Triple-negative breast cancer (TNBC) is an aggressive and often fatal disease, especially since the brain metastasis of TNBC has been a particularly severe manifestation. However, brain metastasis in TNBC at early sta...Triple-negative breast cancer (TNBC) is an aggressive and often fatal disease, especially since the brain metastasis of TNBC has been a particularly severe manifestation. However, brain metastasis in TNBC at early stages often lacks noticeable symptoms, making it challenging to detect. Near-infrared II (NIR-II) fluorescence microscopic imaging obtains long wavelength, which enables reduced scattering, high spatial resolution and minimal autofluorescence, it is also a favorable imaging method for tumor diagnosis. PbS@CdS quantum dots (QDs) are one of the popular NIR-II fluorescence nanoprobes for well brightness. In this study, NIR-II emissive PbS@CdS QDs were utilized and further encapsulated with thiol-terminated poly(ethylene oxide) (SH-PEG, MW = 5000) to form PbS@CdS@PEG QDs nanoparticles (NPs). The obtained PbS@CdS@PEG QDs NPs were then characterized and further studied in detail. The PbS@CdS@PEG QDs NPs had large absorption spectra, exhibited strong NIR-II fluorescence emission at approximately 1300nm, and possessed good NIR-II fluorescence properties. Then, the mice model of early-stage brain metastases of TNBC was established, and the PbS@CdS@PEG QDs NPs were injected into the tumor-bearing mice for NIR-II fluorescence microscopic bioimaging. The brain vessels and tumors of the living mice were detected with high spatial resolution under the NIR-II fluorescence microscopic imaging system with irradiation of 808nm laser. The tumor tissues were further restricted and prepared as thin slices. The NIR-II fluorescence signals were collected from the tumor slices with high spatial resolution and signal-to-background ratio (SBR). Thus, the PbS@CdS@PEG QDs NPs-assisted NIR-II fluorescence microscopic system can effectively achieve targeting brain metastases of TNBC imaging, offering a novel and promising approach for TNBC-specific diagnosis.展开更多
An intelligent lithology identification method is proposed based on deep learning of the rock microscopic images.Based on the characteristics of rock images in the dataset,we used Xception,MobileNet_v2,Inception_ResNe...An intelligent lithology identification method is proposed based on deep learning of the rock microscopic images.Based on the characteristics of rock images in the dataset,we used Xception,MobileNet_v2,Inception_ResNet_v2,Inception_v3,Densenet121,ResNet101_v2,and ResNet-101 to develop microscopic image classification models,and then the network structures of seven different convolutional neural networks(CNNs)were compared.It shows that the multi-layer representation of rock features can be represented through convolution structures,thus better feature robustness can be achieved.For the loss function,cross-entropy is used to back propagate the weight parameters layer by layer,and the accuracy of the network is improved by frequent iterative training.We expanded a self-built dataset by using transfer learning and data augmentation.Next,accuracy(acc)and frames per second(fps)were used as the evaluation indexes to assess the accuracy and speed of model identification.The results show that the Xception-based model has the optimum performance,with an accuracy of 97.66%in the training dataset and 98.65%in the testing dataset.Furthermore,the fps of the model is 50.76,and the model is feasible to deploy under different hardware conditions and meets the requirements of rapid lithology identification.This proposed method is proved to be robust and versatile in generalization performance,and it is suitable for both geologists and engineers to identify lithology quickly.展开更多
Leukaemia is a type of blood cancer that is caused by undeveloped White Blood Cells(WBC),and it is also called a blast blood cell.In the marrow of human bones,leukaemia is developed and is responsible for blood cell g...Leukaemia is a type of blood cancer that is caused by undeveloped White Blood Cells(WBC),and it is also called a blast blood cell.In the marrow of human bones,leukaemia is developed and is responsible for blood cell generation with leukocytes and WBC,and if any cell gets blasted,then it may become a cause of death.Therefore,the diagnosis of leukaemia in its early stages helps greatly in the treatment along with saving human lives.Subsequently,in terms of detection,image segmentation techniques play a vital role,and they turn out to be the important image processing steps for the extraction of feature patterns from the Acute Lymphoblastic Leukaemia(ALL)type of blood cancer.Moreover,the image segmentation technique focuses on the division of cells by segmenting a microscopic image into background and cancer blood cell nucleus,which is well-known as the Region Of Interest(ROI).As a result,in this article,we attempt to build a segmentation technique capable of solving blood cell nucleus segmentation issues using four distinct scenarios,including K-means,FCM(Fuzzy Cmeans),K-means with FFA(Firefly Algorithm),and FCM with FFA.Also,we determine the most effective method of blood cell nucleus segmentation,which we subsequently use for the Leukaemia classification model.Finally,using the Convolution Neural Network(CNN)as a classifier,we developed a leukaemia cancer classification model from the microscopic images.The proposed system’s classification accuracy is tested using the CNN to test the model on the ALL-IDB dataset and equate it to the current state of the art.In terms of experimental analysis,we observed that the accuracy of the model is near to 99%,and it is far better than other existing models that are designed to segment and classify the types of leukaemia cancer in terms of ALL.展开更多
Microscopic vision has been widely applied in precision assembly.To achieve sufficiently high resolution in measurements for precision assembly when the sizes of the parts involved exceed the field of view of the visi...Microscopic vision has been widely applied in precision assembly.To achieve sufficiently high resolution in measurements for precision assembly when the sizes of the parts involved exceed the field of view of the vision system,an image mosaic technique must be used.In this paper,a method for constructing an image mosaic with non-overlapping areas with enhanced efficiency is proposed.First,an image mosaic model for the part is created using a geometric model of the measurement system installed on a X-Y-Z precision stages with high repeatability,and a path for image acquisition is established.Second,images are captured along the same path for a specified calibration plate,and an entire image is formed based on the given model.The measurement results obtained from the specified calibration plate are utilized to identify mosaic errors and apply compensation for the part requiring measurement.Experimental results show that the maximum error is less than 4μm for a camera with pixel equivalent 2.46μm,thereby demonstrating the accuracy of the proposed method.This image mosaic technique with non-overlapping regions can simplify image acquisition and reduce the workload involved in constructing an image mosaic.展开更多
