An optimised YOLOv4 deep learning model for efficient malarial cell detection in thin blood smear images.

BACKGROUND: Malaria is a serious public health concern worldwide. Early and accurate diagnosis is essential for controlling the disease's spread and avoiding severe health complications. Manual examination of blood smear samples by skilled technicians is a time-consuming aspect of the conventional malaria diagnosis toolbox. Malaria persists in many parts of the world, emphasising the urgent need for sophisticated and automated diagnostic instruments to expedite the identification of infected cells, thereby facilitating timely treatment and reducing the risk of disease transmission. This study aims to introduce a more lightweight and quicker model-but with improved accuracy-for diagnosing malaria using a YOLOv4 (You Only Look Once v. 4) deep learning object detector. METHODS: The YOLOv4 model is modified using direct layer pruning and backbone replacement. The primary objective of layer pruning is the removal and individual analysis of residual blocks within the C3, C4 and C5 (C3-C5) Res-block bodies of the backbone architecture's C3-C5 Res-block bodies. The CSP-DarkNet53 backbone is simultaneously replaced for enhanced feature extraction with a shallower ResNet50 network. The performance metrics of the models are compared and analysed. RESULTS: The modified models outperform the original YOLOv4 model. The YOLOv4-RC3_4 model with residual blocks pruned from the C3 and C4 Res-block body achieves the highest mean accuracy precision (mAP) of 90.70%. This mAP is > 9% higher than that of the original model, saving approximately 22% of the billion floating point operations (B-FLOPS) and 23 MB in size. The findings indicate that the YOLOv4-RC3_4 model also performs better, with an increase of 9.27% in detecting the infected cells upon pruning the redundant layers from the C3 Res-block bodies of the CSP-DarkeNet53 backbone. CONCLUSIONS: The results of this study highlight the use of the YOLOv4 model for detecting infected red blood cells. Pruning the residual blocks from the Res-block bodies helps to determine which Res-block bodies contribute the most and least, respectively, to the model's performance. Our method has the potential to revolutionise malaria diagnosis and pave the way for novel deep learning-based bioinformatics solutions. Developing an effective and automated process for diagnosing malaria will considerably contribute to global efforts to combat this debilitating disease. We have shown that removing undesirable residual blocks can reduce the size of the model and its computational complexity without compromising its precision.

Muscular Function Recovery from General Anesthesia in 132 Patients Undergoing Surgery with Acceleromyography, Combined Acceleromyography, and Ultrasonography, and without Monitoring Muscular Function.

BACKGROUND Diaphragmatic thickness fraction (DTF), measured by ultrasound, can predict the occurrence of postoperative residual neuromuscular blockade (RNMB). We hypothesized that the utilization of diaphragmatic ultrasound during the postoperative awakening phase of anesthesia in patients offers a successful means of avoiding RNMB in a notably comfortable manner, as compared to the use of acceleromyograph. MATERIAL AND METHODS Patients who underwent elective thyroid cancer radical surgery were enrolled in this prospective clinical study. Eligible participants were randomly assigned to 1 of 3 groups: 1) combined ultrasonography with acceleromyography group (the US+AMG group), 2) the AMG group, or 3) the usual clinical practice group (the UCP group). The primary outcomes of the study were the incidence of RNMB and hypoxemia after tracheal extubation. RESULTS The study included a total of 127 patients (43 in the US+AMG group, 44 in the AMG group, and 40 in the UCP group). The incidence of RNMB and hypoxemia was higher in the UCP group than in the US+AMG and AMG groups at 15 and 30 min after extubation, respectively. The mean area under the receiver operating characteristic curve, and the decision curve of the recovery rate of DTF (DTF) was greater than that of DTF. CONCLUSIONS The use of diaphragm ultrasound during the postoperative awakening phase of anesthesia can significantly reduce the incidence of RNMB. This method was non-inferior to the use of AMG during the entire perioperative period.

The effect of glycopyrrolate vs. atropine in combination with neostigmine on cardiovascular system for reversal of residual neuromuscular blockade in the elderly: a randomized controlled trial.

