The printed circuit heat exchanger(PCHE) is receiving wide attention as a new kind of compact heat exchanger and is considered as a promising vaporizer in the LNG process. In this paper, a PCHE straight channel in the...The printed circuit heat exchanger(PCHE) is receiving wide attention as a new kind of compact heat exchanger and is considered as a promising vaporizer in the LNG process. In this paper, a PCHE straight channel in the length of 500 mm is established, with a semicircular cross section in a diameter of 1.2 mm.Numerical simulation is employed to investigate the flow and heat transfer performance of supercritical methane in the channel. The pseudo-boiling theory is adopted and the liquid-like, two-phase-like, and vapor-like regimes are divided for supercritical methane to analyze the heat transfer and flow features.The results are presented in micro segment to show the local convective heat transfer coefficient and pressure drop. It shows that the convective heat transfer coefficient in segments along the channel has a significant peak feature near the pseudo-critical point and a heat transfer deterioration when the average fluid temperature in the segment is higher than the pseudo-critical point. The reason is explained with the generation of vapor-like film near the channel wall that the peak feature related to a nucleateboiling-like state and heat transfer deterioration related to a film-boiling-like state. The effects of parameters, including mass flow rate, pressure, and wall heat flux on flow and heat transfer were analyzed.In calculating of the averaged heat transfer coefficient of the whole channel, the traditional method shows significant deviation and the micro segment weighted average method is adopted. The pressure drop can mainly be affected by the mass flux and pressure and little affected by the wall heat flux. The peak of the convective heat transfer coefficient can only form at high mass flux, low wall heat flux, and near critical pressure, in which condition the nucleate-boiling-like state is easier to appear. Moreover,heat transfer deterioration will always appear, since the supercritical flow will finally develop into a filmboiling-like state. So heat transfer deterioration should be taken seriously in the design and safe operation of vaporizer PCHE. The study of this work clarified the local heat transfer and flow feature of supercritical methane in microchannel and contributed to the deep understanding of supercritical methane flow of the vaporization process in PCHE.展开更多
Segment Anything Model(SAM)is a cutting-edge model that has shown impressive performance in general object segmentation.The birth of the segment anything is a groundbreaking step towards creating a universal intellige...Segment Anything Model(SAM)is a cutting-edge model that has shown impressive performance in general object segmentation.The birth of the segment anything is a groundbreaking step towards creating a universal intelligent model.Due to its superior performance in general object segmentation,it quickly gained attention and interest.This makes SAM particularly attractive in industrial surface defect segmentation,especially for complex industrial scenes with limited training data.However,its segmentation ability for specific industrial scenes remains unknown.Therefore,in this work,we select three representative and complex industrial surface defect detection scenarios,namely strip steel surface defects,tile surface defects,and rail surface defects,to evaluate the segmentation performance of SAM.Our results show that although SAM has great potential in general object segmentation,it cannot achieve satisfactory performance in complex industrial scenes.Our test results are available at:https://github.com/VDT-2048/SAM-IS.展开更多
Background:To evaluate the efficacy of stent-assisted coiling(SAC)for the treatment of carotid ophthalmic segment aneurysm segment aneurysms(OSAs)of the internal carotid artery(ICA)through detailed long-term follow-up...Background:To evaluate the efficacy of stent-assisted coiling(SAC)for the treatment of carotid ophthalmic segment aneurysm segment aneurysms(OSAs)of the internal carotid artery(ICA)through detailed long-term follow-up of a large patient cohort.Methods:We retrospectively analyzed 88 consecutive patients with OSAs between January 2009 and January 2020 at our center.Angiographic results were evaluated using the modified Raymond grading system and clinical outcomes were evaluated using the mRS scale.The primary endpoints were major aneurysm recurrence and poor clinical outcomes for at least 18 months of follow-up.The patients were asked to attend clinical follow-up assessments and possibly undergo DSA or MR via telephone.Results:We enrolled 88 patients with 99 OSAs treated with coiling,of whom 76 were treated with SAC.The coiling procedures were successful in all 88 patients.Overall,complications occurred in 8 patients(9.1%).No procedure-related mortality was observed.67(76.1%)experienced immediate aneurysm occlusion at the end of the procedure.Long-term angiographic follow-up(18 months)was available in 45/88 aneurysms(51%)(average 18.7±5.2 months).Four patients continued their follow-up for 5 years after initial aneurysm treatment.After a clinical follow-up time of 28.7 months(range,12-51 months),85 patients(95.5%)achieved favorable clinical outcomes(mRS scores of 0-2).Conclusions:This study indicates that SAC treatment is a safe and effective therapeutic alternative for ruptured and unruptured OSAs.The procedural risks are low with relatively long-term effectiveness.展开更多
AIM:To predict postoperative intraocular lens(IOL)position using the Sirius anterior segment analysis system and investigate the effect of lens position and IOL type on postoperative refraction.METHODS:A total of 97 p...AIM:To predict postoperative intraocular lens(IOL)position using the Sirius anterior segment analysis system and investigate the effect of lens position and IOL type on postoperative refraction.METHODS:A total of 97 patients(102 eyes)were enrolled in the final analysis.An anterior segment biometry measurement was performed preoperatively with Sirius and Lenstar.The results of predicted lens position(PLP)and IOL power were automatically calculated by the software used by the instruments.Effective lens position(ELP)was measured manually using Sirius 3 mo postoperatively.Pearson's correlation analysis and linear regression analysis were used to determine the correlation of lens position to other parameters.RESULTS:PLP and ELP were positively correlated to axial length(AL;r=0.42,P<0.0001 and r=0.49,P<0.0001,respectively).There was a weak correlation between the peLP(ELP-PLP)and the prediction error of spherical refraction(peSR;r=0.34,P<0.0001).The peLP of Softec HD IOL differed statistically from those of both the TECNIS ZCB00 and Sensor AR40E IOLs.Multiple linear regression was used to obtain the prediction formula:ELP=0.66+0.63×[aqueous depth(AQD)+0.6 LT](r=0.61,P<0.0001),and a new variable(AQD+0.6 LT)was found to have the strongest correlation with ELP.CONCLUSION:The Sirius anterior segment analysis system is helpful to predict ELP,which reduces postoperative refraction error.展开更多
Myelinated axons of the peripheral and central nervous system（PNS＆CNS）are divided into molecularly distinct excitable domains,including the axon initial segment（AIS）and nodes of Ranvier.The AIS is composed of a d...Myelinated axons of the peripheral and central nervous system（PNS＆CNS）are divided into molecularly distinct excitable domains,including the axon initial segment（AIS）and nodes of Ranvier.The AIS is composed of a dense network of cytoskeletal proteins,cell adhesion molecules,and voltage gated ion channels and is located at the proximal most region of the axon（Koleand Stuart, 2012）.展开更多