Accurate histopathology classification is a crucial factor in the diagnosis and treatment of Cholangiocarcinoma(CCA).Hyperspectral images(HSI)provide rich spectral information than ordinary RGB images,making them more...Accurate histopathology classification is a crucial factor in the diagnosis and treatment of Cholangiocarcinoma(CCA).Hyperspectral images(HSI)provide rich spectral information than ordinary RGB images,making them more useful for medical diagnosis.The Convolutional Neural Network(CNN)is commonly employed in hyperspectral image classification due to its remarkable capacity for feature extraction and image classification.However,many existing CNN-based HSI classification methods tend to ignore the importance of image spatial context information and the interdependence between spectral channels,leading to unsatisfied classification performance.Thus,to address these issues,this paper proposes a Spatial-Spectral Joint Network(SSJN)model for hyperspectral image classification that utilizes spatial self-attention and spectral feature extraction.The SSJN model is derived from the ResNet18 network and implemented with the non-local and Coordinate Attention(CA)modules,which extract long-range dependencies on image space and enhance spatial features through the Branch Attention(BA)module to emphasize the region of interest.Furthermore,the SSJN model employs Conv-LSTM modules to extract long-range depen-dencies in the image spectral domain.This addresses the gradient disappearance/explosion phenom-ena and enhances the model classification accuracy.The experimental results show that the pro-posed SSJN model is more efficient in leveraging the spatial and spectral information of hyperspec-tral images on multidimensional microspectral datasets of CCA,leading to higher classification accuracy,and may have useful references for medical diagnosis of CCA.展开更多
Pigmented spot is an important branch in the science of skin. But when processing those images, the microscopical focusing problem arises. It affects the image recognition later. In order to find the best method to so...Pigmented spot is an important branch in the science of skin. But when processing those images, the microscopical focusing problem arises. It affects the image recognition later. In order to find the best method to solve it, comparison and analysis are given to various existing methods of image fusion in this paper . The conclusion is wavelet transform based on pixel-level.展开更多
In image acquisition process, the quality of microscopic images will be degraded by electrical noise, quantizing noise, light illumination etc. Hence, image preprocessing is necessary and important to improve the qual...In image acquisition process, the quality of microscopic images will be degraded by electrical noise, quantizing noise, light illumination etc. Hence, image preprocessing is necessary and important to improve the quality. The background noise and pulse noise are two common types of noise existing in microscopic images. In this paper, a gradient-based anisotropic filtering algorithm was proposed, which can filter out the background noise while preserve object boundary effectively. The filtering performance was evaluated by comparing that with some other filtering algorithms.展开更多
In order to accurately identify the rock, it is necessary to study the identification method of the rock. The rock identification method, the thin slice microscopic image technique, the electron probe analysis method ...In order to accurately identify the rock, it is necessary to study the identification method of the rock. The rock identification method, the thin slice microscopic image technique, the electron probe analysis method or the X-ray powder crystal diffraction method cannot accurately determine the rock. An X-ray powder diffraction method combined with thin-film microscopic image technique and rock identification method was proposed. The X-ray powder diffraction method was combined with the thin-film microscopic image technique to identify the rock, and the microscopic image technique was used to determine the rock. The particle size, structure, shape, mineral color and structure, determine the type of rock, and then determine the mineral and mineral content of the rock by X-ray powder diffraction method, name the rock, and complete the identification of the rock. The experimental results show that the X-ray powder diffraction method or the thin-film microscopic image technique can not accurately determine the rock and combine the X-ray powder diffraction method with the thin-film microscopic image technology to identify the rock. Improve the accuracy of rock identification results.展开更多
Optimal vision and ergonomics are essential factors contributing to the achievement of good results during microsurgery.The three-dimensional(3D)digital image microscope system with a better 3D depth of field can rele...Optimal vision and ergonomics are essential factors contributing to the achievement of good results during microsurgery.The three-dimensional(3D)digital image microscope system with a better 3D depth of field can release strain on the surgeon's neck and back,which can improve outcomes in microsurgery.We report a randomized prospective study of vasoepididymostomy and vasovasostomy using a 3D digital image microscope system(3D-DIM)in rats.A total of 16 adult male rats were randomly divided into two groups of 8 each:the standard operating microscope(SOM)group and the 3D-DIM group.The outcomes measured included the operative time,real-time postoperative mechanical patency,and anastomosis leakage.Furthermore,a user-friendly microscope score was designed to evaluate the ergonomic design and equipment characteristics of the microscope.There were no differences in operative time between the two groups.The real-time postoperative mechanical patency rates were 100.0%for both groups.The percentage of vasoepididymostomy anastomosis leakage was 16.7%in the SOM group and 25.0%in the 3D-DIM group;however,no vasovasostomy anastomosis leakage was found in either group.In terms of the ergonomic design,the 3D-DIM group obtained better scores based on the surgeon's feelings;in terms of the equipment characteristics,the 3D-DIM group had lower scores for clarity and higher scores for flexibility and adaptivity.Based on our randomized prospective study in a rat model,we believe that the 3D-DIM can improve surgeon comfort without compromising outcomes in male infertility reconstructive microsurgery,so the 3D-DIM might be widely used in the future.展开更多
