Dear AI Insider,
The precise delineation of tumors for volume analysis -- tumor contouring -- poses practical challenges and often causes a bottleneck in research projects and clinical applications involving volumetric disease assessment. This task is not only time-consuming but also prone to variability between and among different observers, according to Dr. Raquel Perez-Lopez, PhD, head of the Vall d'Hebron Institute of Oncology’s Radiomics Group in Barcelona.
This prompted Perez-Lopez and her team to develop AI software that works directly on medical images, automatically detecting and delineating tumors. You can find out more in our special feature article.
When it comes to healthcare AI research, Kicky van Leeuwen, PhD, and Stephan Romeijn are among the most respected in Europe, so don’t miss their evaluation of how AI products assist in the management of intracranial hemorrhage.
Another Dutch group led by Dr. Bastiaan Van Der Zwart from Erasmus Medical Center in Rotterdam has investigated how AI-enabled software designed can help in fracture detection. You can find out more in our news report.
The UK Imaging and Oncology Congress ended yesterday in Liverpool. AI luminary Jan Beger was there, and he’s shared his thoughts from the congress about the current status of radiology AI.
Finally, we have an article about a study conducted at the Technical University of Munich in Germany. The authors analyzed pixel-level lung thickness maps and total lung volume estimation using the U-Net trained on over 7,000 synthetic x-rays, validated using 2,191 images, and applied to real radiographs.
These articles are only a small selection of the material we’ve posted recently in the AI content area. Please check out the full list here.
Philip Ward
Editor in Chief
AuntMinnieEurope.com
