• Login
    • Join
  • FOLLOW:
  • Subscribe Free
    • Magazine
    • eNewsletter
    Checkout
    • Magazine
    • News
    • Opinions
    • Top 30
    • Research
    • Supply Chain
    • Device Sectors
    • Directory
    • Events
    • Resources
    • Microsites
    • More
  • Magazine
  • News
  • Opinions
  • Top 30
  • Research
  • Supply Chain
  • Device Sectors
  • Directory
  • Events
  • Resources
  • Microsites
  • Current / Back Issues
    Features
    Editorial
    Digital Edition
    eNewsletter Archive
    Our Team
    Editorial Guidelines
    Reprints
    Subscribe Now
    Advertise Now
    Top Features
    Adding Fabrication Capabilities: Additive Manufacturing for Production Parts

    Delivering the Goods: The Evolving World of Combination Products

    Anxious Undertones: The 2019 Year in Review

    From Art to Science: The Changing Face of Extrusion

    Exact Science: A Micromolding Roundtable
    OEM News
    Supplier News
    Service / Press Releases
    Online Exclusives
    Press Releases
    People in the News
    Product & Service Releases
    Supplier News
    Technical Features
    International News
    Videos
    Product & Service Releases
    Live From Shows
    Top News
    Philips & Paige to Deliver Clinical-Grade AI Applications to Pathology Labs

    Eye Test for Parkinson's Gains Breakthrough Designation

    Biomerics Forms New Business Unit

    J&J's New Monofocal IOL for Cataract Patients with Astigmatism

    FDA OKs MolecuLight's Handheld Fluorescence Imaging Device
    From the Editor
    Blogs
    Guest Opinions
    Top Opinions
    Adding Fabrication Capabilities: Additive Manufacturing for Production Parts

    Delivering the Goods: The Evolving World of Combination Products

    Anxious Undertones: The 2019 Year in Review

    From Art to Science: The Changing Face of Extrusion

    Exact Science: A Micromolding Roundtable
    Top 30 Medical Device Companies
    Market Data
    White Papers
    Top Research
    From Genome Sequencing to the World’s First Portable MRI

    An Update on Digital Health

    ‘If You’re Reading This, You Need to Be at This Meeting’

    Five Steps for Succeeding Globally in Medtech

    Unlocking Market Doors with Real-World Evidence
    3D/Additive Manufacturing
    Contract Manufacturing
    Electronics
    Machining & Laser Processing
    Materials
    Molding
    Packaging & Sterilization
    R&D & Design
    Software & IT
    Testing
    Tubing & Extrusion
    Cardiovascular
    Diagnostics
    Digital Health
    Neurological
    Patient Monitoring
    Surgical
    All Companies
    Categories
    Company Capabilities
    Add New Company
    Outsourcing Directory
    S-Y-M Products Company

    Fusion Biotec Inc.

    IQMS

    Eurofins Medical Device Testing

    MicroLumen Inc.
    MPO Summit
    Industry Events
    Webinars
    Live From Show Event
    Industry Associations
    Videos
    Career Central
    eBook
    Slideshows
    Top Resources
    Understanding Key Processes for Mixing APIs with Silicone

    How to Minimize Color Variations in Your Medical Device

    Don’t Touch: Gesture Tech Is Reshaping How We Interact with Devices

    Revenue-Based Financing: A New Form of Growth Capital

    Pre-Filled Safety Syringes and the Self-Administration Trend
    Companies
    News Releases
    Product Releases
    Press Releases
    Product Spec Sheets
    Service Releases
    Case Studies
    White Papers
    Brochures
    Videos
    Outsourcing Directory
    IQMS

    Glenbrook Technologies Inc.

