# Projection-Based 2.5D U-net Architecture for Fast Volumetric Segmentation

arXiv: https://arxiv.org/abs/1902.00347 · HTML: https://mlsanity.com/paper/1902.00347/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Feb 2019.

## Built on by (most cited first, 6 of 6)

- [Unsupervised Single-shot Depth Estimation using Perceptual Reconstruction](https://mlsanity.com/paper/2201.12170/) (2022)
- [MLP-GAN for Brain Vessel Image Segmentation](https://mlsanity.com/paper/2207.08265/) (2022)
- [Plug-and-Play with 2.5D Artifact Reduction Prior for Fast and Accurate Industrial Computed Tomography Reconstruction](https://mlsanity.com/paper/2506.14719/) (2025)
- [Unpaired Single-Image Depth Synthesis with cycle-consistent Wasserstein GANs](https://mlsanity.com/paper/2103.16938/) (2021)
- [CNN-based fully automatic wrist cartilage volume quantification in MR Image](https://mlsanity.com/paper/2206.11127/) (2022)
- [Protect the Brain When Treating the Heart: Feasibility of 2.5D U-Net for Real-Time Gaseous Microemboli Detection](https://mlsanity.com/paper/2604.22258/) (2026)

## Abstract (arXiv)

Convolutional neural networks are state-of-the-art for various segmentation tasks. While for 2D images these networks are also computationally efficient, 3D convolutions have huge storage requirements and require long training time. To overcome this issue, we introduce a network structure for volumetric data without 3D convolutional layers. The main idea is to include maximum intensity projections from different directions to transform the volumetric data to a sequence of images, where each image contains information of the full data. We then apply 2D convolutions to these projection images and lift them again to volumetric data using a trainable reconstruction algorithm.The proposed network architecture has less storage requirements than network structures using 3D convolutions. For a tested binary segmentation task, it even shows better performance than the 3D U-net and can be trained much faster.