Pluta polarizing interference microscope was used to follow the crazing that occur on the surface of stretched polypropylene fibres at different drawing conditions. The samples were stretched until crazing initiated, ...Pluta polarizing interference microscope was used to follow the crazing that occur on the surface of stretched polypropylene fibres at different drawing conditions. The samples were stretched until crazing initiated, and then craze propagation was monitored as a function of drawing speed and test temperature. The effect of craze dimension on their propagation velocity was taken into account. Three-dimensional birefringence profile for crazed polypropylene fibre has been demonstrated to investigate the birefringence of crazed fibre at different test times for fixed drawing speed value. Also the mean birefringence values of crazed polypropylene fibres were calculated and the results showed that, these values increased with the areal craze density. Video images were used to calculate the craze velocity. Optical micrographs and microinterferograms were presented for demonstrations.展开更多
Analysis of cellular behavior is significant for studying cell cycle and detecting anti-cancer drugs. It is a very difficult task for image processing to isolate individual cells in confocal microscopic images of non-...Analysis of cellular behavior is significant for studying cell cycle and detecting anti-cancer drugs. It is a very difficult task for image processing to isolate individual cells in confocal microscopic images of non-stained live cell cultures. Because these images do not have adequate textural variations. Manual cell segmentation requires massive labor and is a time consuming process. This paper describes an automated cell segmentation method for localizing the cells of Chinese hamster ovary cell culture. Several kinds of high-dimensional feature descriptors, K-means clustering method and Chan-Vese model-based level set are used to extract the cellular regions. The region extracted are used to classify phases in cell cycle. The segmentation results were experimentally assessed. As a result, the proposed method proved to be significant for cell isolation. In the evaluation experiments, we constructed a database of Chinese Hamster Ovary Cell’s microscopic images which includes various photographing environments under the guidance of a biologist.展开更多
Hadamard transform spatial multiplexed imaging technique is combined with fluorescence microscope and an instrument of Hadamard transform microscope fluorescence image analysis is developed. Images acquired by this in...Hadamard transform spatial multiplexed imaging technique is combined with fluorescence microscope and an instrument of Hadamard transform microscope fluorescence image analysis is developed. Images acquired by this instrument can provide a lot of useful information simultaneously, including three-dimensional Hadamard transform microscope cell fluorescence image, the fluorescence intensity and fluorescence distribution of a cell, the background signal intensity and the signal/noise ratio, etc.展开更多
Background With the gradual increase of infertility in the world,among which male sperm problems are the main factor for infertility,more and more couples are using computer-assisted sperm analysis(CASA)to assist in t...Background With the gradual increase of infertility in the world,among which male sperm problems are the main factor for infertility,more and more couples are using computer-assisted sperm analysis(CASA)to assist in the analysis and treatment of infertility.Meanwhile,the rapid development of deep learning(DL)has led to strong results in image classification tasks.However,the classification of sperm images has not been well studied in current deep learning methods,and the sperm images are often affected by noise in practical CASA applications.The purpose of this article is to investigate the anti-noise robustness of deep learning classification methods applied on sperm images.Methods The SVIA dataset is a publicly available large-scale sperm dataset containing three subsets.In this work,we used subset-C,which provides more than 125,000 independent images of sperms and impurities,including 121,401 sperm images and 4,479 impurity images.To investigate the anti-noise robustness of deep learning classification methods applied on sperm images,we conducted a comprehensive comparative study of sperm images using many convolutional neural network(CNN)and visual transformer(VT)deep learning methods to find the deep learning model with the most stable anti-noise robustness.Results This study proved that VT had strong robustness for the classification of tiny object(sperm and impurity)image datasets under some types of conventional noise and some adversarial attacks.In particular,under the influence of Poisson noise,accuracy changed from 91.45%to 91.08%,impurity precison changed from 92.7%to 91.3%,impurity recall changed from 88.8%to 89.5%,and impurity F1-score changed 90.7%to 90.4%.Meanwhile,sperm precision changed from 90.9%to 90.5%,sperm recall changed from 92.5%to 93.8%,and sperm F1-score changed from 92.1%to 90.4%.Conclusion Sperm image classification may be strongly affected by noise in current deep learning methods;the robustness with regard to noise of VT methods based on global information is greater than that of CNN methods based on local information,indicating that the robustness with regard to noise is reflected mainly in global information.展开更多
