Design of axial flaps with color Doppler flow imaging technique for repairing deep wounds of heels

To report the methods and effect of axial pattern flap on lower limb in repairing deep wounds of heels by using color Doppler flow imaging (CDFI) technique so as to solve the ever before problems that the vessel can not be displayed in designing axial flap.Methods Suitable axial flaps on lower limbs were selected according to the character of the wounds.There were 25 flaps including 10 cases of the distal-based sural neurovascular flap,nine medial sole flap and six medial leg flap.All the axial pattern flaps were designed on the basis of traditional design ways before operation;then,CDFI appliance with high resolution was used to examine the starting spot,exterior diameter,trail and length of the flap’s major artery.The flaps were redesigned according to the results of CDFI and transferred to cover the wounds.In the meantime,both the results of operation and examination were compared.Results The major artery’s starting spot,exterior diameter,trail and anatomic layers were displayed clearly,in consistency with the results of operation.The flaps survived completely and recovered well,with perfect appearance,color and arthral function.Conclusion CDFI is a simple,macroscopic and atraumatic method for designing the axial pattern flap on lower limb,can provide more scientific and accurate evidence for preoperative determination of flap transplantation and is worthy of clinical application.10 refs,4 figs,2 tabs.

To investigate the clinical effect of modified closed negative pressure suction technique combined with flap transplantation on the treatment of deep chronic refractory wounds

Objective:To investigate the clinical effect of modified closed negative pressure suction technique combined with flap transplantation on the treatment of deep chronic refractory wounds.Methods:During March of 2015 to April of 2018,52 cases of patients with deep chronic refractory wounds were selected as research objects.They were divided into the control group and the treatment group by use of the random number table method,with 26 cases in each group.Among them,the control group was given conventional debridement combined with flap reconstruction,and the treatment group was treated with modified closed negative pressure suction technique combined with flap transplantation to observe the clinical effect.Results:(1)According to the analysis on the effect of flap transplantation,the excellent and good rate of the treatment group was 92.3%,and in the control group,it was 76.9%(p<0.05).(2)According to the statistics,the incidence of complications in the treatment group was lower than that in the control group(p<0.05).Conclusions:Modified closed negative pressure suction technique combined with flap transplantation has a good effect on the treatment of deep chronic refractory wounds with fewer complications.

UAV-Assisted Dynamic Avatar Task Migration for Vehicular Metaverse Services: A Multi-Agent Deep Reinforcement Learning Approach

Avatars, as promising digital representations and service assistants of users in Metaverses, can enable drivers and passengers to immerse themselves in 3D virtual services and spaces of UAV-assisted vehicular Metaverses. However, avatar tasks include a multitude of human-to-avatar and avatar-to-avatar interactive applications, e.g., augmented reality navigation,which consumes intensive computing resources. It is inefficient and impractical for vehicles to process avatar tasks locally. Fortunately, migrating avatar tasks to the nearest roadside units(RSU)or unmanned aerial vehicles(UAV) for execution is a promising solution to decrease computation overhead and reduce task processing latency, while the high mobility of vehicles brings challenges for vehicles to independently perform avatar migration decisions depending on current and future vehicle status. To address these challenges, in this paper, we propose a novel avatar task migration system based on multi-agent deep reinforcement learning(MADRL) to execute immersive vehicular avatar tasks dynamically. Specifically, we first formulate the problem of avatar task migration from vehicles to RSUs/UAVs as a partially observable Markov decision process that can be solved by MADRL algorithms. We then design the multi-agent proximal policy optimization(MAPPO) approach as the MADRL algorithm for the avatar task migration problem. To overcome slow convergence resulting from the curse of dimensionality and non-stationary issues caused by shared parameters in MAPPO, we further propose a transformer-based MAPPO approach via sequential decision-making models for the efficient representation of relationships among agents. Finally, to motivate terrestrial or non-terrestrial edge servers(e.g., RSUs or UAVs) to share computation resources and ensure traceability of the sharing records, we apply smart contracts and blockchain technologies to achieve secure sharing management. Numerical results demonstrate that the proposed approach outperforms the MAPPO approach by around 2% and effectively reduces approximately 20% of the latency of avatar task execution in UAV-assisted vehicular Metaverses.

