3D-NASE: A Novel 3D CT Nasal Attention-Based Segmentation Ensemble

Abstract

Accurate segmentation of the nasal cavity and paranasal sinuses in CT scans is crucial for disease assessment, treatment planning, and surgical navigation. It also facilitates the advanced computational modeling of airflow dynamics and enhances endoscopic surgery preparation. This work presents a novel ensemble framework for 3D nasal CT segmentation that synergistically combines CNN-based and transformer-based architectures, 3D-NASE. By integrating 3D U-Net, UNETR, Swin UNETR, SegResNet, DAF3D, and V-Net with majority and soft voting strategies, our approach leverages both local details and global context to improve segmentation accuracy and robustness. Results on the NasalSeg dataset demonstrate that the proposed ensemble method surpasses previous state-of-the-art results by achieving a 35.88% improvement in the DICE score and reducing the standard deviation by 4.53%. These promising results highlight the potential of our method to advance clinical workflows in diagnosis, treatment planning, and surgical navigation while also promoting further research into computationally efficient and highly accurate segmentation techniques.

Keywords: 3D CT segmentation; 3D U-Net; Swin UNETR; UNETR; ensemble methods; nasal CT.

Figure 1

Samples from the NasalSeg dataset along with corresponding labels.

Figure 2

The proposed framework, 3D-NASE: the input volume is processed in parallel by the selected models, their outputs are concatenated, and an ensemble strategy is applied to generate the final prediction.

Figure 3

Qualitative results: original images, ground-truth labels, and predictions from 3D U-Net, UNETR, Swin UNETR, DAF3D, V-Net, SegResNet, majority voting, and soft voting. The first two rows represent the first example, while the last two rows represent the second one.