Research on Bearing Surface Scratch Detection Based on Improved YOLOV5.

Bearings are crucial components of machinery and equipment, and it is essential to inspect them thoroughly to ensure a high pass rate. Currently, bearing scratch detection is primarily carried out manually, which cannot meet industrial demands. This study presents research on the detection of bearing surface scratches. An improved YOLOV5 network, named YOLOV5-CDG, is proposed for detecting bearing surface defects using scratch images as targets. The YOLOV5-CDG model is based on the YOLOV5 network model with the addition of a Coordinate Attention (CA) mechanism module, fusion of Deformable Convolutional Networks (DCNs), and a combination with the GhostNet lightweight network. To achieve bearing surface scratch detection, a machine vision-based bearing surface scratch sensor system is established, and a self-made bearing surface scratch dataset is produced as the basis. The scratch detection final Average Precision (AP) value is 97%, which is 3.4% higher than that of YOLOV5. Additionally, the model has an accuracy of 99.46% for detecting defective and qualified products. The average detection time per image is 263.4 ms on the CPU device and 12.2 ms on the GPU device, demonstrating excellent performance in terms of both speed and accuracy. Furthermore, this study analyzes and compares the detection results of various models, demonstrating that the proposed method satisfies the requirements for detecting scratches on bearing surfaces in industrial settings.

Microfluidics-aided fabrication of 3D micro-nano hierarchical SERS substrate for rapid detection of dual hepatocellular carcinoma biomarkers.

The simultaneous analysis of trace amounts of dual biomarkers is crucial in the early diagnosis, treatment, and prognosis of hepatocellular carcinoma (HCC). In this study, we prepared SERS-active hydrogel microparticles (SAHMs) with 3D hierarchical gold nanoparticles (AuNPs) micro-nanostructures by microdroplet technology and in situ synthesis, which demonstrated high reproducibility and sensitivity. Compared with traditional 2D SERS substrates, this newly prepared 3D SERS substrate provided a high density of nano-wrinkled structures and numerous AuNPs. Furthermore, a newly designed SERS-active substrate was proposed for the simultaneous microfluidic detection of AFP and AFU. The Raman signals of sandwich immunocomplexes on the surface of the SAHMs were measured for the trace analysis of these biomarkers. The proposed microfluidic platform achieved AFP and AFU detection in the range of 0.1-100 ng mL-1 and 0.01-100 ng mL-1, respectively, which represents a good response. Indeed, this platform is easy to fabricate, of low cost and has short detection time and comparable detection limits to other methods. As far as we know, this is the first study to achieve the simultaneous detection of AFP and AFU on a microfluidic platform. Therefore, we proposed a new simultaneous detection platform for dual HCC biomarkers that shows strong potential for the early diagnosis of HCC.

A micro-nano interface integrated SERS-based microfluidic sensor for miRNA detection using DNAzyme walker amplification.

BACKGROUND: Precise and specific miRNA detection plays a vital role in exploring development mechanisms of cancer disease, thereby it can significantly improve relevant prevention and treatment strategies. RESULTS: In this work, a surface-enhanced Raman spectroscopy (SERS)-based microfluidic chip has been devised with a microcone array SERS substrate (MCASS) for the miR-141 detection. This substrate excels in unique SERS activity and large surface area for DNA oligonucleotide modification. As the presence of miR-141, the DNAzyme walker induced cleavage reaction took place on the finely designed and prepared dual DNA conjugated SERS nanoprobes. The SERS nanoprobes can anchor on MCASS by the DNA hybridization that achieved an impressive detection limit in the femtomolar level. SIGNIFICANCE: With this integrated SERS-based microfluidic chip, we provided a miRNA detection strategy using DNAzyme walker amplification technology. It is believed that this strategy could be a powerful tool for miRNA detection and related cancer screening test.

Single-shot 3D shape measurement based on RGB dot patterns and stereovision: retraction.