The Application of Bilayer Artificial Dermis Combined with VSD Technology in Chronic Wounds

Background: Bilayer artificial dermis promotes wound healing and offers a treatment option for chronic wounds. Aim: Examine the clinical efficacy of bilayer artificial dermis combined with Vacuum Sealing Drainage (VSD) technology in the treatment of chronic wounds. Method: From June 2021 to December 2023, our hospital treated 24 patients with chronic skin tissue wounds on their limbs using a novel tissue engineering product, the bilayer artificial dermis, in combination with VSD technology to repair the wounds. The bilayer artificial dermis protects subcutaneous tissue, blood vessels, nerves, muscles, and tendons, and also promotes the growth of granulation tissue and blood vessels to aid in wound healing when used in conjunction with VSD technology for wound dressing changes in chronic wounds. Results: In this study, 24 cases of chronic wounds with exposed bone or tendon larger than 1.0 cm2 were treated with a bilayer artificial skin combined with VSD dressing after wound debridement. The wounds were not suitable for immediate skin grafting. At 2 - 3 weeks post-treatment, good granulation tissue growth was observed. Subsequent procedures included thick skin grafting or wound dressing changes until complete wound healing. Patients were followed up on average for 3 months (range: 1 - 12 months) post-surgery. Comparative analysis of the appearance, function, skin color, elasticity, and sensation of the healed chronic wounds revealed superior outcomes compared to traditional skin fl repairs, resulting in significantly higher satisfaction levels among patients and their families. Conclusion: The application of bilayer artificial dermis combined with VSD technology for the repair of chronic wounds proves to be a viable method, yielding satisfactory therapeutic effects compared to traditional skin flap procedures.

Eyelid Wounds: Epidemiological, Clinical and Etiological Aspects

Purpose: The aim is to show epidemiological, clinical and etiological characteristics of palpebral wounds. Methodology: This was a retrospective study focusing on patients with an eyelid wound, over a 10-year period from 2012 to 2021. We collected and analyzed the data using Excel. Results: The frequency of eyelid wounds was 0.1%. The average age of our patients was 19.38 years with a range of 1 and 62 years. The sex ratio was 3.7. Eighty-one percent of patients lived in Dakar. Fifty-seven percent (57%) of patients consulted less than 24 hours after the trauma and 7% of patients on D1. The circumstances were brawls (11%), domestic accidents (9%), road accidents (6%), and work accidents (6%). We noted 1 case of dog bite. Thirteen patients presented with post-traumatic decreased visual acuity. Involvement of the isolated upper eyelid was noted in 40% of cases and both eyelids in 15% of cases. Involvement of the lacrimal ducts was noted in 17% of cases, and that of the free edge in 21% of cases. Eyelid wounds were associated with eyeball damage in 21% of cases. Various associated lesions were observed. Ninety-one percent of patients received surgical treatment. Three cases of superinfections, 1 case of conjunctival granuloma and 1 case of phthysis of the eyeball with postoperative retinal detachment were noted. Conclusion: Eyelid sores are relatively common in our context. They require rapid surgical treatment in order to preserve the functional and aesthetic prognosis. .

Click-hydrogel delivered aggregation-induced emissive nanovesicles for simultaneous remodeling and antibiosis of deep burn wounds

As a high-risk trauma,deep burns are always hindered in their repair process by decreased tissue regeneration capacity and persistent infections.In this study,we developed a simultaneous strategy for deep burn wounds treatment using functional nanovesicles with antibacterial and tissue remodeling properties,delivered via a click-chemistry hydrogel.An aggregation-induced emission photosensitizer of 4-(2-(5-(4-(diphenylamino)phenyl)thiophen-2-yl)vinyl)-1-(2-hydroxyethyl)pyridin-1-ium bromide(THB)with excellent photodynamic properties was first prepared,and then combined with readily accessible adipose stem cells-derived nanovesicles to generate the THB functionalized nanovesicles(THB@ANVs).The THB@ANVs showed strong antibacterial activity against Gram-positive bacteria(up to 100%killing rate),and also beneficial effects on tissue remodeling,including promoting cell migration,cell proliferation,and regulating immunity.In addition,we prepared a click-hydrogel of carboxymethyl chitosan for effective delivery of THB@ANVs on wounds.This hydrogel could be injected to conform to the wound morphology while responding to the acidic microenvironment.In vivo evaluations of wound healing revealed that the THB@ANVs hydrogel dressing efficiently accelerated the healing of second-degree burn wounds by reducing bacterial growth,regulating inflammation,promoting early angiogenesis,and collagen deposition.This study provides a promising candidate of wound dressing with diverse functions for deep burn wound repair.

