A Novel Tongue Coating Segmentation Method Based on Improved TransUNet.

BACKGROUND: As an important part of the tongue, the tongue coating is closely associated with different disorders and has major diagnostic benefits. This study aims to construct a neural network model that can perform complex tongue coating segmentation. This addresses the issue of tongue coating segmentation in intelligent tongue diagnosis automation. METHOD: This work proposes an improved TransUNet to segment the tongue coating. We introduced a transformer as a self-attention mechanism to capture the semantic information in the high-level features of the encoder. At the same time, the subtraction feature pyramid (SFP) and visual regional enhancer (VRE) were constructed to minimize the redundant information transmitted by skip connections and improve the spatial detail information in the low-level features of the encoder. RESULTS: Comparative and ablation experimental findings indicate that our model has an accuracy of 96.36%, a precision of 96.26%, a dice of 96.76%, a recall of 97.43%, and an IoU of 93.81%. Unlike the reference model, our model achieves the best segmentation effect. CONCLUSION: The improved TransUNet proposed here can achieve precise segmentation of complex tongue images. This provides an effective technique for the automatic extraction in images of the tongue coating, contributing to the automation and accuracy of tongue diagnosis.

Improving the Accuracy in Classification of Blood Pressure from Photoplethysmography Using Continuous Wavelet Transform and Deep Learning.

BACKGROUND: Continuous wavelet transform (CWT) based scalogram can be used for photoplethysmography (PPG) signal transformation to classify blood pressure (BP) with deep learning. We aimed to investigate the determinants that can improve the accuracy of BP classification based on PPG and deep learning and establish a better algorithm for the prediction. METHODS: The dataset from PhysioNet was accessed to extract raw PPG signals for testing and its corresponding BPs as category labels. The BP category of normal or abnormal followed the criteria of the 2017 American College of Cardiology/American Heart Association (ACC/AHA) Hypertension Guidelines. The PPG signals were transformed into 224 ∗ 224 ∗ 3-pixel scalogram via different CWTs and segment units. All of them are fed into different convolutional neural networks (CNN) for training and validation. The receiver-operating characteristic and loss and accuracy curves were used to evaluate and compare the performance of different methods. RESULTS: Both wavelet type and segment length could affect the accuracy, and Cgau1 wavelet and segment-300 revealed the best performance (accuracy 90%) without obvious overfitting. This method performed better than previously reported MATLAB Morse wavelet transformed scalogram on both of our proposed CNN and CNN-GoogLeNet. CONCLUSIONS: We have established a new algorithm with high accuracy to predict BP classification from PPG via matching of CWT type and segment length, which is a promising solution for rapid prediction of BP classification from real-time processing of PPG signal on a wearable device.

High-power actively Q-switched Ho-doped gadolinium tantalate laser.

In this paper, we present the acousto-optical (AO) Q-switched performance of a holmium (Ho):gadolinium tantalate (GdTaO4) (Ho:GTO) laser pumped by a thulium (Tm)-fiber laser emitting at 1.94 µm. In the efficient continuous wave (CW) regime, a maximum output power of 30.5 W at 2068.8 nm was achieved, corresponding to a slope efficiency of 74.9% with respect to the absorbed pump power. In the Q-switching regime, pulse energies of 2.4 mJ, 1.2 mJ, and 0.9 mJ were obtained with pulse repetition frequencies of 10 kHz, 20 kHz, and 30 kHz, respectively. The minimum pulse widths were 18 ns, 23 ns, and 26 ns, corresponding to peak powers of approximately 133.3 kW, 52.2 kW, and 34.6 kW, respectively.

Technical Note: Automatic real-time ultrasound tracking of respiratory signal using selective filtering and dynamic template matching.

PURPOSE: In respiratory motion modeling for liver interventions, the respiratory signal is usually obtained by using special tracking devices to monitor external skin. However, due to intrinsic limits and cost consideration of these tracking devices, a purely ultrasound image-based approach to tracking the signal is a more feasible option. METHODS: In this study, a novel image-based method is proposed to obtain the respiratory signal directly from 2D ultrasound images by automatically identifying and tracking the liver boundary. The boundary identification is a multistage process, which is the key to utilize a Hessian matrix-based 2D filter to enhance the line-like liver boundary and weaken other liver tissues. For tracking the identified boundary, a new dynamic template matching technique is first applied to estimate 2D displacements, and a boundary-specific selection mechanism is then introduced to extract the respiratory signal from the 2D displacements. RESULTS: The experiments demonstrate that their method can obtain accurate breathing signals, which are in key phases comparable to the manually annotation and highly consistent to the electromagnetic-tracked ground-truth signals (average correlation coefficients 0.9209 and statistically significant p < 0.01). Meanwhile, the experiments also prove their method can achieve high real-time performance of about 80-160 Hz. CONCLUSIONS: This method provides a good alternative to traditional external-landmark-based tracking methods and may be widely applied for respiratory compensation in ultrasound-guided liver interventions.

A manifold learning method to detect respiratory signal from liver ultrasound images.

Respiratory gating has been widely applied for respiratory correction or compensation in image acquisition and image-guided interventions. A novel image-based method is proposed to extract respiratory signal directly from 2D ultrasound liver images. The proposed method utilizes a typical manifold learning method, based on local tangent space alignment based technique, to detect principal respiratory motion from a sequence of ultrasound images. This technique assumes all the images lying on a low-dimensional manifold embedding into the high-dimensional image space, constructs an approximate tangent space of each point to represent its local geometry on the manifold, and then aligns the local tangent spaces to form the global coordinate system, where the respiratory signal is extracted. The experimental results show that the proposed method can detect relatively accurate respiratory signal with high correlation coefficient (0.9775) with respect to the ground-truth signal by tracking external markers, and achieve satisfactory computing performance (2.3s for an image sequence of 256 frames). The proposed method is also used to create breathing-corrected 3D ultrasound images to demonstrate its potential application values.

Fast and robust extraction of surrogate respiratory signal from intra-operative liver ultrasound images.

PURPOSE:    In model-based respiratory motion estimation for the liver or other abdominal organs, the surrogate respiratory signal is usually obtained by using special tracking devices from skin or diaphragm, and subsequently applied to parameterize a 4D motion model for prediction or compensation. However, due to the intrinsic limits and economical costs of these tracking devices, the identification of the respiratory signal directly from intra-operative ultrasound images is a more attractive alternative. METHODS:    We propose a fast and robust method to extract the respiratory motion of the liver from an intra-operative 2D ultrasound image sequence. Our method employs a preprocess to remove speckle-like noises in the ultrasound images and utilizes the normalized cross-correlation to measure the image similarity fast. More importantly, we present a novel adaptive search strategy, which makes full use of the inter-frame dependency of the image sequence. This search strategy narrows the search range of the optimal matching, thus greatly reduces the search time, and makes the matching process more robust and accurate. RESULTS:    The experimental results on four volunteers demonstrate that our method is able to extract the respiratory signal from an image sequence of 256 image frames in 5 s. The quantitative evaluation using the correlation coefficient reveals that the respiratory motion, extracted near the liver boundaries and vessels, is highly consistent with the reference motion tracked by an EM device. CONCLUSIONS:    Our method can use 2D ultrasound to track natural landmarks from the liver as surrogate respiratory signal and hence provide a feasible solution to replace special tracking devices.