To map the rock joints in the underground rock mass,a method was proposed to semiautomatically detect the rock joints from borehole imaging logs using a deep learning algorithm.First,450 images containing rock joints ...To map the rock joints in the underground rock mass,a method was proposed to semiautomatically detect the rock joints from borehole imaging logs using a deep learning algorithm.First,450 images containing rock joints were selected from borehole ZKZ01 in the Rumei hydropower station.These images were labeled to establish ground truth which was subdivided into training,validation,and testing data.Second,the YOLO v2 model with optimal parameter settings was constructed.Third,the training and validation data were used for model training,while the test data was used to generate the precision-recall curve for prediction evaluation.Fourth,the trained model was applied to a new borehole ZKZ02 to verify the feasibility of the model.There were 12 rock joints detected from the selected images in borehole ZKZ02 and four geometric parameters for each rock joint were determined by sinusoidal curve fitting.The average precision of the trained model reached 0.87.展开更多
The cleanliness of seed cotton plays a critical role in the pre-treatment of cotton textiles,and the removal of impurity during the harvesting process directly determines the quality and market value of cotton textile...The cleanliness of seed cotton plays a critical role in the pre-treatment of cotton textiles,and the removal of impurity during the harvesting process directly determines the quality and market value of cotton textiles.By fusing band combination optimization with deep learning,this study aims to achieve more efficient and accurate detection of film impurities in seed cotton on the production line.By applying hyperspectral imaging and a one-dimensional deep learning algorithm,we detect and classify impurities in seed cotton after harvest.The main categories detected include pure cotton,conveyor belt,film covering seed cotton,and film adhered to the conveyor belt.The proposed method achieves an impurity detection rate of 99.698%.To further ensure the feasibility and practical application potential of this strategy,we compare our results against existing mainstream methods.In addition,the model shows excellent recognition performance on pseudo-color images of real samples.With a processing time of 11.764μs per pixel from experimental data,it shows a much improved speed requirement while maintaining the accuracy of real production lines.This strategy provides an accurate and efficient method for removing impurities during cotton processing.展开更多
Automated prostate cancer detection in magnetic resonance imaging(MRI)scans is of significant importance for cancer patient management.Most existing computer-aided diagnosis systems adopt segmentation methods while ob...Automated prostate cancer detection in magnetic resonance imaging(MRI)scans is of significant importance for cancer patient management.Most existing computer-aided diagnosis systems adopt segmentation methods while object detection approaches recently show promising results.The authors have(1)carefully compared performances of most-developed segmentation and object detection methods in localising prostate imaging reporting and data system(PIRADS)-labelled prostate lesions on MRI scans;(2)proposed an additional customised set of lesion-level localisation sensitivity and precision;(3)proposed efficient ways to ensemble the segmentation and object detection methods for improved performances.The ground-truth(GT)perspective lesion-level sensitivity and prediction-perspective lesion-level precision are reported,to quantify the ratios of true positive voxels being detected by algorithms over the number of voxels in the GT labelled regions and predicted regions.The two networks are trained independently on 549 clinical patients data with PIRADS-V2 as GT labels,and tested on 161 internal and 100 external MRI scans.At the lesion level,nnDetection outperforms nnUNet for detecting both PIRADS≥3 and PIRADS≥4 lesions in majority cases.For example,at the average false positive prediction per patient being 3,nnDetection achieves a greater Intersection-of-Union(IoU)-based sensitivity than nnUNet for detecting PIRADS≥3 lesions,being 80.78%�1.50%versus 60.40%�1.64%(p<0.01).At the voxel level,nnUnet is in general superior or comparable to nnDetection.The proposed ensemble methods achieve improved or comparable lesion-level accuracy,in all tested clinical scenarios.For example,at 3 false positives,the lesion-wise ensemble method achieves 82.24%�1.43%sensitivity versus 80.78%�1.50%(nnDetection)and 60.40%�1.64%(nnUNet)for detecting PIRADS≥3 lesions.Consistent conclusions are also drawn from results on the external data set.展开更多
Butyrylcholinesterase(BChE)is a key enzyme in the metabolism of cholinergic compounds.It has been recognized as a key biomarker for many diseases,including liver diseases and Alzheimer’s disease.However,classical met...Butyrylcholinesterase(BChE)is a key enzyme in the metabolism of cholinergic compounds.It has been recognized as a key biomarker for many diseases,including liver diseases and Alzheimer’s disease.However,classical methods for detecting BChE activity suffer from low sensitivity,cumbersome pre-treatment,and poor stability.Chemiluminescence is a promising new method for detecting and imaging the activity of BChE.It has several advantages over traditional methods,including low background interference,high sensitivity,and the absence of external illumination.In this study,we developed a novel BChE-activatable chemiluminescent probe(CL-BChE).It exhibited a significant chemiluminescence enhancement at 525nm upon incubation with BChE.It had a low limit of detection(6.25×10^(−3)U/mL)and was highly selective for BChE.CL-BChE was used to image BChE activity in living cells and tumor-bearing animal models.It was also successfully applied to detect pesticide residue,even under the interference of representative phytochromes and real vegetable samples.Given its high sensitivity,selectivity,and versatility,we believe that CL-BChE will be a promising tool for investigating BChE’s activity in biomedical research as well as other BChE-related scenarios.展开更多
Aggregation-induced emission(AIE)is a unique phenomenon where certain organic materials exhibit enhanced luminescence in their aggregated states,overcoming the typical quenching observed in conventional organic materi...Aggregation-induced emission(AIE)is a unique phenomenon where certain organic materials exhibit enhanced luminescence in their aggregated states,overcoming the typical quenching observed in conventional organic materials.Since its discovery in 2001,AIE has driven significant advances in fields like OLEDs and biological imaging,earning recognition in fundamental research.However,its application in high-energy radiation detection remains underexplored.Organic scintillators,though widely used,face challenges such as low light yield and poor radiation attenuation.AIE materials offer promising solutions by improving light yield,response speed,and radiation attenuation.This review summarizes the design strategies behind AIE scintillators and their very recent applications in X-ray,γ-ray,and fast neutron detection.We highlight their advantages in enhancing detection sensitivity,reducing background noise,and achieving high-resolution imaging.By addressing the current challenges,we believe AIE materials will play a pivotal role in advancing future radiation detection and imaging technologies.展开更多
