Related Experiment Video
Updated: Jun 8, 2026
11:09
Construction of a Realistic, Whole-Body, Three-Dimensional Equine Skeletal Model using Computed Tomography Data
Published on: February 25, 2021
3.1K
Synthetic temporal bone CT generation from UTE-MRI using a cycleGAN-based deep learning model: advancing beyond CT-MR
Sung-Hye You1, Yongwon Cho2,3, Byungjun Kim4
1Department of Radiology, Anam Hospital, Korea University College of Medicine, Seoul, Korea.
European Radiology
|July 18, 2024
Summary
A deep learning model creates synthetic temporal bone CT images from MRI scans. This advancement improves the visualization of key anatomical sites, overcoming MRI
Area of Science:
- Radiology
- Medical Imaging
- Artificial Intelligence
Background:
- Computed tomography (CT) is preferred for temporal bone imaging but has limitations in differentiating pathology.
- Magnetic resonance imaging (MRI) has intrinsic limitations in localizing specific anatomical landmarks within the temporal bone.
Purpose of the Study:
- To develop a deep-learning model for generating synthetic temporal bone CT images from ultrashort echo-time MRI scans.
- To address the limitations of MRI in localizing temporal bone anatomical landmarks.
Main Methods:
- A retrospective study included patients who underwent both temporal MRI and temporal bone CT.
- A CycleGAN model was developed using temporal bone CT and pointwise encoding-time reduction with radial acquisition (PETRA) MRI data.
- Model performance was assessed by measuring mastoid air cell pixel counts and evaluating the generation rates of anatomical landmarks by neuroradiologists.
Main Results:
- The study included 102 patients, randomly divided into training (n=54) and validation (n=48) datasets.
- No significant difference was observed in the pixel count of mastoid air cells between synthetic and real CT images (p=0.13).
- The model achieved high positive generation rates (97-100%) for six major anatomical sites and moderate rates (24-83%) for five major anatomical structures.
Conclusions:
- A deep-learning model was successfully developed to generate synthetic temporal bone CT images from PETRA MRI.
- The model provides valuable information on major temporal bone anatomic sites using MRI data.
- This approach overcomes MRI's limitations in visualizing key anatomical sites within the temporal bone.
More Related Videos
Related Concept Videos
01:10Computed Tomography
Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
01:14Imaging Studies I: CT and MRI
Introduction: MRI and CT scans are crucial advancements in medical imaging techniques, playing a vital role in diagnosing conditions related to the gastrointestinal (GI) system. Each scan serves distinct purposes, targets specific areas, and requires unique nursing duties.
Description of the Procedures
Computed Tomography (CT) scan:
Computed Tomography (CT) scans use X-ray technology to generate detailed images of bones, organs, and tissues. During the scan, the patient lies on a moving table...
Description of the Procedures
Computed Tomography (CT) scan:
Computed Tomography (CT) scans use X-ray technology to generate detailed images of bones, organs, and tissues. During the scan, the patient lies on a moving table...