CROSS-REFERENCE TO RELATED APPLICATION This application claims the benefit of U.S. Provisional Patent App. No. 62/291,925, filed February 5, 2016, which is incorporated by reference in its entirety herein.

TECHNICAL FIELD

Embodiments of the present disclosure relate generally to the field of systems for medical image processing, particularly to systems for ophthalmic medical images for use in diagnosis of neurodegenerative disease.

BACKGROUND

Neurodegenerative diseases such as Alzheimer's and Parkinson's disease are debilitating and incurable conditions that cause the progressive degeneration of neurons cells. These diseases affect millions of people worldwide, and the economic costs of these disorders are comparably high. Reports in 2010 estimated the global cost of patient care for neurological diseases to be $6 trillion in 2030. Unfortunately, despite the overwhelming need for reliable and affordable patient care, diagnostic methods and treatments for many neurodegenerative diseases are not effective or accurate. Accurate methods of diagnosing and monitoring the progression of these diseases are crucial for the development of new medications.

The hippocampal complex and entorhinal complex are commonly known to be sites of early disease pathology in the brain, but recently the retina has been shown to be affected by neurological diseases. Research has even suggested that signs of neurodegenerative diseases in the retina occur even earlier than they occur in the brain. Studies have suggested that anterior visual pathways are affected by these diseases, as shown by degeneration in the retina.

Alzheimer's disease (also known as simply "Alzheimer's" or "AD") is a neurodegenerative disorder that affects currently 46 million people in the world and is expected to affect 131.5 million people by the year 2050. Alzheimer's is the most common form of dementia. Other types of dementia include vascular dementia, dementia with Lewy bodies, mixed dementia, frontotemporal dementia, Creutzfeldt-Jakob disease, normal pressure hydrocephalus dementia, Huntington's disease, and Wernicke- Korsakoff syndrome.

Although there have been numerous studies to determine what causes Alzheimer's, these studies are not definitive. Studies of Alzheimer's suggest that Alzheimer's is caused by a build up of different substances in the brain such as tau proteins that spur neuronal death, β- amyloid plaque, which are toxic to neurons, and neurofibrillary tangles that damage the ability of neurons to communicate with each other. Unfortunately, even though there have been numerous studies conducted on the causes and possible treatments for Alzheimer's, medications that are used to treat Alzheimer's fail to stop or slow the progression of the disease. Instead, these drugs focus on treating the symptoms of Alzheimer's, such as reduced thinking ability and anxiety.

Recent work has suggested that diagnosing Alzheimer's before it has progressed to later, more severe stages may lead to a better understanding of the causes of Alzheimer's. Understanding the pathogenesis and progression of Alzheimer's may be valuable in creating effective treatments for the disease.

Currently, neuropsychological tests and neurological imaging techniques are used to diagnose Alzheimer's. The most commonly used neurological imaging techniques include computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET). However, these imaging methods do not provide sufficient molecular specificity to detect amyloid plaques, neurofibrillary tangles or tau tangles. As a result, these tests are only 75% accurate and have a high risk for false positives and false negatives. In addition, amyloid imaging is restricted to very few specialized research centers and the cost of this imaging is prohibitive. Furthermore, even after diagnosis, an Alzheimer's patient has likely entered later, more severe stages of the disease where severe brain damage has already occurred because many patients go to neurologists only after they start showing a reduction in cognitive function, which occurs many years after physical signs of Alzheimer's occur. Studies have suggested that signs of Alzheimer's in the brain occur when patients are as young as 20.

Diagnosing Alzheimer's through cognitive tests alone has also been found to be problematic. A 2015 study by Shea et al. suggested that behavioral symptoms of dementia can be misleading and that mental state exams have difficulty in distinguishing between different types of dementia. Y.F. Shea et al, Comparisons of clinical symptoms in biomarker- conflrmed Alzheimer 's disease, dementia with Lewy bodies, and frontotemporal dementia patients in a local memory clinic, Psychogeriatrics, 15(4):235-241 (2015).