The YOLO(You Only Look Once)series,a leading single-stage object detection framework,has gained significant prominence in medical-image analysis due to its real-time efficiency and robust performance.Recent iterations...The YOLO(You Only Look Once)series,a leading single-stage object detection framework,has gained significant prominence in medical-image analysis due to its real-time efficiency and robust performance.Recent iterations of YOLO have further enhanced its accuracy and reliability in critical clinical tasks such as tumor detection,lesion segmentation,and microscopic image analysis,thereby accelerating the development of clinical decision support systems.This paper systematically reviews advances in YOLO-based medical object detection from 2018 to 2024.It compares YOLO’s performance with othermodels(e.g.,Faster R-CNN,RetinaNet)inmedical contexts,summarizes standard evaluation metrics(e.g.,mean Average Precision(mAP),sensitivity),and analyzes hardware deployment strategies using public datasets such as LUNA16,BraTS,andCheXpert.Thereviewhighlights the impressive performance of YOLO models,particularly from YOLOv5 to YOLOv8,in achieving high precision(up to 99.17%),sensitivity(up to 97.5%),and mAP exceeding 95%in tasks such as lung nodule,breast cancer,and polyp detection.These results demonstrate the significant potential of YOLO models for early disease detection and real-time clinical applications,indicating their ability to enhance clinical workflows.However,the study also identifies key challenges,including high small-object miss rates,limited generalization in low-contrast images,scarcity of annotated data,and model interpretability issues.Finally,the potential future research directions are also proposed to address these challenges and further advance the application of YOLO models in healthcare.展开更多
Neutron capture event imaging is a novel technique that has the potential to substantially enhance the resolution of existing imaging systems.This study provides a measurement method for neutron capture event distribu...Neutron capture event imaging is a novel technique that has the potential to substantially enhance the resolution of existing imaging systems.This study provides a measurement method for neutron capture event distribution along with multiple reconstruction methods for super-resolution imaging.The proposed technology reduces the point-spread function of an imag-ing system through single-neutron detection and event reconstruction,thereby significantly improving imaging resolution.A single-neutron detection experiment was conducted using a highly practical and efficient^(6)LiF-ZnS scintillation screen of a cold neutron imaging device in the research reactor.In milliseconds of exposure time,a large number of weak light clusters and their distribution in the scintillation screen were recorded frame by frame,to complete single-neutron detection.Several reconstruction algorithms were proposed for the calculations.The location of neutron capture was calculated using several processing methods such as noise removal,filtering,spot segmentation,contour analysis,and local positioning.The proposed algorithm achieved a higher imaging resolution and faster reconstruction speed,and single-neutron super-resolution imaging was realized by combining single-neutron detection experiments and reconstruction calculations.The results show that the resolution of the 100μm thick^(6)LiF-ZnS scintillation screen can be improved from 125 to 40 microns.This indicates that the proposed single-neutron detection and calculation method is effective and can significantly improve imaging resolution.展开更多
Manganese(Mn),an essential trace element in the human body,plays critical roles in many biological processes.Recent studies have discovered that Mn^(2+)may promote or directly activate the cGAS-STING pathway,thereby s...Manganese(Mn),an essential trace element in the human body,plays critical roles in many biological processes.Recent studies have discovered that Mn^(2+)may promote or directly activate the cGAS-STING pathway,thereby subsequently initiating the natural immune response and augmenting antitumor therapy.However,the current lack of accurate methods for Mn^(2+)determination in cells significantly limits their mechanism investigation;hence,it is urgent to establish novel tools to detect Mn^(2+)in cells.In this study,the dual-emission carbon dots were initially synthesized via the one-pot hydrothermal method employing L-aspartic acid and p-phenylenediamine as raw materials.In the presence of Mn^(2+),the emission peak centered at 350 nm exhibited significant enhancement,whereas another peak at 610 nm remained stable.Consequently,a ratiometric sensor for Mn^(2+)determination was established using the signal at 350 nm as the responsive signal and the signal at 610 nm as an internal reference.Under the optimal condition,a good linear relationship was achieved between the F350/F610 value and Mn^(2+)concentration ranging from 0.9 to 15μmol/L,with a calculated LOD of 61 nmol/L.Benefiting from the special Mn^(2+)-induced ratiometric approach,this method demonstrates outstanding sensitivity,selectivity,and stability,rendering it applicable for Mn^(2+)determination in complex biological samples,as well as Mn^(2+)imaging in MKN-45 and LO2 cells.展开更多
Using 2-dicyanomethylene-3-cyano-4,5,5-trimethyl-2,5-dihydrofuran(TCF)as a near-infrared fluorescent chromophore,we designed and synthesized a TCF-based fluorescent probe TCF-NS by introducing 2,4-dinitrophenyl ether ...Using 2-dicyanomethylene-3-cyano-4,5,5-trimethyl-2,5-dihydrofuran(TCF)as a near-infrared fluorescent chromophore,we designed and synthesized a TCF-based fluorescent probe TCF-NS by introducing 2,4-dinitrophenyl ether as the recognized site for H_(2)S.The probe TCF-NS displayed a rapid-response fluorescent against H_(2)S with high sensitivity and selection but had no significant fluorescence response to other biothiols.Furthermore,TCF-NS was applied to sense H_(2)S in living cells successfully with minimized cytotoxicity and a large Stokes shift.展开更多
Malignant tumours always threaten human health.For tumour diagnosis,positron emission tomography(PET)is the most sensitive and advanced imaging technique by radiotracers,such as radioactive^(18)F,^(11)C,^(64)Cu,^(68)G...Malignant tumours always threaten human health.For tumour diagnosis,positron emission tomography(PET)is the most sensitive and advanced imaging technique by radiotracers,such as radioactive^(18)F,^(11)C,^(64)Cu,^(68)Ga,and^(89)Zr.Among the radiotracers,the radioactive^(18)F-labelled chemical agent as PET probes plays a predominant role in monitoring,detecting,treating,and predicting tumours due to its perfect half-life.In this paper,the^(18)F-labelled chemical materials as PET probes are systematically summarized.First,we introduce various radionuclides of PET and elaborate on the mechanism of PET imaging.It highlights the^(18)F-labelled chemical agents used as PET probes,including[^(18)F]-2-deoxy-2-[^(18)F]fluoro-D-glucose([^(18)F]-FDG),^(18)F-labelled amino acids,^(18)F-labelled nucleic acids,^(18)F-labelled receptors,^(18)F-labelled reporter genes,and^(18)F-labelled hypoxia agents.In addition,some PET probes with metal as a supplementary element are introduced briefly.Meanwhile,the^(18)F-labelled nanoparticles for the PET probe and the multi-modality imaging probe are summarized in detail.The approach and strategies for the fabrication of^(18)F-labelled PET probes are also described briefly.The future development of the PET probe is also prospected.The development and application of^(18)F-labelled PET probes will expand our knowledge and shed light on the diagnosis and theranostics of tumours.展开更多
Rockfalls are among the frequent hazards in underground mines worldwide,requiring effective methods for detecting unstable rock blocks to ensure miners’and equipment’s safety.This study proposes a novel approach for...Rockfalls are among the frequent hazards in underground mines worldwide,requiring effective methods for detecting unstable rock blocks to ensure miners’and equipment’s safety.This study proposes a novel approach for identifying potential rockfall zones using infrared thermal imaging and image segmentation techniques.Infrared images of rock blocks were captured at the Draa Sfar deep underground mine in Morocco using the FLUKE TI401 PRO thermal camera.Two segmentation methods were applied to locate the potential unstable areas:the classical thresholding and the K-means clustering model.The results show that while thresholding allows a binary distinction between stable and unstable areas,K-means clustering is more accurate,especially when using multiple clusters to show different risk levels.The close match between the clustering masks of unstable blocks and their corresponding visible light images further validated this.The findings confirm that thermal image segmentation can serve as an alternative method for predicting rockfalls and monitoring geotechnical issues in underground mines.Underground operators worldwide can apply this approach to monitor rock mass stability.However,further research is recommended to enhance these results,particularly through deep learning-based segmentation and object detection models.展开更多
