IBM Research has announced new research developments in IBM Watson’s ability to detect abnormalities of the eye’s retina.
The Melbourne based IBM researchers have trained a research version of Watson to recognize abnormalities in retina images, which could in the future offer doctors greater insights and speed in their early identification of patients who may be at risk of eye diseases – such as glaucoma, a leading cause of blindness in the developed world.
The research began in 2015 and the latest work has focused on streamlining some of the manual processes experienced by doctors today. This includes distinguishing between left and right eye images, evaluating the quality of retina scans, as well as ranking possible indicators of glaucoma.
Glaucoma has been named “the silent thief of sight” as many patients remain undiagnosed until irreversible vision loss occurs. Glaucoma can be treated but early detection is critical, with doctors currently relying on regular eye examination screening programs.
The researchers applied deep learning techniques and image analytics technology to 88,000 de-identified retina images accessed through EyePACS®, to analyze key anomalies of the eye.
The research results demonstrate Watson’s ability to accurately measure the ratio of the optic cup to disc – which is a key sign of glaucoma – with statistical performance as high as 95 percent. The technology has also been trained to distinguish between left and right eye images (with up to 94 percent confidence), which are important for downstream analysis and for the development effective treatment programs.
The research is expected to continue to improve over time as the research technology expands to detect features of other eye diseases such as diabetic retinopathy and age-related macular degeneration.
You can learn more about IBM Research efforts here.
IBM today introduced IBM Watson Imaging Clinical Review — the first cognitive imaging offering from Watson Health.
It also announced the expansion of the Watson Health medical imaging collaborative to 24 organizations worldwide, adding clinical and industry expertise for the worldwide initiative already tackling eye, brain, breast, heart and related conditions.
The Watson Health medical imaging collaborative is an initiative comprised of leading health systems, academic medical centers, private radiology practices, ambulatory radiology providers, and imaging technology companies that are finding ways to use medical imaging to identify and predict the risk of cancer, diabetes, and diseases of the eye, brain and heart and related conditions.
Watson Health will debut Watson Clinical Imaging Review, the first cognitive imaging offering from IBM. The offering reviews medical data including images to help healthcare providers identify the most critical cases that require attention.
The first application for the offering is cardiovascular disease, starting with a common condition called aortic stenosis (AS). AS, which affects 1.5 million Americans, occurs when the aortic valve in the heart is narrowed, impeding blood flow to the rest of the body and causing shortness of breath, tiredness, and chest pain.
A pilot study found that Watson Clinical Imaging Review was able to help hospital personnel identify potential AS patients who had not been previously flagged for follow up cardiovascular care.
Using Watson Imaging Clinical Review, hospital administrators may identify cases where follow up care is warranted and assure EMR information is complete. It uses cognitive text analytics to read structured and unstructured information in a cardiologist’s medical report, combines that with a variety of data from other sources (e.g. EMR problem list), and extracts relevant information to verify key data, including the diagnosis, is accurately reflected throughout the health record.
“Watson Imaging Clinical Review is the type of targeted AI-driven tool that providers could put to use to help them standardize care delivered across their organization, and gradually build a critical mass of reproducible results from their patient population. In doing so, it can support a population health-driven approach to personalized care,” said Nadim Michel Daher, a medical imaging and informatics analyst for Frost & Sullivan.
“Out of the gate, this type of cognitive tool may provide big benefits to hospitals and doctors, providing insights we don’t currently have and doing so in a way that fits how we work,” said Ricardo C. Cury, M.D., director of Cardiac Imaging at Baptist Health of South Florida and chairman and CEO of Radiology Associates of South Florida.
IBM plans to supplement the release of this offering with nine additional cardiovascular conditions, such as myocardial infarctions (heart attacks), valve disorders, cardiomyopathy (disease of the heart muscle), and deep vein thrombosis.
You can learn more about Watson Health here.
More Apple news overnight…
The company will soon start to manufacture its iPhone SE model in Bangalore through its subcontractor, Wistron.
This would be Apple’s first move to assemble its iPhones in India. However, as the Economic Times of India observes, “the biggest hurdle preventing Apple from cornering a larger slice of the Indian smartphone pie” is its price points. A new model iPhone in India starts at upwards of Rs 50,000 (roughly $745 U.S.).
MacRumors explains that Apple had been in talks with the Indian federal government to garner possible tax concessions if the company agreed to manufacture its phones locally, but that apparently the “initial manufacturing of the iPhone SE is not contingent on any such concessions.”
It goes on to explain that this move into India “looks to offset slowing growth in China by boosting its share of the Indian phone market.”
The iPhone is expected to come in at around Rs 28,460 (roughly $424).