Objectives:Distal segment aortic enlargement(DSAE)is a common complication that influences the long-term prognosis of type B aortic dissection(TBAD)after thoracic endovascular aortic repair(TEVAR).In this study,a mult...Objectives:Distal segment aortic enlargement(DSAE)is a common complication that influences the long-term prognosis of type B aortic dissection(TBAD)after thoracic endovascular aortic repair(TEVAR).In this study,a multivariate analysis was performed to find potential factors predictive of DSAE.Methods:A single-center retrospective study was performed from 1999 to 2016.Included in the study were complicated TBAD patients who underwent TEVAR with uncovered residual tears.Based on the diameter of the distal segment of the uncovered aorta,we assigned patients to an enlargement group and a non-enlargement group.Data extracted from the medical records included demographic and clinical characteristics and followup computed tomography angiography data.The primary endpoints were the all-cause mortality and the presumably aortic-related events that required reintervention during the follow-up period.Results:For the 333 patients,all-cause mortality was 38(11.41%),and 76(22.82%)patients underwent reintervention.A total of 70(21.02%)patients experienced DSAE,among them were 2 patients who died of aortic rupture and 58 patients who accepted reintervention.Multivariate analysis reviewed independent risk factors of postoperative DSAE,including current smoking,the residual length of the patent false lumen,the postoperative number of dissection tears in the thoracic aorta and type III aortic arch;as well as protective factors,including the application of a restrictive bare stent(RBS),the length of covered stent in the descending thoracic aorta,and the distance from the residual first tear to the left subclavian artery(LSA).Conclusion:DSAE after TEVAR for patients with a complicated TBAD can be influenced by their current smoking habit,the residual length of patent false lumen,the postoperative number of dissection tears in the thoracic aorta and the aortic arch type.Meanwhile,RBS usage,the length of the covered stent in the descending thoracic aorta and the distance from the residual first tear to the LSA could have positive effect on the prognosis.展开更多
AIM：To quantitatively assess narrow anterior chamber angle using spectral-domain anterior segment optical coherence tomography（SD-AS-OCT） and ultrasound biomicroscopy（UBM）,and to evaluate the correlations and con...AIM：To quantitatively assess narrow anterior chamber angle using spectral-domain anterior segment optical coherence tomography（SD-AS-OCT） and ultrasound biomicroscopy（UBM）,and to evaluate the correlations and consistency between SD-AS-OCT and UBM.· METHODS：Fifty-five eyes from 40 patients were examined.Patients were diagnosed with primary angleclosure glaucoma（PACG） remission（11 eyes from 8patients）,primary angle closure（PAC,20 eyes from 20patients） and PAC suspect（24 eyes from 12 patients）.Each eye was examined by SD-AS-OCT and UBM after laser peripheral iridotomy（LPI）.The measurements of SD-AS-OCT were angle open distance（AOD）,anterior chamber angle（ACA）,trabecular iris angle（TIA）,and trabecular iris space area（TISA）.UBM measurements were AOD and TIA.Correlations of AOD500 and TIA500 between UBM and AS-OCT were assessed.All parameters were analysed by SPSS 16.0 and MedCalc.· RESULTS：ACA,TIA and AOD measured by SD-ASOCT reached a maximum at the temporal quadrant and minimum at the nasal quadrant.Group parameters of AOD500 and AOD750 showed a linear positive correlation,and AOD750 had less variability.UBM outcomes of AOD500 and TIA500 were significantly smaller than those of SD-AS-OCT.The results of the two techniques were correlated at the superior,nasal and inferior quadrants.CONCLUSION：Both UBM and SD-AS-OCT are efficient tools for follow-up during the course of PACG.We recommended using parameters at 750 μm anterior to the sclera spur for the screening and follow-up of PACG and PAC.The two methods might be alternatives to each other.展开更多
AIM:To evaluate the clinical results after implantation of a new intrastromal corneal ring segment(ICRS)associated with photorefractive keratectomy(PRK)to correct high myopia(HM)patients with thin corneas.METHODS:We e...AIM:To evaluate the clinical results after implantation of a new intrastromal corneal ring segment(ICRS)associated with photorefractive keratectomy(PRK)to correct high myopia(HM)patients with thin corneas.METHODS:We evaluated 42 eyes of 23 HM patients that had ICRS implantation followed by PRK.The mean age of patients was 29.1±7.12 y(range 18 to 40 years old).Uncorrected visual acuity(UCVA),best corrected visual acuity(BCVA),keratometry,spherical equivalent,pachymetry,and aberrometry were compared using ANOVA with repeated measurements evaluated preoperatively and at last follow-up visit after the procedures.The refractive predictability and simulated/real corneal ablation were also assessed.RESULTS:The mean follow-up time after PRK was 6.8±1.6 mo.The mean preoperative UCVA improved from 20/800 preoperative to 20/100 after ICRS and 20/35 after PRK.The mean preoperative BCVA was 20/25(range from 20/30 to 20/20)and remained unchanged after ICRS implantation.Following the PRK the mean BCVA was 20/25(range from 20/30 to 20/20).The mean spherical equivalent decreased from-7.25±1.12(range-5.00 to-9.00)preoperatively to-3.32±1.0(range-2.00 to-5.00)postoperatively(P<0.001)after ICRS implantation and decreased from-2.44±1.51 preoperatively to 0.32±0.45(range-0.625 to 0.875)postoperatively(P<0.001)after PRK.The change in BCVA and topographic astigmatism was statistically significant(P<0.0001).CONCLUSION:ICRS in HM associated with PRK can be a tissue saving procedure and an alternative surgical option for correction of moderate to high myopia.展开更多
BACKGROUND: Bilio-intestinal drainage is routinely per- formed by Roux-en-Y reconstruction after resection of the central bile duct. Alternatively reconstruction can be achieved by cholangio-duodenal interposition of ...BACKGROUND: Bilio-intestinal drainage is routinely per- formed by Roux-en-Y reconstruction after resection of the central bile duct. Alternatively reconstruction can be achieved by cholangio-duodenal interposition of an isolated jejunal segment (CDJI). This method offers the benefit of potential endoscopic control and intervention during fol- low-up. Critics of CDJI assume a higher rate of postopera- tive cholangitis compared to the Roux-en-Y construction. METHODS: Seventy-six patients with malignant tumors (n = 56) or benign strictures and choledochal cysts (n =20) were treated between 1989 and 2002 by cholangio-duodenal interposition of an isolated jejunal segment (measuring 15- 25 cm) after central bile duct resection. In 22 patients endoscopic control was first performed postoperatively dur- ing hospitalization. In 12 patients bilio-intestinal anastomo- sis could be inspected endoscopically. In the remaining patients the anastomosis could not be visualized endoscopi- cally because of kinking of the jejunal segment, but in all patients it could be evaluated by endoscopic retrograde cholangiography (ERC). RESULTS: During follow-up, 25 (33%) patients died from extrahepatic tumor recurrence. Three patients receiving CDJI after severe iatrogenic bile duct injury developed anas- tomotic strictures. Two of these patients were treated by endoscopic pigtail drainage, and one was treated by percu- taneous drainage. Two patients who had received CDJI af- ter choledochal cyst resection developed cholestasis post- operatively because of sludge formation (1 patient) and an intrahepatic concrement (1), which could be solved endo- scopically. One patient after resection of a Klatskin tumor developed an anastomotic stricture which could not be vi- sualized endoscopically, making percutaneous drainage necessary. The rate of postoperative cholangitis after CDJI in our patients was comparable to that after the Roux-en-Y reconstruction.CONCLUSION: Interposition of an isolated jejunal seg- ment for reconstruction after bile duct resection should be performed in patients with a high risk of postoperative ste- nosis. To benefit endoscopic follow-up the jejunal segment should be shorter than 20 cm.展开更多