Parkinson's disease (or simply "Parkinson's" or "PD") is a neurodegenerative condition that causes progressive and chronic movement disorders, along with cognitive, autonomic, and visual dysfunctions. Currently, Parkinson's affects more than 10 million people in the world. It is predicted to cost the United States $25 billion per year. Parkinson's patients pay an average of $2500 per year for checkups and about $100,000 for surgery. Surgical techniques can include deep brain stimulation, thalomotomy, pallidotomy, and subthalamotomy. The causes of Parkinson's are unknown despite numerous and extensive studies. Researchers know that patients risk for contracting Parkinson's increases as they age and for most patients, Parkinson's progresses slowly and continues to worsen over time. This is also true for Alzheimer's. So far, the best objective test for Parkinson's is through specialized brain scans, which are only available at special imaging centers and are very expensive. Parkinson's is often monitored by analyzing brain scans for nerve cell death and an increase in the protein alpha-synuclein (also called Lewy Bodies).

Biomarkers are measurable substances or features in an organism, the presence or dimensions of which may be indicative of some phenomenon such as disease, infection, or environmental exposure. Biomarkers can also include measures of strength, mood, or mental acuity. Research has suggested that ocular biomarkers (especially the sizes of various features of retina) may be indicative of neurological diseases such as Alzheimer's or Parkinson's. See, e.g., Berisha et al., Retinal abnormalities in early Alzheimer 's disease, Investigative Ophthalmology & Visual Science, 48(5):2285-2289 (2007) and Pillao et al., Retinal nerve fiver layer thinning in Alzheimer ' s disease: A case-control study in comparison to normal aging, Parkinson 's disease, and non-Alzheimer 's dementia, American Journal of Alzheimer's Disease & Other Dementias, 31(5):430-436 (2016).

The ability to accurately and efficiently measure biomarkers can assist in the diagnosis of various neurodegenerative diseases.

SUMMARY

Embodiments of the present disclosure include systems and methods for processing retinal images to detect retinal biomarkers that may be indicative of neurodegenerative disease. In embodiments, a retinal biomarker processing system comprises an image processor configured to receive image data corresponding to a patient and depicting at least one retinal image, the at least one retinal image having a scale a pixel size of one or more retinal biomarkers, a measurement analyzer configured to determine an absolute size of each of the one or more retinal biomarkers, a biomarker database configured to store each of the absolute sizes of each of the one or more retinal biomarkers, a biomarker analyzer configured to calculate a score related to a health outcome for the patient based on the absolute size of at least one of the one or more retinal biomarkers, and a user interface configured to produce an output related to the score.

In embodiments, the system presents user interface elements enabling a user to identify and measure one or more biomarkers in each image by asking the user to input the scale of the image, converting the pixels of the image to the user's preferred scale, asking the user to then indicate the top and the bottom the retinal biomarker to measure, collecting the x and y coordinates of the user's indications, displaying a line between the two points that the user clicked on the image to show the user what line would be measured and converting this highlighted length in pixels to an actual length for display and processing.

In embodiments the indicator related to the probability of the patient having a neurological disease for the patient is determined by by determining a disease range and a control range for the absolute size or the rate of change of at least one of the one or more retinal biomarkers, assigning a score for each one of the at least one retinal biomarkers based on whether the absolute size or the rate of change over time of the retinal biomarker is within the disease range for the absolute size or the rate of change over time of the retinal biomarker, the control range for the absolute size or the rate of change over time of the retinal biomarker, or outside of both ranges for the absolute size or the rate of change over time of the retinal biomarker and selecting the indicator related to the health outcome based on the sum of scores of each of the at least one retinal biomarkers.

The above summary is not intended to describe each illustrated embodiment or every implementation of the subject matter hereof. The figures and the detailed description that follow more particularly exemplify various embodiments.

