDRS mapping information 108, as well as the known measurements and dimensions of the ETDRS grid 110 (e.g., three concentric circles each having a diameter of 1 mm, 3 mm, and 6 mm respectively, and four radial lines extending from the central circle to the outermost circle and crossing the 3 mm circle at four locations), and knowledge of one or more OCT images 116 (e.g., one or more B-scans) regarding depth information (e.g., the depth of the retinal layer), the computing platform 102 may utilize one or more image processing techniques (e.g., morphological image processing) to determine the number of volume measurements 142.

[0059] For example, in some embodiments, the computing platform 102 may derive some subspace constraints (e.g., the indication of 3D subspaces such as the intraretinal subspace and the subretinal subspace where disease-related features may occur) based on layer features (e.g., BM, BMEIS, GCL-IPL, IB-OPR, OB-OPR layer, IB-RPE, OB-RPE, ILM, IPL-INL, IPL-ONL, ISJ-OSJ, OPL-HFL, RNFL-GCL), and the derived some subspace constraints may then be mapped and / or masked with respect to the nine subfields of the ETDRS grid 110. Next, the computing platform 102 may determine one or more volume measurements 142 (e.g., volume, thickness, area, degree, disrupted area, presence or absence of one or more disease-related features, number of one or more disease-related features) by, for example, counting the number of pixels per subfield of the ETDRS grid 110 and converting the determined number of pixels per subfield of the ETDRS grid 110 to microns for thickness, square microns for area, cubic microns for volume, etc.

[0060] In certain embodiments, the number of volume measurements 142 can include, for example, the total volume of one or more disease-related features (e.g., the total volume in cubic microns between various layers of the retina) for one or more of the nine subfields of the ETDRS grid 110, the total volume of the fluid volume of one or more fluid features (e.g., the total volume in cubic microns of various fluids) for one or more of the nine subfields of the ETDRS grid 110, the total volume of the deposition volume of one or more deposition features (e.g., the total volume in cubic microns of various deposition materials) for one or more of the nine subfields of the ETDRS grid 110, the thickness of one or more of the layers of the retina (e.g., measurement of the thickness in microns of all layers of the retina, measurement of the thickness in microns for one or more specific layers of the retina, or measurement of the thickness in microns of a "slab" or space between layers of the retina) for one or more of the nine subfields of the ETDRS grid 110, the extent of the fluid of one or more fluid features (e.g., measurement of the volume in microns for various fluids) for one or more of the nine subfields of the ETDRS grid 110, or the number of one or more deposition features (e.g., a numerical value representing the total number of identified deposition materials) for one or more of the nine subfields of the ETDRS grid 110.

[0061] In certain embodiments, one or more volume measurements 142 can further include, for example, the area of one or more disease-related features (e.g., frontal image area measurement in square microns for various fluids or deposition materials) for one or more of the nine subfields of the ETDRS grid 110, an indication of the presence or absence of one or more disease-related features (e.g., a binary value indicating the presence or absence of various fluids and deposition materials) for one or more of the nine subfields of the ETDRS grid 110, or the disrupted area of one or more disease-related features (e.g., frontal image of the disrupted area in square microns for various fluids or deposition materials) for one or more of the nine subfields of the ETDRS grid 110.

[0062] Next, in block 216, method 200B may end with one or more processing devices mapping one or more volume measurements and ETDRS mapping information to a frontal image or thickness map. For example, as previously described, one or more OCT images 116 (e.g., one or more B-scans) are segmented and annotated to identify retinal layers and any disease-related features (e.g., fluid, deposited material) of a patient's retina. The computing platform 102 may then determine one or more volume measurements (e.g., volume, thickness, area, extent, disruption area, presence or absence of one or more disease-related features) of the retinal layers and disease-related features (e.g., fluid, deposited material). For example, since one or more OCT images 116 (e.g., one or more B-scans) and the frontal image or thickness map may each be known to correspond to the fovea of the patient, one or more volume measurements 142 determined from the one or more OCT images 116 (e.g., one or more B-scans) may be appropriately mapped to the frontal image or thickness map according to the ETDRS mapping information 108 and the ETDRS grid 110.