The mathematic theory for uncertainty model of line segment are summed up to achieve a general conception, and the line error hand model of εσ is a basic uncertainty model that can depict the line accuracy and quali...The mathematic theory for uncertainty model of line segment are summed up to achieve a general conception, and the line error hand model of εσ is a basic uncertainty model that can depict the line accuracy and quality efficiently while the model of εm and error entropy can be regarded as the supplement of it. The error band model will reflect and describe the influence of line uncertainty on polygon uncertainty. Therefore, the statistical characteristic of the line error is studied deeply by analyzing the probability that the line error falls into a certain range. Moreover, the theory accordance is achieved in the selecting the error buffer for line feature and the error indicator. The relationship of the accuracy of area for a polygon with the error loop for a polygon boundary is deduced and computed.展开更多
BACKGROUND Epithelioid trophoblastic tumor(ETT) is the rarest type of gestational trophoblastic tumor(GTT). It has been reported that more than 50% of ETTs arise in the uterine cervix or the lower uterine segment. Her...BACKGROUND Epithelioid trophoblastic tumor(ETT) is the rarest type of gestational trophoblastic tumor(GTT). It has been reported that more than 50% of ETTs arise in the uterine cervix or the lower uterine segment. Here, we report a case of ETT within the lower uterine segment and cervical canal and discuss its manifestations,possible causes, and related influencing factors.CASE SUMMARY A 35-year-old woman(gravida 7, miscarriage 3, induction 2 with 1 being twins,para 2 of cesarean section, live 2), who had amenorrhea for 9 mo after breastfeeding for 22 mo after the last cesarean section, was diagnosed with ETT. The lesion was present in the lower uterine segment and endocervical canal with severe involvement of the anterior wall of the lower uterine segment and the front wall of the lower uterine segment where the cesarean incisions were made.Laboratory tests showed slight elevation of serum beta-human chorionic gonadotropin. Intraoperative exploration showed the presence of a normal-sized uterus body with an enlarged tumor in the lower uterine segment. The surface of the lower uterine segment was light blue, the entire lesion was approximately about 8cm × 8 cm × 9 cm, with compression and displacement of the surrounding tissue.Histological examination diagnosed ETT. Immunohistochemical analysis showed positive expression of p63, with a Ki-67 proliferation index of 40%.CONCLUSION A search of the PubMed database using the search terms "cesarean section" and "epithelioid trophoblastic tumor" retrieved nine articles, including 13 cases of ETT and ETT-related lesions, all 13 cases had a history of cesarean section, and the lesions were all located at the cesarean section incision on the anterior wall of the lower uterine segment. The present case is the 14th reported case of ETT after cesarean section. Therefore, we deduced that cesarean section trauma had an important effect on the occurrence of ETT at this site.展开更多
Purpose: To evaluate the accuracy of sonographic measurements of the lower uterine segment (LUS) thickness at term in predicting uterine scar defects in women with previous Cesarean delivery (CD). Methods: Eighty-nine...Purpose: To evaluate the accuracy of sonographic measurements of the lower uterine segment (LUS) thickness at term in predicting uterine scar defects in women with previous Cesarean delivery (CD). Methods: Eighty-nine pregnant women who underwent CD between 37 and 41 weeks of gestation from 2013 to 2015 were enrolled in this study and divided into two groups. Group A consisted of women with previous CD, and Group B consisted of women with previous vaginal deliveries. We performed an ultrasound evaluation of the myometrial and full thickness of LUS (mLUS and fLUS) transvaginally before a CD and evaluated the appearance of LUS during surgery, which was defined as follows: grade I, well-developed;grade II, thin without visible content;grade III, translucent with visible content;and grade IV, either dehiscence or rupture. Results: The median mLUS and fLUS were 1.50 and 4.07 mm in the group A, and 2.75 and 5.37 mm in the group B. We observed significant differences in the median mLUS and fLUS between grades I/II (2.07 and 4.37 mm) and grades III/IV (0.67 and 2.52 mm). Both mLUS and fLUS were predictive factors for grades III/IV and cutoff values were 0.97 mm of mLUS and 3.13 mm of fLUS, having a sensitivity of 87.5% and 75.0%, and a specificity of 87.7% and 91.4% in mLUS and fLUS measurement, respectively. Conclusion: Sonographic measurements of LUS at term may be a feasible and reliable method to predict uterine rupture or uterine dehiscence in women with prior CD.展开更多
Traumatic rupture of the right diaphragmatic dome with herniation of a segment of the hail into the thorax is a rare lesion. It is often the result of a thoraco-abdominal trauma. It can generally lead to early or late...Traumatic rupture of the right diaphragmatic dome with herniation of a segment of the hail into the thorax is a rare lesion. It is often the result of a thoraco-abdominal trauma. It can generally lead to early or late cardiopulmonary complications due to compression. The objective of this clinical case is to study the physiopathological mechanisms, the diagnostic and therapeutic modalities of this complication. The diagnosis is often difficult in front of a diaphragmatic rupture since there are no specific clinical signs. In our case, the clinical picture on arrival was that of a high occlusion in an immediate postoperative context. The X-ray which makes it possible to visualize the ascended organs but more difficultly the rupture itself could not be carried out. Treatment is essentially surgical. Although the thoracic approach is preferred by several surgeons because of the difficulties of exposing the diaphragm in the presence of the liver, we chose the abdominal approach instead. The postoperative course is made up of parietal suppuration.展开更多
The use of AI technologies in remote sensing(RS)tasks has been the focus of many individuals in both the professional and academic domains.Having more accessible interfaces and tools that allow people of little or no ...The use of AI technologies in remote sensing(RS)tasks has been the focus of many individuals in both the professional and academic domains.Having more accessible interfaces and tools that allow people of little or no experience to intuitively interact with RS data of multiple formats is a potential provided by this integration.However,the use of AI and AI agents to help automate RS-related tasks is still in its infancy stage,with some frameworks and interfaces built on top of well-known vision language models(VLM)such as GPT-4,segment anything model(SAM),and grounding DINO.These tools do promise and draw guidelines on the potentials and limitations of existing solutions concerning the use of said models.In this work,the state of the art AI foundation models(FM)are reviewed and used in a multi-modal manner to ingest RS imagery input and perform zero-shot object detection using natural language.The natural language input is then used to define the classes or labels the model should look for,then,both inputs are fed to the pipeline.The pipeline presented in this work makes up for the shortcomings of the general knowledge FMs by stacking pre-processing and post-processing applications on top of the FMs;these applications include tiling to produce uniform patches of the original image for faster detection,outlier rejection of redundant bounding boxes using statistical and machine learning methods.The pipeline was tested with UAV,aerial and satellite images taken over multiple areas.The accuracy for the semantic segmentation showed improvement from the original 64%to approximately 80%-99%by utilizing the pipeline and techniques proposed in this work.GitHub Repository:MohanadDiab/LangRS.展开更多
