Multimodal Learning With Intraoperative CBCT & Variably Aligned Preoperative CT Data To Improve Segmentation
This addresses segmentation accuracy for liver interventions in medical imaging, but it is incremental as it builds on existing multimodal fusion methods with a focus on handling misalignment.
The paper tackled the problem of improving liver and liver tumor segmentation in intraoperative CBCT scans, which suffer from artifacts, by fusing them with preoperative CT scans despite imperfect alignment. The result showed that multimodal fusion mostly improved segmentation performance compared to using CBCT alone, with even misaligned CT data providing benefits.
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.