About us
Transforming Women's Health with AI Ultrasound
At Scanvio Medical, we improve health by making expert ultrasound available to everyone. We help millions of women get a faster endometriosis diagnosis with our AI-augmented ultrasound software. Our solution provides every gynecologist with expert sonography skills.
We are an ETH Zurich Spin-off, founded in 2024. Our team members have extensive experience in gynecology, machine learning, and building successful solutions for medical technology and surgical education.
We are an ETH Zurich Spin-off, founded in 2024. Our team members have extensive experience in gynecology, machine learning, and building successful solutions for medical technology and surgical education.
Our Partners
Join us!
Meet our team
Our team specializes in gynecology, machine learning, and developing medical technology and surgical education solutions.
Stefan Tuchschmid, Ph.D.
Chief Executive Officer
Stefan shaped his ETH Zurich PhD thesis into VirtaMed, a global leader in surgical training with 130+ employees. He's a winner of the Swiss Economic Award in Hightech/Biotech and a serial winner of most business plan competitions in Switzerland. Before starting Scanvio Medical, he mentored aspiring student entrepreneurs and start-up / scale up companies. Stefan supports strategic research at the ETH AI Center within surgery, medtech and health-related activities.
Fabian Laumer, Ph.D.
Chief Technology Officer
Fabian finished his PhD Thesis entitled “Deep Learning for 3D Heart Shape Reconstruction in Echocardiography” at the Institute for Machine Learning at ETH Zürich in 2023. His research focused around the development of intelligent algorithms for automated and robust interpretation of ultrasound videos. In 2021 Fabian Laumer received the ML4H NeurIPS2020 best paper award.
Michael Bajka, M.D., Prof.
Chief Medical Officer
Michael is a specialist in obstetrics and gynecology with educational responsibility, particularly in surgery, ultrasound, and endometriosis. Since 1994, Michael Bajka has been a national leader in gynecologic ultrasound while pursuing a passionate career as a clinical practitioner. His central interests are basic research, prototyping, clinical validation, establishing curricula, and assessing future surgeons and ultrasound specialists. He established national and international contacts between medical experts of different specialties, leading to a broad network in all aspects of ultrasound.
Gabriel Fringeli, M.Sc. ETH Zürich
Lead AI Engineer
Gabriel Fringeli earned his Master and Bachelor degree in Computer Science from ETH Zurich. His focus of study was on machine learning with applications in the areas of medicine and software security and includes an awarded publication at NeurIPS 2020 on information extraction for cardiac ultrasound data. Before joining Scanvio, Gabriel worked as a software and AI engineer at Snyk developing machine learning methods for fixing source code vulnerabilities.
Co-Founders and advisors
Joachim M. Buhmann, PhD, Prof.
Co-Founder, Research Advisory
Joachim M. Buhmann is full professor in Computer Science at ETH Zurich, where he leads the Information Science and Engineering group. His research interests cover the area of pattern recognition and data analysis, i.e., machine learning, statistical learning theory and applied statistics with focus in bioinformatics.
Julian Metzler, M.D.
Co-Founder, Medical Advisory
Julian M. Metzler is a consultant gynecologist at the University Hospital Zurich where he co-leads the Endometriosis center. His main focus is gynecological sonography and minimally-invasive gynecological surgery.
Julia Vogt, PhD, Prof.
Research Advisory
Julia Vogt is an assistant professor in Computer Science at ETH Zurich, where she leads the Medical Data Science Group. The focus of her research is on linking computer science with medicine, with the ultimate aim of personalized patient treatment.
Ece Özkan Elsen, PhD
Scientific Advisor
Ece Özkan Elsen is an established researcher in Computer Science at ETH Zurich. The focus of her research lie in enhancing the generalization, explainability, and fairness of machine learning models to address medical challenges and interpret medical data.