This narrative review examines the use of imaging biomarkers for diagnosing and monitoring hydrocephalus from birth through childhood.Early detection and longitudinal follow-up are essential for guiding timely interve...This narrative review examines the use of imaging biomarkers for diagnosing and monitoring hydrocephalus from birth through childhood.Early detection and longitudinal follow-up are essential for guiding timely interventions and asse-ssing treatment outcomes.Cranial ultrasound and magnetic resonance imaging(MRI)are the primary imaging modalities,providing critical insights into ventri-cular size,cerebrospinal fluid dynamics,and neurodevelopmental implications.Key parameters,including Evans’index,Levene’s index,and the Cella Media index,as well as volumetric and diffusion-based MRI techniques,have been explored for their diagnostic and prognostic value.Advances in automated image analysis and artificial intelligence have further improved measurement precision and reproducibility.Despite these developments,challenges remain in standar-dizing imaging protocols and establishing normative reference values across different pediatric populations.This review highlights the strengths and limita-tions of current imaging approaches,emphasizing the need for consistent metho-dologies to enhance diagnostic accuracy and optimize patient management in hydrocephalus.展开更多
BACKGROUND Appendicitis is an abdominal medical emergency and can be of various types.It can lead to a series of gastrointestinal symptoms and can affect health status.Therefore,attention should be paid to the diagnos...BACKGROUND Appendicitis is an abdominal medical emergency and can be of various types.It can lead to a series of gastrointestinal symptoms and can affect health status.Therefore,attention should be paid to the diagnosis of appendicitis to improve prognosis.AIM To assess the value of transabdominal superficial ultrasonography(TASU)in the clinical diagnosis of various types of appendicitis.METHODS A total of 100 patients suspected to have acute appendicitis that were admitted to our hospital between July 2022 and July 2024 were selected for this study.All of them underwent conventional abdominal ultrasonography and TASU.Taking surgical pathology as the gold standard,the diagnostic efficacy of the two ultrasonographic examinations was compared,and the ultrasonographic features of patients with different types of appendicitis were analyzed.RESULTS Comparison with the gold standard showed that among the 100 patients suspected of appendicitis,72 cases were diagnosed as appendicitis while 28 cases were deemed to be normal.Compared with conventional abdominal ultrasonography,TASU displayed a higher diagnostic efficiency(P<0.05).Among the 72 patients with acute appendicitis,22 cases were diagnosed as simple appendicitis,26 cases as suppurative appendicitis,and 24 cases as gangrenous appendicitis.TASU was more effective in the diagnosis of the various types of appendicitis,and the difference was significant between groups(P<0.05).Ultrasonography radiographs revealed an enlarged appendix with a tubular anechoic area,a widened lumen,with a visible occlusion or stercoral shadow and a cystic mass in the parenchyma.CONCLUSION TASU can accurately diagnose appendicitis and also be used to identify the various types of appendicitis,thereby having application value.展开更多
Background:Diabetic retinopathy remains one of the leading causes of vision impairment globally and poses diagnostic challenges due to the complexity of clinical imaging data and variability in disease progression.In ...Background:Diabetic retinopathy remains one of the leading causes of vision impairment globally and poses diagnostic challenges due to the complexity of clinical imaging data and variability in disease progression.In this study,we propose an innovative methodology that integrates artificial intelligence and quantum computing to enhance the early detection and clinical management of diabetic retinopathy.Methods:We developed a hybrid model combining machine learning algorithms with simulated quantum circuits to classify retinal images and associated clinical data.Anonymized datasets were used,and deep inductive transfer techniques were applied to improve diagnostic precision and generalizability.Results:The proposed model achieved a classification accuracy of 94.6%,significantly reducing diagnostic time and improving the prioritization of high-risk cases compared to conventional methods.The hybrid approach demonstrated superior performance in processing speed and accuracy for complex clinical scenarios.Conclusion:This study highlights the potential of combining AI and quantum computing to revolutionize the diagnosis of diabetic retinopathy.The proposed model provides a scalable and efficient solution for clinical environments,enabling faster and more accurate decision-making in ophthalmic care.展开更多
Unmanned aerial vehicle(UAV)imagery poses significant challenges for object detection due to extreme scale variations,high-density small targets(68%in VisDrone dataset),and complex backgrounds.While YOLO-series models...Unmanned aerial vehicle(UAV)imagery poses significant challenges for object detection due to extreme scale variations,high-density small targets(68%in VisDrone dataset),and complex backgrounds.While YOLO-series models achieve speed-accuracy trade-offs via fixed convolution kernels and manual feature fusion,their rigid architectures struggle with multi-scale adaptability,as exemplified by YOLOv8n’s 36.4%mAP and 13.9%small-object AP on VisDrone2019.This paper presents YOLO-LE,a lightweight framework addressing these limitations through three novel designs:(1)We introduce the C2f-Dy and LDown modules to enhance the backbone’s sensitivity to small-object features while reducing backbone parameters,thereby improving model efficiency.(2)An adaptive feature fusion module is designed to dynamically integrate multi-scale feature maps,optimizing the neck structure,reducing neck complexity,and enhancing overall model performance.(3)We replace the original loss function with a distributed focal loss and incorporate a lightweight self-attention mechanism to improve small-object recognition and bounding box regression accuracy.Experimental results demonstrate that YOLO-LE achieves 39.9%mAP@0.5 on VisDrone2019,representing a 9.6%improvement over YOLOv8n,while maintaining 8.5 GFLOPs computational efficiency.This provides an efficient solution for UAV object detection in complex scenarios.展开更多
In recent years,with the development of synthetic aperture radar(SAR)technology and the widespread application of deep learning,lightweight detection of SAR images has emerged as a research direction.The ultimate goal...In recent years,with the development of synthetic aperture radar(SAR)technology and the widespread application of deep learning,lightweight detection of SAR images has emerged as a research direction.The ultimate goal is to reduce computational and storage requirements while ensuring detection accuracy and reliability,making it an ideal choice for achieving rapid response and efficient processing.In this regard,a lightweight SAR ship target detection algorithm based on YOLOv8 was proposed in this study.Firstly,the C2f-Sc module was designed by fusing the C2f in the backbone network with the ScConv to reduce spatial redundancy and channel redundancy between features in convolutional neural networks.At the same time,the Ghost module was introduced into the neck network to effectively reduce model parameters and computational complexity.A relatively lightweight EMA attention mechanism was added to the neck network to promote the effective fusion of features at different levels.Experimental results showed that the Parameters and GFLOPs of the improved model are reduced by 8.5%and 7.0%when mAP@0.5 and mAP@0.5:0.95 are increased by 0.7%and 1.8%,respectively.It makes the model lightweight and improves the detection accuracy,which has certain application value.展开更多