    NN Life Sciences/Paragon Medical

    Marox Corporation

    Lyons
    • Magazine
      • Current/Back Issues
      • Features
      • Editorial
      • Columns
      • Digital Editions
      • Subscribe Now
      • Advertise Now
    • News
    • Directory
      • All Companies
      • ALL CATEGORIES
      • Industry Associations
      • Company Capabilities
      • Add Your Company
    • Supply Chain
      • 3D/Additive Manufacturing
      • Contract Manufacturing
      • Electronics
      • Machining & Laser Processing
      • Materials
      • Molding
      • Packaging & Sterilization
      • R&D & Design
      • Software & IT
      • Testing
      • Tubing & Extrusion
    • Device Sectors
      • Cardiovascular
      • Diagnostics
      • Digital Health
      • Neurological
      • Patient Monitoring
      • Surgical
    • Top 30 Company Report
    • Expert Insights
    • Slideshows
    • Videos
    • Podcasts
    • Resources
    • eBook
    • Infographics
    • Whitepapers
    • Research
      • White Papers
      • Case Studies
      • Product Spec Sheets
      • Market Data
    • MPO Summit
    • Events
      • Industry Events
      • Live From Show Events
      • Webinars
    • Microsite
      • Companies
      • Product Releases
      • Product Spec Sheets
      • Services
      • White Papers / Tech Papers
      • Press Releases
      • Videos
      • Literature / Brochures
      • Case Studies
    • About Us
      • About Us
      • Contact Us
      • Advertise with Us
      • eNewsletter Archive
      • Privacy Policy
      • Terms of Use
    Breaking News

    From One Brain Scan, More Info for Medical AI

    System helps machine-learning models glean training information for diagnosing and treating brain conditions.

    From One Brain Scan, More Info for Medical AI
    MIT researchers have developed a system that gleans far more labeled training data from unlabeled data, which could help machine-learning models better detect structural patterns in brain scans associated with neurological diseases. The system learns structural and appearance variations in unlabeled scans, and uses that information to shape and mold one labeled scan into thousands of new, distinct labeled scans. Image courtesy of the researchers.
    Related CONTENT
    • The Pace Maker
    • Can Video Game-Based 'Digital Medicine' Help Children with Autism & ADHD?
    • CES 2019: 7 More Health Tech Highlights
    • Blood Test Spots Alzheimer’s Damage Before Symptoms
    • Ingestible, Expanding Pill Monitors Stomach for up to a Month
    Rob Matheson, MIT News Office06.20.19
    MIT researchers have devised a novel method to glean more information from images used to train machine-learning models, including those that can analyze medical scans to help diagnose and treat brain conditions.
     
    An active new area in medicine involves training deep-learning models to detect structural patterns in brain scans associated with neurological diseases and disorders, such as Alzheimer’s disease and multiple sclerosis. But collecting the training data is laborious: All anatomical structures in each scan must be separately outlined or hand-labeled by neurological experts. And, in some cases, such as for rare brain conditions in children, only a few scans may be available in the first place.
     
    In a paper presented at the recent Conference on Computer Vision and Pattern Recognition, the MIT researchers describe a system that uses a single labeled scan, along with unlabeled scans, to automatically synthesize a massive dataset of distinct training examples. The dataset can be used to better train machine-learning models to find anatomical structures in new scans—the more training data, the better those predictions.
     
    The crux of the work is automatically generating data for the “image segmentation” process, which partitions an image into regions of pixels that are more meaningful and easier to analyze. To do so, the system uses a convolutional neural network (CNN), a machine-learning model that’s become a powerhouse for image-processing tasks. The network analyzes a lot of unlabeled scans from different patients and different equipment to “learn” anatomical, brightness, and contrast variations. Then, it applies a random combination of those learned variations to a single labeled scan to synthesize new scans that are both realistic and accurately labeled. These newly synthesized scans are then fed into a different CNN that learns how to segment new images.
     
    “We’re hoping this will make image segmentation more accessible in realistic situations where you don’t have a lot of training data,” said first author Amy Zhao, a graduate student in the Department of Electrical Engineering and Computer Science (EECS) and Computer Science and Artificial Intelligence Laboratory (CSAIL). “In our approach, you can learn to mimic the variations in unlabeled scans to intelligently synthesize a large dataset to train your network.”
     
    There’s interest in using the system, for instance, to help train predictive-analytics models at Massachusetts General Hospital, Zhao said, where only one or two labeled scans may exist of particularly uncommon brain conditions among child patients.
     
    Joining Zhao on the paper are: Guha Balakrishnan, a postdoc in EECS and CSAIL; EECS professors Fredo Durand and John Guttag, and senior author Adrian Dalca, who is also a faculty member in radiology at Harvard Medical School.
     
    The “Magic” Behind the System
    Although now applied to medical imaging, the system actually started as a means to synthesize training data for a smartphone app that could identify and retrieve information about cards from the popular collectable card game, “Magic: The Gathering.” Released in the early 1990s, “Magic” has more than 20,000 unique cards—with more released every few months—that players can use to build custom playing decks.
     