BACKGROUND: Glycopyrrolate-neostigmine (G/N) for reversing neuromuscular blockade (NMB) causes fewer changes in heart rate (HR) than atropine-neostigmine (A/N). This advantage may be especially beneficial for elderly patients. Therefore, this study aimed to compare the cardiovascular effects of G/N and A/N for the reversal of NMB in elderly patients. METHODS: Elderly patients aged 65-80 years who were scheduled for elective non-cardiac surgery under general anesthesia were randomly assigned to the glycopyrrolate group (group G) or the atropine group (group A). Following the last administration of muscle relaxants for more than 30 min, group G received 4 ug/kg glycopyrrolate and 20 ug/kg neostigmine, while group A received 10 ug/kg atropine and 20 ug/kg neostigmine. HR, mean arterial pressure (MAP), and ST segment in lead II (ST-II) were measured 1 min before administration and 1-15 min after administration. RESULTS: HR was significantly lower in group G compared to group A at 2-8 min after administration (P < 0.05). MAP was significantly lower in group G compared to group A at 1-4 min after administration (P < 0.05). ST-II was significantly depressed in group A compared to group G at 2, 3, 4, 5, 6, 7, 8, 9, 11, 13, 14, and 15 min after administration (P < 0.05). CONCLUSIONS: In comparison to A/N, G/N for reversing residual NMB in the elderly has a more stable HR, MAP, and ST-II within 15 min after administration.

BrainNet: a fusion assisted novel optimal framework of residual blocks and stacked autoencoders for multimodal brain tumor classification.

A significant issue in computer-aided diagnosis (CAD) for medical applications is brain tumor classification. Radiologists could reliably detect tumors using machine learning algorithms without extensive surgery. However, a few important challenges arise, such as (i) the selection of the most important deep learning architecture for classification (ii) an expert in the field who can assess the output of deep learning models. These difficulties motivate us to propose an efficient and accurate system based on deep learning and evolutionary optimization for the classification of four types of brain modalities (t1 tumor, t1ce tumor, t2 tumor, and flair tumor) on a large-scale MRI database. Thus, a CNN architecture is modified based on domain knowledge and connected with an evolutionary optimization algorithm to select hyperparameters. In parallel, a Stack Encoder-Decoder network is designed with ten convolutional layers. The features of both models are extracted and optimized using an improved version of Grey Wolf with updated criteria of the Jaya algorithm. The improved version speeds up the learning process and improves the accuracy. Finally, the selected features are fused using a novel parallel pooling approach that is classified using machine learning and neural networks. Two datasets, BraTS2020 and BraTS2021, have been employed for the experimental tasks and obtained an improved average accuracy of 98% and a maximum single-classifier accuracy of 99%. Comparison is also conducted with several classifiers, techniques, and neural nets; the proposed method achieved improved performance.

ERCP-Net: a channel extension residual structure and adaptive channel attention mechanism for plant leaf disease classification network.

Plant leaf diseases are a major cause of plant mortality, especially in crops. Timely and accurately identifying disease types and implementing proper treatment measures in the early stages of leaf diseases are crucial for healthy plant growth. Traditional plant disease identification methods rely heavily on visual inspection by experts in plant pathology, which is time-consuming and requires a high level of expertise. So, this approach fails to gain widespread adoption. To overcome these challenges, we propose a channel extension residual structure and adaptive channel attention mechanism for plant leaf disease classification network (ERCP-Net). It consists of channel extension residual block (CER-Block), adaptive channel attention block (ACA-Block), and bidirectional information fusion block (BIF-Block). Meanwhile, an application for the real-time detection of plant leaf diseases is being created to assist precision agriculture in practical situations. Finally, experiments were conducted to compare our model with other state-of-the-art deep learning methods on the PlantVillage and AI Challenger 2018 datasets. Experimental results show that our model achieved an accuracy of 99.82% and 86.21%, respectively. Also, it demonstrates excellent robustness and scalability, highlighting its potential for practical implementation.

SRT: Swin-residual transformer for benign and malignant nodules classification in thyroid ultrasound images.