The referenced article [Opt. Express30, 28220 (2022)10.1364/OE.466148] has been retracted by the authors.

Rapid simultaneous SERS detection of dual myocardial biomarkers on single-track finger-pump microfluidic chip.

Acute myocardial infarction (AMI) is a serious disease with high mortality that afflicts many people around the world. The main cause of death from AMI was the inaccurate early diagnosis, which resulted from the medical treatment might be a delay. Therefore, it is crucial to achieve the rapid detection of AMI. The cardiac troponin I (cTnI) level in human serum may significantly increase as the myocardial membrane ruptured, and the creatine kinase-MB (CK-MB) was also associated with the AMI recurrence and the infarct size of myocardial infarction. Both of them are regarded as important cardiac biomarkers for the early diagnosis of AMI. Therefore, we chose these two cardiac biomarkers as indicators for simultaneous detection. We proposed a single-track finger-pump microfluidic chip for simultaneous surface-enhanced Raman scattering (SERS) detection of cTnI and CK-MB. The entire detection process takes only 5 min without the cumbersome syringe pump. Meanwhile, it enables multiple reagent additions and removals of the unbonded reactants. This microfluidic sensor employed "sandwich" immunoassays based on SERS nanoprobes, AMI biomarkers, and magnetic beads. It is possible to detect two cardiac biomarkers simultaneously in a single measurement, greatly simplifying the detection process and reducing the detection time. Magnetic beads with SERS nanoprobes were separated and captured in the microchamber by a round magnet integrated into the chip. Our results showed that the detection limits of cTnI and CK-MB could reach to 0.01 ng mL-1, respectively. The limit of detections (LODs) match with the clinical threshold values for AMI biomarkers. It is believed that the proposed single-track finger-pump microfluidic chip can be used as an effective tool for determining early AMI.

SERS-Based Immunoassay of Myocardial Infarction Biomarkers on a Microfluidic Chip with Plasmonic Nanostripe Microcones.

We developed a new plasmonic nanostripe microcone array (PNMA) substrate-integrated microfluidic chip for the simultaneous surface-enhanced Raman scattering (SERS)-based immunoassay of the creatine kinase MB isoenzyme (CK-MB) and cardiac troponin (cTnI) cardiac markers. The conventional immunoassay usually employs a microtiter plate as the solid capture plate to form the immunocomplexes. However, the two-dimensional (2D) surface of the microtiter plate limits the capture efficiency of the target antigens due to the steric hindrance effect. To address this issue, a gold film-coated microcone array with nanostripes was developed that can provide a large surface area for capture antibody conjugation and serve as a SERS-active substrate. This unique nano-microhierarchical structure showed an excellent light trapping effect and induced surface plasmon resonance to further enhance the Raman signals of the SERS nanoprobes. It significantly improved the sensitivity and applicability of SERS-based immunoassay on the microfluidic chip. With this integrated microfluidic chip, we successfully performed the simultaneous detection of CK-MB and cTnI, and the detection limit can reach 0.01 ng mL-1. It is believed that the PNMA substrate-integrated microfluidic chip would play a critical role in the rapid and sensitive diagnostics of cardiac diseases.

Single-shot 3D shape measurement based on RGB dot patterns and stereovision.

One-shot projection structured light 3D measurement is a method to establish the stereo matching relationship and reconstruct 3D shape by projecting one pattern. However, the traditional stereo matching algorithm does not solve the problem of low matching accuracy and matching efficiency, which fundamentally limits the accuracy of 3D measurement. As the projector and imaging systems have daily higher resolution and imaging quality, RGB dots projection has more application prospects because of its ability to establish a stereo matching relationship through one projection. In this work, we proposed a single-shot 3D measurement method using line clustering stereo matching, and model correction methods. The projected RGB dots are extracted by slope differenced distribution and area constrained erosion method. Area constrained erosion can solve the problem of the segmented connected blobs caused by insufficient projection resolution. The clustering stereo matching method is utilized to coarse match the segmented center red points. A model correction method is utilized to restore and constrain the pattern that cannot be imaged. Experimental results demonstrated that our method achieves the best accuracy of about 0.089mm, better than the traditional disparity and RGB line method, which may shed light on the proposed method can accurately reconstruct the 3D surface.

