Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Difference from Background: Limit of Detection01:05

Difference from Background: Limit of Detection

6.7K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
6.7K
Instrument Calibration01:12

Instrument Calibration

233
Instrument calibration is essential for ensuring that instruments produce accurate and consistent results. It is vital in manufacturing, healthcare, testing laboratories, and scientific research. Calibration processes are specific to each instrument and help enhance data accuracy. Each instrument has a unique calibration process tailored to its design and function to improve data accuracy.
Analytical Balance Calibration
An analytical balance measures mass and requires regular calibration to...
233

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Integrating Participatory Social Innovation Into Requirements Engineering for AI Health Care Solutions: Case Study.

Journal of medical Internet research·2026
Same author

STHLM3 NorDCaP: prospective multicentre trial of Stockholm3 for active surveillance biopsy guidance.

BJU international·2026
Same author

A Non-Invasive Gas Exchange Monitor To Assess Swimming-Induced Pulmonary Edema.

Undersea & hyperbaric medicine : journal of the Undersea and Hyperbaric Medical Society, Inc·2026
Same author

Stockholm3-Magnetic Resonance Imaging Population-Based Prostate Cancer Screening Study: Two-Year Follow-up.

Annals of internal medicine·2026
Same author

Artificial Intelligence Detection Scores in Screening Mammography for Early Breast Cancer Alerts.

Radiology·2026
Same author

Laterality of Swimming-Induced Pulmonary Edema During Combat Sidestroke Assessed by Lung Ultrasound and Chest Radiography.

Chest·2026

Related Experiment Video

Updated: Aug 3, 2025

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.8K

Implications for downstream workload based on calibrating an artificial intelligence detection algorithm by

Karin Dembrower1, Mattie Salim2, Martin Eklund3

  • 1Capio S:t Göran Hospital, Department of Radiology, Stockholm, Sweden.

Journal of Medical Imaging (Bellingham, Wash.)
|April 10, 2023
PubMed
Summary
This summary is machine-generated.

Choosing the right operating point for artificial intelligence (AI) in mammogram screening is crucial. Matching AI sensitivity to a radiologist nearly doubles workload, while matching combined AI-human sensitivity offers a modest 15% increase.

Keywords:
artificial intelligencebreast cancer screeningcalibrationcomputer-aided detectionimplementation

More Related Videos

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles
11:54

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Published on: March 13, 2017

9.4K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.9K

Related Experiment Videos

Last Updated: Aug 3, 2025

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.8K
Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles
11:54

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Published on: March 13, 2017

9.4K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.9K

Area of Science:

  • Radiology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Screening mammograms are essential for early breast cancer detection.
  • Double-reading by two radiologists is standard practice to improve accuracy.
  • Artificial intelligence (AI) offers potential to assist or replace one human reader.

Purpose of the Study:

  • To evaluate the impact of different operating points for AI algorithms in screening mammography.
  • To compare workload and cancer detection rates between AI-human and human-human reading pairs.
  • To determine the optimal AI operating point for efficient and effective double-reading.

Main Methods:

  • Retrospective analysis of full-field digital screening mammograms from Stockholm County (2012-2015).
  • Inclusion of exams from women with breast cancer and healthy controls.
  • Generation of an exam-level AI abnormality score using Insight MMG (Lunit Inc).
  • Estimation of sensitivity and abnormal interpretation rates for two AI operating point strategies: standalone-reader matching and combined-reader matching.

Main Results:

  • The study included 1684 cancer cases and 5024 controls.
  • Human reader sensitivity ranged from 69.7% to 78.6% with interpretation rates of 4.4% to 6.1%.
  • Reader 1 + AI achieved 82.4% sensitivity at 12.6% interpretation rate (standalone matching).
  • Reader 1 + AI achieved 78.6% sensitivity at 7.0% interpretation rate (combined matching).

Conclusions:

  • Setting the AI operating point to match standalone radiologist sensitivity nearly doubles downstream workload.
  • Matching sensitivity between combined AI-human and two human readers results in a modest 15% workload increase.
  • The combined-reader matching approach is more efficient for AI integration in mammography screening.