Screening and diagnosing of abnormal Leukocytes are crucial for the diagnosis of immune diseases and Acute Lymphoblastic Leukemia(ALL).As the deterioration of abnormal leukocytes is mainly due to the changes in the ch...Screening and diagnosing of abnormal Leukocytes are crucial for the diagnosis of immune diseases and Acute Lymphoblastic Leukemia(ALL).As the deterioration of abnormal leukocytes is mainly due to the changes in the chromatin distribution,which signicantly affects the absorption and reflection of light,the spectral feature is proved to be important for leukocytes classication and identication.This paper proposes an accurate identication method for healthy and abnormal leukocytes based on microscopic hyperspectral imaging(HSI)technology which combines the spectral information.The segmentation of nucleus and cytoplasm is obtained by the morphological watershed algorithm.Then,the spectral features are extracted and combined with the spatial features.Based on this,the support vector machine(SVM)is applied for classication ofve types of leukocytes and abnormal leukocytes.Compared with different classication methods,the proposed method utilizes spectral features which highlight the differences between healthy leukocytes and abnormal leukocytes,improving the accuracy in the classication and identication of leukocytes.This paper only selects one subtype of ALL for test,and the proposed method can be applied for detection of other leukemia in the future.展开更多
In this work,an old scanning electron microscope(SEM)is refurbished to enhance its image processing capability.How to digitally sample and process an analog image is also presented.An NI PCI-6259 multiple input/output...In this work,an old scanning electron microscope(SEM)is refurbished to enhance its image processing capability.How to digitally sample and process an analog image is also presented.An NI PCI-6259 multiple input/output data acquisition(DAQ)board is used to acquire signals originally being sent to an analog display,and then convert the signals into a digital image.Two output channels are used for raster scan of the horizontal and verticle axes of the image buffer,while one input channel is used to read the brightness signals at various coordinate points.Synchronous method is used to maximize the DAQ speed.Finally,the digitally buffered images are read out to display and saved in a hard drive.The hardware and software designs of this work are explained in great detail,which can serve as a very good example for fast synchronous DAQ,advanced virtual instrument design and structural driver programming with LabVIEW.展开更多
A decision map contains complete and clear information about the image to be fused, which is crucial to various image fusion issues, especially multi-focus image fusion. However, in order to get a satisfactory image f...A decision map contains complete and clear information about the image to be fused, which is crucial to various image fusion issues, especially multi-focus image fusion. However, in order to get a satisfactory image fusion effect, getting a decision map is very necessary and usually difficult to finish. In this letter, we address this problem with convolutional neural network(CNN), aiming to get a state-of-the-art decision map. The main idea is that the max-pooling of CNN is replaced by a convolution layer, the residuals are propagated backwards by gradient descent, and the training parameters of the individual layers of the CNN are updated layer by layer. Based on this, we propose a new all CNN(ACNN)-based multi-focus image fusion method in spatial domain. We demonstrate that the decision map obtained from the ACNN is reliable and can lead to high-quality fusion results. Experimental results clearly validate that the proposed algorithm can obtain state-of-the-art fusion performance in terms of both qualitative and quantitative evaluations.展开更多
Considering the continuous advancement in the field of imaging sensor, a host of other new issues have emerged. A major problem is how to find focus areas more accurately for multi-focus image fusion. The multi-focus ...Considering the continuous advancement in the field of imaging sensor, a host of other new issues have emerged. A major problem is how to find focus areas more accurately for multi-focus image fusion. The multi-focus image fusion extracts the focused information from the source images to construct a global in-focus image which includes more information than any of the source images. In this paper, a novel multi-focus image fusion based on Laplacian operator and region optimization is proposed. The evaluation of image saliency based on Laplacian operator can easily distinguish the focus region and out of focus region. And the decision map obtained by Laplacian operator processing has less the residual information than other methods. For getting precise decision map, focus area and edge optimization based on regional connectivity and edge detection have been taken. Finally, the original images are fused through the decision map. Experimental results indicate that the proposed algorithm outperforms the other series of algorithms in terms of both subjective and objective evaluations.展开更多
Recent advances in artificial intelligence(AI)have led to the development of sophisticated algorithms that significantly improve image analysis capabilities.This combination of AI and microscopic imaging is transformi...Recent advances in artificial intelligence(AI)have led to the development of sophisticated algorithms that significantly improve image analysis capabilities.This combination of AI and microscopic imaging is transforming the way we interpret and analyze imaging data,simplifying complex tasks and enabling innovative experimental methods previously thought impossible.In smart manufacturing,these improvements are especially impactful,increasing precision and efficiency in production processes.This review examines the convergence of AI with particle image analysis,an area we refer to as“particle vision analysis(PVA).”We offer a detailed overview of how this technology integrates into and impacts various fields within the physical sciences and materials sectors,where it plays a crucial role in both innovation and operational improvements.We explore four key areas of advancement-namely,particle classification,detection,segmentation,and object tracking-along with a look into the emerging field of augmented microscopy.This paper also underscores the vital role of the existing datasets and implementations that support these applications,which provide essential insights and resources that drive continuous research and development in this fast-evolving field.Our thorough analysis aims to outline the transformative potential of AI-driven PVA in improving precision in future manufacturing at the microscopic scale and thereby preparing the ground for significant technological progress and broad industrial applications in nanomanufacturing,biomanufacturing,and pharmaceutical manufacturing.This exploration not only highlights the advantages of integrating AI into conventional manufacturing processes but also anticipates the rise of next-generation smart manufacturing,which is set to revolutionize industry standards and operational practices.展开更多