Data augmentation plays an important role in training deep neural model by expanding the size and diversity of the dataset.Initially,data augmentation mainly involved some simple transformations of images.Later,in ord...Data augmentation plays an important role in training deep neural model by expanding the size and diversity of the dataset.Initially,data augmentation mainly involved some simple transformations of images.Later,in order to increase the diversity and complexity of data,more advanced methods appeared and evolved to sophisticated generative models.However,these methods required a mass of computation of training or searching.In this paper,a novel training-free method that utilises the Pre-Trained Segment Anything Model(SAM)model as a data augmentation tool(PTSAM-DA)is proposed to generate the augmented annotations for images.Without the need for training,it obtains prompt boxes from the original annotations and then feeds the boxes to the pre-trained SAM to generate diverse and improved annotations.In this way,annotations are augmented more ingenious than simple manipulations without incurring huge computation for training a data augmentation model.Multiple comparative experiments on three datasets are conducted,including an in-house dataset,ADE20K and COCO2017.On this in-house dataset,namely Agricultural Plot Segmentation Dataset,maximum improvements of 3.77%and 8.92%are gained in two mainstream metrics,mIoU and mAcc,respectively.Consequently,large vision models like SAM are proven to be promising not only in image segmentation but also in data augmentation.展开更多
Segmental atrophy(SA)of the liver is a rare,often underrecognized,benign condition that presents as a mass lesion,mimicking a neoplasm,which poses a significant diagnostic challenge.Given its rarity,only a limited num...Segmental atrophy(SA)of the liver is a rare,often underrecognized,benign condition that presents as a mass lesion,mimicking a neoplasm,which poses a significant diagnostic challenge.Given its rarity,only a limited number of case reports and series have been published,resulting in sparse literature on the entity.This review aims to summarize the clinicopathologic and diagnostic features of SA and thus improve its recognition.展开更多
Despite its remarkable performance on natural images,the segment anything model(SAM)lacks domain-specific information in medical imaging.and faces the challenge of losing local multi-scale information in the encoding ...Despite its remarkable performance on natural images,the segment anything model(SAM)lacks domain-specific information in medical imaging.and faces the challenge of losing local multi-scale information in the encoding phase.This paper presents a medical image segmentation model based on SAM with a local multi-scale feature encoder(LMSFE-SAM)to address the issues above.Firstly,based on the SAM,a local multi-scale feature encoder is introduced to improve the representation of features within local receptive field,thereby supplying the Vision Transformer(ViT)branch in SAM with enriched local multi-scale contextual information.At the same time,a multiaxial Hadamard product module(MHPM)is incorporated into the local multi-scale feature encoder in a lightweight manner to reduce the quadratic complexity and noise interference.Subsequently,a cross-branch balancing adapter is designed to balance the local and global information between the local multi-scale feature encoder and the ViT encoder in SAM.Finally,to obtain smaller input image size and to mitigate overlapping in patch embeddings,the size of the input image is reduced from 1024×1024 pixels to 256×256 pixels,and a multidimensional information adaptation component is developed,which includes feature adapters,position adapters,and channel-spatial adapters.This component effectively integrates the information from small-sized medical images into SAM,enhancing its suitability for clinical deployment.The proposed model demonstrates an average enhancement ranging from 0.0387 to 0.3191 across six objective evaluation metrics on BUSI,DDTI,and TN3K datasets compared to eight other representative image segmentation models.This significantly enhances the performance of the SAM on medical images,providing clinicians with a powerful tool in clinical diagnosis.展开更多
The Internet of Vehicles (IoV) has become an important direction in the field of intelligent transportation, in which vehicle positioning is a crucial part. SLAM (Simultaneous Localization and Mapping) technology play...The Internet of Vehicles (IoV) has become an important direction in the field of intelligent transportation, in which vehicle positioning is a crucial part. SLAM (Simultaneous Localization and Mapping) technology plays a crucial role in vehicle localization and navigation. Traditional Simultaneous Localization and Mapping (SLAM) systems are designed for use in static environments, and they can result in poor performance in terms of accuracy and robustness when used in dynamic environments where objects are in constant movement. To address this issue, a new real-time visual SLAM system called MG-SLAM has been developed. Based on ORB-SLAM2, MG-SLAM incorporates a dynamic target detection process that enables the detection of both known and unknown moving objects. In this process, a separate semantic segmentation thread is required to segment dynamic target instances, and the Mask R-CNN algorithm is applied on the Graphics Processing Unit (GPU) to accelerate segmentation. To reduce computational cost, only key frames are segmented to identify known dynamic objects. Additionally, a multi-view geometry method is adopted to detect unknown moving objects. The results demonstrate that MG-SLAM achieves higher precision, with an improvement from 0.2730 m to 0.0135 m in precision. Moreover, the processing time required by MG-SLAM is significantly reduced compared to other dynamic scene SLAM algorithms, which illustrates its efficacy in locating objects in dynamic scenes.展开更多
Brain tumors present significant challenges in medical diagnosis and treatment,where early detection is crucial for reducing morbidity and mortality rates.This research introduces a novel deep learning model,the Progr...Brain tumors present significant challenges in medical diagnosis and treatment,where early detection is crucial for reducing morbidity and mortality rates.This research introduces a novel deep learning model,the Progressive Layered U-Net(PLU-Net),designed to improve brain tumor segmentation accuracy from Magnetic Resonance Imaging(MRI)scans.The PLU-Net extends the standard U-Net architecture by incorporating progressive layering,attention mechanisms,and multi-scale data augmentation.The progressive layering involves a cascaded structure that refines segmentation masks across multiple stages,allowing the model to capture features at different scales and resolutions.Attention gates within the convolutional layers selectively focus on relevant features while suppressing irrelevant ones,enhancing the model's ability to delineate tumor boundaries.Additionally,multi-scale data augmentation techniques increase the diversity of training data and boost the model's generalization capabilities.Evaluated on the BraTS 2021 dataset,the PLU-Net achieved state-of-the-art performance with a dice coefficient of 0.91,specificity of 0.92,sensitivity of 0.89,Hausdorff95 of 2.5,outperforming other modified U-Net architectures in segmentation accuracy.These results underscore the effectiveness of the PLU-Net in improving brain tumor segmentation from MRI scans,supporting clinicians in early diagnosis,treatment planning,and the development of new therapies.展开更多
