• 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
    FDA OKs World's First Single-Use Duodenoscope

    Dr. Stephen Hahn Confirmed as New FDA Leader

    FDA OKs First Test to Help Screen for Newborn Duchenne Muscular Dystrophy

    MedStar Health and Cleveland Clinic Innovations Awarded Grant

    3M to Sell Drug Delivery Business for $650M
    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
    Glenbrook Technologies Inc.

    Nelson Laboratories LLC

    Lyons

    GS Plastic Optics

    MicroLumen Inc.
    MPO Summit
    Industry Events
    Webinars
    Live From Show Event
    Industry Associations
    Videos
    Career Central
    eBook
    Slideshows
    Top Resources
    EU's MDR: Irresistible Force Meets Immovable Object

    Ladies First: An Examination of the Women's Health Device Industry

    Localizing Medical Devices

    Sounding Board: Looking Back at 2019 and Gazing at 2020

    Understanding Key Processes for Mixing APIs with Silicone
    Companies
    News Releases
    Product Releases
    Press Releases
    Product Spec Sheets
    Service Releases
    Case Studies
    White Papers
    Brochures
    Videos
    Outsourcing Directory
    Zeus

    Carclo Technical Plastics

    Halkey-Roberts Corporation

    Fusion Biotec Inc.

    RJG Inc.
    • 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

    Algorithm Makes 3D Image Comparison Process up to 1,000 Times Faster

    The algorithm works by “learning” while registering thousands of pairs of images.

    Algorithm Makes 3D Image Comparison Process up to 1,000 Times Faster
    MIT researchers describe a machine-learning algorithm that can register brain scans and other 3D images more than 1,000 times more quickly using novel learning techniques.
    Related CONTENT
    • New AI Tech Significantly Boosts Kidney Analysis
    • Ultrathin Needle Delivers Drugs Directly to the Brain
    • CRISPR-Based Tool Uses Paper Strips to Detect Genetic Signatures
    • Practical Matters: A Look at Medical Device Materials
    • New Brain Scanner Lets Patients Move Freely for the First Time
    Rob Matheson, MIT News Office06.18.18
    Medical image registration is a common technique that involves overlaying two images, such as magnetic resonance imaging (MRI) scans, to compare and analyze anatomical differences in great detail. If a patient has a brain tumor, for instance, doctors can overlap a brain scan from several months ago onto a more recent scan to analyze small changes in the tumor’s progress.
     
    This process, however, can often take two hours or more, as traditional systems meticulously align each of potentially a million pixels in the combined scans. In a pair of upcoming conference papers, MIT researchers describe a machine-learning algorithm that can register brain scans and other 3D images more than 1,000 times more quickly using novel learning techniques.
     
    The algorithm works by “learning” while registering thousands of pairs of images. In doing so, it acquires information about how to align images and estimates some optimal alignment parameters. After training, it uses those parameters to map all pixels of one image to another, all at once. This reduces registration time to a minute or two using a normal computer, or less than a second using a GPU with comparable accuracy to state-of-the-art systems.
     
    “The tasks of aligning a brain MRI shouldn’t be that different when you’re aligning one pair of brain MRIs or another,” said co-author on both papers Guha Balakrishnan, a graduate student in MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and Department of Engineering and Computer Science (EECS). “There is information you should be able to carry over in how you do the alignment. If you’re able to learn something from previous image registration, you can do a new task much faster and with the same accuracy.”
     
    The papers are being presented at the Conference on Computer Vision and Pattern Recognition (CVPR), held this week, and at the Medical Image Computing and Computer Assisted Interventions Conference (MICCAI), held in September. Co-authors are: Adrian Dalca, a postdoc at Massachusetts General Hospital and CSAIL; Amy Zhao, a graduate student in CSAIL; Mert R. Sabuncu, a former CSAIL postdoc and now a professor at Cornell University; and John Guttag, the Dugald C. Jackson Professor in Electrical Engineering at MIT.
     
