Deep Learning with Transfer Learning for Detecting Abnormalities in X-ray Images

Deep learning (DL) applications with medical imaging systems revolutionized the process of detecting abnormalities especially in chest X-ray examination. The existing difficulties in medical imaging analysis stem from insufficient data availability as well as unbalanced classes. The emergence of transfer learning (TL) as an effective strategy allows models to use pre-trained data for better performance and speed in their operations. This paper employed InceptionV3 model with modified layers to detect chest X-ray images which fall into COVID-19, Lung Opacity, Normal, and Viral Pneumonia categories. The proposed method adjusts InceptionV3 by fine-tuning it for better feature extraction and classifier performance improvement. The proposed model demonstrated superior performance by scoring 90.06% accuracy alongside 88.02% recall value and 92.19% precision along with 89.75% F1-score in chest X-ray classification. The research proves that applying transfer learning from InceptionV3 enhances medical imaging abnormality detection leading to a dependable automated diagnostic system.