alt FUW
logo UW
other language
webmail
search
menu

Seminarium z fizyki biologicznej i bioinformatyki

join us / spotkanie
2024-10-09 (15:15) Calendar icon
Dr Szymon Płotka (Sano Centre for Computational Medicine, Poland; University of Amsterdam, the Netherlands; Amsterdam University Medical Center, the Netherlands)

Enhancing fetoscopic surgery through deep learning

Abstract:
Twin-to-Twin Transfusion Syndrome (TTTS) is a rare condition that affects about 15% of monochorionic pregnancies, in which identical twins share a single placenta. Fetoscopic laser photocoagulation (FLP) is the standard treatment for TTTS, which significantly improves the survival of fetuses. The aim of FLP is to identify abnormal connections between blood vessels and to laser ablate them in order to equalize blood supply to both fetuses. However, performing fetoscopic surgery is challenging due to limited visibility, a narrow field of view, and significant variability among patients and domains. In order to enhance the visualization of placental vessels during surgery, we propose TTTSNet, a network architecture designed for real-time and accurate placental vessel segmentation. To address the challenges posed by FLP-specific fiberscope and amniotic sac-based artifacts, we employed novel data augmentation techniques. These techniques simulate various artifacts, including laser pointer, amniotic sac particles, and structural and optical fiber artifacts. Our method achieved significant performance improvements compared to state-of-the-art methods. This potentially opens the door to real-time application during surgical procedures.
---
https://zoom.us/j/91976153012?pwd=azNiMWE4UnhPN3lRQlY2UHZHOXVkQT09
Meeting ID: 919 7615 3012
Passcode: 747922
One tap mobile
+48223073488,,91976153012#,,,,*747922# Poland
+48223987356,,91976153012#,,,,*747922# Poland
Dial by your location
+48 22 307 3488 Poland
+48 22 398 7356 Poland
+48 22 306 5342 Poland

Bogdan Lesyng (UW)
Anna Niedźwiecka (IF PAN)
Piotr Zielenkiewicz (IBB)

Wróć

Wersja desktopowa Stopka redakcyjna