Machine Learning Approach for COVID-19 Detection Using Chest X-Ray Images
Deep Learning Model with Transfer Learning Optimization
Penulis: Prof. Dr. Mada Rahman, S.Kom., M.T., Dr. Lisa Chen, Ph.D., Dr. Ahmad Wijaya, S.T., M.T.
Penulis Korespondensi: Prof. Dr. Mada Rahman, S.Kom., M.T.
Jurnal: 2024 IEEE International Conference on Artificial Intelligence and Machine Learning
Penerbit: IEEE
Abstrak
Abstract
This paper presents a novel machine learning approach for automated COVID-19 detection using chest X-ray images. The proposed method leverages deep learning techniques with transfer learning optimization to achieve high accuracy in medical diagnosis.
Methodology:
We developed a convolutional neural network (CNN) model based on ResNet-50 architecture with transfer learning. The model was trained on a dataset of 15,000 chest X-ray images comprising COVID-19 positive, pneumonia, and normal cases.
Results:
- Overall accuracy: 96.5%
- COVID-19 detection sensitivity: 94.8%
- Specificity: 97.2%
- Processing time: <2 seconds per image
The proposed system demonstrates significant potential for rapid screening and diagnosis support in clinical settings, particularly valuable during pandemic situations.
Kata Kunci
COVID-19, chest X-ray, deep learning, transfer learning, medical diagnosis
Bidang Subjek
Medical Imaging
Informasi Tambahan
Jurnal:
Lihat Jurnal
Machine Learning, Medical Diagnosis, Computer Vision
Kategori: Prosiding Konferensi
Diterbitkan: 29/12/2025 01:22:49