Diagnostic Medicine


Just What the Doctor Ordered: Smarter Systems for AI-Assisted Radiology The Official NVIDIA Blog

#artificialintelligence

The research team at the Center for Clinical Data Science (CCDS) today received the world's first purpose-built AI supercomputer from the all-new portfolio of NVIDIA DGX systems with Volta. In only eight months -- beginning in December when the center received NVIDIA's first generation DGX-1 AI supercomputer -- CCDS data scientists have successfully trained machines to "see" abnormalities and patterns in medical images. Now, having just received the world's first NVIDIA DGX-1 with Volta supercomputer and with an all-new DGX Station, the world's first personal AI supercomputer coming later this month, CCDS will build upon its groundbreaking research to develop a host of new training algorithms and bring the power of AI directly to doctors. The new DGX-1 with Volta delivers groundbreaking AI computing power three times faster than the prior DGX generation, providing the performance of up to 800 CPUs in a single system.


Scanning The Future, Radiologists See Their Jobs At Risk

NPR

He's sitting inside a dimly lit reading room, looking at digital images from the CT scan of a patient's chest, trying to figure out why he's short of breath. Health care companies like vRad, which has radiologists analyzing 7 million scans a year, provide data to partners that develop medical algorithms. Chief Medical Officer Eldad Elnekave says computers can detect diseases from images better than humans because they can multitask -- say, look for appendicitis while also checking for low bone density. Radiologist John Mongan is researching ways to use artificial intelligence in radiology.


Scanning The Future, Radiologists See Their Jobs At Risk

@machinelearnbot

He's sitting inside a dimly lit reading room, looking at digital images from the CT scan of a patient's chest, trying to figure out why he's short of breath. 'You need them working together' The reality is this: dozens of companies, including IBM, Google and GE, are racing to develop formulas that could one day make diagnoses from medical images. Health care companies like vRad, which has radiologists analyzing 7 million scans a year, provide data to partners that develop medical algorithms. Chief Medical Officer Eldad Elnekave says computers can detect diseases from images better than humans because they can multitask -- say, look for appendicitis while also checking for low bone density.


The UK desperately needs a Radiology AI Incubator – Hugh Harvey – Medium

#artificialintelligence

In the UK academic circuit there are dozens of medical imaging researchers building algorithms on small datasets, but they lack the resources to test them on millions of images, let alone get their product into the market. What is needed is the alignment of big technology companies, the RCR and the NHS governing bodies to drive a fully collaborative vision in the field of radiology AI. We should be capitalising on the NHS as a national system, by pooling imaging data and building a nationalised imaging warehouse and technology incubator (I'd like to call this BRAIN -- British Radiology Artificial Intelligence Network). This would create a national institute for radiology in AI, capable of attracting industry partners, funding for researchers and equipment.


Medical Image Analysis with Deep Learning , Part 4

@machinelearnbot

Medical Images have 4 key constituents -- Pixel Depth, Photometric Interpretation,Metadata and Pixel data. There are 6 predominant formats for radiology images -- DICOM (Digital Imaging and Communications in Medicine), NIFTI (Neuroimaging Informatics Technology Initiative), PAR/REC (Philips MRI scanner formats), ANALYZE (Mayo Medical Imaging), NRRD (Nearly Raw Raster Data) and MNIC. A Nrrd header accurately represents N-dimensional raster information for scientific visualization and medical image processing. National Alliance for Medical Image Computing (NA-MIC) has developed a way of using the Nrrd format to represent Diffusion Weighted Images (DWI) volumes and Diffusion Tensor Images (DTI).Nrrd DWI and Nrrd DTI data can be read into 3D Slicer, to visually confirm that the orientation of the tensors is consistent with expected neuroanatomy [link] MINC stands for Medical Imaging NetCDF Toolkit.


Machine Learning & Radiology – CancerGeek – Medium

#artificialintelligence

He happens to be dual board certified, fellowship trained, has multiple decades of experience in reading images, curating information that makes up a patient's medical history, has an amazing "sense" for what is relevant versus not relevant, and is a great teacher. It is to provide radiologists more time to spend with patients directly, having more time to educate their medical community on how to correctly order the right imaging exam to answer the right question for their patients, and to have more time to show how radiology (along with pathology) are not about cost centers, but are about how to deliver care at the N of 1. Radiologists earn trust at the N of 1. As always you can feel free to email me at cancergeek@gmail.com or follow me on Twitter @cancergeek You can read past issues of my weekly newsletter by clicking this link: newsletter and feel free to signup using the subscribe tab at the top.