With the advancement of deep learning technology, computer-aided diagnosis (CAD) is playing an increasing role in the field of medical diagnosis. In particular, the emergence of Transformer-based models has led to a wider application of computer vision technology in the field of medical image processing. In the diagnosis of thyroid diseases, the diagnosis of benign and malignant thyroid nodules based on the TI-RADS classification is greatly influenced by the subjective judgment of ultrasonographers, and at the same time, it also brings an extremely heavy workload to ultrasonographers. To address this, we propose Swin-Residual Transformer (SRT) in this paper, which incorporates residual blocks and triplet loss into Swin Transformer (SwinT). It improves the sensitivity to global and localized features of thyroid nodules and better distinguishes small feature differences. In our exploratory experiments, SRT model achieves an accuracy of 0.8832 with an AUC of 0.8660, outperforming state-of-the-art convolutional neural network (CNN) and Transformer models. Also, ablation experiments have demonstrated the improved performance in the thyroid nodule classification task after introducing residual blocks and triple loss. These results validate the potential of the proposed SRT model to improve the diagnosis of thyroid nodules' ultrasound images. It also provides a feasible guarantee to avoid excessive puncture sampling of thyroid nodules in future clinical diagnosis.

A portable household detection system based on the combination of bidirectional LSTM and residual block for automatical arrhythmia detection.

OBJECTIVES: Arrhythmia is an important component of cardiovascular disease, and electrocardiogram (ECG) is a method to detect arrhythmia. Arrhythmia detection is often paroxysmal, and ECG signal analysis is time-consuming and expensive. We propose a model and device for convenient monitoring of arrhythmia at any time. METHODS: This work proposes a model combining residual block and bidirectional long-term short-term memory network (BiLSTM) to detect and classify ECG signals. Residual blocks can extract deep features and avoid performance degradation caused by convolutional networks. Combined with the feature of BiLSTM to strengthen the connection relationship of the local window, it can achieve a better classification and prediction effect. RESULTS: Model optimization experiments were performed on the MIT-BIH Atrial Fibrillation Database (AFDB) and MIT-BIH Arrhythmia Database (MITDB). The accuracy simulation results on both long and short signal was higher than 99 %. To further demonstrate the applicability of the model, validation experiments were conducted on MIT-BIH Normal Sinus Rhythm Database (NSRDB) and the Long-Term AF Database (LTAFDB) datasets, and the related recognition accuracy were 99.830 and 91.252 %, respectively. Additionally, we proposed a portable household detection system including an ECG and a blood pressure detection module. The detection accuracy was higher than 98 % using the collected data as testing set. CONCLUSIONS: Hence, we thought our system can be used for practical application.

The effect of sugammadex on patient morbidity and quality of recovery after general anaesthesia: a systematic review and meta-analysis.

BACKGROUND: Residual neuromuscular block is associated with increased patient morbidity. Therefore prevention of residual neuromuscular block is an important component of general anaesthesia where neuromuscular blocking agents are used. Whereas sugammadex improves reversal based on neuromuscular twitch monitoring parameters, there have been no prospective, adequately powered definitive studies demonstrating that sugammadex is also associated with less patient morbidity. METHODS: We performed a systematic review of randomised trials comparing sugammadex with anticholinesterase-based reversal or placebo reversal that reported important patient outcomes beyond the postanaesthesia care unit. RESULTS: We identified 43 articles, including 5839 trial participants. Only one trial reported days alive and out of hospital to 30 days (DAOH-30), which showed that the number of DAOH-30 was similar in those allocated to sugammadex compared with neostigmine-based reversal (25 days [19-27] vs 24 days [21-27], median difference 0.00 [-2.15 to 2.15]). Pooled analyses of data from 16 trials showed an estimated odds ratio (OR) for postoperative pulmonary complications of 0.67 (95% confidence interval 0.47-0.95) with sugammadex use. Pooled analysis showed that pneumonia (eight trials OR 0.51 [0.24-1.01] with sugammadex use), hospital length of stay (23 trials, mean difference -0.31 [-0.84 to 0.22] with sugammadex use), and patient-reported quality of recovery (11 trials, varied depending on metric used) are similar in those allocated to sugammadex vs control. The difference seen in mortality (11 trials, OR 0.39 [0.15-1.01] with sugammadex use) would be considered to be clinically significant and warrants further investigation, however, the rarity of these events precludes drawing definitive conclusions. CONCLUSION: Although few trials reported on DAOH-30 or important patient outcomes, sugammadex is associated with a reduction in postoperative pulmonary complications, however, this might not translate to a difference in hospital length of stay, patient-reported quality of recovery, or mortality. CLINICAL TRIAL REGISTRATION: PROSPERO database (CRD42022325858).

A Convolutional Neural Network for Automated Detection of Cervical Ossification of the Posterior Longitudinal Ligament using Magnetic Resonance Imaging.