BRIEF DESCRIPTION OF THE DRAWINGS

Subject matter hereof may be more completely understood in consideration of the following detailed description of various embodiments in connection with the accompanying figures, in which:

FIG. 1 is a screenshot depicting an annotated scan of an eye;

FIG. 2 is a block diagram depicting a schematic view of various engines and components of a retinal biomarker processing system, according to an embodiment;

FIG. 3 is a screenshot depicting a screen of a user interface, according to an embodiment;

FIG. 4A is a screenshot depicting a screen of a user interface, according to an embodiment;

FIG. 4B is a screenshot depicting a screen of a user interface, according to an embodiment;

FIG. 4C is a screenshot depicting a screen of a user interface, according to an embodiment;

FIG. 5A is a block diagram depicting raw measurement data elements, according to an embodiment;

FIG. 5B is a block diagram depicting data elements of a scan record, according to an embodiment;

FIG. 6 is a graph depicting the change in various retinal biomarkers in patients over time; and,

FIG. 7 is a flowchart depicting a method for determining a biomarker score, according an embodiment.

While various embodiments are amenable to various modifications and alternative forms, specifics thereof have been shown by way of example in the drawings and will be described in detail. It should be understood, however, that the intention is not to limit the claimed inventions to the particular embodiments described. On the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the subject matter as defined by the claims.

DETAILED DESCRIPTION

Embodiments of the present disclosure include systems and methods configured to detect features of ophthalmic biomarkers that may be indicative of neurological disease. FIG. 1 is an annotated image depicting an end on, or front, scan 102a of an eye and a selected cross-section scan 102b of the same eye of the type that can be received by embodiments. In the example of FIG. 1 , scans (or retinal images) 102a and 102b were produced by an optical coherence tomography (OCT) scanning device manufactured by Heidelberg Engineering, however scans 102 can be produced by a number of other devices known in the art. In addition, while depicted scans 102a and 102b are based on OCT scans, any image capture method suitable to render accurate scale images of the retina and associated biomarkers can be used.

Scans 102a and 102b have been annotated to highlight ophthalmic biomarkers 104. In embodiments, biomarkers 104 can include retinal (or central) vein 104a, nerve fiber layer 104b, ganglion cell layer 104c, and choroid 104d. In embodiments, more, fewer, or alternate biomarkers 104 can be analyzed. For example, in embodiments, other biomarkers such as optic disk cupping, optic disk coloration, and optic nerve thickness may be used instead over, or in combination with the biomarkers discussed herein. Also depicted in scans 102a and 102 are scale indicators 106a and 106b, legend 108, and eye indicator, 110.

FIG. 2 is a block diagram depicting various engines (or components) of retinal biomarker processing system 100, according to an embodiment. In one embodiment, retinal biomarker processing system 100 can comprise a user interface 120, an image processor 122, a measurement analyzer 124, a biomarker analyzer 126, and a biomarker database 128.

Scans 102 are received by an image processor 122. Scans 102 generally comprise one or more image files. In embodiments, image processor 122 can receive multiple disparate image file formats such as portable network graphics (PNG) files, graphics interchange format (GIF) files, joint photographic experts group (JPEG or JPG) files, tag image file format (TIFF), or other file formats. Scans 102 can be received from a local permanent or removable storage medium, over a network connection, such as from an electronic medical record (EMR) system, or via a direct connect to a device capable of producing scans 102. In embodiments, image processor 122 can be configured to receive data from local or remote systems using provided application programming interface (API) methods. In embodiments, image processor 122 can convert scans 102 to data formats appropriate for use by other engines of system 100.

In embodiments, image processor 122 can decode or receive metadata associated with scans 102. In embodiments, image processor 122 can decode metadata that is embedded within scans 102 as exchangeable image file format (Exif) or extensible metadata platform XMP data or other embedded metadata formats. In embodiments, image processor 122 can receive metadata from the network or other source of scans 102, for example as associated data files or as data returned via an API. In embodiments, metadata can be entered via user interface 120 (discussed in more detail below), or can be retrieved from one or more remote systems. Metadata can include data related to the patient, such as an identifier, demographic information such as gender and age, and the patient's medical history. Metadata can also include data related to the scan 102, such as the scan resolution and scale, the equipment used to create the scan, and the date and/or time stamp information related to the creation of the scan.

