We use cookies to understand how you use our site and to improve your experience. This includes personalizing content and advertising. To learn more, click here. By continuing to use our site, you accept our use of cookies. Cookie Policy.

Features Partner Sites Information LinkXpress hp
Sign In
Advertise with Us

Download Mobile App




Advanced Assistive Technology Predicts Organ Deformation during Radiotherapy

By MedImaging International staff writers
Posted on 06 Oct 2023
Image: A new technology can accurately predict organ deformation during radiation therapy (Photo courtesy of 123RF)
Image: A new technology can accurately predict organ deformation during radiation therapy (Photo courtesy of 123RF)

Radiation therapy is a popular choice for treating cancer and other conditions, largely because it's minimally invasive, allowing patients to quickly resume their normal lives. One issue, though, is that radiation can affect nearby healthy organs, particularly when high radiation doses are administered to diseased tissues in motion. While regular movements like breathing are somewhat predictable, irregular movements caused by the organ's interactions with neighboring organs can be hard to predict. The ability to precisely anticipate how organs move during radiation treatment is crucial for improving the therapy's effectiveness. Now, a new technology can capture real-time cross-sectional images of the affected area and use them to create three-dimensional (3D) motion of organs. This enables accurate predictions of the deformation of the pancreas and other organs depending on their position related to the nearby organs during radiation therapy.

Researchers from the University of Tsukuba (Ibaraki, Japan) have developed an innovative technique to determine the 3D movement of organs based on their relative positions to neighboring organs. This is done by acquiring real-time cross-sectional (2D) images of the targeted area from three different orientations during radiation therapy. Additionally, the researchers have created a cross-section selection system for picking the most accurate 2D image for further analysis.

The research team validated their technique using publicly accessible MRI data from 20 cases to evaluate the pancreas's position. When using data from just one angle, the error in locating the pancreas was 5.11 mm. However, when data from all three angles was employed, this error shrank dramatically to just 2.13 mm. In some cases, the accuracy was even comparable to what would be achieved if 3D information had been gathered beforehand. These findings could pave the way for radiation therapy protocols designed to minimize radiation exposure to nearby healthy organs, resulting in safer radiation therapy.

Related Links:
University of Tsukuba

Computed Tomography System
Aquilion ONE / INSIGHT Edition
MRI System
nanoScan MRI 3T/7T
Silver Member
X-Ray QA Device
Accu-Gold+ Touch Pro
Pocket Fetal Doppler
CONTEC10C/CL

Channels

Imaging IT

view channel
Image: Researchers develop a vision-language model trained on large-scale data to generate clinically relevant findings from chest computed tomography images through visual question answering (Ms. Maiko Nagao from Meijo University, Japan)

Interactive AI Tool Supports Explainable Lung Nodule Assessment

Lung cancer is a leading cause of cancer mortality, and timely characterization of pulmonary nodules on chest computed tomography (CT) is essential for directing care. Interpreting nodule morphology demands... Read more

Industry News

view channel
Image: MIM KineticID is 510(k)-pending software for dynamic PET imaging and kinetic modeling, enabling time-based radiotracer analysis for clinical and research decisions (Photo courtesy of GE Healthcare)

GE HealthCare Showcases AI-Enabled Nuclear Medicine Portfolio at SNMMI 2026

Nuclear medicine is expanding rapidly as health systems adopt theranostics and broaden access to radiopharmaceuticals, increasing demand for scalable operations and consistent diagnostic confidence.... Read more
Copyright © 2000-2026 Globetech Media. All rights reserved.