The Tan-Lu Fault Zone is a large NNE-trending fault zone that has a substantial effect on the development of eastern China and its earthquake disaster prevention efforts. Aiming at the azimuthally anisotropic structur...The Tan-Lu Fault Zone is a large NNE-trending fault zone that has a substantial effect on the development of eastern China and its earthquake disaster prevention efforts. Aiming at the azimuthally anisotropic structure in the upper crust and seismogenic tectonics in the Hefei segment of this fault, we collected phase velocity dispersion data of fundamental mode Rayleigh waves from ambient noise cross-correlation functions of ~400 temporal seismographs in an area of approximately 80 × 70 km along the fault zone. The period band of the dispersion data was ~0.5–10 s. We inverted for the upper crustal three-dimensional(3-D) shear velocity model with azimuthal anisotropy from the surface to 10 km depth by using a 3-D direct azimuthal anisotropy inversion method. The inversion result shows the spatial distribution characteristics of the tectonic units in the upper crust. Additionally, the deformation of the Tan-Lu Fault Zone and its conjugated fault systems could be inferred from the anisotropy model. In particular, the faults that have remained active from the early and middle Pleistocene control the anisotropic characteristics of the upper crustal structure in this area. The direction of fast axes near the fault zone area in the upper crust is consistent with the strike of the faults, whereas for the region far away from the fault zone, the direction of fast axes is consistent with the direction of the regional principal stress caused by plate movement. Combined with the azimuthal anisotropy models in the deep crust and uppermost mantle from the surface wave and Pn wave, the different anisotropic patterns caused by the Tan-Lu Fault Zone and its conjugated fault system nearby are shown in the upper and lower crust. Furthermore,by using the double-difference method, we relocated the Lujiang earthquake series, which contained 32 earthquakes with a depth shallower than 10 km. Both the Vs model and earthquake relocation results indicate that earthquakes mostly occurred in the vicinity of structural boundaries with fractured media, with high-level development of cracks and small-scale faults jammed between more rigid areas.展开更多
基金provided by Science and Technology Development Project of Jilin Province(No.20230101338JC)。
文摘The printed circuit heat exchanger(PCHE) is receiving wide attention as a new kind of compact heat exchanger and is considered as a promising vaporizer in the LNG process. In this paper, a PCHE straight channel in the length of 500 mm is established, with a semicircular cross section in a diameter of 1.2 mm.Numerical simulation is employed to investigate the flow and heat transfer performance of supercritical methane in the channel. The pseudo-boiling theory is adopted and the liquid-like, two-phase-like, and vapor-like regimes are divided for supercritical methane to analyze the heat transfer and flow features.The results are presented in micro segment to show the local convective heat transfer coefficient and pressure drop. It shows that the convective heat transfer coefficient in segments along the channel has a significant peak feature near the pseudo-critical point and a heat transfer deterioration when the average fluid temperature in the segment is higher than the pseudo-critical point. The reason is explained with the generation of vapor-like film near the channel wall that the peak feature related to a nucleateboiling-like state and heat transfer deterioration related to a film-boiling-like state. The effects of parameters, including mass flow rate, pressure, and wall heat flux on flow and heat transfer were analyzed.In calculating of the averaged heat transfer coefficient of the whole channel, the traditional method shows significant deviation and the micro segment weighted average method is adopted. The pressure drop can mainly be affected by the mass flux and pressure and little affected by the wall heat flux. The peak of the convective heat transfer coefficient can only form at high mass flux, low wall heat flux, and near critical pressure, in which condition the nucleate-boiling-like state is easier to appear. Moreover,heat transfer deterioration will always appear, since the supercritical flow will finally develop into a filmboiling-like state. So heat transfer deterioration should be taken seriously in the design and safe operation of vaporizer PCHE. The study of this work clarified the local heat transfer and flow feature of supercritical methane in microchannel and contributed to the deep understanding of supercritical methane flow of the vaporization process in PCHE.
基金supported by the National Natural Science Foundation of China(51805078)Project of National Key Laboratory of Advanced Casting Technologies(CAT2023-002)the 111 Project(B16009).
文摘Segment Anything Model(SAM)is a cutting-edge model that has shown impressive performance in general object segmentation.The birth of the segment anything is a groundbreaking step towards creating a universal intelligent model.Due to its superior performance in general object segmentation,it quickly gained attention and interest.This makes SAM particularly attractive in industrial surface defect segmentation,especially for complex industrial scenes with limited training data.However,its segmentation ability for specific industrial scenes remains unknown.Therefore,in this work,we select three representative and complex industrial surface defect detection scenarios,namely strip steel surface defects,tile surface defects,and rail surface defects,to evaluate the segmentation performance of SAM.Our results show that although SAM has great potential in general object segmentation,it cannot achieve satisfactory performance in complex industrial scenes.Our test results are available at:https://github.com/VDT-2048/SAM-IS.
基金supported by grants from the National Natural Science Foundation of China,grant no. 81370041, 81771233, 81671655the Outstanding Clinical Discipline Project of Shanghai Pudonggrant no.PWYgy2018-04.
文摘Background:To evaluate the efficacy of stent-assisted coiling(SAC)for the treatment of carotid ophthalmic segment aneurysm segment aneurysms(OSAs)of the internal carotid artery(ICA)through detailed long-term follow-up of a large patient cohort.Methods:We retrospectively analyzed 88 consecutive patients with OSAs between January 2009 and January 2020 at our center.Angiographic results were evaluated using the modified Raymond grading system and clinical outcomes were evaluated using the mRS scale.The primary endpoints were major aneurysm recurrence and poor clinical outcomes for at least 18 months of follow-up.The patients were asked to attend clinical follow-up assessments and possibly undergo DSA or MR via telephone.Results:We enrolled 88 patients with 99 OSAs treated with coiling,of whom 76 were treated with SAC.The coiling procedures were successful in all 88 patients.Overall,complications occurred in 8 patients(9.1%).No procedure-related mortality was observed.67(76.1%)experienced immediate aneurysm occlusion at the end of the procedure.Long-term angiographic follow-up(18 months)was available in 45/88 aneurysms(51%)(average 18.7±5.2 months).Four patients continued their follow-up for 5 years after initial aneurysm treatment.After a clinical follow-up time of 28.7 months(range,12-51 months),85 patients(95.5%)achieved favorable clinical outcomes(mRS scores of 0-2).Conclusions:This study indicates that SAC treatment is a safe and effective therapeutic alternative for ruptured and unruptured OSAs.The procedural risks are low with relatively long-term effectiveness.
基金Supported by Jiangsu Provincial Medical Innovation Team(No.CXTDA2017039)the Soochow Scholar Project of Soochow University(No.R5122001)。
文摘AIM:To predict postoperative intraocular lens(IOL)position using the Sirius anterior segment analysis system and investigate the effect of lens position and IOL type on postoperative refraction.METHODS:A total of 97 patients(102 eyes)were enrolled in the final analysis.An anterior segment biometry measurement was performed preoperatively with Sirius and Lenstar.The results of predicted lens position(PLP)and IOL power were automatically calculated by the software used by the instruments.Effective lens position(ELP)was measured manually using Sirius 3 mo postoperatively.Pearson's correlation analysis and linear regression analysis were used to determine the correlation of lens position to other parameters.RESULTS:PLP and ELP were positively correlated to axial length(AL;r=0.42,P<0.0001 and r=0.49,P<0.0001,respectively).There was a weak correlation between the peLP(ELP-PLP)and the prediction error of spherical refraction(peSR;r=0.34,P<0.0001).The peLP of Softec HD IOL differed statistically from those of both the TECNIS ZCB00 and Sensor AR40E IOLs.Multiple linear regression was used to obtain the prediction formula:ELP=0.66+0.63×[aqueous depth(AQD)+0.6 LT](r=0.61,P<0.0001),and a new variable(AQD+0.6 LT)was found to have the strongest correlation with ELP.CONCLUSION:The Sirius anterior segment analysis system is helpful to predict ELP,which reduces postoperative refraction error.