During the thawing process of a railway subgrade,bidirectional thawing complicates water-heat transfer,leading to serious thaw settlement issues under train loads.Focusing on the severely frozen section of the Shuozho...During the thawing process of a railway subgrade,bidirectional thawing complicates water-heat transfer,leading to serious thaw settlement issues under train loads.Focusing on the severely frozen section of the Shuozhou-Huanghua port heavy-haul railway,this study conducted indoor soil-column laterally-limited compression tests on thawing fine-grained soil specimens to analyze the cumulative deformation during thawing.The deformation evolution was examined from both macroscopic and microscopic perspectives.The test results revealed a sig-nificant increase in the water content at the frozen interlayer during thawing,with minimal thaw settlement under no-load conditions.However,under dynamic loads,the thawing soil exhibited rapid settlement during the initial stages of the process.Increasing the dynamic load amplitude did not result in significant additional thaw settlement compression.Particle image velocimetry revealed substantial thaw settlement and compression at the top of thawing soil.Microscopically,the porosity at the top of the specimens significantly decreased,whereas the porosity in the frozen interlayer remained largely unchanged.Under dynamic loading,the specimens exhibited a concentrated distribution of large pores with scattered smaller pores.The phase change from ice to water,combined with dynamic loading,induced particle movement and expanded the inter-particle pore space,leading to macroscopic thaw settlement and soil compression.The findings can provide a theoretical foundation for maintaining and ensuring the safety of railway subgrades in cold regions.展开更多
Two key points of pixel-level multi-focus image fusion are the clarity measure and the pixel coeffi- cients fusion rule. Along with different improvements on these two points, various fusion schemes have been proposed...Two key points of pixel-level multi-focus image fusion are the clarity measure and the pixel coeffi- cients fusion rule. Along with different improvements on these two points, various fusion schemes have been proposed in literatures. However, the traditional clarity measures are not designed for compressive imaging measurements which are maps of source sense with random or likely ran- dom measurements matrix. This paper presents a novel efficient multi-focus image fusion frame- work for compressive imaging sensor network. Here the clarity measure of the raw compressive measurements is not obtained from the random sampling data itself but from the selected Hada- mard coefficients which can also be acquired from compressive imaging system efficiently. Then, the compressive measurements with different images are fused by selecting fusion rule. Finally, the block-based CS which coupled with iterative projection-based reconstruction is used to re- cover the fused image. Experimental results on common used testing data demonstrate the effectiveness of the proposed method.展开更多
A protocol for obtaining digital images from natural porous media with a wide range of pore sizes, intended for fractal studies of the porosity, is proposed. Soil porosity is used as para- digm of complex natural poro...A protocol for obtaining digital images from natural porous media with a wide range of pore sizes, intended for fractal studies of the porosity, is proposed. Soil porosity is used as para- digm of complex natural porous media in this study. The use of several imaging devices and fluores- cent compounds to enhance the contrast between the solid and the pore phase is tested. Finally a protocol is reached using a photo camera and a confocal microscope. It is the first time that confocal microscopy is used for this purpose. Artificial porous images are created through random Sierpinski carpet fractals and the statistical information of real soil images. These ground truth images are used in an objective comparison of automatic segmentation algorithms for the obtained images. A statistical classification on the performance of several automatic segmentation algorithms for this tv^e of images is reached.展开更多
Cracking behaviors of rocks significantly affect the safety and stability of the explorations of underground space and deep resources.To understand deeply the microscopic cracking process and mechanical property of ro...Cracking behaviors of rocks significantly affect the safety and stability of the explorations of underground space and deep resources.To understand deeply the microscopic cracking process and mechanical property of rocks,X-ray micro-computed tomography(X-μCT)is applied to capture the rock microstructures.The digital color difference UNet(DCD-UNet)-based deep learning algorithm with 3D reconstruction is proposed to reconstruct the multiphase heterogeneity microstructure models of rocks.The microscopic cracking and mechanical properties are studied based on the proposed microstructure-based peridynamic model.Results show that the DCD-UNet algorithm is more effective to recognize and to represent the microscopic multiphase heterogeneity of rocks.As damage characteristic index of multiphase rocks increases,transgranular cracks in the same grain phase,transgranular and intergranular cracks of pore-grain phase,intergranular and secondary transgranular cracks and transgranular crack between different grains propagate.The ultimate microscopic failure modes of rocks are mainly controlled by the transgranular cracks-based T1-shear,T3-shear,T1-tension,T2-tension and T3-tension failures,and the intergranular cracks-based T1-tension,T1-shear and T3-shear failures under uniaxial compression.展开更多
基金supported by the National Natural Science Foundation of China(NSFC)under Grant Nos.62035011,82202220 and 82060326State Key Laboratory of Pathogenesis,Prevention and treat ment of High Incident Diseases in central Asia(Nos.SKL-HIDCA-2022-3 and SKL-HIDCA-2022-GJ1)+3 种基金the Xinjiang Uygur Autonomous Region Regional Collaborative Innovation Special Science and Technology Assistance Program(No.2022E02130)Xinjiang Uygur Autonomous Region Natural Sci ence Foundation Key Project(No.2022D01D40)Outstanding Youth Project(2023D01E06)Y.Gao and C.Zhang authors contributed equally to this work.