[0063] FIGS. 3, 3A, 3B, and 3C each show one or more high-resolution examples 300, 300A, 300B, and 300C for performing volume measurements of an OCT retina based on an ETDRS grid and mapping the volume measurements and the ETDRS grid to a thickness map, according to the disclosed embodiments. It should be understood that the one or more high-resolution examples 300, 300A, 300B, and 300C may represent only one example of an embodiment of the present disclosure. Indeed, in other examples, according to embodiments of the present disclosure, any of various retinal volume measurements (e.g., measurement of volume, measurement of thickness, measurement of area, measurement of extent, indication of presence or absence, measurement of disruption area, etc.) may be calculated for any of various subfields of each OCT B-scan and the ETDRS grid.

[0064] For example, the high - resolution example 300 of FIG. 3 shows an OCT B - scan 302 (corresponding to, e.g., the high - resolution OCT B - scan 300A of FIG. 3A), a segmented and annotated OCT B - scan 304 (corresponding to, e.g., the high - resolution segmented and annotated OCT B - scan 300B of FIG. 3B), and a thickness map 306 showing the measurement of the thickness of one or more layers (corresponding to, e.g., the high - resolution thickness map 300C of FIG. 3C). For example, referring to FIG. 3, the OCT B - scan 302 can be an OCT B - scan generated based on one or more scans of a patient's retina by an ophthalmoscope or other retinal imaging device. The OCT B - scan 302 can be associated with an ETDRS grid and / or ETDRS mapping information (e.g., the position of one or more features or regions of interest with respect to the nine sub - fields of the ETDRS grid). Similarly, the thickness map 306 can be generated along with the OCT B - scan 302, and the OCT B - scan 302 and the thickness map 306 can each correspond to an image of the anatomical center (e.g., the fovea of the patient) of the patient's macula.

[0065] As further shown, the segmented and annotated OCT B - scan 304 can include annotations (e.g., colored lines) that label one or more boundaries of the layers of the patient's retina. Then, based on the ETDRS grid and / or ETDRS mapping information, one or more retinal volume measurements (e.g., the thickness of each of the retinal layer features) can be determined, and then the one or more retinal volume measurements can be mapped to the thickness map 306 corresponding to the OCT B - scan 302. Specifically, since it can be known that the OCT B - scan 302 and the thickness map 306 each correspond to the fovea of the patient, the one or more volume measurements determined from the segmented and annotated OCT B - scan 304 can be appropriately mapped to the thickness map 306 according to the ETDRS grid and / or ETDRS mapping information.

[0066] For example, as shown in FIG. 3, using the segmented and annotated OCT B-scan 304, it is possible to determine the thickness measurement of one or more layers of the retina. Next, the thickness measurement (e.g., a numerical value) can be mapped to a thickness map 306 according to the ETDRS grid and / or ETDRS mapping information (e.g., according to the nine subfields 308, 310, 312, 314, 316, 318, 320, 322, 324 of the ETDRS grid). In this way, the thickness measurement can quantify the thickness of the visual layer as shown by the thickness map 306. For example, as shown in the figure, the thickness measurement can include J microns mapped to subfield 308, K microns mapped to subfield 310, L microns mapped to subfield 312, M microns mapped to subfield 314, N microns mapped to subfield 316, Q microns mapped to subfield 318, P microns mapped to subfield 320, R microns mapped to subfield 322, and S microns mapped to subfield 324, where J, K, L, M, N, Q, P, R, and S each represent numerical values.

