Please select the desired project time frame:

• July 2026
• January 2026
• July 2025
• January 2025
• July 2024
• January 2024
• July 2023
• January 2023
• July 2022
• January 2022
• July 2021
• January 2021
• July 2020
• January 2020
• July 2019
• January 2019
• July 2018
• January 2018
• July 2017
• January 2017
• July 2016
• January 2016
• July 2015
• January 2015
• July 2014
• January 2014
• July 2013
• January 2013
• July 2012
• January 2012
• July 2011
• January 2011
• July 2010
• January 2010
• July 2009
• January 2009
• July 2008
• January 2008
• July 2007
• January 2007
• July 2006
• January 2006
• July 2005
• January 2005
• July 2004
• January 2004
• July 2003
• January 2003
• July 2002
• January 2002
• July 2001
• January 2001

Start of funding 01.07.2023

AI Driven Robotic Synthetic Aperture Volumetric Ultrasound Compounding for Beast Cancer Diagnosis with Molecular Imaging

---

Breast cancer is the most common cancer in women, and early detection can significantly reduce mortality rates. Factors influencing diagnosis and treatment include anatomical factors such as dense breast tissue, which can affect the accuracy of X-ray mammography, and socioeconomic factors, highlighting the need for affordable detection and monitoring methods. Ultrasound imaging is widely used in medical diagnosis for screening and follow-up exams, due to its non-invasiveness, affordability, and high soft-tissue contrast. Moreover, Ultrasound Molecular Imaging (UMI) is a promising modality that uses visible targeted microbubbles to detect breast cancer with high spatiotemporal resolution and low cost, without radiation.

Yet, interpreting ultrasound images can be challenging due to lower resolution and a smaller field of view. Robotic manipulators can improve reproducibility and standardize imaging results and have the potential to alieve the shortcomings of ultrasound but face challenges such as phase aberration and pose-dependent imaging, which can affect image quality. In this project, TU Munich, in collaboration with Stanford University, aim to create a robotic-based 3D microbubble imaging algorithm for real-time patient screening. Our goal is to develop an accurate AI-based system for the early detection of small and difficult-to-image breast cancer tumors.

Final report:
The project "AI-Driven Robotic Synthetic Aperture Volumetric Ultrasound Compounding for Breast Cancer Diagnosis with Molecular Imaging”, funded by BaCaTeC, was initiated to establish a close collaboration between the Chair for Computer Aided Medical Procedures (TUM) and the laboratory of Prof. Jeremy Dahl at Stanford University. The project built upon prior work on acoustically driven microbubbles for targeted drug delivery and aimed to extend this research through robotic automation. During the project, a robotic ultrasound framework was developed to automate the focused ultrasound therapy procedure, including full 3D liver scanning, tumor localization, and robot-guided targeted insonation. Experiments on phantoms demonstrated the feasibility of integrating real-time ultrasound imaging with robot trajectory planning, enabling precise targeting and visualization of the treatment area. Ph.D. student Yordanka Velikova visited Stanford for a total of four months, working closely with the Dahl Lab team and strengthening the exchange between both institutions. Throughout the project, collaborators from Stanford and TUM met weekly to ensure continuous coordination and technical progress. Although full automation remains in development, the collaboration effectively combined expertise in robotics and ultrasound physics, laying the groundwork for future translational research and consolidating a sustainable partnership between the two institutions.