Abstract
At present, deep learning has been widely adopted in medical image processing. However, the current deep neural networks depend on a large number of labeled training data, but medical images segmentation tasks often suffer from the problem of small quantity of labeled data because labeling medical images is a very expensive and time-consuming task. In order to overcome this difficulty, this paper proposes a new image augmentation strategy based on statistical shape model and three-dimensional thin plate spline, which can generate many simulated images from a small number of real images. Firstly, the shape information of the real labeled images is modeled with the statistical shape model, and a series of simulated shapes are generated by sampling from this model. Secondly, the simulated shapes are filled with texture using three-dimensional thin plate spline to generate the simulated images. Finally, the simulated images and the real images are used together for training deep neural networks. The proposed framework is a general data augmentation method that can be used in any anatomical structure segmentation tasks with any deep neural network architecture. We used two different datasets, including prostate MRI dataset and liver CT dataset, and used two different deep network structures, including multi-scale 3D Convolutional Neural Networks (multi-scale 3D CNN) and U-net. The experimental results showed that the proposed data augmentation strategy can improve the accuracy of existing segmentation algorithms based on deep neural networks.
Highlights
As a popular research field of artificial intelligence, deep learning technology has developed rapidly in recent years, and many deep learning frameworks have been proposed, such as Convolutional Neural Networks (CNN) [1], Recurrent Neural Network (RNN) [2], Stacked Auto-Encoder (SAE) [3], Deep Belief Nets (DBN) [4], etc
For solving the problem of insufficient medical data, in this paper, we proposed a new image augmentation strategy by exploring elastic transformation, which is suitable for training deep neural networks for medical image segmentation, registration and so on
In this paper, we reported a novel data augmentation strategy based on statistical shape model and 3D thin plate spline texture interpolation
Summary
As a popular research field of artificial intelligence, deep learning technology has developed rapidly in recent years, and many deep learning frameworks have been proposed, such as Convolutional Neural Networks (CNN) [1], Recurrent Neural Network (RNN) [2], Stacked Auto-Encoder (SAE) [3], Deep Belief Nets (DBN) [4], etc. In the field of medical image processing, deep learning has achieved very good results in image segmentation, registration, classification and so on [7]. Deep learning based algorithms often obtain more accurate results if the training data is abundant. In ImageNet Large Scale Visual Recognition Competition (ILSVRC) [8], it is the existence of millions of training data that enables the algorithms of deep learning to achieve great results. In medical field, it is difficult to obtain such a big number of medical images for training due to the following reasons. Though millions of medical images are taken every day, it is very difficult to collect these images and to make them public available because of medical ethics and patient privacy consideration. High-quality labeled medical images excessively rely on manual labelling by senior doctors, which is very
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.