In the field of image forensics,image tampering detection is a critical and challenging task.Traditional methods based on manually designed feature extraction typically focus on a specific type of tampering operation,...In the field of image forensics,image tampering detection is a critical and challenging task.Traditional methods based on manually designed feature extraction typically focus on a specific type of tampering operation,which limits their effectiveness in complex scenarios involving multiple forms of tampering.Although deep learningbasedmethods offer the advantage of automatic feature learning,current approaches still require further improvements in terms of detection accuracy and computational efficiency.To address these challenges,this study applies the UNet 3+model to image tampering detection and proposes a hybrid framework,referred to as DDT-Net(Deep Detail Tracking Network),which integrates deep learning with traditional detection techniques.In contrast to traditional additive methods,this approach innovatively applies amultiplicative fusion technique during downsampling,effectively combining the deep learning feature maps at each layer with those generated by the Bayar noise stream.This design enables noise residual features to guide the learning of semantic features more precisely and efficiently,thus facilitating comprehensive feature-level interaction.Furthermore,by leveraging the complementary strengths of deep networks in capturing large-scale semantic manipulations and traditional algorithms’proficiency in detecting fine-grained local traces,the method significantly enhances the accuracy and robustness of tampered region detection.Compared with other approaches,the proposed method achieves an F1 score improvement exceeding 30% on the DEFACTO and DIS25k datasets.In addition,it has been extensively validated on other datasets,including CASIA and DIS25k.Experimental results demonstrate that this method achieves outstanding performance across various types of image tampering detection tasks.展开更多
The application of deep learning for target detection in aerial images captured by Unmanned Aerial Vehicles(UAV)has emerged as a prominent research focus.Due to the considerable distance between UAVs and the photograp...The application of deep learning for target detection in aerial images captured by Unmanned Aerial Vehicles(UAV)has emerged as a prominent research focus.Due to the considerable distance between UAVs and the photographed objects,coupled with complex shooting environments,existing models often struggle to achieve accurate real-time target detection.In this paper,a You Only Look Once v8(YOLOv8)model is modified from four aspects:the detection head,the up-sampling module,the feature extraction module,and the parameter optimization of positive sample screening,and the YOLO-S3DT model is proposed to improve the performance of the model for detecting small targets in aerial images.Experimental results show that all detection indexes of the proposed model are significantly improved without increasing the number of model parameters and with the limited growth of computation.Moreover,this model also has the best performance compared to other detecting models,demonstrating its advancement within this category of tasks.展开更多
BACKGROUND Optical coherence tomography(OCT)enables high-resolution,non-invasive visualization of retinal structures.Recent evidence suggests that retinal layer alterations may reflect central nervous system changes a...BACKGROUND Optical coherence tomography(OCT)enables high-resolution,non-invasive visualization of retinal structures.Recent evidence suggests that retinal layer alterations may reflect central nervous system changes associated with psychiatric disorders such as schizophrenia(SZ).AIM To develop an advanced deep learning model to classify OCT images and distinguish patients with SZ from healthy controls using retinal biomarkers.METHODS A novel convolutional neural network,Self-AttentionNeXt,was designed by integrating grouped self-attention mechanisms,residual and inverted bottleneck blocks,and a final 1×1 convolution for feature refinement.The model was trained and tested on both a custom OCT dataset collected from patients with SZ and a publicly available OCT dataset(OCT2017).RESULTS Self-AttentionNeXt achieved 97.0%accuracy on the collected SZ OCT dataset and over 95%accuracy on the public OCT2017 dataset.Gradient-weighted class activation mapping visualizations confirmed the model’s attention to clinically relevant retinal regions,suggesting effective feature localization.CONCLUSION Self-AttentionNeXt effectively combines transformer-inspired attention mechanisms with convolutional neural networks architecture to support the early and accurate detection of SZ using OCT images.This approach offers a promising direction for artificial intelligence-assisted psychiatric diagnostics and clinical decision support.展开更多
Aimed at the long and narrow geometric features and poor generalization ability of the damage detection in conveyor belts with steel rope cores using the X-ray image,a detection method of damage X-ray image is propose...Aimed at the long and narrow geometric features and poor generalization ability of the damage detection in conveyor belts with steel rope cores using the X-ray image,a detection method of damage X-ray image is proposed based on the improved fully convolutional one-stage object detection(FCOS)algorithm.The regression performance of bounding boxes was optimized by introducing the complete intersection over union loss function into the improved algorithm.The feature fusion network structure is modified by adding adaptive fusion paths to the feature fusion network structure,which makes full use of the features of accurate localization and semantics of multi-scale feature fusion networks.Finally,the network structure was trained and validated by using the X-ray image dataset of damages in conveyor belts with steel rope cores provided by a flaw detection equipment manufacturer.In addition,the data enhancement methods such as rotating,mirroring,and scaling,were employed to enrich the image dataset so that the model is adequately trained.Experimental results showed that the improved FCOS algorithm promoted the precision rate and the recall rate by 20.9%and 14.8%respectively,compared with the original algorithm.Meanwhile,compared with Fast R-CNN,Faster R-CNN,SSD,and YOLOv3,the improved FCOS algorithm has obvious advantages;detection precision rate and recall rate of the modified network reached 95.8%and 97.0%respectively.Furthermore,it demonstrated a higher detection accuracy without affecting the speed.The results of this work have some reference significance for the automatic identification and detection of steel core conveyor belt damage.展开更多
基金supported by the National Key R&D Program of China(No.2023YFC3081200)the National Natural Science Foundation of China(No.42077264)。
文摘To map the rock joints in the underground rock mass,a method was proposed to semiautomatically detect the rock joints from borehole imaging logs using a deep learning algorithm.First,450 images containing rock joints were selected from borehole ZKZ01 in the Rumei hydropower station.These images were labeled to establish ground truth which was subdivided into training,validation,and testing data.Second,the YOLO v2 model with optimal parameter settings was constructed.Third,the training and validation data were used for model training,while the test data was used to generate the precision-recall curve for prediction evaluation.Fourth,the trained model was applied to a new borehole ZKZ02 to verify the feasibility of the model.There were 12 rock joints detected from the selected images in borehole ZKZ02 and four geometric parameters for each rock joint were determined by sinusoidal curve fitting.The average precision of the trained model reached 0.87.