基金supported by National Institutes of Health Grants NS069688 and NS044916, TIRR Foundationthe Dr. Miriam and Sheldon G. Adelson Medical Research Foundation
文摘Myelinated axons of the peripheral and central nervous system（PNS＆CNS）are divided into molecularly distinct excitable domains,including the axon initial segment（AIS）and nodes of Ranvier.The AIS is composed of a dense network of cytoskeletal proteins,cell adhesion molecules,and voltage gated ion channels and is located at the proximal most region of the axon（Koleand Stuart, 2012）.
基金supported by the National Nature Science Foundation of China[grant number 81800403].
文摘Objectives:Distal segment aortic enlargement(DSAE)is a common complication that influences the long-term prognosis of type B aortic dissection(TBAD)after thoracic endovascular aortic repair(TEVAR).In this study,a multivariate analysis was performed to find potential factors predictive of DSAE.Methods:A single-center retrospective study was performed from 1999 to 2016.Included in the study were complicated TBAD patients who underwent TEVAR with uncovered residual tears.Based on the diameter of the distal segment of the uncovered aorta,we assigned patients to an enlargement group and a non-enlargement group.Data extracted from the medical records included demographic and clinical characteristics and followup computed tomography angiography data.The primary endpoints were the all-cause mortality and the presumably aortic-related events that required reintervention during the follow-up period.Results:For the 333 patients,all-cause mortality was 38(11.41%),and 76(22.82%)patients underwent reintervention.A total of 70(21.02%)patients experienced DSAE,among them were 2 patients who died of aortic rupture and 58 patients who accepted reintervention.Multivariate analysis reviewed independent risk factors of postoperative DSAE,including current smoking,the residual length of the patent false lumen,the postoperative number of dissection tears in the thoracic aorta and type III aortic arch;as well as protective factors,including the application of a restrictive bare stent(RBS),the length of covered stent in the descending thoracic aorta,and the distance from the residual first tear to the left subclavian artery(LSA).Conclusion:DSAE after TEVAR for patients with a complicated TBAD can be influenced by their current smoking habit,the residual length of patent false lumen,the postoperative number of dissection tears in the thoracic aorta and the aortic arch type.Meanwhile,RBS usage,the length of the covered stent in the descending thoracic aorta and the distance from the residual first tear to the LSA could have positive effect on the prognosis.
文摘AIM：To quantitatively assess narrow anterior chamber angle using spectral-domain anterior segment optical coherence tomography（SD-AS-OCT） and ultrasound biomicroscopy（UBM）,and to evaluate the correlations and consistency between SD-AS-OCT and UBM.· METHODS：Fifty-five eyes from 40 patients were examined.Patients were diagnosed with primary angleclosure glaucoma（PACG） remission（11 eyes from 8patients）,primary angle closure（PAC,20 eyes from 20patients） and PAC suspect（24 eyes from 12 patients）.Each eye was examined by SD-AS-OCT and UBM after laser peripheral iridotomy（LPI）.The measurements of SD-AS-OCT were angle open distance（AOD）,anterior chamber angle（ACA）,trabecular iris angle（TIA）,and trabecular iris space area（TISA）.UBM measurements were AOD and TIA.Correlations of AOD500 and TIA500 between UBM and AS-OCT were assessed.All parameters were analysed by SPSS 16.0 and MedCalc.· RESULTS：ACA,TIA and AOD measured by SD-ASOCT reached a maximum at the temporal quadrant and minimum at the nasal quadrant.Group parameters of AOD500 and AOD750 showed a linear positive correlation,and AOD750 had less variability.UBM outcomes of AOD500 and TIA500 were significantly smaller than those of SD-AS-OCT.The results of the two techniques were correlated at the superior,nasal and inferior quadrants.CONCLUSION：Both UBM and SD-AS-OCT are efficient tools for follow-up during the course of PACG.We recommended using parameters at 750 μm anterior to the sclera spur for the screening and follow-up of PACG and PAC.The two methods might be alternatives to each other.
文摘AIM:To evaluate the clinical results after implantation of a new intrastromal corneal ring segment(ICRS)associated with photorefractive keratectomy(PRK)to correct high myopia(HM)patients with thin corneas.METHODS:We evaluated 42 eyes of 23 HM patients that had ICRS implantation followed by PRK.The mean age of patients was 29.1±7.12 y(range 18 to 40 years old).Uncorrected visual acuity(UCVA),best corrected visual acuity(BCVA),keratometry,spherical equivalent,pachymetry,and aberrometry were compared using ANOVA with repeated measurements evaluated preoperatively and at last follow-up visit after the procedures.The refractive predictability and simulated/real corneal ablation were also assessed.RESULTS:The mean follow-up time after PRK was 6.8±1.6 mo.The mean preoperative UCVA improved from 20/800 preoperative to 20/100 after ICRS and 20/35 after PRK.The mean preoperative BCVA was 20/25(range from 20/30 to 20/20)and remained unchanged after ICRS implantation.Following the PRK the mean BCVA was 20/25(range from 20/30 to 20/20).The mean spherical equivalent decreased from-7.25±1.12(range-5.00 to-9.00)preoperatively to-3.32±1.0(range-2.00 to-5.00)postoperatively(P<0.001)after ICRS implantation and decreased from-2.44±1.51 preoperatively to 0.32±0.45(range-0.625 to 0.875)postoperatively(P<0.001)after PRK.The change in BCVA and topographic astigmatism was statistically significant(P<0.0001).CONCLUSION:ICRS in HM associated with PRK can be a tissue saving procedure and an alternative surgical option for correction of moderate to high myopia.
文摘BACKGROUND: Bilio-intestinal drainage is routinely per- formed by Roux-en-Y reconstruction after resection of the central bile duct. Alternatively reconstruction can be achieved by cholangio-duodenal interposition of an isolated jejunal segment (CDJI). This method offers the benefit of potential endoscopic control and intervention during fol- low-up. Critics of CDJI assume a higher rate of postopera- tive cholangitis compared to the Roux-en-Y construction. METHODS: Seventy-six patients with malignant tumors (n = 56) or benign strictures and choledochal cysts (n =20) were treated between 1989 and 2002 by cholangio-duodenal interposition of an isolated jejunal segment (measuring 15- 25 cm) after central bile duct resection. In 22 patients endoscopic control was first performed postoperatively dur- ing hospitalization. In 12 patients bilio-intestinal anastomo- sis could be inspected endoscopically. In the remaining patients the anastomosis could not be visualized endoscopi- cally because of kinking of the jejunal segment, but in all patients it could be evaluated by endoscopic retrograde cholangiography (ERC). RESULTS: During follow-up, 25 (33%) patients died from extrahepatic tumor recurrence. Three patients receiving CDJI after severe iatrogenic bile duct injury developed anas- tomotic strictures. Two of these patients were treated by endoscopic pigtail drainage, and one was treated by percu- taneous drainage. Two patients who had received CDJI af- ter choledochal cyst resection developed cholestasis post- operatively because of sludge formation (1 patient) and an intrahepatic concrement (1), which could be solved endo- scopically. One patient after resection of a Klatskin tumor developed an anastomotic stricture which could not be vi- sualized endoscopically, making percutaneous drainage necessary. The rate of postoperative cholangitis after CDJI in our patients was comparable to that after the Roux-en-Y reconstruction.CONCLUSION: Interposition of an isolated jejunal seg- ment for reconstruction after bile duct resection should be performed in patients with a high risk of postoperative ste- nosis. To benefit endoscopic follow-up the jejunal segment should be shorter than 20 cm.