User interface 120 is configured to allow interaction between a user and the various components and engines of biomarker processing system 100. User interface 120 enables the user to provide scan information to image processor 122 (such as, for example, the file name or network location of a scan 102), and can display scans 102 and other information to user. User interface 120 can comprise a graphical user interface (GUI), a web based interface for access via a web browser, a command line interface, or a programmatic interface such as an application programming interface (API). User interface 120 can receive user input via a network connection, keyboard, touchscreen, mouse, joystick, or any other input device. FIGS. 3-4 are screenshots depicting various example screens that may be presented by user interface 120, in embodiments. Those of ordinary skill in the art will recognize that the depicted screens are merely examples, and the screens of user interface 120 can be presented with a variety of looks and feels different than those shown.

FIG. 3 is a screen shot of a biomarker measurement screen 400 presented by user interface 120 in an embodiment. Screen 400 presents a scan 102 and various selectable functions 402. Functions 402 can include scale function 404. When scale function 404 is selected by the user, user interface 120 can request that the user enter the scale directly (for example, by providing data entry stating that each pixel in scan 102 has an actual size of 3.9 μηι) in embodiments. In embodiments, user interface 120 can assist the user in determining the scale. For example, user interface 120 can request that the user indicate an upper and a lower boundary of a scale line 406 within the scan 102 (such as scales 106a and 106b of FIG. 1) using mouse clicks, mouse strokes, or other input methods. User interface 120 can also request that the user provide the actual size in micrometers of the scale line (for example, 200 μιη). Scale dialog 405 which can display and enable user input of distance in pixels, known distance, aspect ratio and units can be present in embodiments. Regardless of method used, user interface 120 can confirm the scale (in μιη/pixel) at scale output 408. In embodiments, user interface 120 can enable the user to zoom in or out of scan 102, and present scaled lines and measurements as appropriate.

When measurement function 410 is selected by the user, user interface 120 can request that the user provide entry regarding which biomarker 104 is being measured. In embodiments, user interface 120 can present a list of biomarkers 104 available, or may allow free text entry. User interface 120 can then request that the user indicate a starting and an ending boundary of a measurement line 412. The actual size of the biomarker 104 can then be determined by multiplying the size of measurement line 412 in pixels by scale. The actual length of the measurement line can be indicated to the user at measurement output 414.

FIGS. 4A-4C present an alternative screen 400' of user interface 120 for enabling user entry of biomarker measurements in embodiments. When measurement function 410 is selected by the user, user interface 120 can request that the user indicate an upper and a lower boundary of a gradient line 414. Unlike measurement line 412, gradient line 414 need only extend beyond the boundaries of any feature of interest, as opposed to ending at a specific upper and lower point of a biomarker 104. User interface 120 can then present gradient graph 416 which, in embodiments, represents the actual length of gradient line 414 as the x-axis and the gray value of the pixels along the actual length of the gradient line 414 as the y-axis. In embodiments, the gray value is useful for determining the boundaries of features in black and white or grayscale scans 102. In embodiments other values that can be detected from scan 102 can be used, such as a hue, saturation, total value or transparency level of each pixel, or the values of each pixel in the red, green, or blue channels, or cyan, magenta, yellow, and black channels.

Graph 416 can enable the user to determine the boundaries of features and biomarkers 140 based on the local minimums, maximums, and slope of the curve. Generally, in OCT scans 102 such as those depicted herein, the gray value curve will exhibit steep slopes at feature boundaries. User interface 120 can then enable the user to select the start and end points of a graph measurement line 418 on graph 416, indicating the actual length of the feature being measured as seen in FIG. 4B. The actual length of measurement line 420 can be indicated to the user. In embodiments, the correspondence between graph measurement line 418 and scan 102 can be depicted directly on scan 102 as seen in FIG. 4C, where multiple graph measurement lines 420 are indicated on scan 102.

In embodiments, the values plotted on graph 416 can be used to double check the entry by the user. For example, if the user plots graph measurement line 418, across multiple boundaries with steep slope, user interface 120 can request that the user confirm the selections. In addition, graph 416 can be used to compute possible boundaries for presentation and confirmation by the user, in embodiments. The graph-based measurement functionality of FIGS. 4A-4C can enable easier user entry of measurements, where the boundary lines between features in scan 102 may be difficult to see or select accurately. In embodiments, user interface 120 can enable the user to enter data associated with a test of mental state, for example a Mini-Mental State Examination (MMSE). In embodiments, user interface 120 can present test questions and receive answers. In embodiments, user interface 120 can enable the user to enter a total score.

