Related Experiment Video
Updated: May 2, 2026
14:08
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
42.5K
Incorporating indirect MRI information in a CT-based deep learning model for prostate auto-segmentation
Daan Stas1, Geert De Kerf1, Michaël Claessens2
1Department of Radiation Oncology, Iridium Network, Antwerp, Belgium; Faculty of Medicine and Health Sciences, University of Antwerp, Antwerp, Belgium.
Summary
A new deep learning model accurately delineates prostate cancer structures on CT scans, adhering to MRI-based guidelines. This AI tool aids radiotherapy planning by improving contouring accuracy without needing direct MRI input.
Area of Science:
- Radiotherapy
- Medical Imaging
- Artificial Intelligence
Background:
- Computed tomography (CT) imaging presents challenges in delineating soft tissues for prostate cancer external beam radiotherapy.
- Current guidelines necessitate the integration of magnetic resonance imaging (MRI) information for accurate contouring.
- Accurate organ-at-risk delineation is crucial for effective prostate cancer radiotherapy.
Purpose of the Study:
- To develop and evaluate a deep learning (DL) model for prostate and organ-at-risk contouring on CT images.
- The model aims to replicate MRI-based contouring accuracy directly from CT data.
- To align with European Society for Radiotherapy and Oncology (ESTRO) and Advisory Committee on Radiation Oncology Practice (ACROP) guidelines.
Main Methods:
- Utilized CT scan data from 165 prostate cancer patients (136 for training, 29 for testing).
- Developed a 3D U-Net deep learning architecture for contouring key regions: clinical target volume (prostate with/without venous plexus), bladder, anorectum, and seminal vesicles.
- Performed qualitative review by clinicians and quantitative comparison using Dice Similarity Coefficient (DSC) and Hausdorff distance (HD95) against manual delineations.
Main Results:
- DL model achieved high qualitative scores for prostate target volumes (CTV-iVP, CTV-eVP), requiring minimal clinician adjustments (96%).
- Quantitative analysis showed comparable performance for CTV-iVP and CTV-eVP with a DSC of 89% and HD95 of ~4mm.
- The model demonstrated strong results for bladder (DSC 96%, HD95 2.9mm) and acceptable performance for anorectum and seminal vesicles.
Conclusions:
- This is the first DL model to implement MRI contouring guidelines within CT imaging.
- The CT-based DL model is trained according to ESTRO-ACROP guidelines, representing a novel approach.
- The developed model serves as a valuable tool for prostate delineation in radiotherapy, reducing reliance on direct MRI input.
Related Concept Videos
01:24Magnetic Resonance Imaging
7.6K
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...
7.6K
01:14Imaging Studies I: CT and MRI
1.3K
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...
1.3K
01:27Imaging Studies IV: Magnetic Resonance Imaging
427
Introduction:Magnetic Resonance Imaging, or MRI, can include a specialized imaging technique of the urinary system known as Magnetic Resonance Urography (MRU). This radiation-free technique uses strong magnetic fields and radio waves to produce detailed images with the help of a computer. MRU is particularly effective for visualizing fluid-filled structures like the kidneys, ureters, and bladder.Applications of MRI in the Genitourinary SystemKidneys and Ureters: MRI detects tumors, cysts,...
427