# A two-stage 3D Unet framework for multi-class segmentation on full resolution image

arXiv: https://arxiv.org/abs/1804.04341 · HTML: https://mlsanity.com/paper/1804.04341/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Apr 2018.

## Built on by (most cited first, 9 of 9)

- [D-Former: A U-shaped Dilated Transformer for 3D Medical Image Segmentation](https://mlsanity.com/paper/2201.00462/) (2022)
- [ImageCHD: A 3D Computed Tomography Image Dataset for Classification of Congenital Heart Disease](https://mlsanity.com/paper/2101.10799/) (2021)
- [CAT-Net: A Cross-Slice Attention Transformer Model for Prostate Zonal Segmentation in MRI](https://mlsanity.com/paper/2203.15163/) (2022)
- [Virtual Temporal Samples for Recurrent Neural Networks: applied to semantic segmentation in agriculture](https://mlsanity.com/paper/2106.10118/) (2021)
- [CSAM: A 2.5D Cross-Slice Attention Module for Anisotropic Volumetric Medical Image Segmentation](https://mlsanity.com/paper/2311.04942/) (2023)
- [3D Mitochondria Instance Segmentation with Spatio-Temporal Transformers](https://mlsanity.com/paper/2303.12073/) (2023)
- [IP-UNet: Intensity Projection UNet Architecture for 3D Medical Volume Segmentation](https://mlsanity.com/paper/2308.12761/) (2023)
- [Preserving Cardiac Integrity: A Topology-Infused Approach to Whole Heart Segmentation](https://mlsanity.com/paper/2410.10551/) (2024)
- [NUMSnet: Nested-U Multi-class Segmentation network for 3D Medical Image Stacks](https://mlsanity.com/paper/2304.02713/) (2023)

## Abstract (arXiv)

Deep convolutional neural networks (CNNs) have been intensively used for multi-class segmentation of data from different modalities and achieved state-of-the-art performances. However, a common problem when dealing with large, high resolution 3D data is that the volumes input into the deep CNNs has to be either cropped or downsampled due to limited memory capacity of computing devices. These operations lead to loss of resolution and increment of class imbalance in the input data batches, which can downgrade the performances of segmentation algorithms. Inspired by the architecture of image super-resolution CNN (SRCNN) and self-normalization network (SNN), we developed a two-stage modified Unet framework that simultaneously learns to detect a ROI within the full volume and to classify voxels without losing the original resolution. Experiments on a variety of multi-modal volumes demonstrated that, when trained with a simply weighted dice coefficients and our customized learning procedure, this framework shows better segmentation performances than state-of-the-art Deep CNNs with advanced similarity metrics.