Interventional robots play a crucial role in surgical procedures, where accurate force measurement is essential for enhancing safety. Compliant mechanisms utilize material deformation to achieve millinewton-scale force output and millimeter-level displacement with high repeatability. Motivated by this, we propose a method for measuring the catheter force by integrating a compliant mechanism and a sensor. First, we designed an operating force detection module. It comprises a double-parallelogram structure with four elastic units, a catheter drive module, and a sensor. The sensor connects the compliant mechanism to the base. Second, stiffness and gravity compensation models were established and validated experimentally. Finally, we constructed an experimental platform to evaluate the force measurement accuracy, drive accuracy, and real-time detection capability. Experimental results demonstrate that the proposed method achieves a maximum detection error of 0.1482 N, an average error of 0.0096 N, a resolution of 0.01 N, and an average axial delivery error of 0.8287 mm. Additionally, a master–slave control framework was developed, along with a master controller that manipulates the slave robot to deliver the catheter within a vascular phantom, while simultaneously displaying real-time force information via the human–computer interaction interface.
Vessel segmentation is a fundamental task in medical image analysis and plays an important role in disease diagnosis and treatment assessment. However, existing segmentation methods often show limited adaptability to feature extraction from single-channel X-ray coronary angiograms, which restricts their performance in segmenting small vessels and low-contrast vascular regions. To address these limitations, this study proposes a Channel-Attention U-Net, termed CA-UNet, which integrates residual connections and a channel attention mechanism. Based on the conventional encoder–decoder architecture of U-Net, the proposed method introduces a residual-enhanced double-convolution block to alleviate gradient vanishing in deeper networks. In addition, a dual-pooling channel attention module is incorporated to enhance the selection of discriminative vascular features. Furthermore, the data loading, normalization, and augmentation strategies are optimized to improve the adaptability of the network to single-channel PGM grayscale images. Under three-fold out-of-fold evaluation, CA-UNet achieved the highest mean Dice coefficient (0.7450) and IoU (0.5972) among the evaluated models, while maintaining real-time-rate inference at 41.7 frames per second. These results indicate that CA-UNet provides an effective balance of segmentation accuracy, stability, and computational efficiency for vessel segmentation.