[0067] FIGS. 4, 4A, 4B, and 4C each show one or more further high-resolution implementations 400, 400A, 400B, and 400C for performing volume measurements of an OCT retina based on an ETDRS grid and mapping the volume measurements and the ETDRS grid to a front retina image, according to the disclosed embodiments. The high-resolution implementation 400 of FIG. 4 shows a central OCT B-scan 402 (e.g., corresponding to the high-resolution central OCT B-scan 400A of FIG. 4A), a segmented and annotated OCT B-scan 404 (e.g., corresponding to the high-resolution segmented and annotated OCT B-scan 400B of FIG. 4B), and a front image 406 showing measurements of one or more fluid and SRHM volumes (e.g., corresponding to the front image 400C of FIG. 4C). For example, referring to FIG. 4, the central OCT B-scan 402 can be an OCT B-scan generated based on one or more scans of a patient's retina by an ophthalmoscope or other retinal imaging device. The central OCT B-scan 402 can be associated with an ETDRS grid and / or ETDRS mapping information.

[0068] As further shown by FIG. 4, the segmented and annotated OCT B-scan 404 can include annotations (e.g., colored lines) that label one or more disease-related features (e.g., fluid and SRHM) between one or more layers of the patient's retina. One or more volume measurements of the retina (e.g., total volume measurements in cubic millimeters (mm 3 ) of fluid and SRHM or total volume in cubic micrometers (μm 3 ) of fluid and SRHM) can then be determined, and the one or more volume measurements of the retina can be appropriately mapped to the front image 406 corresponding to the central OCT B-scan 402.

[0069] For example, as further shown by FIG. 4, the segmented and annotated OCT B-scan 404 can be utilized to determine the measurement of the volume of the fluid and the SRHM. Next, the volume measurement (e.g., a numerical value) can be mapped to the frontal image 406 according to the ETDRS grid and / or the ETDRS mapping information (e.g., according to the nine sub-fields 408, 410, 412, 414, 416, 418, 420, 422, 424 of the ETDRS grid). For example, as shown by the frontal image 406, the measurement of the volume of the fluid and the SRHM is Jmm mapped to the sub-field 408 3 , Kmm mapped to the sub-field 410 3 , Lmm mapped to the sub-field 412 3 , Mmm mapped to the sub-field 414 3 , Nmm mapped to the sub-field 416 3 , Qmm mapped to the sub-field 418 3 , Pmm mapped to the sub-field 420 3 , Rmm mapped to the sub-field 422 3 , and Smm mapped to the sub-field 424 3 may be included, and J, K, L, M, N, Q, P, R, and S each represent a numerical value. In this way, the measurement of the volume of the fluid and the SRHM can visually correspond to the volume of the fluid and the SRHM displayed by the frontal image 406.

[0070] Figures 5, 5A, 5B, and 5C each show one or more further high-resolution implementations 500, 500A, 500B, and 500C for performing volume measurements of an OCT retina based on an ETDRS grid and mapping the volume measurements and the ETDRS grid to a frontal retina image, according to the disclosed embodiments. High-resolution implementation 500 shows a central OCT B-scan 502 (e.g., corresponding to the high-resolution central OCT B-scan 500A of FIG. 5A), a segmented and annotated OCT B-scan 504 (e.g., corresponding to the high-resolution segmented and annotated OCT B-scan 500B of FIG. 5B), and a frontal image 506 showing region measurements of one or more IRHMs (e.g., corresponding to the high-resolution frontal image 500C of FIG. 5C). For example, referring to FIG. 5, the central OCT B-scan 502 can be an OCT B-scan generated based on one or more scans of a patient's retina by an ophthalmoscope or other retinal imaging device. The central OCT B-scan 502 can be associated with an ETDRS grid and / or ETDRS mapping information.

[0071] As further shown in FIG. 5, the segmented and annotated OCT B-scan 504 can include annotations (e.g., colored lines) that label one or more disease-related features (e.g., IRHM) deposited or dispersed between one or more layers of the patient's retina. One or more volume measurements of the retina (e.g., measurement of the area in square microns (μm 2 ) of the deposited material and / or measurement of the area in square microns (μm 2 ) of the disrupted area of the deposited material) can be determined, and the measurement of one or more regions can be appropriately mapped to the frontal image 506 corresponding to the central OCT B-scan 502.

