Lung diseases identification using hybrid transfer learning and bidirectional long short-term memory

• Published in: Bulletin of Electrical Engineering and Informatics
• Main Author: Cahyani D.E.; Oktoviana L.T.; Yasin M.; Wahyuningsih S.; Dionixius; Maulidaningsih R.; Setumin S.
• Format: Article
• Language: English
• Published: Institute of Advanced Engineering and Science 2025
• Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85216782751&doi=10.11591%2feei.v14i2.9114&partnerID=40&md5=de1d9388502fe975d485a5bffc34839e

Lung diseases rank as the third most prevalent cause of mortality globally. Accurate identification of lung disease is essential to provide appropriate medical intervention for patients. This research devised a categorization system for lung diseases using chest X-Rays (CXR). The system can identify bacterial pneumonia, viral pneumonia, COVID-19, tuberculosis, and normal CXR. The approach for detecting lung diseases utilize a combination of hybrid transfer learning and bidirectional long short-term memory. The research included convolutional neural network (CNN) models including Resnet50-BiLSTM, VGG19-BiLSTM, InceptionV3-BiLSTM, Resnet50, VGG19, and InceptionV3. The Resnet50-BiLSTM model outperforms other models in terms of accuracy and overall performance. The Resnet50-BiLSTM model achieved an accuracy of 99.87%. The models that achieve the second greatest accuracy are Resnet50, VGG19-BiLSTM, VGG19, InceptionV3-BiLSTM, and InceptionV3. The research utilizes precision, recall, and F1-Measure to demonstrate that Resnet50-BiLSTM outperforms other methods by achieving the greatest value. This research improves the performance outcomes when compared to earlier studies. © 2025, Institute of Advanced Engineering and Science. All rights reserved.