AI News, Eye Scans to Detect Cancer and Alzheimer’s Disease
- On 2. december 2017
- By Read More
Eye Scans to Detect Cancer and Alzheimer’s Disease
While the app is not yet ready to be used as a diagnostic tool based only a single small trial, it might soon provide a tool for doctors monitor disease progression in patients undergoing treatment with a simple photograph, rather than a blood test, says first author Alex Mariakakis, a UW graduate student.
First, users take a selfie with their smartphone using one of two accessories to control for environmental conditions: either a cardboard box to block out the light, or colored glasses to give a color reference.
In June 2010, the Cedars-Sinai team, led by Maya Koronyo-Hamaoui and Yosef Koronyo, made a novel discovery: Beta-amyloid protein deposits, a neurotoxic protein that builds up in the brains of Alzheimer’s patients, are also present in the postmortem retina of such patients and even in early-stage cases.
She and collaborators at Cedars-Sinai founded a company, NeuroVision, to develop a way to detect and quantify those plaques in the eye, in the hopes of being able to see early signs of the disease before cognitive decline becomes obvious.
Today, their system consists of a modified scanning laser ophthalmoscope with a special filter to capture a fluorescence signal emitted by the plaques when tagged with a marker, and advanced software to process the images.
“We are testing larger cohorts of living patients for the possible relationship between retinal amyloid index and the gold standard amyloid-PET brain imaging and other AD biomarkers.” She believes that the imaging could someday be adapted to less expensive cameras, but currently a doctor’s office would require a high-definition camera and image processing and quantification tools in order to use the system.
How an eye test could detect Alzheimer's
In a proof-of-concept study, researchers reveal how a noninvasive, high-resolution imaging technique was able to detect beta-amyloid plaques in the retinas of patients with Alzheimer's disease.
In Alzheimer's disease, these beta-amyloid fragments clump together, forming 'plaques' in the brain that disrupt neuronal communication and trigger immune cell activity.
Detecting beta-amyloid in the retina The new technique involves autofluorescent imaging of the retina using a specially designed ophthalmic camera and state-of-the-art image processing software.
The team reports that the retinal imaging technique identified a 4.7-times greater abundance of beta-amyloid plaques in the retinas of patients with Alzheimer's disease, compared with the retinas of the controls.
The researchers also tested the imaging method on the retinas of 23 deceased patients who had Alzheimer's disease, alongside the retinas of 14 age-matched deceased individuals who did not have the disease.
What is more, in both living and deceased patients with Alzheimer's disease, the researchers found that neuronal loss in the retinas as a result of beta-amyloid plaques correlated with neuronal loss in the patients' brains.
The geometric distribution and increased burden of retinal amyloid pathology in AD [Alzheimer's disease], together with the feasibility to noninvasively detect discrete retinal amyloid deposits in living patients, may lead to a practical approach for large-scale AD diagnosis and monitoring.'
Since the start of the program, partner clinic administrators and photographers, working alongside EyePACS staff members, have contributed a great deal of new knowledge about integrating diabetic retinopathy screening into the clinical setting.
The program has been successful because of the hard work and dedication of the primary caregivers who work every day to find new and better ways to use the EyePACS system to improve the health of their diabetic patients.
Through his personal efforts and leadership, he developed EyePACS, an open access, license-free system for clinical communication in eye care that has been used for remote care, diabetic eye disease screening, home care, education, and research.
Within a three year span, he has led a multi-million dollar grant from the California Health Care Foundation to establish telemedicine-based diabetic retinopathy screening services in over 50 safety net clinics in California.
With 21 years of Academic Ophthalmology tenure and 12 years of experience in international and domestic public health, he brings the clinical, technical and the operational experience to help develop and administer telemedicine-based diabetic retinopathy screening programs.
Dr. Bresnick was a Principal Investigator at the University of Wisconsin in the key National Eye Institute-supported studies (DRS/ETDRS) that demonstrated the value of laser treatment for diabetic retinopathy and that laid the groundwork for the telemedicine evaluation of retinopathy severity.
He has designed and conducted a number of public health eye care programs in minority and underserved communities for early detection and treatment of vision-threatening eye diseases.