文摘Triple-negative breast cancer (TNBC) is an aggressive and often fatal disease, especially since the brain metastasis of TNBC has been a particularly severe manifestation. However, brain metastasis in TNBC at early stages often lacks noticeable symptoms, making it challenging to detect. Near-infrared II (NIR-II) fluorescence microscopic imaging obtains long wavelength, which enables reduced scattering, high spatial resolution and minimal autofluorescence, it is also a favorable imaging method for tumor diagnosis. PbS@CdS quantum dots (QDs) are one of the popular NIR-II fluorescence nanoprobes for well brightness. In this study, NIR-II emissive PbS@CdS QDs were utilized and further encapsulated with thiol-terminated poly(ethylene oxide) (SH-PEG, MW = 5000) to form PbS@CdS@PEG QDs nanoparticles (NPs). The obtained PbS@CdS@PEG QDs NPs were then characterized and further studied in detail. The PbS@CdS@PEG QDs NPs had large absorption spectra, exhibited strong NIR-II fluorescence emission at approximately 1300nm, and possessed good NIR-II fluorescence properties. Then, the mice model of early-stage brain metastases of TNBC was established, and the PbS@CdS@PEG QDs NPs were injected into the tumor-bearing mice for NIR-II fluorescence microscopic bioimaging. The brain vessels and tumors of the living mice were detected with high spatial resolution under the NIR-II fluorescence microscopic imaging system with irradiation of 808nm laser. The tumor tissues were further restricted and prepared as thin slices. The NIR-II fluorescence signals were collected from the tumor slices with high spatial resolution and signal-to-background ratio (SBR). Thus, the PbS@CdS@PEG QDs NPs-assisted NIR-II fluorescence microscopic system can effectively achieve targeting brain metastases of TNBC imaging, offering a novel and promising approach for TNBC-specific diagnosis.
基金support from the National Natural Science Foundation of China(Grant Nos.52022053 and 52009073)the Natural Science Foundation of Shandong Province(Grant No.ZR201910270116).
文摘An intelligent lithology identification method is proposed based on deep learning of the rock microscopic images.Based on the characteristics of rock images in the dataset,we used Xception,MobileNet_v2,Inception_ResNet_v2,Inception_v3,Densenet121,ResNet101_v2,and ResNet-101 to develop microscopic image classification models,and then the network structures of seven different convolutional neural networks(CNNs)were compared.It shows that the multi-layer representation of rock features can be represented through convolution structures,thus better feature robustness can be achieved.For the loss function,cross-entropy is used to back propagate the weight parameters layer by layer,and the accuracy of the network is improved by frequent iterative training.We expanded a self-built dataset by using transfer learning and data augmentation.Next,accuracy(acc)and frames per second(fps)were used as the evaluation indexes to assess the accuracy and speed of model identification.The results show that the Xception-based model has the optimum performance,with an accuracy of 97.66%in the training dataset and 98.65%in the testing dataset.Furthermore,the fps of the model is 50.76,and the model is feasible to deploy under different hardware conditions and meets the requirements of rapid lithology identification.This proposed method is proved to be robust and versatile in generalization performance,and it is suitable for both geologists and engineers to identify lithology quickly.
基金We deeply acknowledge Taif University for supporting this study through Taif University Researchers Supporting Project number(TURSP-2020/115),Taif University,Taif,Saudi Arabia.
文摘Leukaemia is a type of blood cancer that is caused by undeveloped White Blood Cells(WBC),and it is also called a blast blood cell.In the marrow of human bones,leukaemia is developed and is responsible for blood cell generation with leukocytes and WBC,and if any cell gets blasted,then it may become a cause of death.Therefore,the diagnosis of leukaemia in its early stages helps greatly in the treatment along with saving human lives.Subsequently,in terms of detection,image segmentation techniques play a vital role,and they turn out to be the important image processing steps for the extraction of feature patterns from the Acute Lymphoblastic Leukaemia(ALL)type of blood cancer.Moreover,the image segmentation technique focuses on the division of cells by segmenting a microscopic image into background and cancer blood cell nucleus,which is well-known as the Region Of Interest(ROI).As a result,in this article,we attempt to build a segmentation technique capable of solving blood cell nucleus segmentation issues using four distinct scenarios,including K-means,FCM(Fuzzy Cmeans),K-means with FFA(Firefly Algorithm),and FCM with FFA.Also,we determine the most effective method of blood cell nucleus segmentation,which we subsequently use for the Leukaemia classification model.Finally,using the Convolution Neural Network(CNN)as a classifier,we developed a leukaemia cancer classification model from the microscopic images.The proposed system’s classification accuracy is tested using the CNN to test the model on the ALL-IDB dataset and equate it to the current state of the art.In terms of experimental analysis,we observed that the accuracy of the model is near to 99%,and it is far better than other existing models that are designed to segment and classify the types of leukaemia cancer in terms of ALL.