Double-nylon purse-string suture in closing postoperative wounds following endoscopic resection of large(≥3 cm)gastric submucosal tumors

BACKGROUND Endoscopic full-thickness resection(EFTR)of gastric submucosal tumors(SMTs)is safe and effective;however,postoperative wound management is equally important.Literature on suturing following EFTR for large(≥3 cm)SMTs is scarce and limited.AIM To evaluate the efficacy and clinical value of double-nylon purse-string suture in closing postoperative wounds following EFTR of large(≥3 cm)SMTs.METHODS We retrospectively analyzed the data of 85 patients with gastric SMTs in the fundus of the stomach or in the lesser curvature of the gastric body whose wounds were treated with double-nylon purse-string sutures after successful tumor resection at the Endoscopy Center of Renmin Hospital of Wuhan University.The operative,postoperative,and follow-up conditions of the patients were evaluated.RESULTS All tumors were completely resected using EFTR.36(42.35%)patients had tumors located in the fundus of the stomach,and 49(57.65%)had tumors located in the body of the stomach.All patients underwent suturing with double-nylon sutures after EFTR without laparoscopic assistance or further surgical treatment.Postoperative fever and stomach pain were reported in 13(15.29%)and 14(16.47%)patients,respectively.No serious adverse events occurred during the intraoperative or postoperative periods.A postoperative review of all patients revealed no residual or recurrent lesions.CONCLUSION Double-nylon purse-string sutures can be used to successfully close wounds that cannot be completely closed with a single nylon suture,especially for large(≥3 cm)EFTR wounds in SMTs.

Diffraction deep neural network-based classification for vector vortex beams

The vector vortex beam(VVB)has attracted significant attention due to its intrinsic diversity of information and has found great applications in both classical and quantum communications.However,a VVB is unavoidably affected by atmospheric turbulence(AT)when it propagates through the free-space optical communication environment,which results in detection errors at the receiver.In this paper,we propose a VVB classification scheme to detect VVBs with continuously changing polarization states under AT,where a diffractive deep neural network(DDNN)is designed and trained to classify the intensity distribution of the input distorted VVBs,and the horizontal direction of polarization of the input distorted beam is adopted as the feature for the classification through the DDNN.The numerical simulations and experimental results demonstrate that the proposed scheme has high accuracy in classification tasks.The energy distribution percentage remains above 95%from weak to medium AT,and the classification accuracy can remain above 95%for various strengths of turbulence.It has a faster convergence and better accuracy than that based on a convolutional neural network.

A credibility-aware swarm-federated deep learning framework in internet of vehicles

Although Federated Deep Learning(FDL)enables distributed machine learning in the Internet of Vehicles(IoV),it requires multiple clients to upload model parameters,thus still existing unavoidable communication overhead and data privacy risks.The recently proposed Swarm Learning(SL)provides a decentralized machine learning approach for unit edge computing and blockchain-based coordination.A Swarm-Federated Deep Learning framework in the IoV system(IoV-SFDL)that integrates SL into the FDL framework is proposed in this paper.The IoV-SFDL organizes vehicles to generate local SL models with adjacent vehicles based on the blockchain empowered SL,then aggregates the global FDL model among different SL groups with a credibility weights prediction algorithm.Extensive experimental results show that compared with the baseline frameworks,the proposed IoV-SFDL framework reduces the overhead of client-to-server communication by 16.72%,while the model performance improves by about 5.02%for the same training iterations.

Low rank optimization for efficient deep learning:making a balance between compact architecture and fast training

Deep neural networks(DNNs)have achieved great success in many data processing applications.However,high computational complexity and storage cost make deep learning difficult to be used on resource-constrained devices,and it is not environmental-friendly with much power cost.In this paper,we focus on low-rank optimization for efficient deep learning techniques.In the space domain,DNNs are compressed by low rank approximation of the network parameters,which directly reduces the storage requirement with a smaller number of network parameters.In the time domain,the network parameters can be trained in a few subspaces,which enables efficient training for fast convergence.The model compression in the spatial domain is summarized into three categories as pre-train,pre-set,and compression-aware methods,respectively.With a series of integrable techniques discussed,such as sparse pruning,quantization,and entropy coding,we can ensemble them in an integration framework with lower computational complexity and storage.In addition to summary of recent technical advances,we have two findings for motivating future works.One is that the effective rank,derived from the Shannon entropy of the normalized singular values,outperforms other conventional sparse measures such as the?_1 norm for network compression.The other is a spatial and temporal balance for tensorized neural networks.For accelerating the training of tensorized neural networks,it is crucial to leverage redundancy for both model compression and subspace training.

