Memory-efficient Segmentation of High-resolution Volumetric MicroCT Images (2022-05-31T00:00:00.000000Z)

TL;DR

Experiments show that the proposed novel memory-efficient network architecture for 3D high-resolution image segmentation outperforms state-of-the-art 3D segmentation methods in terms of both segmentation accuracy and memory efficiency.

Abstract

In recent years, 3D convolutional neural networks have become the dominant approach for volumetric medical image segmentation. However, compared to their 2D counterparts, 3D networks introduce substantially more training parameters and higher requirement for the GPU memory. This has become a major limiting factor for designing and training 3D networks for high-resolution volumetric images. In this work, we propose a novel memory-efficient network architecture for 3D high-resolution image segmentation. The network incorporates both global and local features via a two-stage U-net-based cascaded framework and at the first stage, a memory-efficient U-net (meU-net) is developed. The features learnt at the two stages are connected via post-concatenation, which further improves the information flow. The proposed segmentation method is evaluated on an ultra high-resolution microCT dataset with typically 250 million voxels per volume. Experiments show that it outperforms state-of-the-art 3D segmentation methods in terms of both segmentation accuracy and memory efficiency.

Authors

Wenjia Bai

3 papers

Yuan Wang

1 papers

Laura Blackie

1 papers

Memory-efficient Segmentation of High-resolution Volumetric MicroCT Images

TL;DR

Abstract

Authors

References24 items

OSS-Net: Memory Efficient High Resolution Semantic Segmentation of 3D Medical Data

Multi-Compound Transformer for Accurate Biomedical Image Segmentation

UNETR: Transformers for 3D Medical Image Segmentation

CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentation

TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation

nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation

Two-Stage Cascaded U-Net: 1st Place Solution to BraTS Challenge 2019 Segmentation Task

Skip-connected 3D DenseNet for volumetric infant brain MRI segmentation

CU-Net: Cascaded U-Net with Loss Weighted Sampling for Brain Tumor Segmentation

Clinical-grade computational pathology using weakly supervised deep learning on whole slide images

A Partially Reversible U-Net for Memory-Efficient Volumetric Image Segmentation

UNet++: A Nested U-Net Architecture for Medical Image Segmentation

A multi-scale pyramid of 3D fully convolutional networks for abdominal multi-organ segmentation

Attention U-Net: Learning Where to Look for the Pancreas

Automatic 3D Cardiovascular MR Segmentation with Densely-Connected Volumetric ConvNets

Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations

Deeply-supervised CNN for prostate segmentation

3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation

V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

Deep Residual Learning for Image Recognition

U-Net: Convolutional Networks for Biomedical Image Segmentation

Holistically-Nested Edge Detection

Deeply-Supervised Nets

A 3d coarse-to-fine

Field of Study

Venue Information

Name

Type

URL

Alternate Names