Redirigiendo al acceso original de articulo en 24 segundos...
Inicio  /  Algorithms  /  Vol: 12 Par: 3 (2019)  /  Artículo
ARTÍCULO
TITULO

Optimized Deep Convolutional Neural Networks for Identification of Macular Diseases from Optical Coherence Tomography Images

Qingge Ji    
Jie Huang    
Wenjie He and Yankui Sun    

Resumen

Finetuning pre-trained deep neural networks (DNN) delicately designed for large-scale natural images may not be suitable for medical images due to the intrinsic difference between the datasets. We propose a strategy to modify DNNs, which improves their performance on retinal optical coherence tomography (OCT) images. Deep features of pre-trained DNN are high-level features of natural images. These features harm the training of transfer learning. Our strategy is to remove some deep convolutional layers of the state-of-the-art pre-trained networks: GoogLeNet, ResNet and DenseNet. We try to find the optimized deep neural networks on small-scale and large-scale OCT datasets, respectively, in our experiments. Results show that optimized deep neural networks not only reduce computational burden, but also improve classification accuracy.

 Artículos similares

       
 
Jiancong Xu, Chen Sun and Guorong Rui    
How to evaluate the reliability of deep soft rock tunnels under high stress is a very important problem to be solved. In this paper, we proposed a practical stochastic reliability method based on the third-generation non-dominated sorting genetic algorit... ver más
Revista: Applied Sciences

 
Zijun Li, Qian Jia, Gang Li, Yu Xu, Junjian Wang and Xiaowei Zhai    
A high temperature is the key factor limiting the safe development of deep mine tunnels. By confronting the phenomenon of serious heat exchange between airflow and the surrounding rocks in the tunnel excavation area, a conceptual model of coupled cooling... ver más
Revista: Applied Sciences

 
Ning Zhang, Anye Cao, Weiwei Zhao, Qi Hao, Guowei Lv and Baixuan Wu    
There is a very thick water-bearing key strata above the coal seam in the Binchang mining area. When the mining scale is large, it easily breaks and leads to rockburst with a surge of water gushing in the panel. Adopting the layout pattern of a small pan... ver más
Revista: Applied Sciences

 
Margarida Mendonça and Álvaro Figueira    
As social media (SM) becomes increasingly prevalent, its impact on society is expected to grow accordingly. While SM has brought positive transformations, it has also amplified pre-existing issues such as misinformation, echo chambers, manipulation, and ... ver más
Revista: Informatics

 
Chunling Wang, Tianyi Hang, Changke Zhu and Qi Zhang    
The Czech Republic is one of the countries along the Belt and Road Initiative, and classifying land cover in the Czech Republic helps to understand the distribution of its forest resources, laying the foundation for forestry cooperation between China and... ver más
Revista: Applied Sciences