BACKGROUND Gastrointestinal bleeding(GIB)is a severe and potentially life-threatening condition,especially in cases of delayed treatment.Computed tomography angiography(CTA)plays a pivotal role in the early identifica...BACKGROUND Gastrointestinal bleeding(GIB)is a severe and potentially life-threatening condition,especially in cases of delayed treatment.Computed tomography angiography(CTA)plays a pivotal role in the early identification of upper and lower GIB and in the prompt treatment of the haemorrhage.AIM To determine whether a volumetric estimation of the extravasated contrast at CTA in GIB may be a predictor of subsequent positive angiographic findings.METHODS In this retrospective single-centre study,35 patients(22 men;median age 69 years;range 16-92 years)admitted to our institution for active GIB detected at CTA and further submitted to catheter angiography between January 2018 and February 2022 were enrolled.Twenty-three(65.7%)patients underwent endoscopy before CTA.Bleeding volumetry was evaluated in both arterial and venous phases via a semi-automated dedicated software.Bleeding rate was obtained from volume change between the two phases and standardised for unit time.Patients were divided into two groups,according to the angiographic signs and their concordance with CTA.RESULTS Upper bleeding accounted for 42.9%and lower GIB for 57.1%.Mean haemoglobin value at the admission was 7.7 g/dL.A concordance between positive CTA and direct angiographic bleeding signs was found in 19(54.3%)cases.Despite no significant differences in terms of bleeding volume in the arterial phase(0.55 mL vs 0.33 mL,P=0.35),a statistically significant volume increase in the venous phase was identified in the group of patients with positive angiography(2.06 mL vs 0.9 mL,P=0.02).In the latter patient group,a significant increase in bleeding rate was also detected(2.18 mL/min vs 0.19 mL/min,P=0.02).CONCLUSION In GIB of any origin,extravasated contrast volumetric analysis at CTA could be a predictor of positive angiography and may help in avoiding further unnecessary procedures.展开更多
In this paper,we report upon our recent work aimed at improving and adapting machine learning algorithms to automatically classify nanoscience images acquired by the Scanning Electron Microscope(SEM).This is done by c...In this paper,we report upon our recent work aimed at improving and adapting machine learning algorithms to automatically classify nanoscience images acquired by the Scanning Electron Microscope(SEM).This is done by coupling supervised and unsupervised learning approaches.We first investigate supervised learning on a ten-category data set of images and compare the performance of the different models in terms of training accuracy.Then,we reduce the dimensionality of the features through autoencoders to perform unsupervised learning on a subset of images in a selected range of scales(from 1μm to 2μm).Finally,we compare different clustering methods to uncover intrinsic structures in the images.展开更多
Colon cancer is the third most commonly diagnosed cancer in the world.Most colon AdenoCArcinoma(ACA)arises from pre-existing benign polyps in the mucosa of the bowel.Thus,detecting benign at the earliest helps reduce ...Colon cancer is the third most commonly diagnosed cancer in the world.Most colon AdenoCArcinoma(ACA)arises from pre-existing benign polyps in the mucosa of the bowel.Thus,detecting benign at the earliest helps reduce the mortality rate.In this work,a Predictive Modeling System(PMS)is developed for the classification of colon cancer using the Horizontal Voting Ensemble(HVE)method.Identifying different patterns inmicroscopic images is essential to an effective classification system.A twelve-layer deep learning architecture has been developed to extract these patterns.The developedHVE algorithm can increase the system’s performance according to the combined models from the last epochs of the proposed architecture.Ten thousand(10000)microscopic images are taken to test the classification performance of the proposed PMS with the HVE method.The microscopic images obtained from the colon tissues are classified intoACAor benign by the proposed PMS.Results prove that the proposed PMS has∼8%performance improvement over the architecture without using the HVE method.The proposed PMS for colon cancer reduces the misclassification rate and attains 99.2%of sensitivity and 99.4%of specificity.The overall accuracy of the proposed PMS is 99.3%,and without using the HVE method,it is only 91.3%.展开更多
文摘Pluta polarizing interference microscope was used to follow the crazing that occur on the surface of stretched polypropylene fibres at different drawing conditions. The samples were stretched until crazing initiated, and then craze propagation was monitored as a function of drawing speed and test temperature. The effect of craze dimension on their propagation velocity was taken into account. Three-dimensional birefringence profile for crazed polypropylene fibre has been demonstrated to investigate the birefringence of crazed fibre at different test times for fixed drawing speed value. Also the mean birefringence values of crazed polypropylene fibres were calculated and the results showed that, these values increased with the areal craze density. Video images were used to calculate the craze velocity. Optical micrographs and microinterferograms were presented for demonstrations.