    Retaining Information
    MRI scans are basically hundreds of stacked 2D images that form massive 3D images, called “volumes,” containing a million or more 3D pixels, called “voxels.” Therefore, it’s very time-consuming to align all voxels in the first volume with those in the second. Moreover, scans can come from different machines and have different spatial orientations, meaning matching voxels is even more computationally complex.
     
    “You have two different images of two different brains, put them on top of each other, and you start wiggling one until one fits the other. Mathematically, this optimization procedure takes a long time,” said Dalca, senior author on the CVPR paper and lead author on the MICCAI paper.
     
    This process becomes particularly slow when analyzing scans from large populations. Neuroscientists analyzing variations in brain structures across hundreds of patients with a particular disease or condition, for instance, could potentially take hundreds of hours.
     
    That’s because those algorithms have one major flaw: They never learn. After each registration, they dismiss all data pertaining to voxel location. “Essentially, they start from scratch given a new pair of images,” Balakrishnan said. “After 100 registrations, you should have learned something from the alignment. That’s what we leverage.”
     
    The researchers’ algorithm, called “VoxelMorph,” is powered by a convolutional neural network (CNN), a machine-learning approach commonly used for image processing. These networks consist of many nodes that process image and other information across several layers of computation.
     
    In the CVPR paper, the researchers trained their algorithm on 7,000 publicly available MRI brain scans and then tested it on 250 additional scans.
     
    During training, brain scans were fed into the algorithm in pairs. Using a CNN and modified computation layer called a spatial transformer, the method captures similarities of voxels in one MRI scan with voxels in the other scan. In doing so, the algorithm learns information about groups of voxels—such as anatomical shapes common to both scans—which it uses to calculate optimized parameters that can be applied to any scan pair.
     
    When fed two new scans, a simple mathematical “function” uses those optimized parameters to rapidly calculate the exact alignment of every voxel in both scans. In short, the algorithm’s CNN component gains all necessary information during training so that, during each new registration, the entire registration can be executed using one, easily computable function evaluation.
     
    The researchers found their algorithm could accurately register all of their 250 test brain scans—those registered after the training set—within two minutes using a traditional central processing unit, and in under one second using a graphics processing unit.
     
    Importantly, the algorithm is “unsupervised,” meaning it doesn’t require additional information beyond image data. Some registration algorithms incorporate CNN models but require a “ground truth,” meaning another traditional algorithm is first run to compute accurate registrations. The researchers’ algorithm maintains its accuracy without that data.
     
    The MICCAI paper develops a refined VoxelMorph algorithm that “says how sure we are about each registration,” Balakrishnan said. It also guarantees the registration “smoothness,” meaning it doesn’t produce folds, holes, or general distortions in the composite image. The paper presents a mathematical model that validates the algorithm’s accuracy using something called a Dice score, a standard metric to evaluate the accuracy of overlapped images. Across 17 brain regions, the refined VoxelMorph algorithm scored the same accuracy as a commonly used state-of-the-art registration algorithm, while providing runtime and methodological improvements.
     
    Beyond Brain Scans
    The speedy algorithm has a wide range of potential applications in addition to analyzing brain scans, the researchers said. MIT colleagues, for instance, are currently running the algorithm on lung images.
     
    The algorithm could also pave the way for image registration during operations. Various scans of different qualities and speeds are currently used before or during some surgeries. But those images are not registered until after the operation. When resecting a brain tumor, for instance, surgeons sometimes scan a patient’s brain before and after surgery to see if they’ve removed all the tumor. If any bit remains, they’re back in the operating room.
     