[0072] For example, as further shown by FIG. 5, the measurement of the IRHM region can be determined using the segmented and annotated OCT B-scan 504. Next, the measurement of the region (e.g., a numerical value) can be mapped to the frontal image 506 according to the ETDRS grid and / or the ETDRS mapping information (e.g., according to the nine sub-fields 508, 510, 512, 514, 516, 518, 520, 522, 524 of the ETDRS grid). For example, as shown by the frontal image 506, the region measurement of the IRHM is J μm mapped to the sub-field 408 2 , K μm mapped to the sub-field 410 2 , L μm mapped to the sub-field 412 2 , M μm mapped to the sub-field 414 2 , N μm mapped to the sub-field 416 2 , Q μm mapped to the sub-field 418 2 , P μm mapped to the sub-field 420 2 , R μm mapped to the sub-field 422 2 , and S μm mapped to the sub-field 424 2 and J, K, L, M, N, Q, P, R, and S each represent a numerical value. By doing so, the region measurement of the IRHM can visually correspond to the IRHM region displayed by the frontal image 506.

[0073] In certain embodiments, the ETDRS grid's nine subfields can be visually aligned with visual features displayed by one or more high - resolution retinal images 300C, 400C, and 500C, such as the high - resolution thickness map 300C of FIG. 3C, the high - resolution anterior retinal image 400C of FIG. 4C, and the high - resolution anterior retinal image 500C of FIG. 5C. In this way, the ETDRS grid can be mapped to one or more high - resolution retinal images 300C, 400C, and 500C. When this is done, retinal volume measurements (e.g., volume measurement, thickness measurement, area measurement, range measurement, presence / absence indication, damaged area measurement, etc.) determined and reported for the nine subfields of the ETDRS can visually correspond to disease - related features (e.g., layer thickness, fluid features, deposited material features) grids displayed by one or more high - resolution retinal images 300C, 400C, and 500C.

[0074] FIG. 6 shows an example of one or more computing devices 600 that can be utilized to perform OCT retinal volume measurements based on an ETDRS grid and generate a clinical report therefrom, according to the disclosed embodiments. In certain embodiments, one or more computing devices 600 can perform one or more steps of one or more of the methods described or shown herein. In certain embodiments, one or more computing devices 600 provide the functionality described or shown herein. In certain embodiments, the software operating on one or more computing devices 600 performs one or more steps of one or more of the methods described or shown herein or provides the functionality described or shown herein. Certain embodiments include one or more portions of one or more computing devices 600.

[0075] The present disclosure contemplates any suitable number of computing systems 600. The present disclosure contemplates one or more computing devices 600 in any suitable physical form. By way of example and not limitation, one or more computing devices 600 can be an embedded computer system, a system-on-chip (SOC), a single-board computer system (SBC) (such as a computer-on-module (COM) or system-on-module (SOM)), a desktop computer system, a laptop or notebook computer system, an interactive kiosk, a mainframe, a mesh of computer systems, a cellular phone, a personal digital assistant (PDA), a server, a tablet computer system, an augmented / virtual reality device, or a combination of two or more of these. Where appropriate, one or more computing devices 600 can be single or distributed, spanning multiple locations, spanning multiple machines, spanning multiple data centers, or existing in a cloud that includes one or more components of one or more clouds of one or more networks.

[0076] Where appropriate, one or more computing devices 600 can execute one or more steps of one or more of the methods described or illustrated herein without substantial spatial or temporal limitations. By way of example and not limitation, one or more computing devices 600 can execute one or more steps of one or more of the methods described or illustrated herein in real time or in batch mode. One or more computing devices 600 can, where appropriate, execute one or more steps of one or more of the methods described or illustrated herein at different times or in different locations.

[0077] In certain embodiments, one or more computing devices 600 include a processor 602, a memory 604, a database 606, an input / output (I / O) interface 608, a communication interface 610, and a bus 612. Although the present disclosure describes and illustrates a particular computer system having a particular number of particular components in a particular arrangement, the present disclosure contemplates any suitable computer system having any suitable number of any suitable components in any suitable arrangement. In certain embodiments, processor 602 includes hardware for executing instructions, such as instructions that make up a computer program. By way of example and not limitation, to execute instructions, processor 602 may retrieve (or fetch) the instructions from an internal register, internal cache, memory 604, or database 606, decode and execute those instructions, and then write one or more results to an internal register, internal cache, memory 604, or database 606. In certain embodiments, processor 602 may include one or more internal caches for data, instructions, or addresses. The present disclosure contemplates processor 602 including any suitable number of any suitable internal caches, where appropriate. By way of example and not limitation, processor 602 may include one or more instruction caches, one or more data caches, and one or more translation lookaside buffers (TLBs). Instructions in the instruction cache may be copies of instructions in memory 604 or database 606, and the instruction cache may speed up retrieval of those instructions by processor 602.

