Abstract:
In this era of technological advancement where everything is just a click away, the domain of classification and detection of nodules using bone scan images, a lot of computerized detection and report work is in progress This study explores the application of advanced computer vision techniques for the classification and detection of nodules in bone scan images. Using the deep learning model YOLO, our project aims to enhance the accuracy and efficiency of nodule identification. While utilizing a diverse dataset of BS- 80K, The first large open-access dataset of bone scan images. Our proposed framework not only facilitates accurate classification of normal and abnormal cases but also provides precise localization of nodules through bounding box predictions. The results showcase the potential of automated analysis in aiding clinicians for early detection and diagnosis of skeletal abnormalities in bone scans, fostering advancements in medical imaging and patient care.
