CT organ segmentation using GPU data augmentation, unsupervised labels and IOU loss

11/27/2018
by   Blaine Rister, et al.
0

Fully-convolutional neural networks have achieved superior performance in a variety of image segmentation tasks. However, their training requires laborious manual annotation of large datasets, as well as acceleration by parallel processors with high-bandwidth memory, such as GPUs. We show that simple models can achieve competitive accuracy for organ segmentation on CT images when trained with extensive data augmentation, which leverages existing graphics hardware to quickly apply geometric and photometric transformations to 3D image data. On 3 mm^3 CT volumes, our GPU implementation is 2.6-8X faster than a widely-used CPU version, including communication overhead. We also show how to automatically generate training labels using rudimentary morphological operations, which are efficiently computed by 3D Fourier transforms. We combined fully-automatic labels for the lungs and bone with semi-automatic ones for the liver, kidneys and bladder, to create a dataset of 130 labeled CT scans. To achieve the best results from data augmentation, our model uses the intersection-over-union (IOU) loss function, a close relative of the Dice loss. We discuss its mathematical properties and explain why it outperforms the usual weighted cross-entropy loss for unbalanced segmentation tasks. We conclude that there is no unique IOU loss function, as the naive one belongs to a broad family of functions with the same essential properties. When combining data augmentation with the IOU loss, our model achieves a Dice score of 78-92 each organ. The trained model, code and dataset will be made publicly available, to further medical imaging research.

READ FULL TEXT

page 2

page 4

page 5

page 7

page 9

research
08/14/2018

Automatic Airway Segmentation in chest CT using Convolutional Neural Networks

Segmentation of the airway tree from chest computed tomography (CT) imag...
research
08/11/2021

Deep PET/CT fusion with Dempster-Shafer theory for lymphoma segmentation

Lymphoma detection and segmentation from whole-body Positron Emission To...
research
05/29/2020

Automatic segmentation of the pulmonary lobes with a 3D u-net and optimized loss function

Fully-automatic lung lobe segmentation is challenging due to anatomical ...
research
04/07/2022

TorMentor: Deterministic dynamic-path, data augmentations with fractals

We propose the use of fractals as a means of efficient data augmentation...
research
09/27/2018

Improving Myocardium Segmentation in Cardiac CT Angiography using Spectral Information

Accurate segmentation of the left ventricle myocardium in cardiac CT ang...
research
01/18/2018

On the influence of Dice loss function in multi-class organ segmentation of abdominal CT using 3D fully convolutional networks

Deep learning-based methods achieved impressive results for the segmenta...
research
04/04/2019

Few-shot brain segmentation from weakly labeled data with deep heteroscedastic multi-task networks

In applications of supervised learning applied to medical image segmenta...

Please sign up or login with your details

Forgot password? Click here to reset