The post McGill University Alumni Develop A Synthetic Medical Image Generation Tool appeared first on Techso Mogro.
]]>In this, his first contribution to the Techso Mogro, Rayan describes how, through their research, they hope to reshape the very fabric of medical diagnostics.
Imagine a world where doctors will deliver diagnoses on life-threatening diseases by practicing using thousands of hyper-realistic medical scans. They’ll be able to train using these images before ever seeing a patient. This isn’t science fiction. This is the promise of generative AI in medicine, not to replace reality, but to enhance it and ultimately save lives.
Carez AI is a system powered by generative AI that creates hyper-realistic MRI, X-ray, CT, ultrasound, and pathology data at scale. It allows users of its AI tool to turn rare, difficult-to-capture diseases into 20,000 perfectly annotated medical imaging samples with 98% accuracy. The best radiologists struggle to differentiate the medical imaging samples from real scans.
Why do this?
AI is increasingly seen as a gamechanger for medical diagnostics described as an industry-wide paradigm shift. When building these generative AI and machine learning tools, data is the key. The more test results and images scanned means greater identification and AI predictive capacity. That’s why thousands of teams are working in the medical field to develop AI diagnostic tools.
What’s slowing them down: data scarcity because clinical-grade AI only exists from datasets that are ethically sourced and representative of the demographics, anatomy, and medical conditions of an entire population.
Obtaining such datasets can cost a lot of money. Training per dataset can take up to a year. Even after all that, the data can still have critical gaps due to geography, population source and other systemic biases.
The way OpenAI and other AI developers have approached obtaining data for their AI tools to use for training often involves scraping the entire content of web pages without the permission of the content creators. This has led to lawsuits from the publishers of the content and concerns about invasion of privacy. When dealing with healthcare data, patient privacy is a big thing. In the U.S., HIPAA, in Canada, PIPEDA and in the European Union, GDPR rules govern the collection, digitization and sharing of patient data.
Carez AI has recognized that in developing its diagnostic tool that patient data privacy is paramount. Instead of a cookie-cutter model based on publicly scraped Internet data, it is working with users to create task-specific models based on their proprietary data, secured and insulated to safeguard patient privacy, copyright and model access. Every dataset generated is legally obtained with fully compliant data agreements.
The result is an AI diagnostic tool that fills the gaps found in proprietary datasets through the generation of anatomically accurate synthetic images. These synthetic images reflect population and geographic diversity with no systemic biases. When recently tested by five chief radiologists, the doctors could not distinguish Carez AI synthetic scans from real ones.
What does this mean? Simply put, it means a fully customizable, high-quality, synthetic dataset for diagnostic imaging that can be produced in minutes. To achieve these results, Carez AI has been working with the top companies in medical imaging. It was invited to present last year at the largest medical imaging conference in Europe, the Cardiovascular and Interventional Radiological Society of Europe (CIRSE 2024), where it was chosen as one of the top AI startups in the field.
What is the future of synthetic imaging diagnostic AI tools? Advancements in generative AI and machine learning are seen by the healthcare sector as an increasingly attractive diagnostic imaging option. Market predictions (see graph below) project annual growth of 35.3% through 2030 for this burgeoning field.
Recently, Gretel, a company acquired by NVIDIA, has been accelerating the trend in the adoption of synthetic data. Gretel supports various data types, including tabular, unstructured, time-series, relational, and image data. Carez AI remains focused on diagnostic imaging data tools to save lives. It sees synthetic imaging datasets as a key to democratizing healthcare delivery, leveling the playing field for hospitals worldwide, whether located in Montreal, San Francisco, or rural Uganda.
The post McGill University Alumni Develop A Synthetic Medical Image Generation Tool appeared first on Techso Mogro.
]]>The post Researchers Invent a Wearable Ultrasound Patch to Provide Real-Time Pictures of the Heart appeared first on Techso Mogro.
]]>Cardiologists have a suite of tools designed to monitor heart function. Ultrasounds, also known as echocardiograms, are used to get a look at the physical heart using sound waves. An ultrasound can tell a cardiologist a lot. Are the four chambers normal in appearance? Are the valves functioning properly? Are there leaks? Are they seeing normal blood flow? Is the heart muscle contracting as it should?
To detect irregularities in the heart’s conduction system, electrocardiography is used. This involves getting tracings of the electrical signature of all four chambers and the major blood vessels. When done in a medical office, leads are applied to various areas of the body, upper chest, abdomen and legs. A more portable approach is to use a Holter Monitor which can be worn externally for a number of days to provide a complete record of every beat and missed beat. Then there are portable devices like the Apple Watch and the one I use, Kardiamobile, a pad that combines with a smartphone app to give me a 30-second electrocardiogram which I can then send to my cardiologist. If I have an odd feeling in my chest, I use the pad which is split in two, with two fingers pressed on each side. Since being diagnosed with atrial fibrillation (aF) I tend to use it at least once a day or anytime I feel light-headed or have odd palpitations in my chest.
In addition to the ultrasound imaging previously described, heart function can also be assessed by an MRI, CT scan, and X-rays. More invasive are cardiac catheterization procedures which involve inserting a catheter into a blood vessel and threading it into the heart where a contrast dye and X-ray provide a good two-dimensional real-time image of the heart as it works.