FIG. 5A is a block diagram depicting a schematic view of raw measurement data 200, according to embodiments. Raw measurement data is populated by measurement analyzer 124 in embodiments. In embodiments, raw measurement data 200 can include a mental state score provided by the user, or calculated from the test answers received by user interface 120. In embodiments, raw measurement data can include the actual (or "absolute") sizes of one or more biomarkers 104 within scan 102. In embodiments, raw measurement data 200 can include the mental state score In embodiments, measurement analyzer 124 can determine the boundaries of a biomarker 104 or other feature within the image and determine the actual size of the biomarker 104 or other feature based on the scan resolution and scale. In embodiments, measurement analyzer 124 can detect the location and sizes of features within scan 102 automatically. In other embodiments, measurement analyzer 124 can receive feature size information via user interface 120. While raw measurement data 200 includes nerve fiber layer width 202, choroid width 204, retinal vein diameter 206, ganglion cell layer width 208 and mental state score 210, in the embodiment of FIG 5 A, other data structures can of course be used, especially in embodiments of system 100 configured to process alternative sets of biomarkers.

In embodiments, biomarker database 128 is configured to score scan records 300, as depicted in FIG. 5B. Each scan record 300 can include patient related data, such as a patient identifier 302, patient demographic data 304 (such as patient age or gender), and patient medical history 306. The patient related data can be anonymized, such that patient identifier 302 need not comprise information that can allow a patient identifier 302 and/or the associated scans to be linked to an actual patient within biomarker database 128. For example, patient identifier 302 can be a randomly generated identifier, linked to the patient within another system, or not linked to any particular patient at all. Patient medical history 306 can include one or more indicators regarding ocular or other disease diagnoses that may affect the analysis of raw measurement data 200. For example, in embodiments, health outcome indications can be modified based on the patient having medical history including indications of age-related macular degeneration (AMD), or glaucoma. Each scan record 300 can also include scan related data including an indication of which eye has been scanned 308, and scan date 310 (which can also include time stamp information). Each scan record 300 can further include calculated data such as raw measurement data 200, outcome indicators 312 and biomarker scores 314. More, fewer, and alternative data items can be stored within biomarker database 128 in embodiments.

In embodiments, biomarker database 128 can comprise any data storage device(s) or system(s), suitable for storage of scan records 300 and retrieval of same by biomarker analyzer 126. In embodiments, biomarker database can comprise, for example, local hard drives, removable storage media, and local or remote database systems. Scan records 300 in biomarker database 128 can be retrievable by patient identifier 302, eye 308, scan date 310, or any other data element of scan record 300.

In embodiments, any or all of patient related data items 302, 304, 306 and scan related data items 308 and 310 can be determined from metadata provided by image processor 122.

In embodiments, any or all of patient related data items 302, 204, 306 and scan related data items 308 and 310 can be requested from the user via user interface 120. In embodiments, biomarker database 128 can determine some or all of patient related data items 304 and 306 based on a provided patient identifier 302 and one or more stored scan records 300, or other data associated with the provided patient identifier 302. In embodiments, user interface 120 can enable the user to modify each data item of each scan record 300 within biomarker database 128.

Biomarker analyzer 126 can evaluate raw measurement data 200 from one or more scans 102 to determine one or more health outcomes indicated by biomarkers 104, in embodiments. In embodiments, biomarker analyzer 126 can determine one or more outcome indicators 312, each related to the likelihood that the patient associated with the raw measurement data 200 has a neurodegenerative disease such as Alzheimer's or Parkinson's. In embodiments, outcome indicators 312 can be related to whether the scans 102 are indicative of neurodegenerative disease.