基金supported by the Liaoning Revitalization Talents Program(Grant No.XLYC2002020)the Major Project of Basic Scientific Research of Chinese Ministry(Grant No.JCYK2016205A003).
文摘Microscopic vision has been widely applied in precision assembly.To achieve sufficiently high resolution in measurements for precision assembly when the sizes of the parts involved exceed the field of view of the vision system,an image mosaic technique must be used.In this paper,a method for constructing an image mosaic with non-overlapping areas with enhanced efficiency is proposed.First,an image mosaic model for the part is created using a geometric model of the measurement system installed on a X-Y-Z precision stages with high repeatability,and a path for image acquisition is established.Second,images are captured along the same path for a specified calibration plate,and an entire image is formed based on the given model.The measurement results obtained from the specified calibration plate are utilized to identify mosaic errors and apply compensation for the part requiring measurement.Experimental results show that the maximum error is less than 4μm for a camera with pixel equivalent 2.46μm,thereby demonstrating the accuracy of the proposed method.This image mosaic technique with non-overlapping regions can simplify image acquisition and reduce the workload involved in constructing an image mosaic.
基金supported by National Natural Science Foundation of China(No.62101040).
文摘Accurate histopathology classification is a crucial factor in the diagnosis and treatment of Cholangiocarcinoma(CCA).Hyperspectral images(HSI)provide rich spectral information than ordinary RGB images,making them more useful for medical diagnosis.The Convolutional Neural Network(CNN)is commonly employed in hyperspectral image classification due to its remarkable capacity for feature extraction and image classification.However,many existing CNN-based HSI classification methods tend to ignore the importance of image spatial context information and the interdependence between spectral channels,leading to unsatisfied classification performance.Thus,to address these issues,this paper proposes a Spatial-Spectral Joint Network(SSJN)model for hyperspectral image classification that utilizes spatial self-attention and spectral feature extraction.The SSJN model is derived from the ResNet18 network and implemented with the non-local and Coordinate Attention(CA)modules,which extract long-range dependencies on image space and enhance spatial features through the Branch Attention(BA)module to emphasize the region of interest.Furthermore,the SSJN model employs Conv-LSTM modules to extract long-range depen-dencies in the image spectral domain.This addresses the gradient disappearance/explosion phenom-ena and enhances the model classification accuracy.The experimental results show that the pro-posed SSJN model is more efficient in leveraging the spatial and spectral information of hyperspec-tral images on multidimensional microspectral datasets of CCA,leading to higher classification accuracy,and may have useful references for medical diagnosis of CCA.
文摘Pigmented spot is an important branch in the science of skin. But when processing those images, the microscopical focusing problem arises. It affects the image recognition later. In order to find the best method to solve it, comparison and analysis are given to various existing methods of image fusion in this paper . The conclusion is wavelet transform based on pixel-level.
文摘In image acquisition process, the quality of microscopic images will be degraded by electrical noise, quantizing noise, light illumination etc. Hence, image preprocessing is necessary and important to improve the quality. The background noise and pulse noise are two common types of noise existing in microscopic images. In this paper, a gradient-based anisotropic filtering algorithm was proposed, which can filter out the background noise while preserve object boundary effectively. The filtering performance was evaluated by comparing that with some other filtering algorithms.
文摘In order to accurately identify the rock, it is necessary to study the identification method of the rock. The rock identification method, the thin slice microscopic image technique, the electron probe analysis method or the X-ray powder crystal diffraction method cannot accurately determine the rock. An X-ray powder diffraction method combined with thin-film microscopic image technique and rock identification method was proposed. The X-ray powder diffraction method was combined with the thin-film microscopic image technique to identify the rock, and the microscopic image technique was used to determine the rock. The particle size, structure, shape, mineral color and structure, determine the type of rock, and then determine the mineral and mineral content of the rock by X-ray powder diffraction method, name the rock, and complete the identification of the rock. The experimental results show that the X-ray powder diffraction method or the thin-film microscopic image technique can not accurately determine the rock and combine the X-ray powder diffraction method with the thin-film microscopic image technology to identify the rock. Improve the accuracy of rock identification results.
基金This work was supported by grants from the National Nature Science Foundation of China(81701524,81871215)the Strategic Priority Research Program of the Chinese Academy of Sciences(XDA16020701)the National Key R&D Program of China(2017YFC1002003).
文摘Optimal vision and ergonomics are essential factors contributing to the achievement of good results during microsurgery.The three-dimensional(3D)digital image microscope system with a better 3D depth of field can release strain on the surgeon's neck and back,which can improve outcomes in microsurgery.We report a randomized prospective study of vasoepididymostomy and vasovasostomy using a 3D digital image microscope system(3D-DIM)in rats.A total of 16 adult male rats were randomly divided into two groups of 8 each:the standard operating microscope(SOM)group and the 3D-DIM group.The outcomes measured included the operative time,real-time postoperative mechanical patency,and anastomosis leakage.Furthermore,a user-friendly microscope score was designed to evaluate the ergonomic design and equipment characteristics of the microscope.There were no differences in operative time between the two groups.The real-time postoperative mechanical patency rates were 100.0%for both groups.The percentage of vasoepididymostomy anastomosis leakage was 16.7%in the SOM group and 25.0%in the 3D-DIM group;however,no vasovasostomy anastomosis leakage was found in either group.In terms of the ergonomic design,the 3D-DIM group obtained better scores based on the surgeon's feelings;in terms of the equipment characteristics,the 3D-DIM group had lower scores for clarity and higher scores for flexibility and adaptivity.Based on our randomized prospective study in a rat model,we believe that the 3D-DIM can improve surgeon comfort without compromising outcomes in male infertility reconstructive microsurgery,so the 3D-DIM might be widely used in the future.
