Multimodal Learning With Intraoperative CBCT & Variably Aligned Preoperative CT Data To Improve Segmentation

TL;DR

This paper introduces a multimodal learning approach that combines intraoperative CBCT and preoperative CT scans, even with imperfect alignment, to enhance liver and tumor segmentation accuracy.

Contribution

It presents a novel method for fusing roughly aligned CBCT and CT scans, demonstrating improvements in segmentation despite misalignments.

Findings

Fusion improves segmentation performance over CBCT alone

Even misaligned preoperative data can be beneficial

Synthetic dataset used for evaluation

Abstract

Cone-beam computed tomography (CBCT) is an important tool facilitating computer aided interventions, despite often suffering from artifacts that pose challenges for accurate interpretation. While the degraded image quality can affect downstream segmentation, the availability of high quality, preoperative scans represents potential for improvements. Here we consider a setting where preoperative CT and intraoperative CBCT scans are available, however, the alignment (registration) between the scans is imperfect. We propose a multimodal learning method that fuses roughly aligned CBCT and CT scans and investigate the effect of CBCT quality and misalignment on the final segmentation performance. For that purpose, we make use of a synthetically generated data set containing real CT and synthetic CBCT volumes. As an application scenario, we focus on liver and liver tumor segmentation. We show that the fusion of preoperative CT and simulated, intraoperative CBCT mostly improves segmentation performance (compared to using intraoperative CBCT only) and that even clearly misaligned preoperative data has the potential to improve segmentation performance.