In embodiments, outcome indicators 312 can be determined by first determining one or more biomarker scores 314 for each biomarker based both on the biomarker measurement and patient medical history. Biomarker scores 314 for a disease can be determined based on defined disease and control ranges in embodiments. For example, in an embodiment, disease ranges for Alzheimer's and Parkinson's can be defined as shown in Table 1 below for patients with and without age-related macular degeneration. As depicted in Table 1 below, not all biomarkers 104 must be used, and in embodiments, choroid layer thickness is not considered in the determination of an outcome indicator 312 for Parkinson's.

Biomarker Patient without AM] D Patient with AMD

92 to 85 to

Retinal Vein 69 to 75 127 to 140 67 to 71 121 to 132

98 91

Ganglion Cell 84 to 75 to

59 to 66 90 to 96 58 to 62 89 to 96

Layer 89 81

Table 1 - Disease and Control Ranges for acute measurements

In embodiments, biomarker scores 314 can be determined at least in part based on measurements of biomarkers over time, using the scan date 310. In an embodiment, the rate of change can be calculated based on, for example, the slope of a linear regression of scans of the same eye of the same patient over a period of time, as depicted in FIG. 6 for individual patients known to have Alzheimer's, Parkinson's or neither (control). Other methods of determining the rate of change based on a series of scans 102 can be used in embodiments. In an embodiment, the disease ranges for the rate of change of biomarkers for Alzheimer's and Parkinson's can be defined as shown in Table 2 below, for patients with and without age- related macular degeneration.

Table 2 - Disease and Control Ranges for rate of measurement change over time

FIG 7 is a flowchart depicting a method 700 for determining a biomarker score 314 in embodiments. In embodiments, if the biomarker measurement is in a disease range 702, the biomarker score for that disease is assigned the value of 1.0 at 704. If not, but the biomarker is within the control range at 406, the biomarker score is assigned the value of 0.0 at 708. At 710, if the biomarker measurement is between the control range, the biomarker score is assigned the value of 0.5 at 712. At 714, if the biomarker is outside of both the biomarker and disease ranges, the exception handling can be performed. Exception handling can include reporting an error message to the user, or setting a biomarker score of 0.0 or 0.5, in embodiments or a combination of these. In embodiments, the method of exception handling can vary based on the disease, and be configurable in the same methods as described above for biomarker ranges. In embodiments, other weightings or values for biomarker scores 314 can be used, for example as discussed above choroid layer thickness may be disregarded in determining an outcome indicator 312 for Parkinson's. In embodiments, method 700 can be similarly applied to the rate of change of biomarker measurements over time.

In embodiments, a mental state score can be used to provide an additional biomarker score 314. For example, for an MMSE scored out of 30 points, a severe disease range for Alzheimer's can be between 1 and 12 points and the biomarker score can be set to 1.5, a moderate disease range can be between 13 and 20 points and the biomarker score can be set to 1.0, and a mild disease range can be between 20 and 24 points and the biomarker score can be set to 0.5. Other point values and scores can be used in embodiments.

In embodiments, outcome indicators 312 for each disease can be determined based on the biomarker scores. For example, in one embodiment, an Alzheimer's outcome indicator 310 can be determined based on the sum of the Alzheimer's biomarker scores 314, for each biomarker 104a-104d. Whereas a Parkinson's outcome indicator can be determined based on the sum of the Parkinson's biomarker scores 310 for biomarkers 104a-104c (disregarding choroid layer 104d). Table 3 includes details of outcome indicators 314 for Alzheimer's and Parkinson's that can be used in embodiments. Alzheimer's Outcome Parkinson's Outcome

Indicators Indicators

Retinal Vein

Sum of Biomarker Nerve fiber layer Nerve fiber layer

Scores Ganglion cell layer Ganglion cell layer

Choroid Choroid

0.0 to 0.5 Very Low Probability Very Low Probability

1.0-1.5 Low Probability Low Probability

2.0-2.5 Medium Probability High Probability

> 3.0 High Probability N/A

Table 3 - Outcome Indicators based on sums of biomarker scores

In some cases, acute measurements of biomarkers alone may not provide sufficient differentiation between outcomes. Therefore, in embodiments, outcome indicators 312 can be determined using other combinations of biomarker scores 314. For example, in embodiments, outcome indicators 312 can be determined based on mental state score 210 and the rates of change of any value tracked in raw measurement data 200 for the same patient over time. Therefore in embodiments, outcome indicators 312 can be determined based on combinations of any number of biomarker scores 314, any number of elements of raw measurement data 200, and the rates of change in any number of biomarker scores 314 or any number of elements of raw measurement data 200 for the same patient over time.