Note: I’m a proud iPhone SE owner my own self. I opted to get the four-inch model because I like the smaller form factor than the 6/7, and with a Mophie case lasts a full day burning up the AC/DC. I also like the fact when I’m riding the bus to work I can hold and operate it with a single hand and thumb. The tradeoff is definitely smaller screen size, but for me the SE strikes the right balance.
Apple has announced its developer conference, WWDC 2017, will be held June 5th to June 9th, and will change venues from previous years to the McEnery Convention Center in San Jose.
9to5 Mac is reporting that Apple is expected to unveil the next major versions of its software operating systems, including iOS 11, macOS 10.13, and updates to tvOS and watchOS.
Why the change of venue?
TechCrunch suggests San Jose is simply more convenient to Apple’s HQ in Cupertino (15 minutes to San Jose vs. 45 to San Francisco, where the Moscone Center is located).
Because there are an expected 1,000 Apple engineers that will be addressing the Apple developer community, it’s more convenient for the Apple participants. For the independent Apple developer, it’s less of a hit to the pocketbook (in terms of travel, hotel costs, etc.)
The conference price is expected to cost roughly the same, $1,599.
Developers will be able to register for a WWDC ticket starting March 27. Then, there will be a lottery to select the attendees (demand usually exceeds ticket supply!)
Lotsa news on the telecommunications and smartphone front leading up to Barcelona’s Mobile World Congress later this month.
Verizon threw down its gauntlet on unlimited data, its first since 2011 according to MacRumors. The new plan unveiled Sunday includes unlimited talk, text, and 4G LTE data, and will cost $80/month for a single smartphone or tablet.
But unlimited isn’t completely unlimited, as “Verizon Unlimited” includes a potential slowdown after customers exceed 22 GB of data usage in a single billing cycle.
Over at Chinese smartphone maker Xiaomi, they’re looking to introduce their own code-named processor, “Pinecone” within the month, writes Ars Technica. This moves Xiaomi into an alternative smartphone processor universe, considering that most every Android OEM other than Samsung and Huawei have been Qualcomm customers.
Meanwhile, Android Authority reported that Huawei defied slowing global smartphone sales trends and shipped 139M units in 2016, a nearly 30 percent YOY increase. It’s consumer division revenues grew 42% to $26B.
But probably the most intriguing numbers to recently appear were new device activations leading into the Christmas holidays. Flurry has apparently done this analysis every year for several years, and this year, the headline was this: For every Samsung device activated, Apple saw two activated devices (44 percent for Apple, 21 percent for Samsung).
Admittedly, Samsung had a bit of a rough 2016, but yet and still, 2 to 1…and this as Apple recently announced record earnings, sending their stock price to an all-time high.
The sub-headline was that the so-called “phablet” was the dominant form factor by the end of 2016 (with phablet being defined as a smartphone having a screen intermediate in size, between that of a typical smartphone and a tablet computer.
IBM security has announced the availability of Watson for Cyber Security, the industry’s first augmented intelligence technology designed to power cognitive security operations centers.
Over the past year, Watson has been trained on the language of cyber security, ingesting over 1 million security documents. Watson can now help security analysts parse thousands of natural language research reports that have never before been accessible to modern security tools.
Watson for Cyber Security will be integrated into IBM’s new Cognitive SOC platform, bringing together advanced cognitive technologies with security operations and providing the ability to respond to threats across endpoint, network, users and cloud.
The centerpiece of this platform is IBM QRadar Advisor with Watson, a new app available in the IBM Security App Exchange, which is the first tool that taps into Watson’s corpus of cyber security insights.
This new app is already being used by Avnet, University of New Brunswick, Sopra Steria and 40 other customers globally to augment security analysts’ investigations into security incidents.
IBM has also invested in research to bring cognitive tools into its global X-Force Command Center Network, including a Watson-powered chatbot currently being used to interact with IBM Managed Security Services customers.
IBM also revealed a new research project, codenamed “Havyn,” pioneering a voice-powered security assistant that leverages Watson conversation technology to respond to verbal commands and natural language from security analysts.
The project uses Watson APIs, Bluemix and IBM Cloud to provide real-time response to verbal requests and commands, accessing data from open source security intelligence, including IBM X-Force Exchange, as well as client-specific historic data and their security tools.
Watson is also currently engaging with clients daily via a new chatbot tool deployed in IBM’s X-Force Command Center Network, which manages over 1 trillion security events per month. Clients can choose to ask Watson questions via instant messaging about their security posture or network configurations.
For example, clients can ask Watson questions about a device or ticket status. The tool is also capable of executing commands from IBM MSS customers, such as reassigning a ticket to a new owner.
Go here to learn more about Watson for Cyber Security and the Cognitive SOC.