[0078] Data in the data cache can be a copy of data in memory 604 or database 606 that the instructions executed in processor 602 operate on, the result of previous instructions executed in processor 602 for access by subsequent instructions executed in processor 602, or for writing to memory 604 or database 606, or other suitable data. The data cache can speed up read or write operations by processor 602. The TLB can speed up virtual-address translation for processor 602. In certain embodiments, processor 602 can include one or more internal registers for data, instructions, or addresses. The present disclosure contemplates processor 602 including any suitable number of any suitable internal registers, where appropriate. Where appropriate, processor 602 can include one or more arithmetic logic units (ALUs), be a multi-core processor, or include one or more processors 602. Although the present disclosure describes and illustrates a particular processor, the present disclosure contemplates any suitable processor.

[0079] In certain embodiments, memory 604 includes main memory for storing instructions for processor 602 to execute or data that processor 602 operates on. By way of example and not limitation, one or more computing devices 600 can load instructions into memory 604 from database 606 or another source (such as another one or more computing devices 600, for example). Processor 602 can then load the instructions from memory 604 into internal registers or an internal cache. To execute the instructions, processor 602 can retrieve the instructions from the internal registers or internal cache and decode those instructions. During or after execution of the instructions, processor 602 can write one or more results (which can be intermediate or final results) to the internal registers or internal cache. Processor 602 can then write one or more of those results to memory 604.

[0080] In certain embodiments, the processor 602 executes only instructions in one or more internal registers, internal caches, or memory 604 (as opposed to the database 606 or elsewhere) and operates only on data in one or more internal registers, internal caches, or memory 604 (as opposed to the database 606 or elsewhere). One or more memory buses (which may each include an address bus and a data bus) may connect the processor 602 to the memory 604. The bus 612 may include one or more memory buses, as described below. In certain embodiments, one or more memory management units (MMUs) reside between the processor 602 and the memory 604 and facilitate access to the memory 604 requested by the processor 602. In certain embodiments, the memory 604 includes random access memory (RAM). This RAM may be volatile memory, if appropriate. If appropriate, this RAM may be dynamic RAM (DRAM) or static RAM (SRAM). Moreover, if appropriate, this RAM may be single-port or multi-port RAM. The present disclosure contemplates any suitable RAM. The memory 604 may include one or more memories 604, if appropriate. Although the present disclosure describes and illustrates particular memories, the present disclosure contemplates any suitable memory.

[0081] In certain embodiments, database 606 includes mass storage for data or instructions. By way of example and not limitation, database 606 can include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or universal serial bus (USB) drive, or a combination of two or more of these. Database 606 can include removable or non-removable (or fixed) media, where appropriate. Database 606 can be internal or external to one or more computing devices 600, where appropriate. In certain embodiments, database 606 is non-volatile solid state memory. In certain embodiments, database 606 includes read only memory (ROM). Where appropriate, this ROM can be mask-programmed ROM, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), electrically variable ROM (EAROM), flash memory, or a combination of two or more of these. The present disclosure contemplates mass database 606 in any suitable physical form. Database 606 can include one or more storage control units that facilitate communication between processor 602 and database 606, where appropriate. Where appropriate, database 606 can include one or more databases 606. The present disclosure describes and illustrates particular storage, but the present disclosure contemplates any suitable storage.