STUDY DESIGN: Retrospective cohort study. OBJECTIVE: We aimed to develop and validate a convolutional neural network (CNN) model to distinguish between cervical ossification of posterior longitudinal ligament (OPLL) and multilevel degenerative spinal stenosis using Magnetic Resonance Imaging (MRI) and to compare the diagnostic ability with spine surgeons. SUMMARY OF BACKGROUND DATA: Some artificial intelligence models have been applied in spinal image analysis and many of promising results were obtained; however, there was still no study attempted to develop a deep learning model in detecting cervical OPLL using MRI images. MATERIALS AND METHODS: In this retrospective study, 272 cervical OPLL and 412 degenerative patients underwent surgical treatment were enrolled and divided into the training (513 cases) and test dataset (171 cases). CNN models applying ResNet architecture with 34, 50, and 101 layers of residual blocks were constructed and trained with the sagittal MRI images from the training dataset. To evaluate the performance of CNN, the receiver operating characteristic curves of 3 ResNet models were plotted and the area under the curve were calculated on the test dataset. The accuracy, sensitivity, and specificity of the diagnosis by the CNN were calculated and compared with 3 senior spine surgeons. RESULTS: The diagnostic accuracies of our ResNet34, ResNet50, and ResNet101 models were 92.98%, 95.32%, and 97.66%, respectively; the area under the curve of receiver operating characteristic curves of these models were 0.914, 0.942, and 0.971, respectively. The accuracies and specificities of ResNet50 and ResNet101 models were significantly higher than all spine surgeons; for the sensitivity, ResNet101 model achieved better values than that of the 2 surgeons. CONCLUSION: The performance of our ResNet model in differentiating cervical OPLL from degenerative spinal stenosis using MRI is promising, better results were achieved with more layers of residual blocks applied.

Delayed discharge from post-anesthesia care unit: A 20-case retrospective series.

OBJECTIVE: To summarize the characteristics of patients with delayed discharge from the post-anesthesia care unit and to analyze the factors and outcomes of delayed discharge. METHODS: Twenty cases of delayed discharge from the PACU (PACU stay >2 hours after surgery) of the main operating room in Liaocheng People's Hospital, a class A tertiary comprehensive hospital, between January 1, 2021, and December 31, 2022, among 28,084 patients who were transferred to the PACU from the operating rooms after surgery, were retrospectively analyzed. The collected data included patient characteristics, American society of anesthesiologists grade, information related to surgery and anesthesia, and outcomes. The factors for delay were assigned to 1 of 6 groups: delayed recovery from anesthesia, surgical complications, cardiovascular instability, hypoxia, inadequate analgesia, and waiting for the operating room. RESULTS: The incidence of delayed discharge from PACU was 0.7‰. Among 20 patients, more than half of the patients were over 65 years of age, American society of anesthesiologists grade II~III, body mass index <30 kg/m2, and urological surgery (7, 35%), liver surgery (4, 20%), thoracic surgery (4, 20%) accounted for a relatively high proportion. Nineteen (95%) patients received general anesthesia with or without peripheral nerve block. The main factors included delayed recovery from anesthesia (6, 30%), surgical complications (5, 25%), cardiovascular complications (4, 20%), hypoxia (3,15%). After discharge from the PACU, 1 (5%) died in the intensive care unit, and the other 19 (95%) patients were safely discharged from the hospital. CONCLUSION: The incidence of delayed discharge from the PACU was low, and it was more likely to occur in the elderly, during major operations, and under general anesthesia. Delayed recovery from anesthesia was the most common factor. Most patients were safely discharged from the hospital.

Optimal dose of neostigmine antagonizing cisatracurium-induced shallow neuromuscular block in elderly patients: a randomized control study.