基金Project supported by the National Natural Science Foundation of China (No.40301043) .
文摘The mathematic theory for uncertainty model of line segment are summed up to achieve a general conception, and the line error hand model of εσ is a basic uncertainty model that can depict the line accuracy and quality efficiently while the model of εm and error entropy can be regarded as the supplement of it. The error band model will reflect and describe the influence of line uncertainty on polygon uncertainty. Therefore, the statistical characteristic of the line error is studied deeply by analyzing the probability that the line error falls into a certain range. Moreover, the theory accordance is achieved in the selecting the error buffer for line feature and the error indicator. The relationship of the accuracy of area for a polygon with the error loop for a polygon boundary is deduced and computed.
文摘BACKGROUND Epithelioid trophoblastic tumor(ETT) is the rarest type of gestational trophoblastic tumor(GTT). It has been reported that more than 50% of ETTs arise in the uterine cervix or the lower uterine segment. Here, we report a case of ETT within the lower uterine segment and cervical canal and discuss its manifestations,possible causes, and related influencing factors.CASE SUMMARY A 35-year-old woman(gravida 7, miscarriage 3, induction 2 with 1 being twins,para 2 of cesarean section, live 2), who had amenorrhea for 9 mo after breastfeeding for 22 mo after the last cesarean section, was diagnosed with ETT. The lesion was present in the lower uterine segment and endocervical canal with severe involvement of the anterior wall of the lower uterine segment and the front wall of the lower uterine segment where the cesarean incisions were made.Laboratory tests showed slight elevation of serum beta-human chorionic gonadotropin. Intraoperative exploration showed the presence of a normal-sized uterus body with an enlarged tumor in the lower uterine segment. The surface of the lower uterine segment was light blue, the entire lesion was approximately about 8cm × 8 cm × 9 cm, with compression and displacement of the surrounding tissue.Histological examination diagnosed ETT. Immunohistochemical analysis showed positive expression of p63, with a Ki-67 proliferation index of 40%.CONCLUSION A search of the PubMed database using the search terms "cesarean section" and "epithelioid trophoblastic tumor" retrieved nine articles, including 13 cases of ETT and ETT-related lesions, all 13 cases had a history of cesarean section, and the lesions were all located at the cesarean section incision on the anterior wall of the lower uterine segment. The present case is the 14th reported case of ETT after cesarean section. Therefore, we deduced that cesarean section trauma had an important effect on the occurrence of ETT at this site.
文摘Purpose: To evaluate the accuracy of sonographic measurements of the lower uterine segment (LUS) thickness at term in predicting uterine scar defects in women with previous Cesarean delivery (CD). Methods: Eighty-nine pregnant women who underwent CD between 37 and 41 weeks of gestation from 2013 to 2015 were enrolled in this study and divided into two groups. Group A consisted of women with previous CD, and Group B consisted of women with previous vaginal deliveries. We performed an ultrasound evaluation of the myometrial and full thickness of LUS (mLUS and fLUS) transvaginally before a CD and evaluated the appearance of LUS during surgery, which was defined as follows: grade I, well-developed;grade II, thin without visible content;grade III, translucent with visible content;and grade IV, either dehiscence or rupture. Results: The median mLUS and fLUS were 1.50 and 4.07 mm in the group A, and 2.75 and 5.37 mm in the group B. We observed significant differences in the median mLUS and fLUS between grades I/II (2.07 and 4.37 mm) and grades III/IV (0.67 and 2.52 mm). Both mLUS and fLUS were predictive factors for grades III/IV and cutoff values were 0.97 mm of mLUS and 3.13 mm of fLUS, having a sensitivity of 87.5% and 75.0%, and a specificity of 87.7% and 91.4% in mLUS and fLUS measurement, respectively. Conclusion: Sonographic measurements of LUS at term may be a feasible and reliable method to predict uterine rupture or uterine dehiscence in women with prior CD.
文摘Traumatic rupture of the right diaphragmatic dome with herniation of a segment of the hail into the thorax is a rare lesion. It is often the result of a thoraco-abdominal trauma. It can generally lead to early or late cardiopulmonary complications due to compression. The objective of this clinical case is to study the physiopathological mechanisms, the diagnostic and therapeutic modalities of this complication. The diagnosis is often difficult in front of a diaphragmatic rupture since there are no specific clinical signs. In our case, the clinical picture on arrival was that of a high occlusion in an immediate postoperative context. The X-ray which makes it possible to visualize the ascended organs but more difficultly the rupture itself could not be carried out. Treatment is essentially surgical. Although the thoracic approach is preferred by several surgeons because of the difficulties of exposing the diaphragm in the presence of the liver, we chose the abdominal approach instead. The postoperative course is made up of parietal suppuration.
文摘The use of AI technologies in remote sensing(RS)tasks has been the focus of many individuals in both the professional and academic domains.Having more accessible interfaces and tools that allow people of little or no experience to intuitively interact with RS data of multiple formats is a potential provided by this integration.However,the use of AI and AI agents to help automate RS-related tasks is still in its infancy stage,with some frameworks and interfaces built on top of well-known vision language models(VLM)such as GPT-4,segment anything model(SAM),and grounding DINO.These tools do promise and draw guidelines on the potentials and limitations of existing solutions concerning the use of said models.In this work,the state of the art AI foundation models(FM)are reviewed and used in a multi-modal manner to ingest RS imagery input and perform zero-shot object detection using natural language.The natural language input is then used to define the classes or labels the model should look for,then,both inputs are fed to the pipeline.The pipeline presented in this work makes up for the shortcomings of the general knowledge FMs by stacking pre-processing and post-processing applications on top of the FMs;these applications include tiling to produce uniform patches of the original image for faster detection,outlier rejection of redundant bounding boxes using statistical and machine learning methods.The pipeline was tested with UAV,aerial and satellite images taken over multiple areas.The accuracy for the semantic segmentation showed improvement from the original 64%to approximately 80%-99%by utilizing the pipeline and techniques proposed in this work.GitHub Repository:MohanadDiab/LangRS.
基金Natural Science Foundation of Zhejiang Province,Grant/Award Number:LY23F020025Science and Technology Commissioner Program of Huzhou,Grant/Award Number:2023GZ42Sichuan Provincial Science and Technology Support Program,Grant/Award Numbers:2023ZHCG0005,2023ZHCG0008。
文摘Data augmentation plays an important role in training deep neural model by expanding the size and diversity of the dataset.Initially,data augmentation mainly involved some simple transformations of images.Later,in order to increase the diversity and complexity of data,more advanced methods appeared and evolved to sophisticated generative models.However,these methods required a mass of computation of training or searching.In this paper,a novel training-free method that utilises the Pre-Trained Segment Anything Model(SAM)model as a data augmentation tool(PTSAM-DA)is proposed to generate the augmented annotations for images.Without the need for training,it obtains prompt boxes from the original annotations and then feeds the boxes to the pre-trained SAM to generate diverse and improved annotations.In this way,annotations are augmented more ingenious than simple manipulations without incurring huge computation for training a data augmentation model.Multiple comparative experiments on three datasets are conducted,including an in-house dataset,ADE20K and COCO2017.On this in-house dataset,namely Agricultural Plot Segmentation Dataset,maximum improvements of 3.77%and 8.92%are gained in two mainstream metrics,mIoU and mAcc,respectively.Consequently,large vision models like SAM are proven to be promising not only in image segmentation but also in data augmentation.
