A novel deep learning method to segment parathyroid glands on intraoperative videos of thyroid surgery.

Introduction: The utilization of artificial intelligence (AI) augments intraoperative safety and surgical training. The recognition of parathyroid glands (PGs) is difficult for inexperienced surgeons. The aim of this study was to find out whether deep learning could be used to auxiliary identification of PGs on intraoperative videos in patients undergoing thyroid surgery. Methods: In this retrospective study, 50 patients undergoing thyroid surgery between 2021 and 2023 were randomly assigned (7:3 ratio) to a training cohort (n = 35) and a validation cohort (n = 15). The combined datasets included 98 videos with 9,944 annotated frames. An independent test cohort included 15 videos (1,500 frames) from an additional 15 patients. We developed a deep-learning model Video-Trans-U-HRNet to segment parathyroid glands in surgical videos, comparing it with three advanced medical AI methods on the internal validation cohort. Additionally, we assessed its performance against four surgeons (2 senior surgeons and 2 junior surgeons) on the independent test cohort, calculating precision and recall metrics for the model. Results: Our model demonstrated superior performance compared to other AI models on the internal validation cohort. The DICE and accuracy achieved by our model were 0.760 and 74.7% respectively, surpassing Video-TransUnet (0.710, 70.1%), Video-SwinUnet (0.754, 73.6%), and TransUnet (0.705, 69.4%). For the external test, our method got 89.5% precision 77.3% recall and 70.8% accuracy. In the statistical analysis, our model demonstrated results comparable to those of senior surgeons (senior surgeon 1: χ2 = 0.989, p = 0.320; senior surgeon 2: χ2 = 1.373, p = 0.241) and outperformed 2 junior surgeons (junior surgeon 1: χ2 = 3.889, p = 0.048; junior surgeon 2: χ2 = 4.763, p = 0.029). Discussion: We introduce an innovative intraoperative video method for identifying PGs, highlighting the potential advancements of AI in the surgical domain. The segmentation method employed for parathyroid glands in intraoperative videos offer surgeons supplementary guidance in locating real PGs. The method developed may have utility in facilitating training and decreasing the learning curve associated with the use of this technology.

Enzymatic functionalization of decellularized tilapia skin scaffolds with enhanced skin regeneration.

The decellularized tilapia skin (dTS) has gained significant attention as a promising material for tissue regeneration due to its ability to provide unique structural and functional components that support cell growth, adhesion, and proliferation. However, the clinical application of dTS is limited by its low mechanical strength and rapid biodegradability. Herein, we prepare a novel RGD (arginine-glycine-aspartic acid) functionalized dTS scaffold (dTS/RGD) by using transglutaminase (TGase) crosslinking. The developed dTS/RGD scaffold possesses excellent properties, including a medium porosity of ∼59.2%, a suitable degradation rate of approximately 80% over a period of two weeks, and appropriate mechanical strength with a maximum tensile stress of ∼46.36 MPa which is much higher than that of dTS (∼32.23 MPa). These properties make the dTS/RGD scaffold ideal for promoting cell adhesion and proliferation, thereby accelerating skin wound healing in a full-thickness skin defect model. Such an enzymatic cross-linking strategy provides a favorable microenvironment for wound healing and holds great potential for application in skin regeneration engineering.

A novel wavelet-transform-based convolution classification network for cervical lymph node metastasis of papillary thyroid carcinoma in ultrasound images.

Preoperative assessment of cervical lymph nodes metastasis (CLNM) for accurate qualitative and locating diagnosis is important for choosing the best treatment option for patients with papillary thyroid cancer. Non-destructive, non-invasive ultrasound is currently the imaging method of choice for lymph node metastatic assessment. For lymph node characteristics and ultrasound images, this paper proposes a multitasking network framework for diagnosing metastatic lymph nodes in ultrasound images, in which localization module not only provides information on the location of lymph nodes to focus on the peripheral and self regions of lymph nodes, but also provides structural features of lymph nodes for subsequent classification module. In the classification module, we design a novel wavelet-transform-based convolution network. Wavelet transform is introduced into the deep learning convolution module to analyze ultrasound images in both spatial and frequency domains, which effectively enriches the feature information and improves the classification performance of the model without increasing the model parameters. We collected 510 patient data (N = 1376) from Shanghai Sixth People's Hospital regarding ultrasound lymph nodes in the neck, as well as used three publicly available ultrasound datasets, including SCUI2020 (N = 2914), DDTI (N = 480), and BUSI (N = 780). Compared to the optimal two-stage model, our model has improved its accuracy and AUC indexes by 5.83% and 4%, which outperforms the two-stage architectures and also surpasses the latest classification networks.

Automated classification of cervical lymph-node-level from ultrasound using Depthwise Separable Convolutional Swin Transformer.

