Neural Network based Whole Heart Segmentation from 3D CT images
| Autor: | Irena Galić, Marija Habijan, Danilo Babin, Hrvoje Leventic |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Ground truth
Artificial neural network Computer Networks and Communications Computer science business.industry 0211 other engineering and technologies Pattern recognition Image processing 02 engineering and technology CT data augmentation medical image segmentation neural networks volumetric segmentation whole heart segmentation Convolutional neural network 030218 nuclear medicine & medical imaging 03 medical and health sciences 0302 clinical medicine Whole heart segmentation CT data augmentation medical image segmentation neural networks volumetric segmentation whole heart segmentation Hardware and Architecture Principal component analysis Segmentation Artificial intelligence Electrical and Electronic Engineering business 021101 geological & geomatics engineering |
| Zdroj: | International journal of electrical and computer engineering systems Volume 11 Issue 1 |
| ISSN: | 1847-7003 1847-6996 |
| Popis: | The most recent research is showing the importance and suitability of neural networks for medical image processing tasks. Nonetheless, their efficiency in segmentation tasks is greatly dependent on the amount of available training data. To overcome issues of using small datasets, various data augmentation techniques have been developed. In this paper, an approach for the whole heart segmentation based on the convolutional neural network, specifically on the 3D U-Net architecture, is presented. Also, we propose the incorporation of the principal component analysis as an additional data augmentation technique. The network is trained end-to-end, i.e., no pre-trained network is required. Evaluation of the proposed approach is performed on CT images from MICCAI 2017 Multi-Modality Whole Heart Segmentation Challenge dataset, delivering in a three-fold cross-validation an average dice coefficient overlap of 88.2% for the whole heart, i.e. all heart substructures. Final segmentation results show a high accuracy with the ground truth, indicating that the proposed approach is competitive to the state-of-the-art. Additionally, experiments on the influence of different learning rates are provided as well, showing the optimal learning rate of 0.005 to give the best segmentation results. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|