Simultaneous single-cell phenotype analysis of hepatocellular carcinoma CTCs using a SERS-aptamer based microfluidic chip.

Hepatocellular carcinoma (HCC) is a harmful malady that truly debilitates human health, and hence it is of significance to isolate and on-line profile the phenotype of HCC cells for further diagnosis and therapy. We developed a novel strategy for efficient capture and in situ heterogeneous phenotype analysis of circulating tumor cells (CTCs) at the single-cell level based on surface-enhanced Raman scattering (SERS) fingerprint characteristics. Herein, a new microfluidic chip with lantern-like bypass structure was designed to capture CTCs by their large size from whole blood. Furthermore, two types of SERS-aptamer nanotags were fabricated, realizing spectral recognition of single CTCs in accordance with the surface membrane protein expression. Up to 84% of CTCs with a purity of 95% were captured from whole blood samples using the present SERS-aptamer based microfluidic chip at 20 µL min-1. The results showed that the proposed strategy can successfully identify HCC cell subtypes by SERS measurements, which was related to the clinical surface biomarkers. This may open a new avenue for serving as a powerful tool of cancer diagnosis and prognosis evaluation.

Celiac Disease Detection From Videocapsule Endoscopy Images Using Strip Principal Component Analysis.

The purpose of this study was to implement principal component analysis (PCA) on videocapsule endoscopy (VE) images to develop a new computerized tool for celiac disease recognition. Three PCA algorithms were implemented for feature extraction and sparse representation. A novel strip PCA (SPCA) with nongreedy L1-norm maximization is proposed for VE image analysis. The extracted principal components were interpreted by a non-parametric k-nearest neighbor (k-NN) method for automated celiac disease classification. A benchmark dataset of 460 images (240 from celiac disease patients with small intestinal villous atrophy versus 220 control patients lacking villous atrophy) was constructed from the clinical VE series. It was found that the newly developed SPCA with nongreedy L1-norm maximization was most efficient for computerized celiac disease recognition, having a robust performance with an average recognition accuracy of 93.9 percent. Furthermore, SPCA also has a reduced computation time as compared with other methods. Therefore, it is likely that SPCA will be a helpful adjunct for the diagnosis of celiac disease.

A Transparent Vessel-on-a-Chip Device for Hemodynamic Analysis and Early Diagnosis of Intracranial Aneurysms by CFD and PC-MRI.

Hemodynamics plays a critical role in early diagnosis and investigating the growth mechanism of intracranial aneurysms (IAs), which usually induce hemorrhagic stroke, serious neurological diseases, and even death. We developed a transparent blood vessel-on-a-chip (VOC) device for magnetic resonance imaging (MRI) to provide characteristic flow fields of early IAs as the reference for early diagnosis. This VOC device takes advantage of the transparent property to clearly exhibit the internal structure and identify the needless air bubbles in the biomimetic fluid experiment, which significantly affects the MRI image quality. Furthermore, the device was miniaturized and easily assembled with arbitrary direction using a 3D-printed scaffold in a radiofrequency coil. Computational fluid dynamics (CFD) simulations of the flow field were greatly consistent with those data from MRI. Both internal flow and wall shear stress (WSS) exhibited very low levels during the IA growth, thus leading to the growth and rupture of IAs. PC-MRI images can also provide a reasonable basis for the early diagnosis of IAs. Therefore, we believed that this proposed VOC-based MR imaging technique has great potential for early diagnostic of intracranial aneurysms.

Efficient separation of tumor cells from untreated whole blood using a novel multistage hydrodynamic focusing microfluidics.

