COMPREHENSIVE SURVEY ON THE EFFICACY OF 3D CNNS FOR LUNG ABNORMALITY DETECTION IN MEDICAL IMAGING

Abstract

Abstract- In medical imaging, precise and efficient detection of lung abnormalities is critical for early diagnosis and therapy. In recent years, three-dimensional convolutional neural networks (3D CNNs) have showed promise in enhancing the efficacy of lung anomaly detection. This thorough survey will give an in-depth review of the efficacy of 3D CNNs for detecting lung abnormalities in medical imaging. We discuss the most recent advances in 3D CNN designs, techniques, and applications designed exclusively for lung anomaly detection. We assess the performance metrics of several 3D CNN models in identifying lung abnormalities from computed tomography (CT) scans and X-ray pictures by reviewing a wide range of papers and experimental data, including accuracy, sensitivity, specificity, and area under the curve (AUC). Furthermore, we examine the benefits and limits of existing techniques, real-world implementation issues, and potential future possibilities for using 3D CNNs to identify lung abnormalities. This study offers useful information for medical imaging researchers, doctors, and practitioners, allowing for the development of more accurate and reliable diagnostic tools for early lung disease identification and management.