基金supported in part by the Six Talent Peaks Project in Jiangsu Province under Grant 013040315in part by the China Textile Industry Federation Science and Technology Guidance Project under Grant 2017107+1 种基金in part by the National Natural Science Foundation of China under Grant 31570714in part by the China Scholarship Council under Grant 202108320290。
文摘The cleanliness of seed cotton plays a critical role in the pre-treatment of cotton textiles,and the removal of impurity during the harvesting process directly determines the quality and market value of cotton textiles.By fusing band combination optimization with deep learning,this study aims to achieve more efficient and accurate detection of film impurities in seed cotton on the production line.By applying hyperspectral imaging and a one-dimensional deep learning algorithm,we detect and classify impurities in seed cotton after harvest.The main categories detected include pure cotton,conveyor belt,film covering seed cotton,and film adhered to the conveyor belt.The proposed method achieves an impurity detection rate of 99.698%.To further ensure the feasibility and practical application potential of this strategy,we compare our results against existing mainstream methods.In addition,the model shows excellent recognition performance on pseudo-color images of real samples.With a processing time of 11.764μs per pixel from experimental data,it shows a much improved speed requirement while maintaining the accuracy of real production lines.This strategy provides an accurate and efficient method for removing impurities during cotton processing.
基金National Natural Science Foundation of China,Grant/Award Number:62303275International Alliance for Cancer Early Detection,Grant/Award Numbers:C28070/A30912,C73666/A31378Wellcome/EPSRC Centre for Interventional and Surgical Sciences,Grant/Award Number:203145Z/16/Z。
文摘Automated prostate cancer detection in magnetic resonance imaging(MRI)scans is of significant importance for cancer patient management.Most existing computer-aided diagnosis systems adopt segmentation methods while object detection approaches recently show promising results.The authors have(1)carefully compared performances of most-developed segmentation and object detection methods in localising prostate imaging reporting and data system(PIRADS)-labelled prostate lesions on MRI scans;(2)proposed an additional customised set of lesion-level localisation sensitivity and precision;(3)proposed efficient ways to ensemble the segmentation and object detection methods for improved performances.The ground-truth(GT)perspective lesion-level sensitivity and prediction-perspective lesion-level precision are reported,to quantify the ratios of true positive voxels being detected by algorithms over the number of voxels in the GT labelled regions and predicted regions.The two networks are trained independently on 549 clinical patients data with PIRADS-V2 as GT labels,and tested on 161 internal and 100 external MRI scans.At the lesion level,nnDetection outperforms nnUNet for detecting both PIRADS≥3 and PIRADS≥4 lesions in majority cases.For example,at the average false positive prediction per patient being 3,nnDetection achieves a greater Intersection-of-Union(IoU)-based sensitivity than nnUNet for detecting PIRADS≥3 lesions,being 80.78%�1.50%versus 60.40%�1.64%(p<0.01).At the voxel level,nnUnet is in general superior or comparable to nnDetection.The proposed ensemble methods achieve improved or comparable lesion-level accuracy,in all tested clinical scenarios.For example,at 3 false positives,the lesion-wise ensemble method achieves 82.24%�1.43%sensitivity versus 80.78%�1.50%(nnDetection)and 60.40%�1.64%(nnUNet)for detecting PIRADS≥3 lesions.Consistent conclusions are also drawn from results on the external data set.
基金the financial support from the National Natural Science Foundation of China(Nos.82272067,81974386,and M-0696)Natural Science Foundation of Hunan Province(Nos.2022JJ80052 and 2022JJ40656)the Innovation Fund for Postgraduate Students of Central South University(No.2023ZZTS0609)。
文摘Butyrylcholinesterase(BChE)is a key enzyme in the metabolism of cholinergic compounds.It has been recognized as a key biomarker for many diseases,including liver diseases and Alzheimer’s disease.However,classical methods for detecting BChE activity suffer from low sensitivity,cumbersome pre-treatment,and poor stability.Chemiluminescence is a promising new method for detecting and imaging the activity of BChE.It has several advantages over traditional methods,including low background interference,high sensitivity,and the absence of external illumination.In this study,we developed a novel BChE-activatable chemiluminescent probe(CL-BChE).It exhibited a significant chemiluminescence enhancement at 525nm upon incubation with BChE.It had a low limit of detection(6.25×10^(−3)U/mL)and was highly selective for BChE.CL-BChE was used to image BChE activity in living cells and tumor-bearing animal models.It was also successfully applied to detect pesticide residue,even under the interference of representative phytochromes and real vegetable samples.Given its high sensitivity,selectivity,and versatility,we believe that CL-BChE will be a promising tool for investigating BChE’s activity in biomedical research as well as other BChE-related scenarios.
基金financial support from National Natural Science Foundation of China(No.22175156)the Fundamental Research Funds for the Central Universities,China University of Geosciences(Wuhan)(No.162301202692).
