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

Magnetic Resonance Imaging01:24

Magnetic Resonance Imaging

8.8K
Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...
8.8K

You might also read

Related Articles

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

Sort by
Same author

Atrial fibrillation during palliative chemotherapy with utidelone: a case report.

Frontiers in oncology·2026
Same author

Development and validation of a computed tomography myocardial perfusion imaging radiomic model for major adverse cardiovascular events prediction: a multicenter study.

European heart journal. Cardiovascular Imaging·2026
Same author

Knowledge, attitude and practice toward postoperative upper limb exercise among patients undergoing axillary lymph node dissection for breast cancer.

BMC public health·2025
Same author

Breast MRI and Mammography Registration based on Breast Biomechanical FEM and Edge-Guided Unsupervised Registration Network.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

The Different Effects of Firsthand Pain and Nonpain Electrical Stimulation on Pain Empathy: An EEG Study.

Pain research & management·2025
Same author

Loss of CsCLV2 function causes dwarfism and determinates growth in cucumber.

The Plant journal : for cell and molecular biology·2025

Related Experiment Video

Updated: Dec 26, 2025

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

23.0K

A knowledge-driven feature learning and integration method for breast cancer diagnosis on multi-sequence MRI.

Hongwei Feng1, Jiaqi Cao1, Hongyu Wang2

  • 1Department of Information Science and Technology, Northwest University, Xi'an, Shaanxi 710127, China.

Magnetic Resonance Imaging
|March 17, 2020
PubMed
Summary

A new Knowledge-driven Feature Learning and Integration (KFLI) framework improves breast lesion classification on multi-sequence Magnetic Resonance Imaging (MRI). This approach enhances diagnostic accuracy by integrating domain knowledge with deep learning for better breast cancer detection.

Keywords:
Breast cancer diagnosisDeep learningFeature learningKnowledge-drivenMulti-sequence MRI

More Related Videos

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

7.3K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.6K

Related Experiment Videos

Last Updated: Dec 26, 2025

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

23.0K
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

7.3K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.6K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Radiology

Background:

  • Classifying benign versus malignant breast lesions using multi-sequence Magnetic Resonance Imaging (MRI) is complex due to lesion heterogeneity.
  • Current deep learning methods for breast lesion diagnosis lack domain knowledge, limiting feature comprehensiveness and clinical relevance.
  • Existing data-driven approaches struggle to extract features that directly correlate with clinically significant phenomena in breast cancer diagnosis.

Purpose of the Study:

  • To develop a Knowledge-driven Feature Learning and Integration (KFLI) framework for improved discrimination between benign and malignant breast lesions.
  • To leverage radiologists' cognitive processes to guide feature extraction in multi-sequence MRI for breast cancer diagnosis.
  • To enhance the diagnostic performance of AI models by incorporating domain expertise into deep learning frameworks.

Main Methods:

  • The KFLI framework divides MRI sequences based on characteristics and uses domain knowledge to guide feature learning.
  • Deep networks are employed to extract distinct sub-sequence features, constraining feature vectors to characteristic-related semantic spaces.
  • An adaptive weighting module integrates features from different sub-sequence images for comprehensive breast cancer diagnosis.

Main Results:

  • The KFLI framework, combining domain knowledge and deep network ensembles, extracts sufficient and effective features for comprehensive breast cancer diagnosis.
  • Experiments on 100 MRI studies demonstrated the KFLI framework's superior performance compared to state-of-the-art algorithms.
  • The KFLI achieved a sensitivity of 84.6%, specificity of 85.7%, and accuracy of 85.0% in classifying breast lesions.

Conclusions:

  • The KFLI framework offers a robust approach for breast lesion classification by integrating domain knowledge with deep learning on multi-sequence MRI.
  • This knowledge-driven method enhances the comprehensiveness and clinical relevance of extracted features, leading to improved diagnostic accuracy.
  • The KFLI framework represents a significant advancement in AI-assisted breast cancer diagnosis using medical imaging.