Z-Net: an Anisotropic 3D DCNN for Medical CT Volume Segmentation

TL;DR

Z-Net introduces an anisotropic 3D deep learning framework that improves CT volume segmentation accuracy by addressing patch discontinuities and class imbalance, enhancing intra-operative navigation in minimally invasive surgery.

Contribution

The paper presents Z-Net, a novel anisotropic 3D DCNN that can be integrated into existing models to improve segmentation performance in CT scans.

Findings

Up to 12.6% improvement in IoU for segmentation tasks.

Effective handling of discontinuities and class imbalance in CT volumes.

Validated on aortic, liver, and lung segmentation datasets.

Abstract

Accurate volume segmentation from the Computed Tomography (CT) scan is a common prerequisite for pre-operative planning, intra-operative guidance and quantitative assessment of therapeutic outcomes in robot-assisted Minimally Invasive Surgery (MIS). 3D Deep Convolutional Neural Network (DCNN) is a viable solution for this task, but is memory intensive. Small isotropic patches are cropped from the original and large CT volume to mitigate this issue in practice, but it may cause discontinuities between the adjacent patches and severe class-imbalances within individual sub-volumes. This paper presents a new 3D DCNN framework, namely Z-Net, to tackle the discontinuity and class-imbalance issue by preserving a full field-of-view of the objects in the XY planes using anisotropic spatial separable convolutions. The proposed Z-Net can be seamlessly integrated into existing 3D DCNNs with isotropic convolutions such as 3D U-Net and V-Net, with improved volume segmentation Intersection over Union (IoU) - up to $12.6\%$. Detailed validation of Z-Net is provided for CT aortic, liver and lung segmentation, demonstrating the effectiveness and practical value of Z-Net for intra-operative 3D navigation in robot-assisted MIS.