Significant progress on circulating tumor cells (CTCs) has profound impact for noninvasive tumor profiling including early diagnosis, treatment monitoring, and metastasis recognition. Therefore, CTCs based liquid biopsy technology is taking a rapid growth in the field of precision oncology. The label-free approaches relied on microfluidic chip stand out from a crowd of methods that suffer from time consuming, extensive blood samples, lost target cells and labor-intensive operation. In this paper, a label-free separation microfluidic device was developed using multistage channel, which took full advantage of inertial lift force. Our strategy demonstrated CTCs were efficiently isolated from untreated human blood samples including antibody conjugation and erythrocyte lysis. This device was applied for isolating human brain malignant glioma cells that were spiked in human peripheral blood samples. The experimental condition was optimized and exhibited an average separation efficiency of ≥ 90% across cell morphological analysis, up to 84.96% purity of collected CTCs and the viability of all cells is >95%, which was better than other one-step CTCs separation methods. Furthermore, the CTCs were successfully separated from untreated clinical blood sample of cancer patient on the proposed microfluidic device. The entire experimental procedures are extremely low-cost and easy manipulation. It is believed that the proposed multistage microfluidic chip can become a promising tool for CTCs separation and early diagnosis of cancer.

Celiac disease diagnosis from videocapsule endoscopy images with residual learning and deep feature extraction.

BACKGROUND AND OBJECTIVE: Videocapsule endoscopy (VCE) is a relatively new technique for evaluating the presence of villous atrophy in celiac disease patients. The diagnostic analysis of video frames is currently time-consuming and tedious. Recently, computer-aided diagnosis (CAD) systems have become an attractive research area for diagnosing celiac disease. However, the images captured from VCE are susceptible to alterations in light illumination, rotation direction, and intestinal secretions. Moreover, textural features of the mucosal villi obtained by VCE are difficult to characterize and extract. This work aims to find a novel deep learning feature learning module to assist in the diagnosis of celiac disease. METHODS: In this manuscript, we propose a novel deep learning recalibration module which shows significant gain in diagnosing celiac disease. In this recalibration module, the block-wise recalibration component is newly employed to capture the most salient feature in the local channel feature map. This learning module was embedded into ResNet50, Inception-v3 to diagnose celiac disease using a 10-time 10-fold cross-validation based upon analysis of VCE images. In addition, we employed model weights to extract feature points from training and test samples before the last fully connected layer, and then input to a support vector machine (SVM), k-nearest neighbor (KNN), and linear discriminant analysis (LDA) for differentiating celiac disease images from heathy controls. RESULTS: Overall, the accuracy, sensitivity and specificity of the 10-time 10-fold cross-validation were 95.94%, 97.20% and 95.63%, respectively. CONCLUSIONS: A novel deep learning recalibration module, with global response and local salient factors is proposed, and it has a high potential for utilizing deep learning networks to diagnose celiac disease using VCE images.

SERS-Based Pump-Free Microfluidic Chip for Highly Sensitive Immunoassay of Prostate-Specific Antigen Biomarkers.

Highly sensitive analysis of cancer biomarkers demonstrates an important impact in early diagnosis and therapies of cancer. A novel surface-enhanced Raman scattering (SERS) based immunoassay using microfluidic technique was reported for rapid analysis of prostate-specific antigen (PSA) biomarker. It is a useful screening test to discriminate prostate cancer and other diseases related to prostate. A "sandwich" immunoassay based on SERS nanotags, PSA biomarkers, and magnetic beads was applied on a pump-free microfluidic sensor. Magnetic immunocomplexes are isolated and trapped at the detection chamber by a permanent magnet integrated into the chip. The PBS buffer washed magnetic immunocomplexes and brought the free gold nanoparticles to the downsteam channel for waste. Our results show a good linear response in the range from 0.01 to 100 ng mL-1. The limit of detection of the PSA level is estimated to be below 0.01 ng mL-1 using this chip. This detection level of PSA biomarker in human serum can be accomplished in 5 min without manual incubation and a heavy syringe pump. To the best of our knowledge, this is the first SERS-based immunoassay which applied a pump-free microfluidic chip as a detection platform. We believe that the proposed method reveals a valuable potential tool for the diagnosis of prostate cancer.