[0082] In certain embodiments, I / O interface 608 includes hardware, software, or both that provide one or more interfaces for communication between one or more computing devices 600 and one or more I / O devices. One or more computing devices 600 may include, where appropriate, one or more of these I / O devices. One or more of these I / O devices may enable communication between a person and one or more computing devices 600. By way of example and not limitation, I / O devices can include a keyboard, keypad, microphone, monitor, mouse, printer, scanner, speaker, steel camera, stylus, tablet, touch screen, trackball, video camera, another suitable I / O device, or a combination of two or more of these. An I / O device may include one or more sensors. The present disclosure contemplates any suitable I / O devices and any suitable I / O interface 608 therefor. Where appropriate, I / O interface 608 may include one or more devices or software drivers that enable processor 602 to drive one or more of these I / O devices. I / O interface 608 may, where appropriate, include one or more I / O interfaces 608. The present disclosure describes and illustrates particular I / O interfaces, but the present disclosure contemplates any suitable I / O interface.

[0083] In certain embodiments, communication interface 610 includes hardware, software, or both, that provides one or more interfaces for communication (e.g., packet-based communication) between one or more computing devices 600 and one or more other computing devices 600 or one or more networks. By way of example and not limitation, communication interface 610 can include a network interface controller (NIC) or network adapter for communicating with an Ethernet or other wire-based network, or a wireless NIC (WNIC) or wireless adapter for communicating with a wireless network such as a WI-FI network. The present disclosure contemplates any suitable network and any suitable communication interface 610 therefor.

[0084] By way of example and not limitation, one or more computing devices 600 may communicate with one or more of an ad hoc network, a personal area network (PAN), a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), one or more portions of the Internet, or a combination of two or more of these. One or more portions of one or more of these networks may be wired or wireless. As an example, one or more computing devices 600 may communicate with a wireless PAN (WPAN) (such as, for example, BLUETOOTH WPAN), a WI-FI network, a WI-MAX network, a cellular telephone network (such as, for example, a global system for mobile communications (GSM) network for mobile communications), other suitable wireless networks, or a combination of two or more of these. One or more computing devices 600 may include, where appropriate, any suitable communication interface 610 for any of these networks. Communication interface 610 may include, where appropriate, one or more communication interfaces 610. Although the present disclosure describes and illustrates particular communication interfaces, the present disclosure contemplates any suitable communication interface.

[0085] In certain embodiments, bus 612 includes hardware, software, or both that connect components of one or more computing devices 600 to each other. By way of example and not limitation, bus 612 can include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HYPERTRANSPORT (HT) interconnect, an Industry Standard Architecture (ISA) bus, an INFINIBAND interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI Express (PCIe) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, another suitable bus, or a combination of two or more of these. Bus 612 can, where appropriate, include one or more buses 612. Although the present disclosure describes and illustrates particular buses, the present disclosure contemplates any suitable bus or interconnect.

[0086] As used herein, one or more computer-readable non-transitory storage media can, where appropriate, include one or more semiconductor-based or other integrated circuits (ICs) (such as, for example, a Field Programmable Gate Array (FPGA) or an Application Specific Integrated Circuit (ASIC)), a hard disk drive (HDD), a hybrid hard drive (HHD), an optical disk, an optical disk drive (ODD), a magneto-optical disk, a magneto-optical drive, a floppy disk, a floppy disk drive (FDD), magnetic tape, a solid state drive (SSD), a RAM drive, a SECURE DIGITAL card or drive, any other suitable computer-readable non-transitory storage media, or any suitable combination of two or more of these. The computer-readable non-transitory storage media can, where appropriate, be volatile, non-volatile, or a combination of volatile and non-volatile.

[0087] As used herein, "or" (alternatively, "and / or" or "either / or") is inclusive and not exclusive, unless otherwise expressly indicated or indicated by context. Thus, as used herein, "A or B" means "A, B, or both", unless expressly indicated otherwise or indicated by context. Moreover, "and" is both joint and several, unless expressly indicated otherwise or indicated by context. Thus, as used herein, "A and B" means "A and B, jointly or severally", unless expressly indicated otherwise or indicated by context.

[0088] As used herein, "automatically" and derivatives thereof mean "without human intervention", unless otherwise expressly indicated or indicated by context.

