Bridging 2D and 3D Segmentation Networks for Computation Efficient Volumetric Medical Image Segmentation: An Empirical Study of 2.5D Solutions

TL;DR

This paper empirically compares 2.5D segmentation methods with 2D and 3D CNNs for volumetric medical images, highlighting that 3D CNNs are not always optimal and that 2.5D methods offer a promising balance of efficiency and accuracy.

Contribution

It provides the first large-scale empirical comparison of 2.5D segmentation methods across multiple medical imaging tasks, offering insights into their performance and practical benefits.

Findings

3D CNNs are not always the best choice for volumetric segmentation

Some 2.5D methods improve over 2D baselines but vary across datasets

Not all 2.5D methods consistently outperform others or 3D CNNs

Abstract

Recently, deep convolutional neural networks have achieved great success for medical image segmentation. However, unlike segmentation of natural images, most medical images such as MRI and CT are volumetric data. In order to make full use of volumetric information, 3D CNNs are widely used. However, 3D CNNs suffer from higher inference time and computation cost, which hinders their further clinical applications. Additionally, with the increased number of parameters, the risk of overfitting is higher, especially for medical images where data and annotations are expensive to acquire. To issue this problem, many 2.5D segmentation methods have been proposed to make use of volumetric spatial information with less computation cost. Despite these works lead to improvements on a variety of segmentation tasks, to the best of our knowledge, there has not previously been a large-scale empirical comparison of these methods. In this paper, we aim to present a review of the latest developments of 2.5D methods for volumetric medical image segmentation. Additionally, to compare the performance and effectiveness of these methods, we provide an empirical study of these methods on three representative segmentation tasks involving different modalities and targets. Our experimental results highlight that 3D CNNs may not always be the best choice. Despite all these 2.5D methods can bring performance gains to 2D baseline, not all the methods hold the benefits on different datasets. We hope the results and conclusions of our study will prove useful for the community on exploring and developing efficient volumetric medical image segmentation methods.