Simultaneous immunoassays of dual prostate cancer markers using a SERS-based microdroplet channel.

The simultaneous detection of multiple biomarkers plays an important role in the accurate diagnosis of cancer. In this study, we developed a novel, surface-enhanced Raman scattering (SERS)-based microfluidic device for the simultaneous detection of free prostate-specific antigen (f-PSA) and total PSA (t-PSA) markers. A fully automatic droplet-based microfluidic platform for the rapid and sensitive detection of f-PSA and t-PSA was designed. Magnetic immunocomplexes were aligned on one side of the channel using a permanent magnet embedded in the microfluidic device, and parent microdroplets containing magnetic immunocomplexes and supernatant solutions were split into two smaller daughter droplets at the Y-shaped junction of the channel. Then, Raman signals of sequential droplets including supernatant solutions were measured for the quantitative analysis of the PSA markers. Two parallel microfluidic channels were designed and fabricated for the simultaneous detection of f-PSA and t-PSA. Our results showed a good linear response for both PSA markers in the range from 0.05 to 100 ng mL-1. The limits of detection were estimated to be below 0.1 ng mL-1 for both the f-PSA and t-PSA. This SERS-based assay in a microfluidic channel was completed in 10 min without any manual incubation and washing steps. Our method is a very promising clinical tool for PSA-based screening test of prostate cancer.

Wash-free magnetic immunoassay of the PSA cancer marker using SERS and droplet microfluidics.

We report a novel wash-free magnetic immunoassay technique for prostate-specific antigen (PSA) that uses a surface-enhanced Raman scattering (SERS)-based microdroplet sensor. The magnetic bar embedded in a droplet-based microfluidic system segregates the free and bound SERS tags by splitting the droplets into two smaller parts. The presence of PSA targets leads more SERS tags to immunocomplex in one droplet so that fewer SERS tags remain in another supernatant solution droplet. Thus, SERS signal measurement enables the quantitative evaluation of PSA markers. This approach can provide a rapid and sensitive assay that is applicable for PSA cancer markers in serum without any washing. Specifically, SERS signals were measured at 174 droplets per minute and averaged for quantitative evaluation of PSA. The limit of detection (LOD) determined by our SERS-based microdroplet sensor was estimated to be below 0.1 ng mL(-1), which is significantly below the clinical cut-off value for the diagnosis of prostate cancer. In addition, because the entire assay can be carried out automatically, only a minimal amount of sample is needed. Accordingly, the approach is expected to be useful as a potential clinical tool for the early diagnosis of prostate cancer.

Fast and sensitive detection of an anthrax biomarker using SERS-based solenoid microfluidic sensor.

We report the application of a fully automated surface-enhanced Raman scattering (SERS)-based solenoid-embedded microfluidic device to the quantitative and sensitive detection of anthrax biomarker poly-γ-D-glutamic acid (PGA) in solution. Analysis is based on the competitive reaction between PGA and PGA-conjugated gold nanoparticles with anti-PGA-immobilized magnetic beads within a microfluidic environment. Magnetic immunocomplexes are trapped by yoke-type solenoids embedded within the device, and their SERS signals were directly measured and analyzed. To improve the accuracy of measurement process, external standard values for PGA-free serum were also measured through use of a control channel. This additional measurement greatly improves the reliability of the assay by minimizing the influence of extraneous experimental variables. The limit of detection (LOD) of PGA in serum, determined by our SERS-based microfluidic sensor, is estimated to be 100 pg/mL. We believe that the defined method represents a valuable analytical tool for the detection of anthrax-related aqueous samples.

