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

5.0K
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...
5.0K

You might also read

Related Articles

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

Sort by
Same author

Development and validation of a machine learning-based predictive model for carotid plaque in type 2 diabetes.

Frontiers in cardiovascular medicine·2026
Same author

Corrigendum to "Integrative single-cell analysis reveals Bu-Shen-Huo-Xue Formula rescues iron-overloaded ovarian function via rewiring IFN-γ/JAK/STAT/CXCL10-driven immune-stromal interactions and BNIP3-mediated mitophagy in endometriosis" [Phytomedicine 2026 May:157:158343].

Phytomedicine : international journal of phytotherapy and phytopharmacology·2026
Same author

Echinacoside restores levofloxacin activity against multidrug-resistant Pseudomonas aeruginosa: evidence for iron-responsive siderophore-like properties and membrane disruption.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2026
Same author

Multimodal calcium coordination and transport mechanisms of cod bone-derived novel peptides DYGGEY and GESGEAGDR.

Food chemistry·2026
Same author

Effects of High-Altitude Environments on Gut Microbiota and Their Mechanisms in Immune Regulation and High-Altitude Adaptation.

International journal of molecular sciences·2026
Same author

Distinct UNC13A Haplotype Blocks Define Disease Severity and Survival in Chinese Amyotrophic Lateral Sclerosis.

European journal of neurology·2026

Related Experiment Video

Updated: Jun 11, 2025

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

47.9K

Boosting Deep Learning for Interpretable Brain MRI Lesion Detection through the Integration of Radiology Report

Lisong Dai1, Jiayu Lei1, Fenglong Ma1

  • 1From the Institute of Diagnostic and Interventional Radiology (L.D., Z.S., H.D., J.J., D.W., G.T., X.S., J.Z., Q.Z., Y.L.) and Clinical Research Center (J.W.), Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, 600 Yishan Road, Shanghai 200000, China; Shanghai AI Laboratory, Shanghai, China (J.L., Y.Z.); School of Computer Science and Technology, University of Science and Technology of China, Anhui, China (J.L.); The Pennsylvania State University College of Information Sciences and Technology, University Park, Pa (F.M.); Department of Electrical Engineering, City University of Hong Kong, Hong Kong, China (H.Z.); Department of Radiology, Affiliated Hospital of Nantong University, Nantong, China (J.J.); Department of Radiology, Shanghai Ninth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China (S.A.); Department of Radiology, Shanghai Public Health Clinical Center, Shanghai, China (A.S.); Department of Radiology, Wuhan Hankou Hospital, Wuhan, China (Z.L.); and Cooperative Medianet Innovation Center, Shanghai Jiao Tong University, Shanghai, China (Y.Z.).

Radiology. Artificial Intelligence
|October 8, 2024
PubMed
Summary

Integrating radiology report text into deep learning models significantly improves brain lesion detection accuracy and interpretability. This knowledge-driven approach enhances diagnostic capabilities for medical imaging analysis.

Keywords:
Brain MRIComputer-aided DiagnosisDeep LearningKnowledge-driven ModelRadiology Report

More Related Videos

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.2K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K

Related Experiment Videos

Last Updated: Jun 11, 2025

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

47.9K
Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.2K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K

Area of Science:

  • Artificial Intelligence in Medical Imaging
  • Machine Learning for Diagnostic Support
  • Radiology and Neuroradiology

Background:

  • Deep learning (DL) models show promise in analyzing brain MRI scans for lesion detection.
  • Interpretability and generalizability of DL models in medical diagnostics remain challenges.
  • Radiology reports contain valuable textual information that can potentially guide DL model attention.

Purpose of the Study:

  • To enhance the interpretability and accuracy of deep learning-based brain lesion detection.
  • To guide DL model attention towards specific MRI characteristics of brain lesions using textual features from radiology reports.
  • To develop and evaluate a knowledge-driven DL model (ReportGuidedNet) against a standard DL model (PlainNet).

Main Methods:

  • Retrospective analysis of 35,282 brain MRI scans and reports for training/internal testing.
  • External testing on 2,655 brain MRI scans from multiple centers.
  • Development of ReportGuidedNet incorporating textual features from reports and PlainNet without textual features.
  • Performance evaluation using macro-averaged AUC (ma-AUC) and micro-averaged AUC (mi-AUC).
  • Assessment of model attention maps using a five-point Likert scale.

Main Results:

  • ReportGuidedNet significantly outperformed PlainNet on both internal and external test sets across all diagnoses (e.g., internal ma-AUC: 0.93 vs 0.85).
  • The performance gap between internal and external testing was smaller for ReportGuidedNet, indicating better generalizability (Δma-AUC: 0.03 vs 0.10).
  • ReportGuidedNet demonstrated higher interpretability scores compared to PlainNet (Likert scale: 2.50 ± 1.09 vs 1.32 ± 1.20; P < .001).

Conclusions:

  • Integrating textual features from radiology reports into DL models improves brain lesion detection performance.
  • The knowledge-driven approach enhances model interpretability and generalizability, crucial for clinical applications.
  • This method offers a promising strategy for developing more reliable and understandable AI tools in medical imaging.