There are few studies on cervical ultrasound lymph-node-level classification which is very important for qualitative diagnosis and surgical treatment of diseases. Currently, ultrasound examination relies on the subjective experience of physicians to judge the level of the cervical lymph nodes, which is easily misclassified. Unlike other automated diagnostic tasks, lymph-node-level classification needs to focus on global structural information. Besides, there is a large range of sternocleidomastoid muscles in levels II, III and IV, which leads to small inter-class differences in these levels, so it also needs to focus on key local areas to extract strong distinguishable features. In this paper, we propose the Depthwise Separable Convolutional Swin Transformer, introducing the deepwise separable convolution branch into the self-attention mechanism to capture discriminative local features. Meanwhile, to address the problem of data imbalance, a new loss function is proposed to improve the performance of the classification network. In addition, for the ultrasound data collected by different devices, low contrast and blurring problems of ultrasound imaging, a unified pre-processing algorithm is designed. The model was validated on 1146 cases of cervical ultrasound lymph node collected from the Sixth People's Hospital of Shanghai. The average accuracy precision, sensitivity, specificity, and F1 value of the model for the valid dataset after five-fold cross-validation were 80.65%, 80.68%, 78.73%, 95.99% and 79.42%, respectively. It has been verified by visualization methods that the Region of Interest (ROI) of the model is similar or consistent with the observed region of the experts.

A Deep Learning Method Approach for Sleep Stage Classification with EEG Spectrogram.

The classification of sleep stages is an important process. However, this process is time-consuming, subjective, and error-prone. Many automated classification methods use electroencephalogram (EEG) signals for classification. These methods do not classify well enough and perform poorly in the N1 due to unbalanced data. In this paper, we propose a sleep stage classification method using EEG spectrogram. We have designed a deep learning model called EEGSNet based on multi-layer convolutional neural networks (CNNs) to extract time and frequency features from the EEG spectrogram, and two-layer bi-directional long short-term memory networks (Bi-LSTMs) to learn the transition rules between features from adjacent epochs and to perform the classification of sleep stages. In addition, to improve the generalization ability of the model, we have used Gaussian error linear units (GELUs) as the activation function of CNN. The proposed method was evaluated by four public databases, the Sleep-EDFX-8, Sleep-EDFX-20, Sleep-EDFX-78, and SHHS. The accuracy of the method is 94.17%, 86.82%, 83.02% and 85.12%, respectively, for the four datasets, the MF1 is 87.78%, 81.57%, 77.26% and 78.54%, respectively, and the Kappa is 0.91, 0.82, 0.77 and 0.79, respectively. In addition, our proposed method achieved better classification results on N1, with an F1-score of 70.16%, 52.41%, 50.03% and 47.26% for the four datasets.

MultiR-Net: A Novel Joint Learning Network for COVID-19 segmentation and classification.

The outbreak of COVID-19 has caused a severe shortage of healthcare resources. Ground Glass Opacity (GGO) and consolidation of chest CT scans have been an essential basis for imaging diagnosis since 2020. The similarity of imaging features between COVID-19 and other pneumonia makes it challenging to distinguish between them and affects radiologists' diagnosis. Recently, deep learning in COVID-19 has been mainly divided into disease classification and lesion segmentation, yet little work has focused on the feature correlation between the two tasks. To address these issues, in this study, we propose MultiR-Net, a 3D deep learning model for combined COVID-19 classification and lesion segmentation, to achieve real-time and interpretable COVID-19 chest CT diagnosis. Precisely, the proposed network consists of two subnets: a multi-scale feature fusion UNet-like subnet for lesion segmentation and a classification subnet for disease diagnosis. The features between the two subnets are fused by the reverse attention mechanism and the iterable training strategy. Meanwhile, we proposed a loss function to enhance the interaction between the two subnets. Individual metrics can not wholly reflect network effectiveness. Thus we quantify the segmentation results with various evaluation metrics such as average surface distance, volume Dice, and test on the dataset. We employ a dataset containing 275 3D CT scans for classifying COVID-19, Community-acquired Pneumonia (CAP), and healthy people and segmented lesions in pneumonia patients. We split the dataset into 70% and 30% for training and testing. Extensive experiments showed that our multi-task model framework obtained an average recall of 93.323%, an average precision of 94.005% on the classification test set, and a 69.95% Volume Dice score on the segmentation test set of our dataset.

AUE-Net: Automated Generation of Ultrasound Elastography Using Generative Adversarial Network.