BACKGROUND: Residual neuromuscular block after using neuromuscular blocking agents is a common and potentially harmful complication of general anesthesia. Neostigmine is a widely used antagonist, but its optimal dose for elderly patients is unclear. OBJECTIVES: To compare the optimal dosage and safety of neostigmine for reversing shallow residual block in elderly patients after cisatracurium-induced neuromuscular block. METHODS: A randomized controlled trial was conducted in 196 elderly patients undergoing non-cardiac surgery under general anesthesia with cisatracurium. Patients were assigned to receive either no neostigmine (control group) or neostigmine at 20 µg/kg, 40 µg/kg or 50 µg/kg when train-of-four (TOF) ratio reached 0.2 at the end of surgery. The primary outcome was the time to reach TOF ratio of 0.9 after administration. Secondary outcomes included TOF ratio at 10 min after administration, postoperative nausea and vomiting, postoperative cognitive impairment and post-anesthesia care unit (PACU) stay time. RESULTS: The time to reach TOF ratio of 0.9 in the 20 µg/kg, 40 µg/kg and 50 µg/kg groups was significantly shorter than the control group (H = 104.257, P < 0.01), and the time of 40 µg/kg group and 50 µg/kg group was significantly shorter than the 20 µg/kg group (P < 0.001). There was no significant difference between 40 µg/kg and 50 µg/kg groups (P = 0.249). The TOF ratio at 10 min after administration showed similar results. There were no significant differences among groups in postoperative nausea and vomiting, postoperative cognitive impairment or post-operation hospital stay. CONCLUSIONS: Timely use of neostigmine after general anesthesia in elderly patients can significantly shorten time of TOF value reaching 0.9, among which 40 µg/kg dosage may be a more optimized choice. TRIAL REGISTRATION: this study was registered on chictr.org.cn (ChiCTR2100054685, 24/12/2021).

MAB-DrNet: Bearing Fault Diagnosis Method Based on an Improved Dilated Convolutional Neural Network.

Rolling bearing fault diagnosis is of great significance to the safe and reliable operation of manufacturing equipment. In the actual complex environment, the collected bearing signals usually contain a large amount of noises from the resonances of the environment and other components, resulting in the nonlinear characteristics of the collected data. Existing deep-learning-based solutions for bearing fault diagnosis perform poorly in classification performance under noises. To address the above problems, this paper proposes an improved dilated-convolutional-neural network-based bearing fault diagnosis method in noisy environments named MAB-DrNet. First, a basic model called the dilated residual network (DrNet) was designed based on the residual block to enlarge the model's perceptual field to better capture the features from bearing fault signals. Then, a max-average block (MAB) module was designed to improve the feature extraction capability of the model. In addition, the global residual block (GRB) module was introduced into MAB-DrNet to further improve the performance of the proposed model, enabling the model to better handle the global information of the input data and improve the classification accuracy of the model in noisy environments. Finally, the proposed method was tested on the CWRU dataset, and the results showed that the proposed method had good noise immunity; the accuracy was 95.57% when adding Gaussian white noises with a signal-to-noise ratio of -6 dB. The proposed method was also compared with existing advanced methods to further prove its high accuracy.

Micro-architecture design exploration template for AutoML case study on SqueezeSEMAuto.

Convolutional Neural Network (CNN) models have been commonly used primarily in image recognition tasks in the deep learning area. Finding the right architecture needs a lot of hand-tune experiments which are time-consuming. In this paper, we exploit an AutoML framework that adds to the exploration of the micro-architecture block and the multi-input option. The proposed adaption has been applied to SqueezeNet with SE blocks combined with the residual block combinations. The experiments assume three search strategies: Random, Hyperband, and Bayesian algorithms. Such combinations can lead to solutions with superior accuracy while the model size can be monitored. We demonstrate the application of the approach against benchmarks: CIFAR-10 and Tsinghua Facial Expression datasets. The searches allow the designer to find the architectures with better accuracy than the traditional architectures without hand-tune efforts. For example, CIFAR-10, leads to the SqueezeNet architecture using only 4 fire modules with 59% accuracy. When exploring SE block insertion, the model with good insertion points can lead to an accuracy of 78% while the traditional SqueezeNet can achieve an accuracy of around 50%. For other tasks, such as facial expression recognition, the proposed approach can lead up to an accuracy of 71% with the proper insertion of SE blocks, the appropriate number of fire modules, and adequate input merging, while the traditional model can achieve the accuracy under 20%.

CVCC Model: Learning-Based Computer Vision Color Constancy with RiR-DSN Architecture.

