Medical Design and Outsourcing

  • Home
  • Medical Device Business
    • Mergers & Acquisitions
    • Financial
    • Regulatory
  • Applications
    • Cardiovascular
    • Devices
    • Imaging
    • Implantables
    • Medical Equipment
    • Orthopedic
    • Surgical
  • Technologies
    • Supplies and Components Index
    • Contract Manufacturing
    • Components
    • Electronics
    • Extrusions
    • Materials
    • Motion Control
    • Prototyping
    • Pumps
    • Tubing
  • MedTech Resources
    • Medtech Events in 2025
    • The 2024 Medtech Big 100
    • Medical Device Handbook
    • MedTech 100 Index
    • Subscribe to Print Magazine
    • DeviceTalks
    • Digital Editions
    • eBooks
    • Educational Assets
    • Manufacturer Search
    • Podcasts
    • Print Subscription
    • Webinars / Digital Events
    • Whitepapers
    • Voices
    • Video
  • 2025 Leadership
    • 2024 Winners
    • 2023 Winners
    • 2022 Winners
    • 2021 Winners
  • Women in Medtech
  • Advertise
  • Subscribe

NIH gives cancer detection a gigantic image boost

July 23, 2018 By Nancy Crotti

NIH cancer detection

Visualization of the lesion embeddings on the DeepLesion test set. Colors indicate manually labeled lesion types. [Image courtesy of NIH]

The National Institutes of Health (NIH) has made public more than 32,000 annotated cancer lesions identified on CT images to help radiologists improve their cancer-detection accuracy.

Large enough to train a deep neural network, the DeepLesion database could enable the scientific community to create a large-scale universal lesion detector with one unified framework, according to an NIH statement. The proposed lesion detector achieves a sensitivity of 81.1% with five false positives per image, the researchers wrote in their study, published in the Journal of Medical Imaging.

DeepLesion contains 32,735 lesions in 32,120 CT slices from 10,594 studies of 4,427 unique, anonymized patients. It contains a variety of lesion types, including lung nodules, liver tumors and enlarged lymph nodes. Most publicly available medical image datasets have fewer than 1,000 images, according to NIH’s Clinical Center, where the research took place.

Scientists used radiologists’ electronic bookmarks of clinically meaningful findings to develop DeepLesion. The bookmarks are complex and full of retrospective medical data. They indicate radiologists’ measurements and markings, such as arrows, lines, diameters and text that indicate a lesion’s exact location and size so experts can identify growth or new disease.

Search engines that collect image labels cannot be applied to the medical image domain, because medical image annotations require extensive clinical experience, the agency said. The researchers’ process is scalable and requires minimum manual annotation effort. They hope others will be able to use the dataset to:

  • Develop a universal lesion detector that will help radiologists find all types of lesions. It may open the possibility to serve as an initial screening tool and send its detection results to other specialist systems trained on certain types of lesions.
  • Mine and study the relationship between different types of lesions. In DeepLesion, multiple findings are often marked in one CT exam image. Researchers are able to analyze their relationship to make new discoveries.
  • More accurately and automatically measure sizes of all lesions a patient has, enabling the whole-body assessment of cancer burden.

The NIH Clinical Center hopes to collect more data for DeepLesion, extend it to other image modalities such as MRI, and combine data from multiple hospitals.  The universal lesion detecting capability will become more reliable once researchers are able to leverage 3-D and lesion type information, researchers said.

Images are available via Box: https://nihcc.box.com/v/DeepLesion

 

Related Articles Read More >

A photo showing Assistant Professor Yeo Kee Thai and KKH Dr. Genevieve Llanora showing the BLIPI device for newborn blood testing.
New device uses single drop of blood to assess newborn immune health
A photo of the probiotic-powered dissolvable batteries.
Probiotics-powered bioresorbable battery can run more than 100 minutes, researchers say
A photo of Capstan Medical's mitral valve implant, which uses nitinol.
Capstan Medical’s R&D head discusses the heart valve and robotics startup’s tech, engineering challenges and solutions, advice for others in medtech and how to join his team
Close-up view of a transparent vascular model held by fingers, showcasing the milli-spinner device — a tiny, hollow rotating tube with fins and slits designed to generate localized suction for shrinking blood clots without rupturing them.
This device could double stroke clot removal success
“mdo
EXPAND YOUR KNOWLEDGE AND STAY CONNECTED
Get the latest medical device business news, application and technology trends.

DeviceTalks Weekly

See More >

MDO Digital Edition

Digital Edition

Subscribe to Medical Design & Outsourcing. Bookmark, share and interact with the leading medical design engineering magazine today.

MEDTECH 100 INDEX

Medtech 100 logo
Market Summary > Current Price
The MedTech 100 is a financial index calculated using the BIG100 companies covered in Medical Design and Outsourcing.
DeviceTalks

DeviceTalks is a conversation among medical technology leaders. It's events, podcasts, webinars and one-on-one exchanges of ideas & insights.

DeviceTalks

New MedTech Resource

Medical Tubing

MassDevice

Mass Device

The Medical Device Business Journal. MassDevice is the leading medical device news business journal telling the stories of the devices that save lives.

Visit Website
MDO ad
Medical Design and Outsourcing
  • MassDevice
  • DeviceTalks
  • MedTech100 Index
  • Medical Tubing + Extrusion
  • Medical Design Sourcing
  • Drug Delivery Business News
  • Drug Discovery & Development
  • Pharmaceutical Processing World
  • R&D World
  • About Us/Contact
  • Advertise With Us
  • Subscribe to Print Magazine
  • Subscribe to our E-Newsletter
  • Listen to our Weekly Podcasts
  • Join our DeviceTalks Tuesdays Discussion

Copyright © 2025 WTWH Media, LLC. All Rights Reserved. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of WTWH Media LLC. Site Map | Privacy Policy | RSS

Search Medical Design & Outsourcing

  • Home
  • Medical Device Business
    • Mergers & Acquisitions
    • Financial
    • Regulatory
  • Applications
    • Cardiovascular
    • Devices
    • Imaging
    • Implantables
    • Medical Equipment
    • Orthopedic
    • Surgical
  • Technologies
    • Supplies and Components Index
    • Contract Manufacturing
    • Components
    • Electronics
    • Extrusions
    • Materials
    • Motion Control
    • Prototyping
    • Pumps
    • Tubing
  • MedTech Resources
    • Medtech Events in 2025
    • The 2024 Medtech Big 100
    • Medical Device Handbook
    • MedTech 100 Index
    • Subscribe to Print Magazine
    • DeviceTalks
    • Digital Editions
    • eBooks
    • Educational Assets
    • Manufacturer Search
    • Podcasts
    • Print Subscription
    • Webinars / Digital Events
    • Whitepapers
    • Voices
    • Video
  • 2025 Leadership
    • 2024 Winners
    • 2023 Winners
    • 2022 Winners
    • 2021 Winners
  • Women in Medtech
  • Advertise
  • Subscribe