Redirigiendo al acceso original de articulo en 21 segundos...
Inicio  /  Applied Sciences  /  Vol: 12 Par: 14 (2022)  /  Artículo
ARTÍCULO
TITULO

Sample-Efficient Deep Learning Techniques for Burn Severity Assessment with Limited Data Conditions

Hyunkyung Shin    
Hyeonung Shin    
Wonje Choi    
Jaesung Park    
Minjae Park    
Euiyul Koh and Honguk Woo    

Resumen

The automatic analysis of medical data and images to help diagnosis has recently become a major area in the application of deep learning. In general, deep learning techniques can be effective when a large high-quality dataset is available for model training. Thus, there is a need for sample-efficient learning techniques, particularly in the field of medical image analysis, as significant cost and effort are required to obtain a sufficient number of well-annotated high-quality training samples. In this paper, we address the problem of deep neural network training under sample deficiency by investigating several sample-efficient deep learning techniques. We concentrate on applying these techniques to skin burn image analysis and classification. We first build a large-scale, professionally annotated dataset of skin burn images, which enables the establishment of convolutional neural network (CNN) models for burn severity assessment with high accuracy. We then deliberately set data limitation conditions and adapt several sample-efficient techniques, such as transferable learning (TL), self-supervised learning (SSL), federated learning (FL), and generative adversarial network (GAN)-based data augmentation, to those conditions. Through comprehensive experimentation, we evaluate the sample-efficient deep learning techniques for burn severity assessment, and show, in particular, that SSL models learned on a small task-specific dataset can achieve comparable accuracy to a baseline model learned on a six-times larger dataset. We also demonstrate the applicability of FL and GANs to model training under different data limitation conditions that commonly occur in the area of healthcare and medicine where deep learning models are adopted.

 Artículos similares

       
 
Shihao Ma, Jiao Wu, Zhijun Zhang and Yala Tong    
Addressing the limitations, including low automation, slow recognition speed, and limited universality, of current mudslide disaster detection techniques in remote sensing imagery, this study employs deep learning methods for enhanced mudslide disaster d... ver más
Revista: Applied Sciences

 
Ryota Higashimoto, Soh Yoshida and Mitsuji Muneyasu    
This paper addresses the performance degradation of deep neural networks caused by learning with noisy labels. Recent research on this topic has exploited the memorization effect: networks fit data with clean labels during the early stages of learning an... ver más
Revista: Applied Sciences

 
Xie Lian, Xiaolong Hu, Liangsheng Shi, Jinhua Shao, Jiang Bian and Yuanlai Cui    
The parameters of the GR4J-CemaNeige coupling model (GR4neige) are typically treated as constants. However, the maximum capacity of the production store (parX1) exhibits time-varying characteristics due to climate variability and vegetation coverage chan... ver más
Revista: Water

 
Yongen Lin, Dagang Wang, Tao Jiang and Aiqing Kang    
Reliable streamflow forecasting is a determining factor for water resource planning and flood control. To better understand the strengths and weaknesses of newly proposed methods in streamflow forecasting and facilitate comparisons of different research ... ver más
Revista: Water

 
Hamed Raoofi, Asa Sabahnia, Daniel Barbeau and Ali Motamedi    
Traditional methods of supervision in the construction industry are time-consuming and costly, requiring significant investments in skilled labor. However, with advancements in artificial intelligence, computer vision, and deep learning, these methods ca... ver más