文摘Aggregation-induced emission(AIE)is a unique phenomenon where certain organic materials exhibit enhanced luminescence in their aggregated states,overcoming the typical quenching observed in conventional organic materials.Since its discovery in 2001,AIE has driven significant advances in fields like OLEDs and biological imaging,earning recognition in fundamental research.However,its application in high-energy radiation detection remains underexplored.Organic scintillators,though widely used,face challenges such as low light yield and poor radiation attenuation.AIE materials offer promising solutions by improving light yield,response speed,and radiation attenuation.This review summarizes the design strategies behind AIE scintillators and their very recent applications in X-ray,γ-ray,and fast neutron detection.We highlight their advantages in enhancing detection sensitivity,reducing background noise,and achieving high-resolution imaging.By addressing the current challenges,we believe AIE materials will play a pivotal role in advancing future radiation detection and imaging technologies.
基金supported by the National Natural Science Foundation of China under grant number 62066016the Natural Science Foundation of Hunan Province of China under grant number 2024JJ7395+2 种基金the Scientific Research Project of Education Department of Hunan Province of China under grant number 22B0549International and Regional Science and Technology Cooperation and Exchange Program of the Hunan Association for Science and Technology under grant number 025SKX-KJ-04Hunan Province Undergraduate Innovation and Entrepreneurship Training Program(grant number S202410531015).
文摘The YOLO(You Only Look Once)series,a leading single-stage object detection framework,has gained significant prominence in medical-image analysis due to its real-time efficiency and robust performance.Recent iterations of YOLO have further enhanced its accuracy and reliability in critical clinical tasks such as tumor detection,lesion segmentation,and microscopic image analysis,thereby accelerating the development of clinical decision support systems.This paper systematically reviews advances in YOLO-based medical object detection from 2018 to 2024.It compares YOLO’s performance with othermodels(e.g.,Faster R-CNN,RetinaNet)inmedical contexts,summarizes standard evaluation metrics(e.g.,mean Average Precision(mAP),sensitivity),and analyzes hardware deployment strategies using public datasets such as LUNA16,BraTS,andCheXpert.Thereviewhighlights the impressive performance of YOLO models,particularly from YOLOv5 to YOLOv8,in achieving high precision(up to 99.17%),sensitivity(up to 97.5%),and mAP exceeding 95%in tasks such as lung nodule,breast cancer,and polyp detection.These results demonstrate the significant potential of YOLO models for early disease detection and real-time clinical applications,indicating their ability to enhance clinical workflows.However,the study also identifies key challenges,including high small-object miss rates,limited generalization in low-contrast images,scarcity of annotated data,and model interpretability issues.Finally,the potential future research directions are also proposed to address these challenges and further advance the application of YOLO models in healthcare.
基金supported by the National Natural Science Foundation of China(Nos.12205271,12075217,U20B2011,and 51978218)Sichuan Science and Technology Program(No.2019ZDZX0010)the National Key R&D Program of China(No.2022YFA1604002).
文摘Neutron capture event imaging is a novel technique that has the potential to substantially enhance the resolution of existing imaging systems.This study provides a measurement method for neutron capture event distribution along with multiple reconstruction methods for super-resolution imaging.The proposed technology reduces the point-spread function of an imag-ing system through single-neutron detection and event reconstruction,thereby significantly improving imaging resolution.A single-neutron detection experiment was conducted using a highly practical and efficient^(6)LiF-ZnS scintillation screen of a cold neutron imaging device in the research reactor.In milliseconds of exposure time,a large number of weak light clusters and their distribution in the scintillation screen were recorded frame by frame,to complete single-neutron detection.Several reconstruction algorithms were proposed for the calculations.The location of neutron capture was calculated using several processing methods such as noise removal,filtering,spot segmentation,contour analysis,and local positioning.The proposed algorithm achieved a higher imaging resolution and faster reconstruction speed,and single-neutron super-resolution imaging was realized by combining single-neutron detection experiments and reconstruction calculations.The results show that the resolution of the 100μm thick^(6)LiF-ZnS scintillation screen can be improved from 125 to 40 microns.This indicates that the proposed single-neutron detection and calculation method is effective and can significantly improve imaging resolution.
基金Supported by National Natural Science Foundation of China(22264023)Natural Science Foundation of Shaanxi Province(2024JC-YBQN-0150)+2 种基金Yan'an Science and Technology Bureau Project(2023-SFGG-057)Scientific Research Projects of Education Department of Shaanxi Province(22JK0614)PhD Start Fund of Yan'an University(YDBK2022-15)。
文摘Manganese(Mn),an essential trace element in the human body,plays critical roles in many biological processes.Recent studies have discovered that Mn^(2+)may promote or directly activate the cGAS-STING pathway,thereby subsequently initiating the natural immune response and augmenting antitumor therapy.However,the current lack of accurate methods for Mn^(2+)determination in cells significantly limits their mechanism investigation;hence,it is urgent to establish novel tools to detect Mn^(2+)in cells.In this study,the dual-emission carbon dots were initially synthesized via the one-pot hydrothermal method employing L-aspartic acid and p-phenylenediamine as raw materials.In the presence of Mn^(2+),the emission peak centered at 350 nm exhibited significant enhancement,whereas another peak at 610 nm remained stable.Consequently,a ratiometric sensor for Mn^(2+)determination was established using the signal at 350 nm as the responsive signal and the signal at 610 nm as an internal reference.Under the optimal condition,a good linear relationship was achieved between the F350/F610 value and Mn^(2+)concentration ranging from 0.9 to 15μmol/L,with a calculated LOD of 61 nmol/L.Benefiting from the special Mn^(2+)-induced ratiometric approach,this method demonstrates outstanding sensitivity,selectivity,and stability,rendering it applicable for Mn^(2+)determination in complex biological samples,as well as Mn^(2+)imaging in MKN-45 and LO2 cells.
基金financially supported by the Natural Science Foundation of Jiangsu Province(Grant No.BK20241181)the State Key Laboratory of AnalyticalChemistry for Life Science,School of Chemistry and Chemical Engineering,Nanjing University(Grant No.SKLACLS2419)。
文摘Using 2-dicyanomethylene-3-cyano-4,5,5-trimethyl-2,5-dihydrofuran(TCF)as a near-infrared fluorescent chromophore,we designed and synthesized a TCF-based fluorescent probe TCF-NS by introducing 2,4-dinitrophenyl ether as the recognized site for H_(2)S.The probe TCF-NS displayed a rapid-response fluorescent against H_(2)S with high sensitivity and selection but had no significant fluorescence response to other biothiols.Furthermore,TCF-NS was applied to sense H_(2)S in living cells successfully with minimized cytotoxicity and a large Stokes shift.
