22 October 2021 in IEEE Transactions on Instrumentation and Measurement
Genitourinary syndrome of menopause (GSM) is a disease caused by a physiological decline in estrogen levels, and it can negatively affect a woman’s overall health and quality of life in terms of sexual function. Real-time optical biopsy images can now be obtained with optical coherence tomography (OCT) systems. In this study, we introduce vision transformer (ViT) to the field of medical OCT images for the first time and propose a deep learning-based approach for GSM lesion screening. Specifically, we first build a GSM dataset to train and evaluate the experimental model performance. The study aims to propose a method that combines null convolution with a deep convolutional adversarial generative network classifier to generate the samples needed for training to alleviate the hindrance of such problems, in response to certain practical problems, such as category imbalance that occur during data collection. Next, the experiments present ViT PLUS (ViT-P) for the vaginal OCT image classification task used, which effectively improves the shortcomings of ViT in extracting Patch Embedding using a multibranch convolutional neural network combined with a channel attention mechanism. The clinical images acquired by the OCT device are then automatically classified on the basis of the OCT device to reduce the medical workload of gynecologists. Experimental results show that the ViT-P model outperforms the CNN model and ViT for case screening in the GSM and UCSD datasets, and the accuracy can reach 99.9% and 99.69%, respectively.
18 May 2021 in IEEE Transactions on Instrumentation and Measurement
Real-time identification of threats has been the focus of attention in the security field in recent years. Researchers have aimed to build a fast, efficient, and accurate model to address risks in threat event identification. This study proposes a fast, effective deep learning model-the squeeze and excitation WaveNet (SE-WaveNet). WaveNet is a 1-D convolutional neural network (CNN) model with a large receptive field. It is small, fast, and highly accurate. Thus, it has a great advantage in processing time series data. On this basis, the squeeze and excitation (SE) structure of the attention mechanism is introduced to adapt to matrix data with complete information. To ensure the integrity of information in the experimental verification, the distributed optical fiber vibration sensing (DVS) system is used to collect the data near the vibration point and form the time-space matrix as the input of the model. SE-WaveNet is compared with WaveNet and related models. Results show that the accuracy of SE-WaveNet based on WaveNet is increased by approximately 3.5%, the model size is reduced by 39%, and the speed is increased by 32%. Compared with the five other related models, the average performance is 3%-9% higher, and the final test accuracy rate can reach approximately 97.73%.
1 November 2023 in IEEE Transactions on Instrumentation and Measurement
Diabetic retinopathy (DR) is a common complication of diabetes and one of the main causes of blindness in humans, which can be prevented by early-stage detection and treatment. Clinically, ophthalmologists use optical coherence tomography (OCT) image analysis as a basis for diagnosing DR. The existing medical resources can no longer meet the needs of the escalating patient population. Therefore, deep learning technology has become a mainstream solution for medical image analysis. Vision Transformer (ViT), a new neural network structure, has demonstrated great performance in analyzing images. However, due to the lack of inductive bias and prohibition of input image changes in size, ViT cannot avoid over-fitting problems on small datasets and limits the model to biological tissue characteristics. Thus, we propose an OCT multi-head self-attention (OMHSA) block that especially calculates OCT image information based on a hybrid CNN-Transformer strategy. Compared to traditional MHSA, OMHSA integrates local information extraction differences into the calculation of self-attention and adds local information to the transformer model without relying on a multi-branch network establishment. We built a neural network architecture (OCT-Former) by stacking convolutional layers and OMHSA blocks repeatedly in each stage. Similar to CNN, OCTFormer allows input size change at each stage to achieve a hierarchical structure effect. The model diagnosis effectiveness on the collected retinal OCT dataset was evaluated, and the accuracy reached 98.60%, surpassing the state-of-the-art (SOTA) model. The OCTFormer deployment to mobile terminals through knowledge distillation technology was shown, which presented a reference for deploying transformer models to actual clinical environments.
8 November 2023 in IEEE Sensors Journal
Distributed optical acoustic sensing (DAS) based on phase-sensitive optical time-domain reflectometry (Φ-OTDR) can realize the distributed monitoring of multi-point disturbances along the optical fiber, which has wide-ranging applications in various fields. However, owing to the fading phenomenon in the DAS, the signal strength is greatly attenuated, thereby causing the phase signal to jump and complicating the continuous and effective collection of the disturbance signal. Considering the amplitude, we propose a fading adaptive mask and masked autoencoders (FAM-MAE) algorithm for fading discrimination and suppression of DAS system. The differential calculation and analysis of the amplitude signal are performed, and the non-differentiable point is the fading point. The density-based spatial clustering of applications with noise (DBSCAN) is used to determine the position of the phase fading point. The masked autoencoders (MAE) were used to reconstruct these positions to achieve fading suppression. The experimental results indicate that the average signal-to-noise ratio (SNR) of the vibration signal of piezoelectric transducer (PZT) is improved from 4.81 to 21.92 dB after fading suppression. The SNR of the underwater acoustic disturbance signal is improved by 12.68 dB after fading suppression. Therefore, the proposed method can suppress the signal distortion caused by fading and recover the disturbance signal completely.