The ranges, scores, and outcomes of Tables 1 , 2, and 3 above correspond to values determined from patient data. Those of ordinary skill in the art will appreciate however, that other ranges, scores, and outcomes can be used in embodiments, including ranges, scores, and outcomes for one or more other neurological diseases such as multiple sclerosis, and based on other patient details such as age, gender, or other ocular conditions (such as glaucoma). In embodiments, disease ranges, scores, and outcomes can be defined within biomarker analyzer

126, or can be user configurable through user interface 120, via one or more configuration files, or other via any other configuration means. Embodiments of the present disclosure have been used to review a total of 4,675 OCT retinal scans from 379 patients with known neurological disease status. The patients were sorted into age-matched groups of those diagnosed with Alzheimer's (AD patient group), those diagnosed with Parkinson's (PD patient group), and those without AD or PD (control group). The age ranges for each test group were compared to ensure that the groups were age- matched.

The patients' OCT scans were processed to determine actual biomarker sizes, oneway analyses of variance (ANOVAs) were run and 95% confidence intervals were calculated for the biomarker measurements and the average rate of change of the biomarkers for patients among all six test groups (AD patient group, AD with age-related macular degeneration patient group, PD patient group, PD with age-related macular degeneration patient group, control patient group, and control with age-related macular degeneration patient group). The 95% confidence intervals for each test group for each retinal biomarker 104, and the rate of change of change in retinal biomarkers 104 provided the disease and control ranges listed in Tables 1 and 2 above.

Tests have shown that embodiments of the present disclosure using the disease ranges and scoring of Tables 1 through 3 above were 99% accurate in identifying patients with a diagnosis of Alzheimer's in their medical records and who are currently taking an Alzheimer's medication, 97% accurate in identifying patients with a diagnosis of Parkinson's in their medical records and who are currently taking a Parkinson's medication, and 97% accurate in identifying patients with no serious cognitive diseases documented in their medical records and who are not taking Alzheimer's or Parkinson's medications.

Embodiments of the present disclosure can enable efficient and low-cost detection of biomarker dimensions, which can have significant clinical and research benefits. Embodiments of the present disclosure can assist in the diagnosis of Alzheimer's and Parkinson's or other neurodegenerative diseases without the need for expensive MRI scans. This can facilitate more prophylactic screening of patients before symptoms of neurodegenerative disease are present. Embodiments of the present disclosure can also enable help to lower the cost of tracking the progression of already-diagnosed disease because less MRI imaging may be required. Embodiments of the present disclosure can also be used to discover additional correlations between retinal biomarkers and other diseases.

It should be understood that the individual steps used in the methods of the present teachings may be performed in any order and/or simultaneously, as long as the teaching remains operable. Furthermore, it should be understood that the apparatus and methods of the present teachings can include any number, or all, of the described embodiments, as long as the teaching remains operable.

In one embodiment, the biomarker processing system 100 and/or its components or subsystems can include computing devices, microprocessors, modules and other computer or computing devices, which can be any programmable device that accepts digital data as input, is configured to process the input according to instructions or algorithms, and provides results as outputs. In an embodiment, computing and other such devices discussed herein can be, comprise, contain or be coupled to a central processing unit (CPU) configured to carry out the instructions of a computer program. Computing and other such devices discussed herein are therefore configured to perform basic arithmetical, logical, and input/output operations.

Computing and other devices discussed herein can include memory. Memory can comprise volatile or non-volatile memory as required by the coupled computing device or processor to not only provide space to execute the instructions or algorithms, but to provide the space to store the instructions themselves. In one embodiment, volatile memory can include random access memory (RAM), dynamic random access memory (DRAM), or static random access memory (SRAM), for example. In one embodiment, non-volatile memory can include read-only memory, flash memory, ferroelectric RAM, hard disk, floppy disk, magnetic tape, or optical disc storage, for example. The foregoing lists in no way limit the type of memory that can be used, as these embodiments are given only by way of example and are not intended to limit the scope of the disclosure.

