Elastic Boundary Projection for 3D Medical Image Segmentation

TL;DR

This paper introduces Elastic Boundary Projection (EBP), a novel method that uses 2D networks to effectively segment 3D medical images by focusing on boundary detection through elastic shells around pivot points.

Contribution

EBP bridges the gap between 2D and 3D segmentation by modeling object boundaries as elastic shells, avoiding slice-based methods and enabling efficient 3D segmentation with 2D networks.

Findings

Achieves promising accuracy in abdominal organ segmentation

Operates without slicing the volume into patches or slices

Open-sourced implementation available

Abstract

We focus on an important yet challenging problem: using a 2D deep network to deal with 3D segmentation for medical image analysis. Existing approaches either applied multi-view planar (2D) networks or directly used volumetric (3D) networks for this purpose, but both of them are not ideal: 2D networks cannot capture 3D contexts effectively, and 3D networks are both memory-consuming and less stable arguably due to the lack of pre-trained models. In this paper, we bridge the gap between 2D and 3D using a novel approach named Elastic Boundary Projection (EBP). The key observation is that, although the object is a 3D volume, what we really need in segmentation is to find its boundary which is a 2D surface. Therefore, we place a number of pivot points in the 3D space, and for each pivot, we determine its distance to the object boundary along a dense set of directions. This creates an elastic shell around each pivot which is initialized as a perfect sphere. We train a 2D deep network to determine whether each ending point falls within the object, and gradually adjust the shell so that it gradually converges to the actual shape of the boundary and thus achieves the goal of segmentation. EBP allows boundary-based segmentation without cutting a 3D volume into slices or patches, which stands out from conventional 2D and 3D approaches. EBP achieves promising accuracy in abdominal organ segmentation. Our code has been open-sourced https://github.com/twni2016/Elastic-Boundary-Projection.