Improving CT Image Tumor Segmentation Through Deep Supervision and Attentional Gates
Open Access
- 28 August 2020
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Robotics and AI
- Vol. 7
Abstract
Computer Tomography (CT) is an imaging procedure that combines many X-ray measurements taken from different angles. The segmentation of areas in the CT images provides a valuable aid to physicians and radiologists in order to better provide a patient diagnose. The CT scans of a body torso usually include different neighboring internal body organs. Deep learning has become the state-of-the-art in medical image segmentation. For such techniques, in order to perform a successful segmentation, it is of great importance that the network learns to focus on the organ of interest and surrounding structures and also that the network can detect target regions of different sizes. In this paper, we propose the extension of a popular deep learning methodology, Convolutional Neural Networks (CNN), by including deep supervision and attention gates. Our experimental evaluation shows that the inclusion of attention and deep supervision results in consistent improvement of the tumor prediction accuracy across the different datasets and training sizes while adding minimal computational overhead.Keywords
Funding Information
- European Cooperation in Science and Technology
This publication has 32 references indexed in Scilit:
- Cascaded Semantic Segmentation for Kidney and Tumor2019
- VoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR imagesNeuroImage, 2018
- RADnet: Radiologist level accuracy using deep learning for hemorrhage detection in CT scans2018
- Automatic Multi-Organ Segmentation on Abdominal CT With Dense V-NetworksIEEE Transactions on Medical Imaging, 2018
- 3D convolutional neural network for automatic detection of lung nodules in chest CT2017
- 3D Deeply Supervised Network for Automatic Liver Segmentation from CT Volumes2016
- Attention to Scale: Scale-Aware Semantic Image Segmentation2016
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- Control of goal-directed and stimulus-driven attention in the brainNature Reviews Neuroscience, 2002
- Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in positionBiological Cybernetics, 1980