基金supported in part by the National Natural Science Foundation of China(Grant Nos.61975056 and 61901173)the Shanghai Natural Science Foundation(Grant No.19ZR1416000)the Science and Technology Commission of Shanghai Municipality(Grant Nos.14DZ2260800 and 18511102500).
文摘Screening and diagnosing of abnormal Leukocytes are crucial for the diagnosis of immune diseases and Acute Lymphoblastic Leukemia(ALL).As the deterioration of abnormal leukocytes is mainly due to the changes in the chromatin distribution,which signicantly affects the absorption and reflection of light,the spectral feature is proved to be important for leukocytes classication and identication.This paper proposes an accurate identication method for healthy and abnormal leukocytes based on microscopic hyperspectral imaging(HSI)technology which combines the spectral information.The segmentation of nucleus and cytoplasm is obtained by the morphological watershed algorithm.Then,the spectral features are extracted and combined with the spatial features.Based on this,the support vector machine(SVM)is applied for classication ofve types of leukocytes and abnormal leukocytes.Compared with different classication methods,the proposed method utilizes spectral features which highlight the differences between healthy leukocytes and abnormal leukocytes,improving the accuracy in the classication and identication of leukocytes.This paper only selects one subtype of ALL for test,and the proposed method can be applied for detection of other leukemia in the future.
文摘In this work,an old scanning electron microscope(SEM)is refurbished to enhance its image processing capability.How to digitally sample and process an analog image is also presented.An NI PCI-6259 multiple input/output data acquisition(DAQ)board is used to acquire signals originally being sent to an analog display,and then convert the signals into a digital image.Two output channels are used for raster scan of the horizontal and verticle axes of the image buffer,while one input channel is used to read the brightness signals at various coordinate points.Synchronous method is used to maximize the DAQ speed.Finally,the digitally buffered images are read out to display and saved in a hard drive.The hardware and software designs of this work are explained in great detail,which can serve as a very good example for fast synchronous DAQ,advanced virtual instrument design and structural driver programming with LabVIEW.
基金supported by the National Natural Science Foundation of China(No.61174193)
文摘A decision map contains complete and clear information about the image to be fused, which is crucial to various image fusion issues, especially multi-focus image fusion. However, in order to get a satisfactory image fusion effect, getting a decision map is very necessary and usually difficult to finish. In this letter, we address this problem with convolutional neural network(CNN), aiming to get a state-of-the-art decision map. The main idea is that the max-pooling of CNN is replaced by a convolution layer, the residuals are propagated backwards by gradient descent, and the training parameters of the individual layers of the CNN are updated layer by layer. Based on this, we propose a new all CNN(ACNN)-based multi-focus image fusion method in spatial domain. We demonstrate that the decision map obtained from the ACNN is reliable and can lead to high-quality fusion results. Experimental results clearly validate that the proposed algorithm can obtain state-of-the-art fusion performance in terms of both qualitative and quantitative evaluations.
文摘Considering the continuous advancement in the field of imaging sensor, a host of other new issues have emerged. A major problem is how to find focus areas more accurately for multi-focus image fusion. The multi-focus image fusion extracts the focused information from the source images to construct a global in-focus image which includes more information than any of the source images. In this paper, a novel multi-focus image fusion based on Laplacian operator and region optimization is proposed. The evaluation of image saliency based on Laplacian operator can easily distinguish the focus region and out of focus region. And the decision map obtained by Laplacian operator processing has less the residual information than other methods. For getting precise decision map, focus area and edge optimization based on regional connectivity and edge detection have been taken. Finally, the original images are fused through the decision map. Experimental results indicate that the proposed algorithm outperforms the other series of algorithms in terms of both subjective and objective evaluations.
基金funding support from the US National Science Foundation(2229092)supported by the Eric and Wendy Schmidt AI in Science Postdoctoral Fellowship,a program of Schmidt Sciences,LLC.
文摘Recent advances in artificial intelligence(AI)have led to the development of sophisticated algorithms that significantly improve image analysis capabilities.This combination of AI and microscopic imaging is transforming the way we interpret and analyze imaging data,simplifying complex tasks and enabling innovative experimental methods previously thought impossible.In smart manufacturing,these improvements are especially impactful,increasing precision and efficiency in production processes.This review examines the convergence of AI with particle image analysis,an area we refer to as“particle vision analysis(PVA).”We offer a detailed overview of how this technology integrates into and impacts various fields within the physical sciences and materials sectors,where it plays a crucial role in both innovation and operational improvements.We explore four key areas of advancement-namely,particle classification,detection,segmentation,and object tracking-along with a look into the emerging field of augmented microscopy.This paper also underscores the vital role of the existing datasets and implementations that support these applications,which provide essential insights and resources that drive continuous research and development in this fast-evolving field.Our thorough analysis aims to outline the transformative potential of AI-driven PVA in improving precision in future manufacturing at the microscopic scale and thereby preparing the ground for significant technological progress and broad industrial applications in nanomanufacturing,biomanufacturing,and pharmaceutical manufacturing.This exploration not only highlights the advantages of integrating AI into conventional manufacturing processes but also anticipates the rise of next-generation smart manufacturing,which is set to revolutionize industry standards and operational practices.