The Future of Radiology and Artificial Intelligence

#artificialintelligence

By the early 2000s, cardiac MRI, body MRI, fetal imaging, functional MR imaging became routine exams in many imaging centers. When we can train algorithms to spot and detect many types of abnormalities based on radiology images, why wouldn't we let it do the time-consuming job so we can let radiologists dedicate their precious focus to the hardest issues? By analyzing CT scans from 48 patients, the deep learning algorithms could predict whether they'd die within five years with 69 percent accuracy. Vital also has a similar work-in-progress predictive analytics software for imaging equipment utilization.


The Future of Radiology and Artificial Intelligence - The Medical Futurist

#artificialintelligence

By the early 2000s, cardiac MRI, body MRI, fetal imaging, functional MR imaging became routine exams in many imaging centers. When we can train algorithms to spot and detect many types of abnormalities based on radiology images, why wouldn't we let it do the time-consuming job so we can let radiologists dedicate their precious focus to the hardest issues? By analyzing CT scans from 48 patients, the deep learning algorithms could predict whether they'd die within five years with 69 percent accuracy. IBM's flagship AI analytics platform, Watson is also utilized in the field of radiology.


AI to drive GDP gains of $15.7 trillion with productivity, personalisation improvements

#artificialintelligence

Healthcare: Data-driven diagnostic support: Pandemic identification: Imaging diagnostics (radiology, pathology) Automotive: Autonomous fleets for ride sharing; Smart cars/driver assist; Predictive and autonomous maintenance Financial services: Personalised financial planning; Fraud detection and anti-money laundering; Transaction automation Retail: Personalised design and production; Customer insights generation; Inventory and delivery management Technology, communications and entertainment: Media archiving and search; Content creation (marketing, film, music, etc.); Personalized marketing and advertising Manufacturing; Enhanced monitoring and auto-correction; Supply chain and production optimisation; On-demand production Energy: Smart metering; More efficient grid operation and storage; Intelligent infrastructure maintenance Transport and logistics; Autonomous trucking and delivery: Traffic control and reduced congestion; Enhanced security Methodology: To estimate AI impact, our team conducted a dual-phased top-down and bottom-up analysis combining a detailed assessment of the current and future use of AI and an exploration of the economic impact in terms of new jobs, new products, and other secondary effects. Healthcare: Data-driven diagnostic support: Pandemic identification: Imaging diagnostics (radiology, pathology) Automotive: Autonomous fleets for ride sharing; Smart cars/driver assist; Predictive and autonomous maintenance Financial services: Personalised financial planning; Fraud detection and anti-money laundering; Transaction automation Retail: Personalised design and production; Customer insights generation; Inventory and delivery management Technology, communications and entertainment: Media archiving and search; Content creation (marketing, film, music, etc.); Personalized marketing and advertising Manufacturing; Enhanced monitoring and auto-correction; Supply chain and production optimisation; On-demand production Energy: Smart metering; More efficient grid operation and storage; Intelligent infrastructure maintenance Transport and logistics; Autonomous trucking and delivery: Traffic control and reduced congestion; Enhanced security Healthcare: Data-driven diagnostic support: Pandemic identification: Imaging diagnostics (radiology, pathology) Automotive: Autonomous fleets for ride sharing; Smart cars/driver assist; Predictive and autonomous maintenance Financial services: Personalised financial planning; Fraud detection and anti-money laundering; Transaction automation Retail: Personalised design and production; Customer insights generation; Inventory and delivery management Technology, communications and entertainment: Media archiving and search; Content creation (marketing, film, music, etc.


AI could predict how much time people have left to live by analyzing body scans

#artificialintelligence

For the study, researchers used a machine learning algorithm to analyze routine chest CT scans from 48 adults, all of whom were over 60 years of age. The most immediate application of this AI technology is that it could theoretically analyze more routine chest CT scan data and provide risk calculations without a human expert taking the time to go through each scan. "Our research opens new avenues for the application of artificial intelligence technology in medical image analysis, and could offer new hope for the early detection of serious illness, requiring specific medical interventions." The basic idea behind precision medicine is that large quantities of health data can be analyzed to determine how small differences between people affect their health outcomes.