Fast and Accurate 3D Medical Image Segmentation with Data-swapping Method

by   Haruki Imai, et al.

Deep neural network models used for medical image segmentation are large because they are trained with high-resolution three-dimensional (3D) images. Graphics processing units (GPUs) are widely used to accelerate the trainings. However, the memory on a GPU is not large enough to train the models. A popular approach to tackling this problem is patch-based method, which divides a large image into small patches and trains the models with these small patches. However, this method would degrade the segmentation quality if a target object spans multiple patches. In this paper, we propose a novel approach for 3D medical image segmentation that utilizes the data-swapping, which swaps out intermediate data from GPU memory to CPU memory to enlarge the effective GPU memory size, for training high-resolution 3D medical images without patching. We carefully tuned parameters in the data-swapping method to obtain the best training performance for 3D U-Net, a widely used deep neural network model for medical image segmentation. We applied our tuning to train 3D U-Net with full-size images of 192 x 192 x 192 voxels in brain tumor dataset. As a result, communication overhead, which is the most important issue, was reduced by 17.1 voxels, our training for full-size images achieved improvement on the mean Dice score by 4.48 sub-region, respectively. The total training time was reduced from 164 hours to 47 hours, resulting in 3.53 times of acceleration.



There are no comments yet.


page 10


U-Net and its variants for Medical Image Segmentation : A short review

The paper is a short review of medical image segmentation using U-Net an...

Kid-Net: Convolution Networks for Kidney Vessels Segmentation from CT-Volumes

Semantic image segmentation plays an important role in modeling patient-...

Distributing Deep Learning Hyperparameter Tuning for 3D Medical Image Segmentation

Most research on novel techniques for 3D Medical Image Segmentation (MIS...

Near Real-time Hippocampus Segmentation Using Patch-based Canonical Neural Network

Over the past decades, state-of-the-art medical image segmentation has h...

Efficient Training of High-Resolution Representation Seismic Image Fault Segmentation Network by Weakening Anomaly Labels

Seismic data fault detection has recently been regarded as a 3D image se...

High Resolution Medical Image Analysis with Spatial Partitioning

Medical images such as 3D computerized tomography (CT) scans and patholo...

Efficient Folded Attention for 3D Medical Image Reconstruction and Segmentation

Recently, 3D medical image reconstruction (MIR) and segmentation (MIS) b...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.