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

Imaging Studies II: Positron Emission Tomography and Scintigraphy01:25

Imaging Studies II: Positron Emission Tomography and Scintigraphy

853
Positron Emission Tomography (PET) is a medical imaging technique that provides crucial insights into the body's physiological functions at a molecular level. It is an indispensable resource for diagnosing, staging, and monitoring various illnesses, notably cancer, neurological disorders, and cardiovascular conditions.
Fundamental Principles of PET
853
Imaging Studies III: Computed Tomography01:27

Imaging Studies III: Computed Tomography

893
DefinitionComputed Tomography (CT) of the genitourinary (GU) tract is a non-invasive imaging modality that utilizes X-rays and computer processing to generate detailed cross-sectional images of the urinary system, encompassing the kidneys, ureters, bladder, and adjacent structures such as the adrenal glands.PurposeCT scans of the GU tract serve several diagnostic and therapeutic purposes, including:Diagnosis of Urinary Tract Diseases: Detects kidney stones, tumors, cysts, and congenital...
893

You might also read

Related Articles

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

Sort by
Same author

Effects of Ridge and Furrow Planting Patterns on Crop Yield and Grain Quality in Dryland Maize-Wheat Double Cropping System.

Plants (Basel, Switzerland)·2025
Same author

Long-Term Rotary Tillage and Straw Mulching Enhance Dry Matter Production, Yield, and Water Use Efficiency of Wheat in a Rain-Fed Wheat-Soybean Double Cropping System.

Plants (Basel, Switzerland)·2025
Same author

Mycobacterium tuberculosis Infection in School Contacts of Tuberculosis Cases: A Systematic Review and Meta-Analysis.

The American journal of tropical medicine and hygiene·2024
Same author

Automatic intracranial abnormality detection and localization in head CT scans by learning from free-text reports.

Cell reports. Medicine·2023
Same author

Three-dimensional magnetic assembly of microscale hydrogels.

Advanced materials (Deerfield Beach, Fla.)·2011
Same author

The assembly of cell-encapsulating microscale hydrogels using acoustic waves.

Biomaterials·2011

Related Experiment Video

Updated: May 5, 2026

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

6.8K

Multi-Grained Radiology Report Generation With Sentence-Level Image-Language Contrastive Learning.

Aohan Liu, Yuchen Guo, Jun-Hai Yong

    IEEE Transactions on Medical Imaging
    |March 4, 2024
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a novel framework for automatic radiology report generation using multi-grained contrastive learning. The method improves accuracy without extra manual labels, enhancing clinical decision-making.

    More Related Videos

    Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
    05:56

    Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

    Published on: April 14, 2023

    2.5K
    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
    03:14

    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

    Published on: December 6, 2024

    555

    Related Experiment Videos

    Last Updated: May 5, 2026

    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

    6.8K
    Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
    05:56

    Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

    Published on: April 14, 2023

    2.5K
    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
    03:14

    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

    Published on: December 6, 2024

    555

    Area of Science:

    • Medical Imaging
    • Artificial Intelligence
    • Natural Language Processing

    Background:

    • Automatic radiology report generation is crucial but challenging due to data imbalance and complex report structures.
    • Existing methods often require expensive manual annotations to address these challenges.
    • Accurate generation of abnormal findings in radiology reports remains a significant hurdle.

    Purpose of the Study:

    • To propose a novel multi-grained report generation framework using sentence-level image-sentence contrastive learning.
    • To improve the accuracy of automatic radiology report generation without relying on additional manual annotations.
    • To effectively learn from image-report pairs by capturing fine-grained image features relevant to specific report topics.

    Main Methods:

    • Implemented a multi-grained report generation framework with sentence-level image-sentence contrastive learning.
    • Utilized contrastive learning for image feature extraction, focusing on sentence topics and contents for fine-grained analysis.
    • Employed a two-decoder approach for generating coarse sentence topics followed by fine-grained text, supervised by contrastive objectives and refined with reinforcement learning.

    Main Results:

    • The proposed framework demonstrated superior performance over state-of-the-art methods on MIMIC-CXR and IU-Xray datasets.
    • Evaluations using both language generation metrics and clinical accuracy confirmed the effectiveness of the approach.
    • The fine-grained contrastive learning approach successfully learned distinct abnormal image features for specific topics.

    Conclusions:

    • The multi-grained report generation framework significantly enhances the accuracy of automatic radiology report generation.
    • Sentence-level image-sentence contrastive learning offers an effective labeling-free approach to learn from medical image-report data.
    • The method shows promise for improving clinical decision support through more accurate and detailed radiology reports.