Authors: Ricardo Coimbra Brioso, Damiano Dei, Nicola Lambri, Daniele Loiacono, Pietro Mancosu, Marta Scorsetti

Published on: February 09, 2024

Impact Score: 8.15

Arxiv code: Arxiv:2402.06494

Summary

• What is new: Introduction of nnU-Net framework to develop 2D and 3D U-Net models and its application on the most challenging PTV areas in TMLI treatment.
• Why this is important: The need for an accurate and efficient Planning Target Volume (PTV) contouring in complex cancer treatments like TMLI, where manual contouring is error-prone and time-consuming.
• What the research proposes: Automating the segmentation of the PTV using the nnU-Net framework to develop improved 2D and 3D U-Net models.
• Results: Statistically significant improvement in segmentation performance, demonstrating robustness in challenging areas of the PTV.

Technical Details

Technological frameworks used: nnU-Net

Models used: 2D and 3D U-Net models

Data used: PTV segments excluding bones

Potential Impact

Healthcare providers specializing in radiotherapy, medical imaging software companies

Want to implement this idea in a business?

We have generated a startup concept here: RadAI Therapy Solutions.