Needle insertion is a vital procedure in both clinical diagnosis and therapeutical treatment. To ensure the accurate placement of needle, ultrasound (US) imaging is generally used to guide the needle insertion. However, due to depthdependent attenuation and angular dependency, US imaging always face the challenge in consistently and precisely visualizing the needle, necessitating the development of reliable methods to track the needle. Deep learning, an advanced tool that has proven effective and efficient in addressing imaging challenges, has shown promise in enhancing needle visibility in US images. But the existing approaches often rely on manual annotation or simulated data as ground truth, leading to heavy human workload and bias or difficulties in generalizing to real US images. Recently, photoacoustic (PA) imaging has shown the capability of high-contrast needle visualization. In this study, we explore the potential of PA imaging as reliable ground truth for training deep learning networks, eliminating the need for expert annotation. Our network, trained on ex vivo image datasets, demonstrated the abilities of precise needle localization in US images. This research represents a significant advancement in the application of deep learning and PA imaging in clinical settings, with the potential to enhance the accuracy and safety of needle-based procedures.
|