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

Pulmonary Embolism I: Introduction01:29

Pulmonary Embolism I: Introduction

Pulmonary embolism (PE) occurs when a thrombus, fat or air embolus, amniotic fluid, or tumor tissue blocks one or more pulmonary arteries. These blockages originate in the venous system or the right side of the heart.EtiologyPE primarily arises from deep vein thrombosis (DVT) and other hypercoagulable states, such as inherited thrombophilias. Additional etiological factors include venous stasis, commonly seen in obesity, and endothelial injury from surgery and trauma. Less common causes include...
Pulmonary Embolism II: Diagnostic Studies and Interprofessional Care01:29

Pulmonary Embolism II: Diagnostic Studies and Interprofessional Care

Diagnosing Pulmonary EmbolismDiagnosing pulmonary embolism (PE) involves clinical assessment and advanced imaging tests. The preferred diagnostic tool is the spiral (helical) CT scan or CT angiography (CTA), which uses intravenous contrast media to visualize the pulmonary vasculature and identify emboli.A ventilation-perfusion (V/Q) scan is an alternative for patients unable to receive contrast media. This scan includes both perfusion and ventilation scanning. Perfusion scanning involves...
Pulmonary Embolism I: Introduction01:19

Pulmonary Embolism I: Introduction

A blood clot, or thrombus, is a semi-solid mass composed of fibrin, platelets, and red blood cells. When it forms within a vessel, it can obstruct blood flow, known as thrombosis. If part of the clot detaches, it becomes an embolus that can travel and block distant vessels. When this occurs in the pulmonary arteries, it causes a condition known as pulmonary embolism (PE).Origin and ImpactMost often, the embolus originates from a thrombus in the deep veins of the lower limbs, a condition called...

You might also read

Related Articles

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

Sort by
Same author

Alzheimer's and Parkinson's Detection with Video-Based Hybrid Deep Learning from Brain MRI.

Journal of imaging informatics in medicine·2026
Same author

"Toward a new Era in fracture imaging: zero echo time mri vs ct in intra-articular distal radius fractures - A proof-of-concept study".

Injury·2025
Same author

Estimation of Total Hemoglobin (SpHb) from Facial Videos Using 3D Convolutional Neural Network-Based Regression.

Biosensors·2025
Same author

Ultrasonographic Evaluation of Solid Organ Sizes in Children with Primary Malnutrition: A Preliminary Study.

Journal of clinical medicine·2025
Same author

AI-Enhanced Interface for Colonic Polyp Segmentation Using DeepLabv3+ with Comparative Backbone Analysis.

Biomedical physics & engineering express·2024
Same author

Comparative Bladder Cancer Tissues Prediction Using Vision Transformer.

Journal of imaging informatics in medicine·2024

Related Experiment Video

Updated: Jun 19, 2026

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

14.1K

An Enhanced Mask R-CNN Approach for Pulmonary Embolism Detection and Segmentation.

Kâmil Doğan1, Turab Selçuk2, Ahmet Alkan2

  • 1Department of Radiology, Kahramanmaras Sutcu Imam University, 46050 Onikişubat, Turkey.

Diagnostics (Basel, Switzerland)
|June 19, 2024
PubMed
Summary

This study introduces an enhanced Mask R-CNN deep learning model for automatically detecting pulmonary embolism (PE) in CT scans. The AI system accurately identifies PE in segmental arteries, improving diagnostic capabilities.

Keywords:
CTPA imagesMask R-CNNpulmonary embolism

More Related Videos

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
Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
10:44

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

477

Related Experiment Videos

Last Updated: Jun 19, 2026

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

14.1K
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
Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
10:44

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

477

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Radiology
  • Cardiovascular Disease Diagnostics

Background:

  • Pulmonary embolism (PE) is a life-threatening condition caused by blood clots in pulmonary arteries, with segmental artery PE often missed.
  • Current diagnostic methods for PE can be challenging, particularly for smaller emboli in segmental arteries, impacting patient outcomes.
  • Accurate and timely detection of PE is crucial for effective treatment and reducing mortality rates.

Purpose of the Study:

  • To develop and evaluate an automated computational method for identifying pulmonary embolism (PE) in segmental arteries using computed tomography (CT) images.
  • To enhance the Mask R-CNN deep neural network for improved localization and boundary delineation of PE within CT scans.
  • To compare the performance of the enhanced Mask R-CNN model against traditional Mask R-CNN and U-Net models for PE detection.

Main Methods:

  • Development of an enhanced Mask R-CNN deep neural network architecture.
  • Training the model on a custom dataset of CT images containing pulmonary embolism.
  • Evaluation of model performance using metrics such as sensitivity, specificity, accuracy, Dice coefficient, and Jaccard index, validated against expert radiologist annotations.

Main Results:

  • The enhanced Mask R-CNN model achieved high performance metrics: 96.2% sensitivity, 93.4% specificity, 96.0% accuracy, 0.95 Dice coefficient, and 0.89 Jaccard index.
  • The developed system demonstrated superior performance in detecting and delineating PE in segmental arteries compared to traditional Mask R-CNN and U-Net models.
  • Analysis revealed the significant impact of the loss function on the Mask R-CNN model's performance in CT image analysis.

Conclusions:

  • The enhanced Mask R-CNN model offers a robust and accurate automated solution for detecting pulmonary embolism in segmental arteries from CT images.
  • This AI-driven approach has the potential to improve the diagnostic accuracy and efficiency of PE detection, especially in challenging cases.
  • Further research into optimizing Mask R-CNN loss functions can enhance its utility for object detection and segmentation tasks in medical imaging.