His research interests include telemedicine, digital systems for medical education, clinical IT systems integration, patient directed medical image exchange, clinical data management for research applications with an emphasis on biomedical imaging and grid computing applications, utilization of mobile computing technology to enable point-of-care access to medical information, and the development of applications and processes to enhance the acquisition, exchange and analysis of biomedical research data.
He began his work with EyePACS just after completing his residency in 2010, helping with several research projects evaluating retinal imaging and electrodiagnostic systems for the detection of vision-threatening diabetic retinopathy.
Amanda started working with EyePACS in February of 2016 and is excited to be working with a program that does such an excellent job of linking primary care providers with specialists regardless of their physical location.
- On 28. november 2016
- By Read More
Google Research Blog
Posted by Lily Peng MD PhD, Product Manager and Varun Gulshan PhD, Research Engineer Diabetic retinopathy (DR) is the fastest growing cause of blindness, with nearly 415 million diabetic patients at risk worldwide.
In 'Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs', published today in JAMA, we present a deep learning algorithm capable of interpreting signs of DR in retinal photographs, potentially helping doctors screen more patients in settings with limited resources.
Examples of retinal fundus photographs that are taken to screen for DR. The image on the left is of a healthy retina (A), whereas the image on the right is a retina with referable diabetic retinopathy (B) due a number of hemorrhages (red spots) present.
We then tested the algorithm’s performance on two separate clinical validation sets totalling ~12,000 images, with the majority decision of a panel 7 or 8 U.S. board-certified ophthalmologists serving as the reference standard.
Performance of the algorithm (black curve) and eight ophthalmologists (colored dots) for the presence of referable diabetic retinopathy (moderate or worse diabetic retinopathy or referable diabetic macular edema) on a validation set consisting of 9963 images.
For example, on the validation set described in Figure 2, the algorithm has a F-score (combined sensitivity and specificity metric, with max=1) of 0.95, which is slightly better than the median F-score of the 8 ophthalmologists we consulted (measured at 0.91).
Given the many recent advances in deep learning, we hope our study will be just one of many compelling examples to come demonstrating the ability of machine learning to help solve important problems in medical imaging in healthcare more broadly.
- On 15. april 2021
Introducing D-EYE - Smartphone Based Retinal Imaging System
The D-EYE Portable Retinal Imaging System is a low-cost, mobile eye screening system that can detect the leading causes of blindness including diabetic ...
Case Study: TensorFlow in Medicine - Retinal Imaging (TensorFlow Dev Summit 2017)
Diabetic retinopathy is the fastest growing cause of blindness. Learn from Lily Peng how TensorFlow was trained to analyze retinal fundus images to diagnose ...
Underground Gold And Treasure Detector ( Documentary Film )
Documentary film for searching for ancient treasures underground. Treasure finding and the beginning of exploration. The treasure had been discovered in the ...
Have you ever seen an atom?
Scientists at the University of California Los Angeles have found a way to create stunningly detailed 3D reconstructing of platinum nanoparticles at an atomic ...
Study uses magnetic stimulation to detect dementia
(23 May 2016) LEAD IN: Neurologists are to begin a trial to discover whether transcranial magnetic stimulation, or TMS on the brain can alert doctors to the ...
Eyes-On Glasses help see patient's veins through skin
Originally published on November 28, 2013 Sign up for a free trial of News Direct's animated news graphics at A new ..
Breaking News - 'Nerve centre' of Alzheimer's disease discovered
Scientists believe they have identified the where Alzheimer's disease begins in the brain – sparking hopes for a cure for the devastating illness.They say it is in ...
Philips and PathAI to improve breast cancer diagnosis with artificial intelligence
Philips and PathAI team up to improve breast cancer diagnosis using artificial intelligence technology in 'big data' pathology research. Royal Philips, a global ...
NASA's biggest spacecraft plunges into Saturn in the final act of a 20-year mission showcasing the planet like never before.
Reading through closed books
Spatial resolution, spectral contrast, and occlusion are three major bottlenecks in current imaging technologies for non-invasive inspection of complex samples ...