But what if you could put a patch on your skin and use it to monitor heart function? Up until now, wearable devices that used leads to contact the skin, or watches were the only ones capable of producing heart data useful to medical practitioners. These were exclusively focused on the heart’s conduction system. But with a new invention from the University of California San Diego, these may soon be joined by a companion wearable the size of a postage stamp that could become the way ultrasonic images of the heart are taken.
The patch provides accurate continuous monitoring of cardiac performance using ultrasound images. The illustrations below come from an article published in the January 25, 2023 edition of the journal Nature.
The wearable patch contains liquid metal composite electrodes and piezoelectric transducers. It can image deep into the body and provide a range of images including axial, elevational, and lateral views. Compared to regular ultrasounds the differences when looked at by third parties were considered negligible.
Unlike regular echos, the images this patch can gather can see the heart when a patient is in motion rather than lying on an examination table. Ultrasounds cannot image the image when it is under stress, only after a stress test when the patient is then examined. Conventional ultrasounds use gels which are critical to being able to obtain images. Gels are constantly reapplied throughout an imaging session. The patch uses liquid silicone which retains its liquid state for a full 24 hours so that images can continuously be gathered.
The developers have also created deep learning modelling software which when combined with the images provides measurements of stroke volume, cardiac output and ejection fractions making this technology not only versatile but also likely the next tool in a cardiologist’s arsenal.
The post Researchers Invent a Wearable Ultrasound Patch to Provide Real-Time Pictures of the Heart appeared first on Techso Mogro.
]]>The post Imagine an Ultrasound Scanner for $100 appeared first on Techso Mogro.
]]>The ultrasound images this new device creates are sharper and more detailed than scanning equipment used in world hospitals and clinics today. And better yet, the low energy requirements, drawing only 10 volts to operate, means the scanner can be powered by a smartphone. The flexibility of the polymer material makes it possible to shape it in various ways so that it can be wrapped around a body to create much more detailed views.
Robert Rohling, Professor of Mechanical Engineering and Electrical Computer Engineering, at UBC, and one of the inventors of this new ultrasound technology, states, “You could miniaturize these transducers and use them to look inside your arteries and veins. You could stick them on your chest and do live continuous monitoring of your heart in your daily life. It opens up so many different possibilities.”
This new ultrasound transducer joins a growing market for diagnostic imaging technology. Ultrasound alone was a $4.6 billion US market in 2012 and is expected to hit $7 billion next year. Scanners fetch prices from $10,000 for portables to $250,000 for high-end machines. Imagine just how disruptive the arrival of a $100 ultrasound scanning device that produces more detailed and sharper images than far more expensive devices, will be.
Described in the August 27, 2018 issue of Nature: Microsystems & Nanoengineering, in an article authored by Rohling, Carlos Gerardo, and Edmond Cretu, the inventors are planning to develop a variety of different shaped and sized prototypes for testing in clinical applications.
This should be quite a wakeup call for companies like Canon, Siemens, Toshiba General Electric, Phillips, and others who have been able to make quite a bit of money off of their ultrasound scanners. As of yet, UBC hasn’t announced a spinoff commercial company to further develop the technology. But I suspect some of the big diagnostic imaging companies may become early stakeholders in the months ahead.
The post Imagine an Ultrasound Scanner for $100 appeared first on Techso Mogro.
]]>The post Gizmos & Gadgets: Meet the Smartphone Ultrasound App for Diagnostic Imaging appeared first on Techso Mogro.
]]>This is not yet a general consumer device even though it works with iPhones from the models SE, 6S and up to the new iPhone X. It’s the real deal communicating with PACS and DICOM worklist servers, the picture archiving and communication systems used by diagnostic imaging departments in hospitals today. The images Butterfly iQ creates are stored in the cloud securely and are totally HIPAA compliant.
What’s revolutionary about the Butterfly iQ isn’t just the fact that it works with iPhones.
The wand that creates the pictures and is connected to an iPhone by USB cable uses 9,000 capacitive micro-machined ultrasound transducers (CMUTs) integrated into a semiconductor chip the size of postage stamp. The CMUT is a tiny ultrasonic emitter and each is capable of creating detailed images, but together, they produce ultrasounds that are pretty close in terms of detail to those produced by much more expensive machines found in hospitals and testing labs. And unlike those far more expensive machines which require multiple wands to produce a range of images for different applications, the Butterfly iQ is a single device capable of creating images that meet FDA standards across a range of clinical applications including ultrasound for:
Think of what a difference maker this device can be for an emergency room physician who can pull it out of his or her pocket, plug it into an iPhone and immediately see an image that can lead to a faster diagnosis and intervention. And at the price, every paramedic could have one on board an ambulance to instantly understand the extent of the injury or condition of a patient in their care.
The Butterfly Network will start shipping the Butterfly iQ to what is a growing backlog of orders by early in 2018. Meanwhile, the company continues to work on adding artificial intelligence software to the product so that it can be used by people with no previous experience with ultrasound. The app would then help with positioning the device, collecting the images, and interpreting them. Will all of us soon be able to do our own diagnostic imaging and see the results on a smartphone? Perhaps very soon.
The post Gizmos & Gadgets: Meet the Smartphone Ultrasound App for Diagnostic Imaging appeared first on Techso Mogro.
]]>