PROBLEM: Ultrasonography is recommended as the first choice for evaluation of thyroid nodules, however, conventional ultrasound features may not be able to adequately predict malignancy. Ultrasound elastography, adjunct to conventional B-mode ultrasound, can effectively improve the diagnostic accuracy of thyroid nodules. However, this technology requires professional elastography equipment and experienced physicians. AIM: in the field of computational medicine, Generative Adversarial Networks (GANs) were proven to be a powerful tool for generating high-quality images. This work therefore utilizes GANs to generate ultrasound elastography images. METHODS: this paper proposes a new automated generation method of ultrasound elastography (AUE-net) to generate elastography images from conventional ultrasound images. The AUE-net was based on the U-Net architecture and optimized by attention modules and feature residual blocks, which could improve the adaptability of feature extraction for nodules of different sizes. The additional color loss function was used to balance color distribution. In this network, we first attempted to extract the tissue features of the ultrasound image in the latent space, then converted the attributes by modeling the strain, and finally reconstructed them into the corresponding elastography image. RESULTS: a total of 726 thyroid ultrasound elastography images with corresponding conventional images from 397 patients were obtained between 2019 and 2021 as the dataset (646 in training set and 80 in testing set). The mean rating accuracy of the AUE-net generated elastography images by ultrasound specialists was 84.38%. Compared with that of the existing models in the visual aspect, the presented model generated relatively higher quality elastography images. CONCLUSION: the AUE-net generated ultrasound elastography images showed natural appearance and retained tissue information. Accordingly, it seems that B-mode ultrasound harbors information that can link to tissue elasticity. This study may pave the way to generate ultrasound elastography images readily without the need for professional equipment.

Theoretical model of membrane acoustic absorber with compact magnet.

The membrane sound absorber (MSA) with a compact magnet has exhibited excellent tunable properties for low-frequency sound absorption. To further clarify its acoustic properties, this paper presents a theoretical model based on a multi-mechanism coupling impedance method. The model predicts the absorption coefficients and resonant frequencies of the MSA at different tuning magnetic states for three cavity configurations. These parameters are then experimentally measured using an impedance tube for model validation, demonstrating good agreement between the measured and predicted values. Subsequent analysis reveals the iron-platelet-magnet resonance mechanism introduced by the tuned magnetic field is the main factor behind the appearance and shift of absorption peaks in the low-frequency region, which are mostly independent of the back cavity. In other words, the MSA with a back cavity of any size can achieve sound absorption in the low-frequency region. This demonstrates the potential of the structure in achieving an ultra-thin, low-frequency, tunable sound-absorber design that can be adapted to different noise sources.

Broadband low frequency sound absorption using a monostable acoustic metamaterial.

This Letter presents a monostable acoustic metamaterial that has the potential to implement broadband sound absorption in low frequencies. The proposed metamaterial is realized by placing a flexible panel with a magnetic proof mass in a symmetric magnetic field. A theoretical model of the metamaterial is established and experimentally validated. Predictions and measurements demonstrate that the sound absorption peak frequency significantly shifts downwards with the increasing magnetic field. The relative bandwidth of the metamaterial is also broadened with the increasing magnetic field due to its inverse proportionality to the absorption peak frequency.

Membrane-type acoustic metamaterials with tunable frequency by a compact magnet.

In this letter, a membrane-type acoustic metamaterial with a compact magnet (MAMM) is presented. To investigate its frequency-tunable properties, a theoretical model considering both static and dynamic effects of magnetic force is established. Analytical investigations indicate that tuning of the magnetic force exerted on the centralized rigid iron platelet leads to the shift in the MAMM's transmission loss peaks. The experimental anti-resonance frequencies of the MAMM derived from the impedance tube measurements exhibited good consistency with those predicted theoretically. Continuously tuned in a wide frequency range, this structure can well adapt to the noise source variation in insulation design.

Membrane acoustic metamaterial absorbers with magnetic negative stiffness.

A membrane absorber usually requires a large back cavity to achieve low-frequency sound absorption. This paper describes the design of a membrane acoustic metamaterial absorber in which magnetic negative stiffness is employed to reduce the size of the back cavity. As a baseline for the present research, analysis of a typical membrane sound absorber based on an equivalent circuit model is presented first. Then, a theoretical model is established by introducing negative stiffness into a standard absorber. It is demonstrated that a small cavity with negative stiffness can achieve the acoustic impedance of a large cavity and that the absorption peak is shifted to lower frequencies. Experimental results from an impedance tube test are also presented to validate this idea and show that negative stiffness can be employed to design compact low-frequency membrane absorbers.

Photoacoustic detection of CO2 based on LABVIEW at 10.303 µm.

A detailed study on a photoacoustic carbon dioxide detection system, through sound card based on virtual instrument, is presented in this paper. In this system, the CO(2) concentration was measured with the non-resonant photoacoustic cell technique through measuring the photoacoustic signal caused by the CO(2). In order to obtain small photoacoustic signals buried in noise, a measurement software was designed with LABVIEW. It has functions of Lock-in Amplifier, digital filter, and signal generator; can also be used to achieve spectrum analysis and signal recovery; has been provided with powerful function for data processing and communication with other measuring instrument. The test results show that the entire system has an outstanding measuring performance with the sensitivity of 10 µv between 10-44 KHz. The non-resonance test of the trace gas analyte CO(2) conducted at 100 Hz demonstrated large signals (15.89 mV) for CO(2) concentrations at 600 ppm and high signal-to-noise values (∼85:1).