Controlled formation of fluorescent metalloporphyrin-containing coordination polymer particles from seed structures by designed shape-transformation reactions.

Herein, nanorod structures and four-leaf clover structures of fluorescent zinc 5,10,15,20-tetra(4-pyridyl)-21H,23H-porphine (ZnTPyP)-containing coordination polymer particles (CPPs) were first synthesized by a bottom-up strategy assisted by surfactants and then employed as seed structures for further shape-transformation reactions. We have successfully designed the morphological transformation for different dimensions, achieving the controlled formation of octahedron structures at both the nanometer scale and micrometer scale from the seed structures. Our approach illustrates a new method to design and synthesize metalloporphyrin-containing CPPs in a systematic and controllable manner.

Real-time analysis of diaquat dibromide monohydrate in water with a SERS-based integrated microdroplet sensor.

We report the fast and sensitive trace analysis of diaquat dibromide monohydrate (DQ) in water using a surface-enhanced Raman scattering (SERS)-based microdroplet sensor. This sensor is composed of two compartments: the first one is for droplet generation for fresh silver nanoparticle (AgNP) synthesis and the second for droplet merging for SERS detection. Silver ions were nucleated and grown to large size AgNPs in droplets, and then each droplet was synchronously merged with another droplet containing DQ for SERS detection. This two-phase liquid-liquid segmented flow system prevented memory effects caused by the precipitation of nanoparticle aggregates on channel walls because the aqueous droplets were isolated by a continuous oil phase. The limit of detection (LOD) of DQ in water was determined to be below 5 nM, which satisfies the maximum contaminant level defined by the United States EPA. This method was also validated successfully in DQ-spiked tap water. The SERS-based integrated sensing system is expected to be useful as an in-the-field sensing platform for fast and reproducible trace analysis of environmental pollutants in water.

Trace analysis of mercury(II) ions using aptamer-modified Au/Ag core-shell nanoparticles and SERS spectroscopy in a microdroplet channel.

We report the rapid and highly sensitive trace analysis of mercury(ii) ions in water using a surface-enhanced Raman scattering (SERS)-based microdroplet sensor. Aptamer-modified Au/Ag core-shell nanoparticles have been fabricated and utilized as highly functional sensing probes. All detection processes for the reaction between mercury(II) ions and aptamer-modified nanoparticles were performed in a specially designed microdroplet channel. Small water droplets that included sample reagents were separated from each other by an oil phase that continuously flowed along the channel. This two-phase liquid-liquid segmented flow system prevented the adsorption of aggregated colloids to the channel walls due to localized reagents within encapsulated droplets. The result was reduced residence time distributions. The limit of detection (LOD) of mercury(II) ions in water was determined by the SERS-based microdroplet sensor to be below 10 pM, which is three orders below the EPA-defined maximum contaminant level. This combination of a SERS-based microfluidic sensor with aptamer-based functional nanoprobes can be used for in-the-field sensing platforms, due to its size and simplicity.

Highly sensitive trace analysis of paraquat using a surface-enhanced Raman scattering microdroplet sensor.

We report a rapid and highly sensitive trace analysis of paraquat (PQ) in water using a surface-enhanced Raman scattering (SERS)-based microdroplet sensor. Aqueous samples of PQ, silver nanoparticles, and NaCl as the aggregation agent were introduced into a microfluidic channel and were encapsulated by a continuous oil phase to form a microdroplet. PQ molecules were adsorbed onto particle surfaces in isolated droplets by passing through the winding part of the channel. Memory effects, caused by the precipitation of nanoparticle aggregates on channel walls, were removed because the aqueous droplets were completely isolated by a continuous oil phase. The limit of detection (LOD) of PQ in water, determined by the SERS-based microdroplet sensor, was estimated to be below 2×10(-9) M, and this low detection limit was enhanced by one to two orders of magnitude compared to conventional analytical methods.