    Zhao, an avid “Magic” player, wanted to develop a CNN-powered app that took a photo of any card with a smartphone camera and automatically pulled information such as price and rating from online card databases. “When I was picking out cards from a game store, I got tired of entering all their names into my phone and looking up ratings and combos,” Zhao said. “Wouldn’t it be awesome if I could scan them with my phone and pull up that information?”
     
    But she realized that’s a very tough computer-vision training task. “You’d need many photos of all 20,000 cards, under all different lighting conditions and angles. No one is going to collect that dataset,” Zhao said.
     
    Instead, Zhao trained a CNN on smaller dataset of around 200 cards, with 10 distinct photos of each card, to learn how to warp a card into various positions. It computed different lighting, angles, and reflections—for when cards are placed in plastic sleeves—to synthesized realistic warped versions of any card in the dataset. It was an exciting passion project, Zhao said: “But we realized this approach was really well-suited for medical images, because this type of warping fits really well with MRIs.”
     
    Mind Warp
    Magnetic resonance images (MRIs) are composed of three-dimensional pixels, called voxels. When segmenting MRIs, experts separate and label voxel regions based on the anatomical structure containing them. The diversity of scans, caused by variations in individual brains and equipment used, poses a challenge to using machine learning to automate this process.
     
    Some existing methods can synthesize training examples from labeled scans using “data augmentation,” which warps labeled voxels into different positions. But these methods require experts to hand-write various augmentation guidelines, and some synthesized scans look nothing like a realistic human brain, which may be detrimental to the learning process.
     
    Instead, the researchers’ system automatically learns how to synthesize realistic scans. The researchers trained their system on 100 unlabeled scans from real patients to compute spatial transformations—anatomical correspondences from scan to scan. This generated as many “flow fields,” which model how voxels move from one scan to another. Simultaneously, it computes intensity transformations, which capture appearance variations caused by image contrast, noise, and other factors.
     
    In generating a new scan, the system applies a random flow field to the original labeled scan, which shifts around voxels until it structurally matches a real, unlabeled scan. Then, it overlays a random intensity transformation. Finally, the system maps the labels to the new structures, by following how the voxels moved in the flow field. In the end, the synthesized scans closely resemble the real, unlabeled scans—but with accurate labels.
     
    To test their automated segmentation accuracy, the researchers used Dice scores, which measure how well one 3D shape fits over another, on a scale of 0 to 1. They compared their system to traditional segmentation methods—manual and automated—on 30 different brain structures across 100 held-out test scans. Large structures were comparably accurate among all the methods. But the researchers’ system outperformed all other approaches on smaller structures, such as the hippocampus, which occupies only about 0.6 percent of a brain, by volume.
     
    “That shows that our method improves over other methods, especially as you get into the smaller structures, which can be very important in understanding disease,” Zhao said. “And we did that while only needing a single hand-labeled scan.”
     
    In a nod to the work’s “Magic” roots, the code is publicly available on Github under the name of one of the game’s cards, “Brainstorm.”
    Related Searches
    • analytics
    • camera
    • imaging
    • artificial intelligence
    Related Knowledge Center
    • Patient Monitoring
    • Neurological
    • Software & IT
    Suggested For You
    Glytec Receives Another Patent Allowance for Therapy Advisor Glytec Receives Another Patent Allowance for Therapy Advisor
    Smartphone App Can Help Detect Huntington Smartphone App Can Help Detect Huntington's Early
    Using AI to Predict Breast Cancer and Personalize Care Using AI to Predict Breast Cancer and Personalize Care
    FDA Approves Boston Scientific FDA Approves Boston Scientific's VICI Venous Stent System
    Imaging System Helps Surgeons Remove Tiny Ovarian Tumors Imaging System Helps Surgeons Remove Tiny Ovarian Tumors
    Diagnosing the Cancer in Medical Imagery Security Diagnosing the Cancer in Medical Imagery Security
    Physician and iTether Create App for Pregnant Women & New Moms with Opioid Addiction Physician and iTether Create App for Pregnant Women & New Moms with Opioid Addiction
    FDA OKs New Device to Help Treat Carbon Monoxide Poisoning FDA OKs New Device to Help Treat Carbon Monoxide Poisoning
    Oxygen-Tracking Method Could Improve Diabetes Treatment Oxygen-Tracking Method Could Improve Diabetes Treatment
    New MRI Sensor Can Image Activity Deep within the Brain New MRI Sensor Can Image Activity Deep within the Brain
    ExThera Medical Elects Two New Board Members ExThera Medical Elects Two New Board Members
    Pill Can Deliver Insulin via Stomach Injection Pill Can Deliver Insulin via Stomach Injection
    Electrifying Healthcare: A Look at Electronics Manufacturing Services for Medtech Electrifying Healthcare: A Look at Electronics Manufacturing Services for Medtech
    Ingestible, Expanding Pill Monitors Stomach for up to a Month Ingestible, Expanding Pill Monitors Stomach for up to a Month
    Blood Test Spots Alzheimer’s Damage Before Symptoms Blood Test Spots Alzheimer’s Damage Before Symptoms