    With the new algorithm, Dalca said, surgeons could potentially register scans in near real-time, getting a much clearer picture on their progress. “Today, they can’t really overlap the images during surgery, because it will take two hours, and the surgery is ongoing” he said. “However, if it only takes a second, you can imagine that it could be feasible.”
    Related Searches
    • brain
    • standard
    • it
    • mri
    Related Knowledge Center
    • Digital Health
    • Neurological
    • Software & IT
    Suggested For You
    Fake Kidneys Guide the Way for Fake Kidneys Guide the Way for 'Impossible' Cancer Surgery
    Wireless System Can Power and Communicate with Tiny Devices Inside the Body Wireless System Can Power and Communicate with Tiny Devices Inside the Body
    MIT Engineers Design Color-Changing Compression Bandage MIT Engineers Design Color-Changing Compression Bandage
    Study: AI Outperforms Dermatologists at Diagnosing Skin Cancer Study: AI Outperforms Dermatologists at Diagnosing Skin Cancer
    Ingestible Ingestible 'Bacteria on a Chip' Could Help Diagnose GI Disease
    Modular Blocks Could Enable Modular Blocks Could Enable 'Plug and Play' Diagnostic Devices
    Calcium-Based MRI Sensor Increases Sensitivity of Brain Imaging Calcium-Based MRI Sensor Increases Sensitivity of Brain Imaging
    3D Printing Models Help Predict Leaks Following TAVR Procedures 3D Printing Models Help Predict Leaks Following TAVR Procedures
    Second Sight Appoints Chief Financial Officer Second Sight Appoints Chief Financial Officer
    RenovaCare Board of Directors Elects Majority Stockholder as Chairman RenovaCare Board of Directors Elects Majority Stockholder as Chairman
    Specialized Examination Device Created for Doctors with Limited Mobility Specialized Examination Device Created for Doctors with Limited Mobility
    Second Sight Medical Products Appoints Board Chairman Second Sight Medical Products Appoints Board Chairman
    Deep Learning Transforms Smartphone Microscopes into Laboratory-Grade Devices Deep Learning Transforms Smartphone Microscopes into Laboratory-Grade Devices
    New Blood Test Can Help Identify People at Risk for Developing Alzheimer New Blood Test Can Help Identify People at Risk for Developing Alzheimer's
    Portable Monitor Detects Dangerously Low White Blood Cell Levels Portable Monitor Detects Dangerously Low White Blood Cell Levels

    Related Breaking News

    • Neurological
      First U.S. Patient Implanted With Axonics

      First U.S. Patient Implanted With Axonics' Sacral Neuromodulation System

      The Axonics r-SNM System is approximately the size of a USB stick and is qualified to operate for at least 15 years.
      Businesswire 12.12.19

    • Digital Health
      New Pocket Ultrasound Scanners Smaller, More Powerful, and More Affordable

      New Pocket Ultrasound Scanners Smaller, More Powerful, and More Affordable

      Easier to use, second-generation ultra portable wireless scanners give doctors a clearer picture of what's going on.
      PR Newswire 12.12.19

    • Digital Health | Software & IT
      15-Year Tele-Critical Care Collabration Yields Significant ICU Improvement Results

      15-Year Tele-Critical Care Collabration Yields Significant ICU Improvement Results

      Florida’s first eICU, powered by Philips telehealth technology, touts reduced mortality rates and hospital stays for the sickest patients.
      GlobeNewswire 12.11.19


    • 3D/Additive Manufacturing | Software & IT
      Prellis Biologics

      Prellis Biologics' New Tool Simplifies Complex Tissue Engineering

      TissueWorkshop generates complex 3D scaffolds that can be printed with any 3D printing system.
      Krause Taylor Associates 12.11.19

    • Neurological
      FDA Approves First Nasal Rescue Treatment for Frequent Seizure Activity

      FDA Approves First Nasal Rescue Treatment for Frequent Seizure Activity

      Aptar’s Unidose Liquid System can deliver a formulation in an emergency situation quickly and easily and be administered by a non-healthcare professional.
      Business Wire 12.10.19

    • Patient Monitoring | Software & IT
      Roche

      Roche's Blood Glucose Reading Smartphone App Gains CE Mark

      The app determines blood glucose ranges by taking photos with the smartphone camera without the need for a blood glucose meter.
      GlobeNewswire 12.10.19