To achieve computer vision color constancy (CVCC), it is vital but challenging to estimate scene illumination from a digital image, which distorts the true color of an object. Estimating illumination as accurately as possible is fundamental to improving the quality of the image processing pipeline. CVCC has a long history of research and has significantly advanced, but it has yet to overcome some limitations such as algorithm failure or accuracy decreasing under unusual circumstances. To cope with some of the bottlenecks, this article presents a novel CVCC approach that introduces a residual-in-residual dense selective kernel network (RiR-DSN). As its name implies, it has a residual network in a residual network (RiR) and the RiR houses a dense selective kernel network (DSN). A DSN is composed of selective kernel convolutional blocks (SKCBs). The SKCBs, or neurons herein, are interconnected in a feed-forward fashion. Every neuron receives input from all its preceding neurons and feeds the feature maps into all its subsequent neurons, which is how information flows in the proposed architecture. In addition, the architecture has incorporated a dynamic selection mechanism into each neuron to ensure that the neuron can modulate filter kernel sizes depending on varying intensities of stimuli. In a nutshell, the proposed RiR-DSN architecture features neurons called SKCBs and a residual block in a residual block, which brings several benefits such as alleviation of the vanishing gradients, enhancement of feature propagation, promotion of the reuse of features, modulation of receptive filter sizes depending on varying intensities of stimuli, and a dramatic drop in the number of parameters. Experimental results highlight that the RiR-DSN architecture performs well above its state-of-the-art counterparts, as well as proving to be camera- and illuminant-invariant.

StruNet: Perceptual and low-rank regularized transformer for medical image denoising.

BACKGROUND: Various types of noise artifacts inevitably exist in some medical imaging modalities due to limitations of imaging techniques, which impair either clinical diagnosis or subsequent analysis. Recently, deep learning approaches have been rapidly developed and applied on medical images for noise removal or image quality enhancement. Nevertheless, due to complexity and diversity of noise distribution representations in different medical imaging modalities, most of the existing deep learning frameworks are incapable to flexibly remove noise artifacts while retaining detailed information. As a result, it remains challenging to design an effective and unified medical image denoising method that will work across a variety of noise artifacts for different imaging modalities without requiring specialized knowledge in performing the task. PURPOSE: In this paper, we propose a novel encoder-decoder architecture called Swin transformer-based residual u-shape Network (StruNet), for medical image denoising. METHODS: Our StruNet adopts a well-designed block as the backbone of the encoder-decoder architecture, which integrates Swin Transformer modules with residual block in parallel connection. Swin Transformer modules could effectively learn hierarchical representations of noise artifacts via self-attention mechanism in non-overlapping shifted windows and cross-window connection, while residual block is advantageous to compensate loss of detailed information via shortcut connection. Furthermore, perceptual loss and low-rank regularization are incorporated into loss function respectively in order to constrain the denoising results on feature-level consistency and low-rank characteristics. RESULTS: To evaluate the performance of the proposed method, we have conducted experiments on three medical imaging modalities including computed tomography (CT), optical coherence tomography (OCT) and optical coherence tomography angiography (OCTA). CONCLUSIONS: The results demonstrate that the proposed architecture yields a promising performance of suppressing multiform noise artifacts existing in different imaging modalities.

Evaluation of a Protocol for the Management of Maintenance and Reversal of Rocuronium Block Using Neostigmine or Sugammadex.

BACKGROUND: Postoperative residual neuromuscular blockade (PRNB) is defined as an adductor pollicis train-of-four ratio (TOFR) <0.9. It is a common postoperative complication when nondepolarizing muscle relaxants are either not reversed or reversed with neostigmine. PRNB has been reported in 25% to 58% of patients who receive intermediate-acting nondepolarizing muscle relaxants, and it is associated with increased morbidity and decreased patient satisfaction. We conducted a prospective descriptive cohort study during the implementation of a practice guideline that included the selective use of sugammadex or neostigmine. The primary study aim of this pragmatic study was to estimate the incidence of PRNB at arrival to the postanesthesia care unit (PACU) when the practice guideline is followed. METHODS: We enrolled patients undergoing orthopedic or abdominal surgery requiring neuromuscular blockade. Rocuronium administration was guided by surgical requirements and based on ideal body weight, with dose reductions for women and/or age >55 years. Only qualitative monitoring was available to the anesthesia providers, and selection of sugammadex or neostigmine was guided by tactile assessments of the response to train-of-four (TOF) stimulation by a peripheral nerve stimulator. Neostigmine was administered if no fade was detected in the TOF response at the thumb. Deeper blocks were reversed with sugammadex. The prespecified primary and secondary end points were the incidence of PRNB at arrival to the PACU, defined as a normalized TOFR (nTOFR) < 0.9, and severe PRNB, defined as nTOFR <0.7 on arrival to the PACU. Anesthesia providers were blinded to all quantitative measurements made by research staff. RESULTS: Analysis included 163 patients, and 145 underwent orthopedic and 18 abdominal surgeries. Of the 163 patients, 92 (56%) were reversed with neostigmine and 71 (44%) with sugammadex. The overall incidence of PRNB at PACU arrival was 5 of 163 or 3% (95% confidence interval [CI], 1-7). The incidence of severe PRNB in PACU was 1% (95% CI, 0-4). Three of the 5 subjects with PRNB had TOFR <0.4 at time of reversal but were given neostigmine since anesthesia providers detected no fade by qualitative assessment. CONCLUSIONS: The use of a protocol that specifies rocuronium dosing and selective use of sugammadex versus neostigmine based on qualitative assessment of TOF count and fade allowed us to achieve an incidence of PRNB of 3% (95% CI, 1-7) at PACU arrival. Quantitative monitoring may be needed to further reduce this incidence.

