Multi-signal feature fusion method with an attention mechanism for the Φ-OTDR event recognition system.

Different signal representations show different unique features for classification. In this paper, a feature fusion method with attention mechanism based on multiple signal representations is proposed for Φ-OTDR event classification with buried optical fiber. Each signal representation is fused after feature extraction to get richer and better features. With the help of a layer pruning method based on attention mechanism, the network size can be kept and avoid computation increase. Experiment results show that this method with 3 signal representations can improve the recognition accuracy to 97.93%, with 3.52% improvement compared to single representation approach. It also shows higher recognition accuracy than the tradition multiple signal representations fusion methods at the input stage. Furthermore, when it is used to fuse four representations, the recognition accuracy can be further improved to 99.11%.

Health status monitoring of bridge cable and telescopic compensation device based on fiber grating sensing array.

Laying power cables along the bridge is a new way of laying submarine cables across the sea. Monitoring the health status of cables and their telescopic compensation devices is necessary. In this study, fiber grating sensing technology was used to monitor the strain, temperature, and vibration of the bridge cable of the Zhoushan-Daishan Bridge in Zhoushan, Zhejiang Province, and its compensation device. Two typhoons and one invasion event happened during the monitoring period. Temperature signals, strain signals, and time domain and time-frequency domain vibration signals were analyzed. The results showed that no fire hazards or risk of external damage were found with the bridge cable, and the monitoring system filled a gap in the in situ monitoring of the bridge cable in the Zhoushan-Daishan Bridge by the State Grid.

An Ankle Joint Flexion and Extension Movement-Monitoring Device Based on Pressure Sensors.

Ankle joint flexion and extension movements play an important role in the rehabilitation training of patients who have been injured or bedridden for a long time before and after surgery. Accurately guiding patients to perform ankle flexion and extension movements can significantly reduce deep vein thromboembolism. Currently, most ankle rehabilitation devices focus on assisting patients with ankle flexion and extension movements, and there is a lack of devices for effectively monitoring these movements. In this study, we designed an ankle joint flexion and extension movement-monitoring device based on a pressure sensor. It was composed of an STM32 microcontroller, a pressure sensor, an HX711A/D conversion chip, and an ESP8266 WiFi communication module. The value of the force and the effective number of ankle joint flexion and extension movements were obtained. An experimental device was designed to verify the accuracy of the system. The maximum average error was 0.068 N; the maximum average relative error was 1.7%; the maximum mean-squared error was 0.00464 N. The results indicated that the monitoring device had a high accuracy and could effectively monitor the force of ankle flexion and extension movements, ultimately ensuring that the patient could effectively monitor and grasp the active ankle pump movement.

Segmentation of retinal vessels in fundus images based on U-Net with self-calibrated convolutions and spatial attention modules.

Automated and accurate segmentation of retinal vessels in fundus images is an important step for screening and diagnosing various ophthalmologic diseases. However, many factors, including the variations of vessels in color, shape and size, make this task become an intricate challenge. One kind of the most popular methods for vessel segmentation is U-Net based methods. However, in the U-Net based methods, the size of the convolution kernels is generally fixed. As a result, the receptive field for an individual convolution operation is single, which is not conducive to the segmentation of retinal vessels with various thicknesses. To overcome this problem, in this paper, we employed self-calibrated convolutions to replace the traditional convolutions for the U-Net, which can make the U-Net learn discriminative representations from different receptive fields. Besides, we proposed an improved spatial attention module, instead of using traditional convolutions, to connect the encoding part and decoding part of the U-Net, which can improve the ability of the U-Net to detect thin vessels. The proposed method has been tested on Digital Retinal Images for Vessel Extraction (DRIVE) database and Child Heart and Health Study in England Database (CHASE DB1). The metrics used to evaluate the performance of the proposed method are accuracy (ACC), sensitivity (SE), specificity (SP), F1-score (F1) and the area under the receiver operating characteristic curve (AUC). The ACC, SE, SP, F1 and AUC obtained by the proposed method are 0.9680, 0.8036, 0.9840, 0.8138 and 0.9840 respectively on DRIVE database, and 0.9756, 0.8118, 0.9867, 0.8068 and 0.9888 respectively on CHASE DB1, which are better than those obtained by the traditional U-Net (the ACC, SE, SP, F1 and AUC obtained by U-Net are 0.9646, 0.7895, 0.9814, 0.7963 and 0.9791 respectively on DRIVE database, and 0.9733, 0.7817, 0.9862, 0.7870 and 0.9810 respectively on CHASE DB1). The experimental results indicate that the proposed modifications in the U-Net are effective for vessel segmentation. The structure of the proposed network.

