We've noticed that you're using an ad blocker

Our content is brought to you free of charge because of the support of our advertisers. To continue enjoying our content, please turn off your ad blocker.

It's off now Dismiss How do I disable my ad blocker?
❌

How to disable your ad blocker for our site:

Adblock / Adblock Plus
  • Click on the AdBlock / AdBlock Plus icon on the top right of your browser.
  • Click “Don’t run on pages on this domain.” OR “Enabled on this site.”
  • Close this help box and click "It's off now".
Firefox Tracking Prevention
  • If you are Private Browsing in Firefox, "Tracking Protection" may casue the adblock notice to show. It can be temporarily disabled by clicking the "shield" icon in the address bar.
  • Close this help box and click "It's off now".
Ghostery
  • Click the Ghostery icon on your browser.
  • In Ghostery versions < 6.0 click “Whitelist site.” in version 6.0 click “Trust site.”
  • Close this help box and click "It's off now".
uBlock / uBlock Origin
  • Click the uBlock / uBlock Origin icon on your browser.
  • Click the “power” button in the menu that appears to whitelist the current website
  • Close this help box and click "It's off now".
  • Topics
  • Image IQ
  • Case Studies
  • Blog
  • Conferences
  • Editorial Board
  • DI Executive

Modern Medicine Network
  • Login
  • Register
Skip to main content
Modern Medicine Network
  • Login
  • Register
Menu
User
Home
  • Topics
  • Image IQ
  • Case Studies
  • Blog
  • Conferences
  • Editorial Board
  • DI Executive

SUBSCRIBE: eNewsletter

Two-Step System Improves CAD in Breast Cancer Diagnosis

  • Diagnostic Imaging Staff
Mar 1, 2016
  • MRI, Breast Imaging, CAD, DI Executive

Optimizing both feature selection and training classifiers for mass and nonmass lesions improves the accuracy of computer-aided diagnosis (CAD) for breast MR imaging, according to a study published in Radiology.

Researchers from Canada sought to determine suitable features and optimal classifier design for a CAD system to help clinicians differentiate between mass and nonmass enhancements detected by contrast MRI breast imaging.

The researchers respectively collected 280 histologically proven mass lesions and 129 histologically proven nonmass lesions determined through MR imaging studies. The Breast Imaging Reporting and Data System classification of mass and nonmass enhancement was obtained from radiologic reports.

After extracting 176 features, the researchers ranked them according to kinetic, texture, and morphologic features for mass and nonmass lesions. They found that the best classifier performance was a two-stage cascade classifier, whereby the researchers used mass versus nonmass followed by malignant versus benign classification, as compared with a single, or one-shot, classifier, which was benign versus malignant. “Our proposed two-stage cascade classifier decreases the overall misclassification rate by 12 percent, with 72 of 409 missed diagnoses with cascade versus 82 of 409 missed diagnoses with one-shot classifier,” the authors wrote.

By separating the optimizing features, the researchers found that breast MR imaging with CAD was improved over using a one-shot classifier. They suggested that this may provide an advantage to women who are at high risk for developing breast cancer.

Related Articles

  • Microwave Imaging Shows Great Potential
  • Restricting Screening Mammography Based on Risk May Miss Cancers
  • Could Novel Hybrid Imaging Predict Breast Cancer Prognosis?
  • DBT Screening and BI-RADS Category 3 Classification
  • High BMI and Frequency of Breast Cancer Screening

Resource Topics rightRail

  • Resource Topics
  • Partner Content
Philips Partner Perspective
RSNA 2017
Health Care Executive Toolkit: Resources to take immediate action on quality and cost
[EXCLUSIVE] Healthcare Executive Guide: Should physicians assign their own codes? The practical guide to striking a coding balance
Navigating the coder shortage
The New Healthcare Consumer - Riding The Sea Change
7 Strategies to Slash Your Denial Rate
Connect with Us
  • Twitter
  • Facebook
  • Google+
  • RSS
Modern Medicine Network
  • Home
  • About Us
  • Advertise
  • Advertiser Terms
  • Privacy statement
  • Terms & Conditions
  • Editorial & Advertising Policy
  • Editorial Board
  • Contact Us
Modern Medicine Network
© UBM 2018, All rights reserved.
Reproduction in whole or in part is prohibited.