In one embodiment, the system or components thereof can comprise or include various modules or engines, each of which is constructed, programmed, configured, or otherwise adapted to autonomously carry out a function or set of functions. The term

"engine" as used herein is defined as a real-world device, component, or arrangement of components implemented using hardware, such as by an application specific integrated circuit (ASIC) or field- 10 programmable gate array (FPGA), for example, or as a combination of hardware and software, such as by a microprocessor system and a set of program instructions that adapt the engine to implement the particular functionality, which

(while being executed) transform the microprocessor system into a special-purpose device.

An engine can also be implemented as a combination of the two, with certain functions facilitated by hardware alone, and other functions facilitated by a combination of hardware and software. In certain implementations, at least a portion, and in some cases, all, of an engine can be executed on the processor(s) of one or more computing platforms that are made up of hardware (e.g., one or more processors, data storage devices such as memory or drive storage, input/output facilities such as network interface devices, video devices, keyboard, mouse or touchscreen devices, etc.) that execute an operating system, system programs, and application programs, while also implementing the engine using multitasking, multithreading, distributed (e.g., cluster, peer-peer, cloud, etc.) processing where appropriate, or other such techniques. Accordingly, each engine can be realized in a variety of physically realizable configurations, and should generally not be limited to any particular implementation exemplified herein, unless such limitations are expressly called out. In addition, an engine can itself be composed of more than one sub-engines, each of which can be regarded as an engine in its own right. Moreover, in the embodiments described herein, each of the various engines corresponds to a defined autonomous functionality; however, it should be understood that in other contemplated embodiments, each functionality can be distributed to more than one engine. Likewise, in other contemplated embodiments, multiple defined functionalities may be implemented by a single engine that performs those multiple functions, possibly alongside other functions, or distributed differently among a set of engines than specifically illustrated in the examples herein.

Various embodiments of systems, devices, and methods have been described herein. These embodiments are given only by way of example and are not intended to limit the scope of the claimed inventions. It should be appreciated, moreover, that the various features of the embodiments that have been described may be combined in various ways to produce numerous additional embodiments. Moreover, while various materials, dimensions, shapes, configurations and locations, etc. have been described for use with disclosed embodiments, others besides those disclosed may be utilized without exceeding the scope of the claimed inventions.

Persons of ordinary skill in the relevant arts will recognize that embodiments may comprise fewer features than illustrated in any individual embodiment described above. The embodiments described herein are not meant to be an exhaustive presentation of the ways in which the various features may be combined. Accordingly, the embodiments are not mutually exclusive combinations of features; rather, embodiments can comprise a combination of different individual features selected from different individual embodiments, as understood by persons of ordinary skill in the art. Moreover, elements described with respect to one embodiment can be implemented in other embodiments even when not described in such embodiments unless otherwise noted. Although a dependent claim may refer in the claims to a specific combination with one or more other claims, other embodiments can also include a combination of the dependent claim with the subject matter of each other dependent claim or a combination of one or more features with other dependent or independent claims. Such combinations are proposed herein unless it is stated that a specific combination is not intended. Furthermore, it is intended also to include features of a claim in any other independent claim even if this claim is not directly made dependent to the independent claim.

Moreover, reference in the specification to "one embodiment," "an embodiment," or "some embodiments" means that a particular feature, structure, or characteristic, described in connection with the embodiment, is included in at least one embodiment of the teaching. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment.

Any incorporation by reference of documents above is limited such that no subject matter is incorporated that is contrary to the explicit disclosure herein. Any incorporation by reference of documents above is further limited such that no claims included in the documents are incorporated by reference herein. Any incorporation by reference of documents above is yet further limited such that any definitions provided in the documents are not incorporated by reference herein unless expressly included herein. For purposes of interpreting the claims, it is expressly intended that the provisions of Section 112, sixth paragraph of 35 U.S.C. are not to be invoked unless the specific terms "means for" or "step for" are recited in a claim.