Extended Deep Learning Algorithm for Improved Brain Tumor Diagnosis System

At present,the prediction of brain tumors is performed using Machine Learning(ML)and Deep Learning(DL)algorithms.Although various ML and DL algorithms are adapted to predict brain tumors to some range,some concerns still need enhancement,particularly accuracy,sensitivity,false positive and false negative,to improve the brain tumor prediction system symmetrically.Therefore,this work proposed an Extended Deep Learning Algorithm(EDLA)to measure performance parameters such as accuracy,sensitivity,and false positive and false negative rates.In addition,these iterated measures were analyzed by comparing the EDLA method with the Convolutional Neural Network(CNN)way further using the SPSS tool,and respective graphical illustrations were shown.The results were that the mean performance measures for the proposed EDLA algorithm were calculated,and those measured were accuracy(97.665%),sensitivity(97.939%),false positive(3.012%),and false negative(3.182%)for ten iterations.Whereas in the case of the CNN,the algorithm means accuracy gained was 94.287%,mean sensitivity 95.612%,mean false positive 5.328%,and mean false negative 4.756%.These results show that the proposed EDLA method has outperformed existing algorithms,including CNN,and ensures symmetrically improved parameters.Thus EDLA algorithm introduces novelty concerning its performance and particular activation function.This proposed method will be utilized effectively in brain tumor detection in a precise and accurate manner.This algorithm would apply to brain tumor diagnosis and be involved in various medical diagnoses aftermodification.If the quantity of dataset records is enormous,then themethod’s computation power has to be updated.

Unified deep learning model for predicting fundus fluorescein angiography image from fundus structure image

The prediction of fundus fluorescein angiography(FFA)images from fundus structural images is a cutting-edge research topic in ophthalmological image processing.Prediction comprises estimating FFA from fundus camera imaging,single-phase FFA from scanning laser ophthalmoscopy(SLO),and three-phase FFA also from SLO.Although many deep learning models are available,a single model can only perform one or two of these prediction tasks.To accomplish three prediction tasks using a unified method,we propose a unified deep learning model for predicting FFA images from fundus structure images using a supervised generative adversarial network.The three prediction tasks are processed as follows:data preparation,network training under FFA supervision,and FFA image prediction from fundus structure images on a test set.By comparing the FFA images predicted by our model,pix2pix,and CycleGAN,we demonstrate the remarkable progress achieved by our proposal.The high performance of our model is validated in terms of the peak signal-to-noise ratio,structural similarity index,and mean squared error.

Associative Tasks Computing Offloading Scheme in Internet of Medical Things with Deep Reinforcement Learning

The Internet of Medical Things(Io MT) is regarded as a critical technology for intelligent healthcare in the foreseeable 6G era. Nevertheless, due to the limited computing power capability of edge devices and task-related coupling relationships, Io MT faces unprecedented challenges. Considering the associative connections among tasks, this paper proposes a computing offloading policy for multiple-user devices(UDs) considering device-to-device(D2D) communication and a multi-access edge computing(MEC)technique under the scenario of Io MT. Specifically,to minimize the total delay and energy consumption concerning the requirement of Io MT, we first analyze and model the detailed local execution, MEC execution, D2D execution, and associated tasks offloading exchange model. Consequently, the associated tasks’ offloading scheme of multi-UDs is formulated as a mixed-integer nonconvex optimization problem. Considering the advantages of deep reinforcement learning(DRL) in processing tasks related to coupling relationships, a Double DQN based associative tasks computing offloading(DDATO) algorithm is then proposed to obtain the optimal solution, which can make the best offloading decision under the condition that tasks of UDs are associative. Furthermore, to reduce the complexity of the DDATO algorithm, the cacheaided procedure is intentionally introduced before the data training process. This avoids redundant offloading and computing procedures concerning tasks that previously have already been cached by other UDs. In addition, we use a dynamic ε-greedy strategy in the action selection section of the algorithm, thus preventing the algorithm from falling into a locally optimal solution. Simulation results demonstrate that compared with other existing methods for associative task models concerning different structures in the Io MT network, the proposed algorithm can lower the total cost more effectively and efficiently while also providing a tradeoff between delay and energy consumption tolerance.