Direct Estimation of Choroidal Thickness in Optical Coherence Tomography Images with Convolutional Neural Networks.

Automatic and accurate estimation of choroidal thickness plays a very important role in a computer-aided system for eye diseases. One of the most common methods for automatic estimation of choroidal thickness is segmentation-based methods, in which the boundaries of the choroid are first detected from optical coherence tomography (OCT) images. The choroidal thickness is then computed based on the detected boundaries. A shortcoming in the segmentation-based methods is that the estimating precision greatly depends on the segmentation results. To avoid the dependence on the segmentation step, in this paper, we propose a direct method based on convolutional neural networks (CNNs) for estimating choroidal thickness without segmentation. Concretely, a B-scan image is first cropped into several patches. A trained CNN model is then used to estimate the choroidal thickness for each patch. The mean thickness of the choroid in the B-scan is obtained by taking the average of the choroidal thickness on each patch. Then, 150 OCT volumes are collected to evaluate the proposed method. The experiments show that the results obtained by the proposed method are very competitive with those obtained by segmentation-based methods, which indicates that direct estimation of choroidal thickness is very promising.

Breast ultrasound tumor image classification using image decomposition and fusion based on adaptive multi-model spatial feature fusion.

BACKGROUND AND OBJECTIVE: Breast cancer is a fatal threat to the health of women. Ultrasonography is a common method for the detection of breast cancer. Computer-aided diagnosis of breast ultrasound images can help doctors in diagnosing benign and malignant lesions. In this paper, by combining image decomposition and fusion techniques with adaptive spatial feature fusion technology, a reliable classification method for breast ultrasound images of tumors is proposed. METHODS: First, fuzzy enhancement and bilateral filtering algorithms are used to process the original breast ultrasound image. Then, various decomposition images representing the clinical characteristics of breast tumors are obtained using the original and mask images. By considering the diversity of the benign and malignant characteristic information represented by each decomposition image, the decomposition images are fused through the RGB channel, and three types of fusion images are generated. Then, from a series of candidate deep learning models, transfer learning is used to select the best model as the base model to extract deep learning features. Finally, while training the classification network, adaptive spatial feature fusion technology is used to train the weight network to complete deep learning feature fusion and classification. RESULTS: In this study, 1328 breast ultrasound images were collected for training and testing. The experimental results show that the values of accuracy, precision, specificity, sensitivity/recall, F1 score, and area under the curve of the proposed method were 0.9548, 0.9811, 0.9833, 0.9392, 0.9571, and 0.9883, respectively. CONCLUSION: Our research can automate breast cancer detection and has strong clinical utility. When compared to previous methods, our proposed method is expected to be more effective while assisting doctors in diagnosing breast ultrasound images.

Tumor classification in automated breast ultrasound (ABUS) based on a modified extracting feature network.

People can get consistent Automated Breast Ultrasound (ABUS) images due to the imaging mechanism of scanning. Therefore, it has unique advantages in breast tumor classification using artificial intelligence technology. This paper proposes a method for classifying benign and malignant breast tumors using ABUS sequence based on deep learning. First, Images of Interest (IOI) will be extracted and Region of Interest (ROI) will be cropped in ABUS sequence by two preprocessing deep learning models, Extracting-IOI model and Cropping-ROI model. Then, we propose a Shallowly Dilated Convolutional Branch Network (SDCB-Net). We combine this network with the VGG16 transfer learning network to construct a brand-new Shared Extracting Feature Network (SEF-Net) to extract ROI sequence features. Finally, the correlation features of ABUS images are extracted and integrated by using GRU Classified Network (GRUC-Net) to achieve the accurate breast tumors classification. The final results show that the accuracy of the test set for classifying benign and malignant ABUS sequence is 92.86 %. This method not only has high accuracy but also greatly improves the speed and efficiency of breast tumor classification. It has high clinical application significance that more women can discover breast tumors timely.