[0089] The embodiments disclosed in this specification are merely exemplary and the scope of the present disclosure is not limited thereto. Embodiments according to the present disclosure are disclosed in particular in the appended claims relating to methods, storage media, systems, and computer program products, and any feature mentioned in one claim category, for example a method, may also be claimed in another claim category, for example a system. The dependencies or references in the appended claims are chosen only for formal reasons. However, any subject matter resulting from an intentional reference to any preceding claim (in particular multiple dependencies), so that any combination of claims and their features is disclosed and may be claimed regardless of the dependencies chosen in the appended claims, may likewise be claimed. The subject matter that may be claimed includes not only combinations of features as set forth in the appended claims, but also any other combination of features within the scope of the claims, and each feature set forth in the claims may be combined with any other feature or combination of features within the scope of the claims. Furthermore, any of the embodiments and features described or illustrated in this specification may be claimed in separate claims and / or in any combination with any of the embodiments or features described or illustrated in this specification or with any of the features of the appended claims.

[0090] The scope of the present disclosure encompasses all changes, substitutions, variations, alterations, and modifications to the exemplary embodiments described or illustrated herein that would be understood by those skilled in the art. The scope of the present disclosure is not limited to the exemplary embodiments described or illustrated herein. Further, although the present disclosure describes and illustrates each of its embodiments as including a particular component, element, feature, function, operation, or step, any of these embodiments may include any combination or permutation of any of the components, elements, features, functions, operations, or steps described or illustrated anywhere in this specification that would be understood by those skilled in the art. Moreover, references in the appended claims to an apparatus or system or a component of an apparatus or system that is adapted to perform, arranged to perform, capable of performing, configured to perform, enabled to perform, operable to perform, or operative to perform a particular function include that apparatus, system, or component, whether or not that apparatus, system, component, or its particular function is activated, turned on, or unlocked, as long as that apparatus, system, component is so adapted, arranged, capable, configured, enabled, operable, or operative. Further, although the present disclosure describes or shows a particular embodiment as providing a particular advantage, a particular embodiment may provide none, some, or all of these advantages.

Claims

1. A method for performing retinal volume measurement based on the Early Treatment Research for Diabetic Retinopathy (ETDRS) grid using one or more computing devices, Receiving optical coherence tomography (OCT) images of the patient's retina and ETDRS mapping information that identifies one or more subfields of the ETDRS grid, The OCT image of the retina is segmented to identify one or more layer features corresponding to the layers of the retina, The OCT image of the retina is segmented to obtain an initial feature segmented OCT image that includes one or more disease-related features associated with one or more layer features. The one or more disease-related features are refined by generating a refined segmented OCT image based on the layer features and the initial feature segmented OCT image. Based on the refined segmented OCT image, determine one or more volume measurements of the refined one or more disease-related features, wherein the one or more volume measurements correspond to the ETDRS mapping information, and A method for generating a report based on one or more volume measurements.

2. The method according to claim 1, wherein the one or more layer features include Bruch's membrane (BM), the boundary between the myoloid and the internal segment of the ellipsoid (BMEIS), the ganglion cell layer-internal plexiform layer (GCL-IPL), the internal boundary external photoreceptor (IB-OPR) layer, the external boundary external photoreceptor (OB-OPR) layer, the internal boundary retinal pigment epithelium (IB-RPE) layer, the external boundary retinal pigment epithelium (OB-RPE) layer, the internal limiting membrane (ILM), the internal plexiform layer-internal nucleus layer (IPL-INL), the internal plexiform layer-external nucleus layer (IPL-ONL), the internal segment / external segment junction (ISJ-OSJ) layer, the external plexiform layer-Henle fiber layer (OPL-HFL), or the retinal nerve fiber layer-ganglion cell layer (RNFL-GCL).

3. The method according to claim 1, wherein the one or more disease-related features include one or more fluid features or one or more deposition features, the one or more fluid features include one or more fluids corresponding to intraretinal fluid (IRF), subretinal fluid (SRF), or pigment epithelial detachment (PED), and the one or more deposition features include subretinal high reflectivity material (SHRM), intraretinal high reflectivity material (IHRM), or high reflectivity retinal focus (HRF).