文摘Malignant tumours always threaten human health.For tumour diagnosis,positron emission tomography(PET)is the most sensitive and advanced imaging technique by radiotracers,such as radioactive^(18)F,^(11)C,^(64)Cu,^(68)Ga,and^(89)Zr.Among the radiotracers,the radioactive^(18)F-labelled chemical agent as PET probes plays a predominant role in monitoring,detecting,treating,and predicting tumours due to its perfect half-life.In this paper,the^(18)F-labelled chemical materials as PET probes are systematically summarized.First,we introduce various radionuclides of PET and elaborate on the mechanism of PET imaging.It highlights the^(18)F-labelled chemical agents used as PET probes,including[^(18)F]-2-deoxy-2-[^(18)F]fluoro-D-glucose([^(18)F]-FDG),^(18)F-labelled amino acids,^(18)F-labelled nucleic acids,^(18)F-labelled receptors,^(18)F-labelled reporter genes,and^(18)F-labelled hypoxia agents.In addition,some PET probes with metal as a supplementary element are introduced briefly.Meanwhile,the^(18)F-labelled nanoparticles for the PET probe and the multi-modality imaging probe are summarized in detail.The approach and strategies for the fabrication of^(18)F-labelled PET probes are also described briefly.The future development of the PET probe is also prospected.The development and application of^(18)F-labelled PET probes will expand our knowledge and shed light on the diagnosis and theranostics of tumours.
基金supported by the Moroccan Ministry of Higher Education,Scientific Research,and Innovationthe Moroccan Digital Development Agency(DDA)+2 种基金the National Center for Scientific and Technical Research of Morocco(CNRST)through the Al-Khawarizmi projectthe MANAGEM groupMASCIR supporting this project.
文摘Rockfalls are among the frequent hazards in underground mines worldwide,requiring effective methods for detecting unstable rock blocks to ensure miners’and equipment’s safety.This study proposes a novel approach for identifying potential rockfall zones using infrared thermal imaging and image segmentation techniques.Infrared images of rock blocks were captured at the Draa Sfar deep underground mine in Morocco using the FLUKE TI401 PRO thermal camera.Two segmentation methods were applied to locate the potential unstable areas:the classical thresholding and the K-means clustering model.The results show that while thresholding allows a binary distinction between stable and unstable areas,K-means clustering is more accurate,especially when using multiple clusters to show different risk levels.The close match between the clustering masks of unstable blocks and their corresponding visible light images further validated this.The findings confirm that thermal image segmentation can serve as an alternative method for predicting rockfalls and monitoring geotechnical issues in underground mines.Underground operators worldwide can apply this approach to monitor rock mass stability.However,further research is recommended to enhance these results,particularly through deep learning-based segmentation and object detection models.
文摘This narrative review examines the use of imaging biomarkers for diagnosing and monitoring hydrocephalus from birth through childhood.Early detection and longitudinal follow-up are essential for guiding timely interventions and asse-ssing treatment outcomes.Cranial ultrasound and magnetic resonance imaging(MRI)are the primary imaging modalities,providing critical insights into ventri-cular size,cerebrospinal fluid dynamics,and neurodevelopmental implications.Key parameters,including Evans’index,Levene’s index,and the Cella Media index,as well as volumetric and diffusion-based MRI techniques,have been explored for their diagnostic and prognostic value.Advances in automated image analysis and artificial intelligence have further improved measurement precision and reproducibility.Despite these developments,challenges remain in standar-dizing imaging protocols and establishing normative reference values across different pediatric populations.This review highlights the strengths and limita-tions of current imaging approaches,emphasizing the need for consistent metho-dologies to enhance diagnostic accuracy and optimize patient management in hydrocephalus.
文摘BACKGROUND Appendicitis is an abdominal medical emergency and can be of various types.It can lead to a series of gastrointestinal symptoms and can affect health status.Therefore,attention should be paid to the diagnosis of appendicitis to improve prognosis.AIM To assess the value of transabdominal superficial ultrasonography(TASU)in the clinical diagnosis of various types of appendicitis.METHODS A total of 100 patients suspected to have acute appendicitis that were admitted to our hospital between July 2022 and July 2024 were selected for this study.All of them underwent conventional abdominal ultrasonography and TASU.Taking surgical pathology as the gold standard,the diagnostic efficacy of the two ultrasonographic examinations was compared,and the ultrasonographic features of patients with different types of appendicitis were analyzed.RESULTS Comparison with the gold standard showed that among the 100 patients suspected of appendicitis,72 cases were diagnosed as appendicitis while 28 cases were deemed to be normal.Compared with conventional abdominal ultrasonography,TASU displayed a higher diagnostic efficiency(P<0.05).Among the 72 patients with acute appendicitis,22 cases were diagnosed as simple appendicitis,26 cases as suppurative appendicitis,and 24 cases as gangrenous appendicitis.TASU was more effective in the diagnosis of the various types of appendicitis,and the difference was significant between groups(P<0.05).Ultrasonography radiographs revealed an enlarged appendix with a tubular anechoic area,a widened lumen,with a visible occlusion or stercoral shadow and a cystic mass in the parenchyma.CONCLUSION TASU can accurately diagnose appendicitis and also be used to identify the various types of appendicitis,thereby having application value.
文摘Background:Diabetic retinopathy remains one of the leading causes of vision impairment globally and poses diagnostic challenges due to the complexity of clinical imaging data and variability in disease progression.In this study,we propose an innovative methodology that integrates artificial intelligence and quantum computing to enhance the early detection and clinical management of diabetic retinopathy.Methods:We developed a hybrid model combining machine learning algorithms with simulated quantum circuits to classify retinal images and associated clinical data.Anonymized datasets were used,and deep inductive transfer techniques were applied to improve diagnostic precision and generalizability.Results:The proposed model achieved a classification accuracy of 94.6%,significantly reducing diagnostic time and improving the prioritization of high-risk cases compared to conventional methods.The hybrid approach demonstrated superior performance in processing speed and accuracy for complex clinical scenarios.Conclusion:This study highlights the potential of combining AI and quantum computing to revolutionize the diagnosis of diabetic retinopathy.The proposed model provides a scalable and efficient solution for clinical environments,enabling faster and more accurate decision-making in ophthalmic care.
