Semantic Segmentation for Preoperative Planning in Transcatheter Aortic Valve Replacement

TL;DR

This paper develops and evaluates a semantic segmentation approach to identify key anatomical structures in CT scans for TAVR preoperative planning, improving segmentation accuracy with a novel loss function adaptation.

Contribution

It introduces fine-grained TAVR-relevant pseudo-labels and a modified loss function to enhance segmentation performance in medical imaging for surgical planning.

Findings

Achieved a +1.27% Dice score increase with the new loss function.

Created a dataset of pseudo-labels and CT scans for TAVR planning.

Demonstrated improved segmentation accuracy for relevant anatomical structures.

Abstract

When preoperative planning for surgeries is conducted on the basis of medical images, artificial intelligence methods can support medical doctors during assessment. In this work, we consider medical guidelines for preoperative planning of the transcatheter aortic valve replacement (TAVR) and identify tasks, that may be supported via semantic segmentation models by making relevant anatomical structures measurable in computed tomography scans. We first derive fine-grained TAVR-relevant pseudo-labels from coarse-grained anatomical information, in order to train segmentation models and quantify how well they are able to find these structures in the scans. Furthermore, we propose an adaptation to the loss function in training these segmentation models and through this achieve a +1.27% Dice increase in performance. Our fine-grained TAVR-relevant pseudo-labels and the computed tomography scans we build upon are available at https://doi.org/10.5281/zenodo.16274176.