4. The method according to claim 1, further comprising identifying one or more biomarkers based on the one or more volume measurements.

5. Receiving a frontal image of the patient's retina, wherein the frontal image is associated with the OCT image, and The method according to claim 1, further comprising mapping the one or more volume measurements and the ETDRS mapping information onto the front image before generating the report.

6. The method according to claim 1, wherein determining the one or more volume measurements includes determining the total volume of the one or more disease-related features relating to at least one of the identified one or more subfields, determining the fluid volume of one or more fluid features relating to at least one of the identified one or more subfields, or determining the deposition volume of one or more deposition features relating to at least one of the identified one or more subfields.

7. The method according to claim 3, wherein determining the one or more volume measurements includes determining the fluid range of the one or more fluid features relating to at least one of the identified one or more subfields.

8. The method according to claim 1, wherein determining the one or more volume measurements includes determining the number of one or more depositional features relating to at least one of the identified one or more identified subfields.

9. The method according to claim 1, wherein determining the one or more volume measurements includes determining the region of the one or more disease-related features relating to at least one of the identified one or more subfields, determining the presence or absence of the one or more disease-related features relating to at least one of the identified one or more subfields, or determining the region of destruction of the one or more disease-related features relating to at least one of the identified one or more subfields.

10. The method according to claim 1, wherein the OCT image includes a time-domain optical coherence tomography (TD-OCT) image or a spectral-domain optical coherence tomography (SD-OCT) image.

11. The method according to claim 1, wherein the OCT image includes an image of the patient's fovea taken up by an OCT ophthalmoscope, and the image of the fovea is further divided into three concentric circles having diameters of approximately 1 millimeter (mm), approximately 3 mm, and approximately 6 mm, respectively, according to the ETDRS grid.

12. To receive optical coherence tomography (OCT-A) angiography images of the retina of the patient, and The method according to claim 1, further comprising generating a 3D map of the retinal blood vessels of the retina based on the OCT-A image and one or more volume measurements.

13. To receive a color fundus photograph (CFP) of the retina of the patient, and Mapping the one or more volume measurements and the ETDRS mapping information onto the CFP image. The method according to claim 1, further comprising:

14. A system for performing retinal volume measurement based on the Early Treatment Study for Diabetic Retinopathy (ETDRS) grid, comprising one or more computing devices, One or more non-temporary computer-readable storage media containing instructions, The system comprises one or more processors connected to one or more storage media, and the one or more processors Receiving optical coherence tomography (OCT) images of the patient's retina and ETDRS mapping information that identifies one or more subfields of the ETDRS grid, The OCT image of the retina is segmented to identify one or more layer features of the retina, The OCT image of the retina is segmented to obtain an initial feature segmented OCT image containing one or more disease-related features. The one or more disease-related features are refined by generating a refined segmented OCT image based on the layer features and the initial feature segmented OCT image. Based on the refined segmented OCT image, determine one or more volume measurements of the refined one or more disease-related features that are associated with at least one of the layer features and correspond to the ETDRS mapping information, and A system configured to execute commands for generating a report based on one or more volume measurements.

15. A non-temporary computer-readable medium containing instructions for performing retinal volume measurements based on the Early Treatment Study for Diabetic Retinopathy (ETDRS) grid, wherein when the instructions are executed by one or more processors of one or more computing devices, the one or more processors are instructed to: Receiving optical coherence tomography (OCT) images of the patient's retina and ETDRS mapping information that identifies one or more subfields of the ETDRS grid, Segmenting the OCT image of the retina to identify one or more layer features corresponding to the layers of the retina, The OCT image of the retina is segmented to obtain an initial feature segmented OCT image containing one or more disease-related features. Based on the refined segmented OCT image, determine one or more volume measurements of the refined one or more disease-related features that are associated with at least one of the layer features and correspond to the ETDRS mapping information, and A non-temporary computer-readable medium that generates a report based on one or more volume measurements.

Images