Medical image segmentation methods based on deep learning network are mainly divided into CNN and Transformer. However, CNN struggles to capture long-distance dependencies, while Transformer suffers from high computational complexity and poor local feature learning. To efficiently extract and fuse local features and long-range dependencies, this paper proposes Rolling-Unet, which is a CNN model combined with MLP. Specifically, we propose the core R-MLP module, which is responsible for learning the long-distance dependency in a single direction of the whole image. By controlling and combining R-MLP modules in different directions, OR-MLP and DOR-MLP modules are formed to capture long-distance dependencies in multiple directions. Further, Lo2 block is proposed to encode both local context information and long-distance dependencies without excessive computational burden. Lo2 block has the same parameter size and computational complexity as a 3×3 convolution. The experimental results on four public datasets show that Rolling-Unet achieves superior performance compared to the state-of-the-art methods.

Calibration is required to maximize the sensitivity and measurement accuracy of vibration sensors. In this study, a low-frequency vibration calibration method is proposed that is based on the concept of monocular vision. In this method, we employ a high-accuracy edge extraction method to extract the edges of sequential images so as to obtain the high calibration accuracy. However, the proposed method must rely on a long-stroke shaker to provide vibration excitation to the sensor, and the bending in the guideway caused by the mechanical processing reduces the calibration accuracy, especially at very low frequencies. The proposed setting compensates for the bending using an additional monocular vision technique to significantly improve the calibration accuracy. To validate the calibration accuracy of the proposed method, a comparison was conducted between results obtained via the laser interferometry, the Earth's gravitation method, and the proposed method when applied to calibrate the sensitivity of a tri-axial acceleration sensor at frequencies between 0.04 and 8 Hz. The results of the comparison showed the proposed method calibrated the sensor sensitivity with high accuracy and was able to accurately account for the bending when the frequency was lower than 0.3 Hz. In contrast, the calibration accuracy of the laser interferometry decreased because of the bending.

The detection of surface defects on automotive engine parts is an important part of automobile manufacturing quality assurance. The traditional detection methods rely on manual inspection and can be inaccurate and inefficient, while the existing deep learning-based methods, such as the Mask R-CNN detection method, have insufficient precision for detecting minor defects since the anchor scales design does not consider small defects. To overcome these shortcomings, this paper proposes an IA-Mask R-CNN detection method with an improved anchor scales design. First, an image dataset that contains 560 pictures of surface defects of automotive engine parts is established using a 1080P HDMI high-definition digital microscope capable of recording three million real pixels and labeled manually. Then, the anchor scales suitable for the surface defect detection of automotive engine parts are determined by labeled data analysis and used to improve the anchor design in Mask R-CNN. Finally, the proposed method is compared experimentally with the Faster R-CNN and Mask R-CNN, and qualitative and quantitative analyses are conducted. The experimental results show that, without increasing the number of parameters or training time of the Mask R-CNN, the proposed method performed better in detecting minor, as well as larger defects than the other detection methods.

The grading evaluation of metacarpophalangeal rheumatoid arthritis (RA) ultrasonic images is a diagnostic challenge that heavily relies on the expertise of trained sonographers. This study presents a grading method for detecting and estimating the geometric and texture features of synovium thickening and bone erosion. Unlike previous studies in this area, this work uses the metrics and texture features of region of interest (ROI). The highlighted feature of metacarpophalangeal bone and the dark feature of the synovial thickening are extracted simultaneously by the segmented method based on the Gaussian scale space. The segmented results are analyzed to extract three quantitative geometric parameters, which are combined with gray-level co-occurrence matrix (GLCM) statistic texture features to describe the ultrasonic image of metacarpophalangeal RA. To obtain the preferable ability of classification, we applied a support vector machine (SVM) and various feature descriptors, including GLCM, local binary patterns (LBP), and GLCM + LBP, to grade the ultrasonic image of metacarpophalangeal RA. Results show that the SVM, based on our feature descriptor, provides the highest accuracy of up to 92.50%, of the four descriptors. The SVM based on GLCM+LBP descriptor shows better accuracy (86.55%) than either SVM + LBP (85.43%) or SVM+GLCM (82.51%) for discriminating among four grade RA ultrasonic images. Overall, this methodology points to a significant grading of metacarpophalangeal RA ultrasound images without medical expert analysis or blood sample analysis, such as detecting C-reactive protein, measuring erythrocyte sedimentation rate, and testing rheumatoid factor.

Heterodyne interferometers have been widely used for primary vibration calibration in recent years. Primary vibration calibration performance depends on the precision and real-time nature of vibration measurements, factors determined by the acquisition and demodulation of the heterodyne interferometer signal. This signal is commonly collected using the Nyquist sampling method, requiring devices with high sampling rates and large memories, or a sampling method using a mixer and low-pass filter—analog devices which may create time delays. This study proposes a novel bandpass sampling method that reduces sampling rate and storage capacity without generating time delays. To improve vibration measurement precision, an optimal sampling rate is designed to collect the heterodyne interferometer signal, and the collected signal is demodulated using the phase-unwrapping sine approximation method. The proposed method is compared with existing methods through simulated and experimental data. Experimental results show that the proposed method avoids time delays and high sampling rates, while providing high-precision vibration measurements.