The Damaging Effects of Abstracting the Deep Aquifers’Groundwater in Jordan-Quality Constraints

The deep aquifers in Jordan contain non-renewable and fossil groundwater and their extraction is quasi a mining process, which ends in the depletion of these resources. Although aquifers in the majority of groundwater basins in Jordan are vertically and horizontally interconnected stratification in different water quality horizons with generally increasing water salinity with the depth is observed. Many officials and planners advocate the extraction of deep salty and brackish water to be desalinated and used in household, industrial, and agricultural uses. In this article, the quality of the groundwater in the different deep aquifers and areas in Jordan is discussed. The results of this study show that the consequences of the deep groundwater exploitation are not restricted to depletion of the deep aquifers but also that the overlying fresh groundwater will, due to vertical and horizontal interconnectedness of the different aquifers, percolate down to replace the extracted deep groundwater. This will cause the down-percolating fresh groundwater to become salinized in the deep saline aquifers, which means that extracting the deep brackish and saline groundwater is not only an emptying process of the deep groundwater but also it is an emptying process of the fresh groundwater overlying them. The results allow to conclude that any extraction of the deep groundwater in areas lying to the north of Ras en Naqab Escarpment will have damaging impacts on the fresh groundwater in the overlying fresh groundwater aquifers. This article strongly advises not to extract the deep brackish and saline groundwater, but to conserve that groundwater as a base supporting the overlying fresh groundwater resources, and that will help in protecting the thermal mineralized water springs used in spas originating from these deep aquifers. The increasing water needs of the country can be covered by the desalination of seawater at Aqaba, which is the only viable option for Jordan at present and in the coming decades.

Nonparametric Statistical Feature Scaling Based Quadratic Regressive Convolution Deep Neural Network for Software Fault Prediction

The development of defect prediction plays a significant role in improving software quality. Such predictions are used to identify defective modules before the testing and to minimize the time and cost. The software with defects negatively impacts operational costs and finally affects customer satisfaction. Numerous approaches exist to predict software defects. However, the timely and accurate software bugs are the major challenging issues. To improve the timely and accurate software defect prediction, a novel technique called Nonparametric Statistical feature scaled QuAdratic regressive convolution Deep nEural Network (SQADEN) is introduced. The proposed SQADEN technique mainly includes two major processes namely metric or feature selection and classification. First, the SQADEN uses the nonparametric statistical Torgerson–Gower scaling technique for identifying the relevant software metrics by measuring the similarity using the dice coefficient. The feature selection process is used to minimize the time complexity of software fault prediction. With the selected metrics, software fault perdition with the help of the Quadratic Censored regressive convolution deep neural network-based classification. The deep learning classifier analyzes the training and testing samples using the contingency correlation coefficient. The softstep activation function is used to provide the final fault prediction results. To minimize the error, the Nelder–Mead method is applied to solve non-linear least-squares problems. Finally, accurate classification results with a minimum error are obtained at the output layer. Experimental evaluation is carried out with different quantitative metrics such as accuracy, precision, recall, F-measure, and time complexity. The analyzed results demonstrate the superior performance of our proposed SQADEN technique with maximum accuracy, sensitivity and specificity by 3%, 3%, 2% and 3% and minimum time and space by 13% and 15% when compared with the two state-of-the-art methods.

Dendritic Deep Learning for Medical Segmentation

Dear Editor,This letter presents a novel segmentation approach that leverages dendritic neurons to tackle the challenges of medical imaging segmentation.In this study,we enhance the segmentation accuracy based on a SegNet variant including an encoder-decoder structure,an upsampling index,and a deep supervision method.Furthermore,we introduce a dendritic neuron-based convolutional block to enable nonlinear feature mapping,thereby further improving the effectiveness of our approach.

Upper extremity deep vein thrombosis:An intensivist’s perspective

Upper extremity deep vein thrombosis(UEDVT)is less common than lower extremity DVT but is a cause of significant morbidity and mortality in intensive care unit patients.Increasing cancer incidence,prolonged life expectancy and increasing use of intravascular catheters and devices has led to an increased incidence of UEDVT.It is also associated with high rates of complications like pulmonary embolism,post-thrombotic syndrome and recurrent thrombosis.Clinical prediction scores and D-dimer may not be as useful in identifying UEDVT;hence,a high suspicion index is required for diagnosis.Doppler ultrasound is commonly employed for diagnosis,but other tests like computed tomography and magnetic resonance imaging venography may also be required in some patients.Contrast venography is rarely used in patients with clinical and ultrasound findings discrepancies.Anticoagulant therapy alone is sufficient in most patients,and thrombolysis and surgical decompression is seldom indicated.The outcome depends on the cause and underlying comorbidities.