    • Cardiovascular | Neurological
      Imperative Care Closes a Series C Financing of $85 Million for Stroke Treatments

      Imperative Care Closes a Series C Financing of $85 Million for Stroke Treatments

      The funds will support the commercial launch of the company’s portfolio.
      Imperative Care Inc. 12.10.19

    • 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


    • 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

    • 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

    • Digital Health
      Orbita Launches OrbitaAssist

      Orbita Launches OrbitaAssist

      A voice-powered, AI-driven virtual health assistant.
      PRNewswire 11.21.19


    Breaking News
    • FDA OKs World's First Single-Use Duodenoscope
    • Dr. Stephen Hahn Confirmed as New FDA Leader
    • FDA OKs First Test to Help Screen for Newborn Duchenne Muscular Dystrophy
    • MedStar Health and Cleveland Clinic Innovations Awarded Grant
    • 3M to Sell Drug Delivery Business for $650M
    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

    Deerland Obtains Certification from Australia’s Therapeutic Goods Administration
    OptiMSM Shown to Improve Hair & Nail Appearance and Condition
    DCC Acquires Contract Manufacturer Ion Laboratories
    Coatings World

    Latest Breaking News From Coatings World

    Arkema: Bostik Acquires Danish Company LIP
    Axalta Adds New Epoxy Primer to Tufcote Liquid Industrial Coatings Portfolio
    Chromaflo Technologies Promotes Sergio Duenas to Country Manager of Mexico
    Medical Product Outsourcing

    Latest Breaking News From Medical Product Outsourcing

    FDA OKs World's First Single-Use Duodenoscope
    Dr. Stephen Hahn Confirmed as New FDA Leader
    FDA OKs First Test to Help Screen for Newborn Duchenne Muscular Dystrophy
    Contract Pharma

    Latest Breaking News From Contract Pharma

    Sanofi Awarded $226M by US Gov't for Pandemic Influenza Preparedness
    Amgen Selects Location For R&D Facility
    Arctoris Opens Oxford R&D Facility
    Beauty Packaging

    Latest Breaking News From Beauty Packaging

    Time Features 5 Best Beauty Inventions
    CES 2020 Preview - Innovation Award Honorees in Health & Wellness
    Prada & L’Oréal Sign Long-Term Licensing Deal
    Happi

    Latest Breaking News From Happi

    Cosmetic Assessments Revealed at CIR Panel
    T-Boz Launches CBD Line
    DRF and Flowerkist Develop CBD Range
    Ink World

    Latest Breaking News From Ink World

    Ripon Printers Adds Ricoh Pro C9210
    LogoJet Opens Bogota, Colombia Office
    Canon Solutions America Powers University of Notre Dame Athletics' Printing Capabilities
    Label & Narrow Web

    Latest Breaking News From Label & Narrow Web

    GSE products provide quality assurance for Pharmalabel
    Luminer promotes Heather Bookman to prepress manager
    Materials Exchange launches to solve excess inventory issue
    Nonwovens Industry

    Latest Breaking News From Nonwovens Industry

    DuPont to Acquire Osmosis Specialist
    Nice-Pak to Expand in Indiana
    Hospeco Launches Compact Fem Hy Dispenser
    Orthopedic Design & Technology

    Latest Breaking News From Orthopedic Design & Technology

    FDA OKs First Test to Help Screen for Newborn Duchenne Muscular Dystrophy
    Europe, North America Comprise More Than 80 Percent of Global Bone Marrow Transplantation Demand
    TriMed Closes Out FDA Warning Letter
    Printed Electronics Now

    Latest Breaking News From Printed Electronics Now

    3D Printing Materials Market to Grow at 23.9% CAGR Through 2025: GVR
    Kyocera, TactoTek Collaborate on Injection Molded Structural Electronics Solutions
    Toray Opens R&D Innovation Center for the Future

    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.