文摘Unmanned aerial vehicle(UAV)imagery poses significant challenges for object detection due to extreme scale variations,high-density small targets(68%in VisDrone dataset),and complex backgrounds.While YOLO-series models achieve speed-accuracy trade-offs via fixed convolution kernels and manual feature fusion,their rigid architectures struggle with multi-scale adaptability,as exemplified by YOLOv8n’s 36.4%mAP and 13.9%small-object AP on VisDrone2019.This paper presents YOLO-LE,a lightweight framework addressing these limitations through three novel designs:(1)We introduce the C2f-Dy and LDown modules to enhance the backbone’s sensitivity to small-object features while reducing backbone parameters,thereby improving model efficiency.(2)An adaptive feature fusion module is designed to dynamically integrate multi-scale feature maps,optimizing the neck structure,reducing neck complexity,and enhancing overall model performance.(3)We replace the original loss function with a distributed focal loss and incorporate a lightweight self-attention mechanism to improve small-object recognition and bounding box regression accuracy.Experimental results demonstrate that YOLO-LE achieves 39.9%mAP@0.5 on VisDrone2019,representing a 9.6%improvement over YOLOv8n,while maintaining 8.5 GFLOPs computational efficiency.This provides an efficient solution for UAV object detection in complex scenarios.
文摘In recent years,with the development of synthetic aperture radar(SAR)technology and the widespread application of deep learning,lightweight detection of SAR images has emerged as a research direction.The ultimate goal is to reduce computational and storage requirements while ensuring detection accuracy and reliability,making it an ideal choice for achieving rapid response and efficient processing.In this regard,a lightweight SAR ship target detection algorithm based on YOLOv8 was proposed in this study.Firstly,the C2f-Sc module was designed by fusing the C2f in the backbone network with the ScConv to reduce spatial redundancy and channel redundancy between features in convolutional neural networks.At the same time,the Ghost module was introduced into the neck network to effectively reduce model parameters and computational complexity.A relatively lightweight EMA attention mechanism was added to the neck network to promote the effective fusion of features at different levels.Experimental results showed that the Parameters and GFLOPs of the improved model are reduced by 8.5%and 7.0%when mAP@0.5 and mAP@0.5:0.95 are increased by 0.7%and 1.8%,respectively.It makes the model lightweight and improves the detection accuracy,which has certain application value.
基金supported by National Natural Science Foundation of China(No.61502274).
文摘In the field of image forensics,image tampering detection is a critical and challenging task.Traditional methods based on manually designed feature extraction typically focus on a specific type of tampering operation,which limits their effectiveness in complex scenarios involving multiple forms of tampering.Although deep learningbasedmethods offer the advantage of automatic feature learning,current approaches still require further improvements in terms of detection accuracy and computational efficiency.To address these challenges,this study applies the UNet 3+model to image tampering detection and proposes a hybrid framework,referred to as DDT-Net(Deep Detail Tracking Network),which integrates deep learning with traditional detection techniques.In contrast to traditional additive methods,this approach innovatively applies amultiplicative fusion technique during downsampling,effectively combining the deep learning feature maps at each layer with those generated by the Bayar noise stream.This design enables noise residual features to guide the learning of semantic features more precisely and efficiently,thus facilitating comprehensive feature-level interaction.Furthermore,by leveraging the complementary strengths of deep networks in capturing large-scale semantic manipulations and traditional algorithms’proficiency in detecting fine-grained local traces,the method significantly enhances the accuracy and robustness of tampered region detection.Compared with other approaches,the proposed method achieves an F1 score improvement exceeding 30% on the DEFACTO and DIS25k datasets.In addition,it has been extensively validated on other datasets,including CASIA and DIS25k.Experimental results demonstrate that this method achieves outstanding performance across various types of image tampering detection tasks.
文摘The application of deep learning for target detection in aerial images captured by Unmanned Aerial Vehicles(UAV)has emerged as a prominent research focus.Due to the considerable distance between UAVs and the photographed objects,coupled with complex shooting environments,existing models often struggle to achieve accurate real-time target detection.In this paper,a You Only Look Once v8(YOLOv8)model is modified from four aspects:the detection head,the up-sampling module,the feature extraction module,and the parameter optimization of positive sample screening,and the YOLO-S3DT model is proposed to improve the performance of the model for detecting small targets in aerial images.Experimental results show that all detection indexes of the proposed model are significantly improved without increasing the number of model parameters and with the limited growth of computation.Moreover,this model also has the best performance compared to other detecting models,demonstrating its advancement within this category of tasks.
文摘BACKGROUND Optical coherence tomography(OCT)enables high-resolution,non-invasive visualization of retinal structures.Recent evidence suggests that retinal layer alterations may reflect central nervous system changes associated with psychiatric disorders such as schizophrenia(SZ).AIM To develop an advanced deep learning model to classify OCT images and distinguish patients with SZ from healthy controls using retinal biomarkers.METHODS A novel convolutional neural network,Self-AttentionNeXt,was designed by integrating grouped self-attention mechanisms,residual and inverted bottleneck blocks,and a final 1×1 convolution for feature refinement.The model was trained and tested on both a custom OCT dataset collected from patients with SZ and a publicly available OCT dataset(OCT2017).RESULTS Self-AttentionNeXt achieved 97.0%accuracy on the collected SZ OCT dataset and over 95%accuracy on the public OCT2017 dataset.Gradient-weighted class activation mapping visualizations confirmed the model’s attention to clinically relevant retinal regions,suggesting effective feature localization.CONCLUSION Self-AttentionNeXt effectively combines transformer-inspired attention mechanisms with convolutional neural networks architecture to support the early and accurate detection of SZ using OCT images.This approach offers a promising direction for artificial intelligence-assisted psychiatric diagnostics and clinical decision support.
文摘Aimed at the long and narrow geometric features and poor generalization ability of the damage detection in conveyor belts with steel rope cores using the X-ray image,a detection method of damage X-ray image is proposed based on the improved fully convolutional one-stage object detection(FCOS)algorithm.The regression performance of bounding boxes was optimized by introducing the complete intersection over union loss function into the improved algorithm.The feature fusion network structure is modified by adding adaptive fusion paths to the feature fusion network structure,which makes full use of the features of accurate localization and semantics of multi-scale feature fusion networks.Finally,the network structure was trained and validated by using the X-ray image dataset of damages in conveyor belts with steel rope cores provided by a flaw detection equipment manufacturer.In addition,the data enhancement methods such as rotating,mirroring,and scaling,were employed to enrich the image dataset so that the model is adequately trained.Experimental results showed that the improved FCOS algorithm promoted the precision rate and the recall rate by 20.9%and 14.8%respectively,compared with the original algorithm.Meanwhile,compared with Fast R-CNN,Faster R-CNN,SSD,and YOLOv3,the improved FCOS algorithm has obvious advantages;detection precision rate and recall rate of the modified network reached 95.8%and 97.0%respectively.Furthermore,it demonstrated a higher detection accuracy without affecting the speed.The results of this work have some reference significance for the automatic identification and detection of steel core conveyor belt damage.
