TY - GEN
T1 - Abdominal Segmentation and Blood Vessel Detection in CTA Scans for Diep Reconstruction Procedures
AU - Ashkenazi, Shir
AU - Kiryati, Nahum
AU - Freidin, Dor
AU - Tessone, Ariel
AU - Tejman-Yarden, Shai
AU - Mayer, Arnaldo
N1 - Publisher Copyright: © 2026 IEEE.
PY - 2026/1/1
Y1 - 2026/1/1
N2 - Deep Inferior Epigastric Perforator (DIEP) flap reconstruction requires precise identification of perforator vessels traversing the abdominal muscle to supply the fat and skin tissues. Computed tomography angiography (CTA) reveals contrast-enhanced blood vessels critical for the DIEP surgical harvesting selection. CTA annotation is time-consuming and expertise-dependent, requiring clinicians to trace small perforator vessels through hundreds of image slices. We present an end-to-end automated pipeline that receives raw CTA scans and performs ROI extraction, deep learning multi-class segmentation and detection of perforation points. The pipeline achieves effective segmentation with reliable detection of critical anatomical landmarks. It can reduce pre-operative preparation time while maintaining clinical accuracy for improved surgical planning and navigation.
AB - Deep Inferior Epigastric Perforator (DIEP) flap reconstruction requires precise identification of perforator vessels traversing the abdominal muscle to supply the fat and skin tissues. Computed tomography angiography (CTA) reveals contrast-enhanced blood vessels critical for the DIEP surgical harvesting selection. CTA annotation is time-consuming and expertise-dependent, requiring clinicians to trace small perforator vessels through hundreds of image slices. We present an end-to-end automated pipeline that receives raw CTA scans and performs ROI extraction, deep learning multi-class segmentation and detection of perforation points. The pipeline achieves effective segmentation with reliable detection of critical anatomical landmarks. It can reduce pre-operative preparation time while maintaining clinical accuracy for improved surgical planning and navigation.
KW - Breast reconstruction
KW - CTA
KW - DIEP
KW - Deep Learning
KW - Plastic surgical planning
UR - https://www.scopus.com/pages/publications/105041647164
U2 - 10.1109/ISBI61048.2026.11515327
DO - 10.1109/ISBI61048.2026.11515327
M3 - Conference contribution
T3 - Proceedings - International Symposium on Biomedical Imaging
BT - ISBI 2026 - 23rd IEEE International Symposium on Biomedical Imaging
T2 - 23rd IEEE International Symposium on Biomedical Imaging, ISBI 2026
Y2 - 8 April 2026 through 11 April 2026
ER -