Lung Lesion Images Classification Based on Deep Learning Model and Adaboost Techniques
11th EAI International Conference on Context-Aware Systems and Applications, ICCASA 2022
; 475 LNICST:102-111, 2023.
Article
in English
| Scopus | ID: covidwho-2292310
ABSTRACT
Today, the medical industry is promoting the research and application of artificial intelligence in disease diagnosis and treatment. The development of diagnostic methods with the support of electronic devices and information technology can help doctors save time in diagnosing and treating diseases, especially medical images. Diagnosis of lung lesions based on lung images is a case study. This paper proposed a method for lung lesion images classification based on modified U-Net and VGG-19 combined on adaboost techniques. The modified U-Net architecture with 5 pooling and 5 unpooling. It has the unpooling layer with kernels of size 2 × 2, stride 2 × 2 to get output consistent with the adaboost. The result of the proposed method is about 97.61% and better results than others in the Covid-19 radiography dataset. © 2023, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.
Adaboost; Classification; Lung lesion images; U-Net; VGG-19; Biological organs; Deep learning; Diagnosis; Image classification; Medical imaging; Disease treatment; Images classification; Learning models; Lesion image; Lung lesion image; Lung lesions; Medical industries; Research and application; Adaptive boosting
Full text:
Available
Collection:
Databases of international organizations
Database:
Scopus
Language:
English
Journal:
11th EAI International Conference on Context-Aware Systems and Applications, ICCASA 2022
Year:
2023
Document Type:
Article
Similar
MEDLINE
...
LILACS
LIS