fig5
From: Deep learning-driven catheter tracking from bi-plane X-ray fluoroscopy of 3D printed heart phantoms
![Deep learning-driven catheter tracking from bi-plane X-ray fluoroscopy of 3D printed heart phantoms](https://image.oaes.cc/ae9861eb-f793-49c0-8206-c9b66bec27e6/4112.fig.5.jpg)
Figure 5. Comparison of catheter tip detection using the U-Net model and adaptive thresholding. Illustration of raw fluoroscopic images, groundtruth, and predicted segmentation for the two testing datasets.