폐렴 및 정상군 판별을 위한 딥러닝 모델 성능 비교연구: CNN,VUNO,LUNIT 모델 중심으로
A Comparative Study of Deep Learning Models for Pneumonia Detection: CNN, VUNO, LUIT Models
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
The purpose of this study is to develop a CNN based deep learning model that can effectively detectpneumonia by analyzing chest X-ray images of adults over the age of 20 and compare it with VUNO, LUNIT acommercialized AI model. The data of chest X-ray image was evaluate based on accuracy,precision,recall,F1 score,and AUC score. The CNN model recored an accuracy of 82%, precision 76%, recall 99%, F1 score 86%, and AUCscore 0.7937. The VUNO model recordded an accuracy of 84%, precision 81%, recall 94%, F1 score 87%, andAUC score 0.8233. The LUNIT model recorded an accuracy of 77%, precision 72%, recall 96%, F1 score 83%, andAUC score 0.7436. As a result of the Confusion Matrix analysis, the CNN model showe FN (3), showing the highestrecall rate (99%) in the diagnosis of pneumonia. The VUNO model showed excellent overall perfomance with highaccuracy (84%) and AUC score (0.8233), and the LUNIT model showed high recall rate (96%) but the accuracy andprecision showed relatively low results. This study will be able to provide basic data useful for the development of apneumonia diagnosis system by comprehensively considers the perfomance of the medel is necessary to effectivelydiscriminate between penumonia and normal groups.
Abstract
The purpose of this study is to develop a CNN based deep learning model that can effectively detectpneumonia by analyzing chest X-ray images of adults over the age of 20 and compare it with VUNO, LUNIT acommercialized AI model. The data of chest X-ray image was evaluate based on accuracy,precision,recall,F1 score,and AUC score. The CNN model recored an accuracy of 82%, precision 76%, recall 99%, F1 score 86%, and AUCscore 0.7937. The VUNO model recordded an accuracy of 84%, precision 81%, recall 94%, F1 score 87%, andAUC score 0.8233. The LUNIT model recorded an accuracy of 77%, precision 72%, recall 96%, F1 score 83%, andAUC score 0.7436. As a result of the Confusion Matrix analysis, the CNN model showe FN (3), showing the highestrecall rate (99%) in the diagnosis of pneumonia. The VUNO model showed excellent overall perfomance with highaccuracy (84%) and AUC score (0.8233), and the LUNIT model showed high recall rate (96%) but the accuracy andprecision showed relatively low results. This study will be able to provide basic data useful for the development of apneumonia diagnosis system by comprehensively considers the perfomance of the medel is necessary to effectivelydiscriminate between penumonia and normal groups.
참고문헌 (10)
- Tawsifur Rahman, "Transfer Learning with Deep Convolutional Neural Network (CNN) for Pneumonia Detection Using Chest X-ray", MDPI, 10(3233) (2020)[DOI]
- Dalya S. AI-Dulaimi, "Development of Pneumonia Disease Detection Model Based on Deep Learning Algorithm", Wireless Communications and Mobile Computing, 2022 (2022)[DOI]
- Jaiswal A, "Identifying penumonia in chest X-rays: A deep learning approach", Elsevier, 145, pp.511~518 (2019)[DOI]
- Song HJ, "Evaluation of Classification and Accuracy in Chest X-ray images using Deep Learning with Convolution Neural Network", Korean Soc. Radiol, 14(1) (2020)[DOI]
- Kim JH, "Clinical Validation of a Deep Learning Algorighm for Detection of Pneumonia on Chest Radiographs in Emergency Department Patients with Acute Febrile Respiratory Illness", 9(1981) (2020)[DOI]
- Ni Q, "A deep learning approach to characterize 2019 coronavirus disease (COVID-19) pneumonia in chest CT images", European Soc. Radiol, 30, pp.6517~6527 (2020)[DOI]
- Kim JY, "Diagnostic Classification of Chest X-ray Pneumonia using Inception V3 Modeling", Korean Soc. Radiol, 14(6), pp.773~780 (2020)[DOI]
- Kim JY, "Comparative Evaluation of Chest Image Pneumonia based on Learning Rate Application", Korean Soc. Radiol, 16(5), pp.595~602 (2022)[DOI]
- Kang MJ, "Comparison of Gradient Descent for Deep Learning", Korean Academia-Industrial cooperation Soc, 21(2), pp.189~194 (2020)[DOI]
- Kim JY, "Comparative Analysis by Batch Size when Diagnosing Penumonia on Chest X-Ray Image using Xception Modeling", Korean Soc. Radiol, 16(5), pp.545~554 (2021)[DOI]