Related Experiment Video
Updated: Aug 2, 2026
04:48
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
2.8K
Computer image analysis with artificial intelligence: a practical introduction to convolutional neural networks for
Georgios Kourounis1,2, Ali Ahmed Elmahmudi3, Brian Thomson3
1NIHR Blood and Transplant Research Unit, Newcastle University and Cambridge University, Newcastle upon Tyne, NE1 7RU, United Kingdom.
Postgraduate Medical Journal
|October 5, 2023
Summary
Artificial intelligence, specifically convolutional neural networks (CNNs), enhances healthcare predictions and diagnostics. This review explains CNNs for clinicians, highlighting their use in medical image analysis for improved patient outcomes.
Area of Science:
- Medical Imaging
- Computer Vision
- Artificial Intelligence in Healthcare
Background:
- Convolutional Neural Networks (CNNs) are powerful artificial intelligence tools transforming healthcare.
- Understanding CNNs is crucial for clinicians to leverage AI in medical image analysis.
Approach:
- This review provides a practical explanation of CNNs for a clinical audience.
- It highlights the application and efficacy of CNNs in various medical fields.
Key Points:
- CNNs excel in computer vision tasks, enabling machines to interpret visual data.
- Applications include radiology (pneumonia, embolism, cancer), histopathology (polyps, tumors, malignancies), and medical photography (retinal diseases, skin conditions, polyp detection).
- CNNs offer intraoperative surgical assistance by interpreting anatomy and identifying safe dissection zones.
Conclusions:
- CNN integration in medical image analysis boosts diagnostic accuracy and workflow efficiency.
- It expands access to expert-level analysis, ultimately improving patient and healthcare outcomes.