    Related Breaking News

    • Diagnostics | Digital Health | Software & IT
      Philips & Paige to Deliver Clinical-Grade AI Applications to Pathology Labs

      Philips & Paige to Deliver Clinical-Grade AI Applications to Pathology Labs

      Aim is to help pathologists identify, quantify, and characterize cancer in tissue samples and make precise diagnoses more efficiently.
      Philips 12.05.19

    • Diagnostics | Neurological
      Eye Test for Parkinson

      Eye Test for Parkinson's Gains Breakthrough Designation

      The RightEye Vision System identifies ocular tremors that may help to detect the disease at an earlier stage.
      PR Newswire 12.05.19

    • Patient Monitoring
      FDA OKs MolecuLight

      FDA OKs MolecuLight's Handheld Fluorescence Imaging Device

      MolecuLight i:X enables real-time POC visualization of fluorescence in wounds, measures wounds, and digitally records all images and area measurements.
      PR Newswire 12.05.19


    • Diagnostics | Neurological
      RSNA News: MaxQ AI Expands Partnership with GE

      RSNA News: MaxQ AI Expands Partnership with GE

      MaxQ AI’s ACCIPIO ICH and Stroke platform will be integrated into GE Healthcare’s PACS solution.
      MaxQ Al 12.04.19

    • Diagnostics | Neurological
      RSNA News: MaxQ AI to Offer Accipio Applications on Blackford Platform

      RSNA News: MaxQ AI to Offer Accipio Applications on Blackford Platform

      Represents cost savings and increased quality of care.
      MaxQ AI 12.04.19

    • Diagnostics | Neurological
       RSNA News: MaxQ AI’s Software Integrated with Philips

      RSNA News: MaxQ AI’s Software Integrated with Philips' Tech

      The company’s Accipio Intracranial Hemorrhage and stroke software will be added to Philips’ CT systems
      MaxQ 12.04.19


    • Neurological
      The First Implantable Magnetic Resonance Detector

      The First Implantable Magnetic Resonance Detector

      Ultra-fine needle with an integrated chip that is capable of detecting and transmitting nuclear magnetic resonance (NMR) data.
      Max Planck-Gesellschaft 12.03.19

    • 3D/Additive Manufacturing | Patient Monitoring | Surgical
      RSNA News: GE Invests in 3D Printing, Robotic Surgery, and Virtual Patient Monitoring

      RSNA News: GE Invests in 3D Printing, Robotic Surgery, and Virtual Patient Monitoring

      Investments and collaborations in these fields were made with Formlabs, CMR Surgical, and Decisio Health.
      GE Healthcare 12.03.19

    • Cardiovascular | Patient Monitoring
      VivaLNK Wearable Sensor and Software Development Kit Receive CE Mark

      VivaLNK Wearable Sensor and Software Development Kit Receive CE Mark

      The reusable patch weighs only 7.5 grams.
      PRNewswire 12.03.19


    • Software & IT
      Survey Identifies Challenges to Improving Product Development Processes

      Survey Identifies Challenges to Improving Product Development Processes

      81% of medical device companies are not using tools designed for the medical device industry in their quality management processes.
      PRWeb 11.26.19

    • Diagnostics | Digital Health | Patient Monitoring
      Biofourmis Acquires Biovotion AG

      Biofourmis Acquires Biovotion AG

      Creates an integrated comprehensive digital therapeutics solution.
      Biofourmis 11.19.19

    • Neurological
      Theranica Announces U.S. Recycling Partnership

      Theranica Announces U.S. Recycling Partnership

      Partnership advances circular economy by making Nerivio, a prescribed wearable for acute treatment of migraine, recyclable.
      Theranica Bioelectronics 11.19.19

    • Neurological
      Ekso Bionics Unveils EksoNR

      Ekso Bionics Unveils EksoNR

      The next-generation exoskeleton for neurorehabilitation.
      Ekso Bionics 11.18.19