240 nm AlGaN-based deep ultraviolet micro-LEDs:size effect versus edge effect

240 nm AlGaN-based micro-LEDs with different sizes are designed and fabricated.Then,the external quantum efficiency(EQE)and light extraction efficiency(LEE)are systematically investigated by comparing size and edge effects.Here,it is revealed that the peak optical output power increases by 81.83%with the size shrinking from 50.0 to 25.0μm.Thereinto,the LEE increases by 26.21%and the LEE enhancement mainly comes from the sidewall light extraction.Most notably,transversemagnetic(TM)mode light intensifies faster as the size shrinks due to the tilted mesa side-wall and Al reflector design.However,when it turns to 12.5μm sized micro-LEDs,the output power is lower than 25.0μm sized ones.The underlying mechanism is that even though protected by SiO2 passivation,the edge effect which leads to current leakage and Shockley-Read-Hall(SRH)recombination deteriorates rapidly with the size further shrinking.Moreover,the ratio of the p-contact area to mesa area is much lower,which deteriorates the p-type current spreading at the mesa edge.These findings show a role of thumb for the design of high efficiency micro-LEDs with wavelength below 250 nm,which will pave the way for wide applications of deep ultraviolet(DUV)micro-LEDs.

Flood Velocity Prediction Using Deep Learning Approach

Floods are one of the most serious natural disasters that can cause huge societal and economic losses.Extensive research has been conducted on topics like flood monitoring,prediction,and loss estimation.In these research fields,flood velocity plays a crucial role and is an important factor that influences the reliability of the outcomes.Traditional methods rely on physical models for flood simulation and prediction and could generate accurate results but often take a long time.Deep learning technology has recently shown significant potential in the same field,especially in terms of efficiency,helping to overcome the time-consuming associated with traditional methods.This study explores the potential of deep learning models in predicting flood velocity.More specifically,we use a Multi-Layer Perceptron(MLP)model,a specific type of Artificial Neural Networks(ANNs),to predict the velocity in the test area of the Lundesokna River in Norway with diverse terrain conditions.Geographic data and flood velocity simulated based on the physical hydraulic model are used in the study for the pre-training,optimization,and testing of the MLP model.Our experiment indicates that the MLP model has the potential to predict flood velocity in diverse terrain conditions of the river with acceptable accuracy against simulated velocity results but with a significant decrease in training time and testing time.Meanwhile,we discuss the limitations for the improvement in future work.

Automatic detection of small bowel lesions with different bleeding risks based on deep learning models

BACKGROUND Deep learning provides an efficient automatic image recognition method for small bowel(SB)capsule endoscopy(CE)that can assist physicians in diagnosis.However,the existing deep learning models present some unresolved challenges.AIM To propose a novel and effective classification and detection model to automatically identify various SB lesions and their bleeding risks,and label the lesions accurately so as to enhance the diagnostic efficiency of physicians and the ability to identify high-risk bleeding groups.METHODS The proposed model represents a two-stage method that combined image classification with object detection.First,we utilized the improved ResNet-50 classification model to classify endoscopic images into SB lesion images,normal SB mucosa images,and invalid images.Then,the improved YOLO-V5 detection model was utilized to detect the type of lesion and its risk of bleeding,and the location of the lesion was marked.We constructed training and testing sets and compared model-assisted reading with physician reading.RESULTS The accuracy of the model constructed in this study reached 98.96%,which was higher than the accuracy of other systems using only a single module.The sensitivity,specificity,and accuracy of the model-assisted reading detection of all images were 99.17%,99.92%,and 99.86%,which were significantly higher than those of the endoscopists’diagnoses.The image processing time of the model was 48 ms/image,and the image processing time of the physicians was 0.40±0.24 s/image(P<0.001).CONCLUSION The deep learning model of image classification combined with object detection exhibits a satisfactory diagnostic effect on a variety of SB lesions and their bleeding risks in CE images,which enhances the diagnostic efficiency of physicians and improves the ability of physicians to identify high-risk bleeding groups.