基金supported by the National Natural Science Foundation of China(NSFC)(Nos.52078312,52478461,and 52408379)the Natural Science Foundation of Hebei Province(E2024210134)+2 种基金the Innovative Research Group Project of the Natural Science Foundation of Hebei Province(Grant No.E2021210099)CCCC Science and Technology R&D Project(Grant No.2021-ZJKJ-01)the S&T Program of Hebei(Grant No.225A0802D).
文摘During the thawing process of a railway subgrade,bidirectional thawing complicates water-heat transfer,leading to serious thaw settlement issues under train loads.Focusing on the severely frozen section of the Shuozhou-Huanghua port heavy-haul railway,this study conducted indoor soil-column laterally-limited compression tests on thawing fine-grained soil specimens to analyze the cumulative deformation during thawing.The deformation evolution was examined from both macroscopic and microscopic perspectives.The test results revealed a sig-nificant increase in the water content at the frozen interlayer during thawing,with minimal thaw settlement under no-load conditions.However,under dynamic loads,the thawing soil exhibited rapid settlement during the initial stages of the process.Increasing the dynamic load amplitude did not result in significant additional thaw settlement compression.Particle image velocimetry revealed substantial thaw settlement and compression at the top of thawing soil.Microscopically,the porosity at the top of the specimens significantly decreased,whereas the porosity in the frozen interlayer remained largely unchanged.Under dynamic loading,the specimens exhibited a concentrated distribution of large pores with scattered smaller pores.The phase change from ice to water,combined with dynamic loading,induced particle movement and expanded the inter-particle pore space,leading to macroscopic thaw settlement and soil compression.The findings can provide a theoretical foundation for maintaining and ensuring the safety of railway subgrades in cold regions.
文摘Two key points of pixel-level multi-focus image fusion are the clarity measure and the pixel coeffi- cients fusion rule. Along with different improvements on these two points, various fusion schemes have been proposed in literatures. However, the traditional clarity measures are not designed for compressive imaging measurements which are maps of source sense with random or likely ran- dom measurements matrix. This paper presents a novel efficient multi-focus image fusion frame- work for compressive imaging sensor network. Here the clarity measure of the raw compressive measurements is not obtained from the random sampling data itself but from the selected Hada- mard coefficients which can also be acquired from compressive imaging system efficiently. Then, the compressive measurements with different images are fused by selecting fusion rule. Finally, the block-based CS which coupled with iterative projection-based reconstruction is used to re- cover the fused image. Experimental results on common used testing data demonstrate the effectiveness of the proposed method.
基金partially supported by the Plan Nacional de Investigación Científica, Desarrollo e Investigación Tecnológica (I+D+i) (Nos. AGL2011/25175 and AGL2015/69697P)by DGUI (Comunidad de Madrid) and UPM (No. QM100245066)
文摘A protocol for obtaining digital images from natural porous media with a wide range of pore sizes, intended for fractal studies of the porosity, is proposed. Soil porosity is used as para- digm of complex natural porous media in this study. The use of several imaging devices and fluores- cent compounds to enhance the contrast between the solid and the pore phase is tested. Finally a protocol is reached using a photo camera and a confocal microscope. It is the first time that confocal microscopy is used for this purpose. Artificial porous images are created through random Sierpinski carpet fractals and the statistical information of real soil images. These ground truth images are used in an objective comparison of automatic segmentation algorithms for the obtained images. A statistical classification on the performance of several automatic segmentation algorithms for this tv^e of images is reached.
基金supported by the National Natural Science Foundation of China(Nos.42207193,52027814,and 51839009)the Natural Science Foundation of Hubei Province(No.2022CFB609)+1 种基金the National Center for International Research on Deep Earth Drilling and Resource Development(No.DEDRD-2022-07)the Fundamental Research Funds for the Central Universities(No.2042021kf0058)。
文摘Cracking behaviors of rocks significantly affect the safety and stability of the explorations of underground space and deep resources.To understand deeply the microscopic cracking process and mechanical property of rocks,X-ray micro-computed tomography(X-μCT)is applied to capture the rock microstructures.The digital color difference UNet(DCD-UNet)-based deep learning algorithm with 3D reconstruction is proposed to reconstruct the multiphase heterogeneity microstructure models of rocks.The microscopic cracking and mechanical properties are studied based on the proposed microstructure-based peridynamic model.Results show that the DCD-UNet algorithm is more effective to recognize and to represent the microscopic multiphase heterogeneity of rocks.As damage characteristic index of multiphase rocks increases,transgranular cracks in the same grain phase,transgranular and intergranular cracks of pore-grain phase,intergranular and secondary transgranular cracks and transgranular crack between different grains propagate.The ultimate microscopic failure modes of rocks are mainly controlled by the transgranular cracks-based T1-shear,T3-shear,T1-tension,T2-tension and T3-tension failures,and the intergranular cracks-based T1-tension,T1-shear and T3-shear failures under uniaxial compression.