文摘Segmental atrophy(SA)of the liver is a rare,often underrecognized,benign condition that presents as a mass lesion,mimicking a neoplasm,which poses a significant diagnostic challenge.Given its rarity,only a limited number of case reports and series have been published,resulting in sparse literature on the entity.This review aims to summarize the clinicopathologic and diagnostic features of SA and thus improve its recognition.
基金supported by Natural Science Foundation Programme of Gansu Province(No.24JRRA231)National Natural Science Foundation of China(No.62061023)Gansu Provincial Science and Technology Plan Key Research and Development Program Project(No.24YFFA024).
文摘Despite its remarkable performance on natural images,the segment anything model(SAM)lacks domain-specific information in medical imaging.and faces the challenge of losing local multi-scale information in the encoding phase.This paper presents a medical image segmentation model based on SAM with a local multi-scale feature encoder(LMSFE-SAM)to address the issues above.Firstly,based on the SAM,a local multi-scale feature encoder is introduced to improve the representation of features within local receptive field,thereby supplying the Vision Transformer(ViT)branch in SAM with enriched local multi-scale contextual information.At the same time,a multiaxial Hadamard product module(MHPM)is incorporated into the local multi-scale feature encoder in a lightweight manner to reduce the quadratic complexity and noise interference.Subsequently,a cross-branch balancing adapter is designed to balance the local and global information between the local multi-scale feature encoder and the ViT encoder in SAM.Finally,to obtain smaller input image size and to mitigate overlapping in patch embeddings,the size of the input image is reduced from 1024×1024 pixels to 256×256 pixels,and a multidimensional information adaptation component is developed,which includes feature adapters,position adapters,and channel-spatial adapters.This component effectively integrates the information from small-sized medical images into SAM,enhancing its suitability for clinical deployment.The proposed model demonstrates an average enhancement ranging from 0.0387 to 0.3191 across six objective evaluation metrics on BUSI,DDTI,and TN3K datasets compared to eight other representative image segmentation models.This significantly enhances the performance of the SAM on medical images,providing clinicians with a powerful tool in clinical diagnosis.
基金funded by the Natural Science Foundation of the Jiangsu Higher Education Institutions of China(grant number 22KJD440001)Changzhou Science&Technology Program(grant number CJ20220232).
文摘The Internet of Vehicles (IoV) has become an important direction in the field of intelligent transportation, in which vehicle positioning is a crucial part. SLAM (Simultaneous Localization and Mapping) technology plays a crucial role in vehicle localization and navigation. Traditional Simultaneous Localization and Mapping (SLAM) systems are designed for use in static environments, and they can result in poor performance in terms of accuracy and robustness when used in dynamic environments where objects are in constant movement. To address this issue, a new real-time visual SLAM system called MG-SLAM has been developed. Based on ORB-SLAM2, MG-SLAM incorporates a dynamic target detection process that enables the detection of both known and unknown moving objects. In this process, a separate semantic segmentation thread is required to segment dynamic target instances, and the Mask R-CNN algorithm is applied on the Graphics Processing Unit (GPU) to accelerate segmentation. To reduce computational cost, only key frames are segmented to identify known dynamic objects. Additionally, a multi-view geometry method is adopted to detect unknown moving objects. The results demonstrate that MG-SLAM achieves higher precision, with an improvement from 0.2730 m to 0.0135 m in precision. Moreover, the processing time required by MG-SLAM is significantly reduced compared to other dynamic scene SLAM algorithms, which illustrates its efficacy in locating objects in dynamic scenes.
文摘Brain tumors present significant challenges in medical diagnosis and treatment,where early detection is crucial for reducing morbidity and mortality rates.This research introduces a novel deep learning model,the Progressive Layered U-Net(PLU-Net),designed to improve brain tumor segmentation accuracy from Magnetic Resonance Imaging(MRI)scans.The PLU-Net extends the standard U-Net architecture by incorporating progressive layering,attention mechanisms,and multi-scale data augmentation.The progressive layering involves a cascaded structure that refines segmentation masks across multiple stages,allowing the model to capture features at different scales and resolutions.Attention gates within the convolutional layers selectively focus on relevant features while suppressing irrelevant ones,enhancing the model's ability to delineate tumor boundaries.Additionally,multi-scale data augmentation techniques increase the diversity of training data and boost the model's generalization capabilities.Evaluated on the BraTS 2021 dataset,the PLU-Net achieved state-of-the-art performance with a dice coefficient of 0.91,specificity of 0.92,sensitivity of 0.89,Hausdorff95 of 2.5,outperforming other modified U-Net architectures in segmentation accuracy.These results underscore the effectiveness of the PLU-Net in improving brain tumor segmentation from MRI scans,supporting clinicians in early diagnosis,treatment planning,and the development of new therapies.
基金financially supported by the National Key Research and Development Program of China (2022YFC3005600)the Foundation of the Anhui Educational Commission (2023AH051198)+1 种基金the National Natural Science Foundation of China (42125401 and 42104063)the Joint Open Fund of Mengcheng National Geophysical Observatory (MENGO-202201)。
文摘The Tan-Lu Fault Zone is a large NNE-trending fault zone that has a substantial effect on the development of eastern China and its earthquake disaster prevention efforts. Aiming at the azimuthally anisotropic structure in the upper crust and seismogenic tectonics in the Hefei segment of this fault, we collected phase velocity dispersion data of fundamental mode Rayleigh waves from ambient noise cross-correlation functions of ~400 temporal seismographs in an area of approximately 80 × 70 km along the fault zone. The period band of the dispersion data was ~0.5–10 s. We inverted for the upper crustal three-dimensional(3-D) shear velocity model with azimuthal anisotropy from the surface to 10 km depth by using a 3-D direct azimuthal anisotropy inversion method. The inversion result shows the spatial distribution characteristics of the tectonic units in the upper crust. Additionally, the deformation of the Tan-Lu Fault Zone and its conjugated fault systems could be inferred from the anisotropy model. In particular, the faults that have remained active from the early and middle Pleistocene control the anisotropic characteristics of the upper crustal structure in this area. The direction of fast axes near the fault zone area in the upper crust is consistent with the strike of the faults, whereas for the region far away from the fault zone, the direction of fast axes is consistent with the direction of the regional principal stress caused by plate movement. Combined with the azimuthal anisotropy models in the deep crust and uppermost mantle from the surface wave and Pn wave, the different anisotropic patterns caused by the Tan-Lu Fault Zone and its conjugated fault system nearby are shown in the upper and lower crust. Furthermore,by using the double-difference method, we relocated the Lujiang earthquake series, which contained 32 earthquakes with a depth shallower than 10 km. Both the Vs model and earthquake relocation results indicate that earthquakes mostly occurred in the vicinity of structural boundaries with fractured media, with high-level development of cracks and small-scale faults jammed between more rigid areas.