A COVID-19 medical image classification algorithm based on Transformer.

Coronavirus 2019 (COVID-19) is a new acute respiratory disease that has spread rapidly throughout the world. This paper proposes a novel deep learning network based on ResNet-50 merged transformer named RMT-Net. On the backbone of ResNet-50, it uses Transformer to capture long-distance feature information, adopts convolutional neural networks and depth-wise convolution to obtain local features, reduce the computational cost and acceleration the detection process. The RMT-Net includes four stage blocks to realize the feature extraction of different receptive fields. In the first three stages, the global self-attention method is adopted to capture the important feature information and construct the relationship between tokens. In the fourth stage, the residual blocks are used to extract the details of feature. Finally, a global average pooling layer and a fully connected layer perform classification tasks. Training, verification and testing are carried out on self-built datasets. The RMT-Net model is compared with ResNet-50, VGGNet-16, i-CapsNet and MGMADS-3. The experimental results show that the RMT-Net model has a Test_ acc of 97.65% on the X-ray image dataset, 99.12% on the CT image dataset, which both higher than the other four models. The size of RMT-Net model is only 38.5 M, and the detection speed of X-ray image and CT image is 5.46 ms and 4.12 ms per image, respectively. It is proved that the model can detect and classify COVID-19 with higher accuracy and efficiency.

Rate of residual neuromuscular block using single-dose rocuronium in general anesthesia for ENT surgery: a retrospective cohort study.

INTRODUCTION: NMB facilitates intubating conditions in general anesthesia. However, it is associated with significant residual postoperative paralysis and morbidity. OBJECTIVE: To investigate the rate of underdiagnosed residual NMB based on two TOFR criteria (< 0.91 and < 1.00). METHODS: We performed a retrospective study adhering to STROBE guidelines. We included patients undergoing ENT surgery using single-dose neuromuscular block for balanced general anesthesia from June to December 2018. We collected demographic and anthropometric data, ASA score, NMBA dose, TOFR recordings at 5, 30 and 60 min and end of the surgery, anesthesia and surgery time, and administration of reversal agent. Statistical analysis included descriptive and dispersion measures statistics, curve and cross tables for residual NMB on different TOFR criteria with sub-analysis for AR, RR, and OR in patients over 65 years old. RESULTS: We included 57 patients, mean age 41; 43 females and 14 males. Mean anesthetic and surgical time were 139.4 and 116.1 min, respectively. All the patients received rocuronium under a mean ponderal single-dose of 0.48 mg/kg. Residual NMB rates were 29.9 and 49.1% for a TOFR < 0.91 and < 1.00, respectively. Older adults had an OR of 6.08 for residual NMB. CONCLUSIONS: The rate of residual NMB was 29.9 to 49.1%, depending on the criteria used (TOFR < 0.91 and < 1.00, respectively). Patients above 65 years old had an increased risk of residual NMB (6.08 OR) and clinical symptoms related to residual NMB (11.75 OR). We recommend future research aiming to provide a specific surveillance protocol for patients above 65 years old, including shorter-action NMB, early reversal, and prolonged surveillance using the TOFR criteria of < 1.00 to identify patients at risk of residual NMB readily.