Pancreatic Vessel Landmark Detection in CT Angiography Using Prior Anatomical Knowledge

Rist L, Homm C, Lades F, Hernandez AA, Sühling M, Gudman Steuble Brandt E, Maier A, Taubmann O (2024)

Publication Type: Conference contribution

Publication year: 2024

Journal

Lecture Notes in Computer Science Springer Verlag

Publisher: Springer

Series: Lecture Notes in Computer Science

City/Town: Cham

Book Volume: 15197

Pages Range: 45-54

Conference Proceedings Title: Artificial Intelligence in Pancreatic Disease Detection and Diagnosis, and Personalized Incremental Learning in Medicine

Event location: Marrakesh MA

ISBN: 9783031734823

DOI: 10.1007/978-3-031-73483-0_5

Abstract

Localizing vessels or their defining bifurcations is a frequent clinical problem for advanced visualizations in pancreatic cancer invasion analysis, driving the demand for design guidelines of easy-to-implement landmark detection solutions. When transforming such landmarks appropriately to surrogate targets, the competitive nnDetection and nnU-Net frameworks provide such solutions, especially for small data settings. Here, the underlying networks can further benefit from incorporating additional anatomical information. We present results on two CTA datasets consisting of arterial and venous phase images with 6 and 4 bifurcation landmarks surrounding the pancreas respectively. Landmark points were modeled as spheres to allow for the application of object detection/segmentation models. We evaluate both nn-frameworks for these tasks focusing on the incorporation of anatomical knowledge. Postprocessing nnDetection predictions with organ masks and landmark relation constraints boosts detection accuracies from 66.7 % to 79.4 % in the more challenging venous case and decreases the mean radial error from 9.06 to 4.92 mm. The nnU-Net benefits more from organ masks in the input when targeting problematic vessels, lowering the mean radial error from 12.97 to 8.45 mm when using the splenic mask for the venous task. Both networks have good initial detection rates for the arterial phase which are slightly boosted using our method to 93.7 % (nnU-Net) and 95.5 % (nnDetection). All remaining mispredictions are within the vessel of interest and thus sufficient for many downstream tasks.

Authors with CRIS profile

Leonhard Rist Lehrstuhl für Informatik 5 (Mustererkennung) Andreas Maier Lehrstuhl für Informatik 5 (Mustererkennung)

Involved external institutions

University of Copenhagen DK Denmark (DK) Siemens Healthineers DE Germany (DE) Siemens AG, Healthcare Sector DE Germany (DE)

How to cite

APA:

Rist, L., Homm, C., Lades, F., Hernandez, A.A., Sühling, M., Gudman Steuble Brandt, E.,... Taubmann, O. (2024). Pancreatic Vessel Landmark Detection in CT Angiography Using Prior Anatomical Knowledge. In Artificial Intelligence in Pancreatic Disease Detection and Diagnosis, and Personalized Incremental Learning in Medicine (pp. 45-54). Marrakesh, MA: Cham: Springer.

MLA:

Rist, Leonhard, et al. "Pancreatic Vessel Landmark Detection in CT Angiography Using Prior Anatomical Knowledge." Proceedings of the First International Workshop, AIPAD 2024 and First International Workshop, PILM 2024, Marrakesh Cham: Springer, 2024. 45-54.

BibTeX: Download