    • Patient Monitoring
      One Patient Monitoring Device Replaces Many Others

      One Patient Monitoring Device Replaces Many Others

      The cosinuss° C-Med measures four of the five vital parameters continuously and accurately in the ear.
      cosinuss° 11.18.19

    • Diagnostics | Materials | Patient Monitoring | Surgical
      Rebranded Avery Dennison Medical Introduces Eight New Solutions at Medica 2019

      Rebranded Avery Dennison Medical Introduces Eight New Solutions at Medica 2019

      The new entity comprises the former Vancive Medical Technologies and Finesse Medical Ltd.
      Avery Dennison Medical 11.18.19


    Breaking News
    • Philips & Paige to Deliver Clinical-Grade AI Applications to Pathology Labs
    • Eye Test for Parkinson's Gains Breakthrough Designation
    • Biomerics Forms New Business Unit
    • J&J's New Monofocal IOL for Cataract Patients with Astigmatism
    • FDA OKs MolecuLight's Handheld Fluorescence Imaging Device
    View Breaking News >
    CURRENT ISSUE

    November/December 2019

    • Adding Fabrication Capabilities: Additive Manufacturing for Production Parts
    • Delivering the Goods: The Evolving World of Combination Products
    • Anxious Undertones: The 2019 Year in Review
    • View More >
    • About Us
    • Privacy Policy
    • Terms And Conditions
    • Contact Us

    follow us

    Subscribe
    Nutraceuticals World

    Latest Breaking News From Nutraceuticals World

    International Scientific Society Calls for Omega-3 Blood Testing in Future Research
    Pharmactive Affron Saffron May Help Relieve Depression Symptoms
    Warmer Temperatures Could Lead to Concerning Levels of Arsenic in Rice
    Coatings World

    Latest Breaking News From Coatings World

    BCF: Coatings Industry Reports Record Improvement in Waste, Recycling, Accident Rates
    BASF Doubling Automotive Refinish Coatings Production Capacity at Jiangmen, China Site
    AkzoNobel’s Wanda Vehicle Refinishes Brand Celebrates 85th Anniversary
    Medical Product Outsourcing

    Latest Breaking News From Medical Product Outsourcing

    Philips & Paige to Deliver Clinical-Grade AI Applications to Pathology Labs
    Eye Test for Parkinson's Gains Breakthrough Designation
    Biomerics Forms New Business Unit
    Contract Pharma

    Latest Breaking News From Contract Pharma

    PhRMA Appoints Federal Advocacy SVP
    CStone Hires Shirley Zhao as GM
    Stevanato Group Begins Construction on TEC
    Beauty Packaging

    Latest Breaking News From Beauty Packaging

    Pantone Names Classic Blue the 2020 Color of the Year
    Burst Launches Black Expanding Dental Floss
    Glossier Enters Nordstrom for the Holidays
    Happi

    Latest Breaking News From Happi

    Raining Rose Expands Exec Team
    Scott’s Sells Personal Care Production Site
    Givaudan Unveils RitualEssenz Brazil
    Ink World

    Latest Breaking News From Ink World

    Geoff Loftus Joins EFI
    Berlin Packaging Wins 2 WorldStar Awards
    Graphic Village Expands Offerings with Canon Solutions America
    Label & Narrow Web

    Latest Breaking News From Label & Narrow Web

    Austrian converter installs first Nilpeter press
    Converters Expo schedules return to Green Bay, WI
    Schreiner MediPharm and PragmatIC form strategic partnership
    Nonwovens Industry

    Latest Breaking News From Nonwovens Industry

    Thrace to Relocate U.S. Capacity
    FiltXPO Speaker Line-Up Announced
    Nölken Incorporates Sustainable Wipes Packaging
    Orthopedic Design & Technology

    Latest Breaking News From Orthopedic Design & Technology

    Orthofix Appoints New Spine Business Leader
    Viant to Halt EtO Sterilization at Michigan Plant by End of Year
    Synaptive Medical's Modus V Expands Into Spine Market
    Printed Electronics Now

    Latest Breaking News From Printed Electronics Now

    IDTechEx Show! Announces Graphene Award Winner
    Avancis, Smit Thermal, HZB, CNRS, Solliace Team for Higher Efficiencies in CIGS
    CES 2020: 'Where Tech Changes Business'

    Copyright © 2019 Rodman Media. All rights reserved. Use of this constitutes acceptance of our privacy policy The material on this site may not be reproduced, distributed, transmitted, or otherwise used, except with the prior written permission of Rodman Media.