文摘Analysis of cellular behavior is significant for studying cell cycle and detecting anti-cancer drugs. It is a very difficult task for image processing to isolate individual cells in confocal microscopic images of non-stained live cell cultures. Because these images do not have adequate textural variations. Manual cell segmentation requires massive labor and is a time consuming process. This paper describes an automated cell segmentation method for localizing the cells of Chinese hamster ovary cell culture. Several kinds of high-dimensional feature descriptors, K-means clustering method and Chan-Vese model-based level set are used to extract the cellular regions. The region extracted are used to classify phases in cell cycle. The segmentation results were experimentally assessed. As a result, the proposed method proved to be significant for cell isolation. In the evaluation experiments, we constructed a database of Chinese Hamster Ovary Cell’s microscopic images which includes various photographing environments under the guidance of a biologist.
基金Project supported by the National Natural Science Foundation of China.
文摘Hadamard transform spatial multiplexed imaging technique is combined with fluorescence microscope and an instrument of Hadamard transform microscope fluorescence image analysis is developed. Images acquired by this instrument can provide a lot of useful information simultaneously, including three-dimensional Hadamard transform microscope cell fluorescence image, the fluorescence intensity and fluorescence distribution of a cell, the background signal intensity and the signal/noise ratio, etc.
基金supported by the National Natural Science Foundation of China(Grant No.82220108007).
文摘Background With the gradual increase of infertility in the world,among which male sperm problems are the main factor for infertility,more and more couples are using computer-assisted sperm analysis(CASA)to assist in the analysis and treatment of infertility.Meanwhile,the rapid development of deep learning(DL)has led to strong results in image classification tasks.However,the classification of sperm images has not been well studied in current deep learning methods,and the sperm images are often affected by noise in practical CASA applications.The purpose of this article is to investigate the anti-noise robustness of deep learning classification methods applied on sperm images.Methods The SVIA dataset is a publicly available large-scale sperm dataset containing three subsets.In this work,we used subset-C,which provides more than 125,000 independent images of sperms and impurities,including 121,401 sperm images and 4,479 impurity images.To investigate the anti-noise robustness of deep learning classification methods applied on sperm images,we conducted a comprehensive comparative study of sperm images using many convolutional neural network(CNN)and visual transformer(VT)deep learning methods to find the deep learning model with the most stable anti-noise robustness.Results This study proved that VT had strong robustness for the classification of tiny object(sperm and impurity)image datasets under some types of conventional noise and some adversarial attacks.In particular,under the influence of Poisson noise,accuracy changed from 91.45%to 91.08%,impurity precison changed from 92.7%to 91.3%,impurity recall changed from 88.8%to 89.5%,and impurity F1-score changed 90.7%to 90.4%.Meanwhile,sperm precision changed from 90.9%to 90.5%,sperm recall changed from 92.5%to 93.8%,and sperm F1-score changed from 92.1%to 90.4%.Conclusion Sperm image classification may be strongly affected by noise in current deep learning methods;the robustness with regard to noise of VT methods based on global information is greater than that of CNN methods based on local information,indicating that the robustness with regard to noise is reflected mainly in global information.
文摘BACKGROUND Gastrointestinal bleeding(GIB)is a severe and potentially life-threatening condition,especially in cases of delayed treatment.Computed tomography angiography(CTA)plays a pivotal role in the early identification of upper and lower GIB and in the prompt treatment of the haemorrhage.AIM To determine whether a volumetric estimation of the extravasated contrast at CTA in GIB may be a predictor of subsequent positive angiographic findings.METHODS In this retrospective single-centre study,35 patients(22 men;median age 69 years;range 16-92 years)admitted to our institution for active GIB detected at CTA and further submitted to catheter angiography between January 2018 and February 2022 were enrolled.Twenty-three(65.7%)patients underwent endoscopy before CTA.Bleeding volumetry was evaluated in both arterial and venous phases via a semi-automated dedicated software.Bleeding rate was obtained from volume change between the two phases and standardised for unit time.Patients were divided into two groups,according to the angiographic signs and their concordance with CTA.RESULTS Upper bleeding accounted for 42.9%and lower GIB for 57.1%.Mean haemoglobin value at the admission was 7.7 g/dL.A concordance between positive CTA and direct angiographic bleeding signs was found in 19(54.3%)cases.Despite no significant differences in terms of bleeding volume in the arterial phase(0.55 mL vs 0.33 mL,P=0.35),a statistically significant volume increase in the venous phase was identified in the group of patients with positive angiography(2.06 mL vs 0.9 mL,P=0.02).In the latter patient group,a significant increase in bleeding rate was also detected(2.18 mL/min vs 0.19 mL/min,P=0.02).CONCLUSION In GIB of any origin,extravasated contrast volumetric analysis at CTA could be a predictor of positive angiography and may help in avoiding further unnecessary procedures.
基金This work has been done within the NFFA-EUROPE project and has received funding from the European Union’s Horizon 2020 Research and Innovation Program under grant agreement No.654360 NFFA-EUROPE.
文摘In this paper,we report upon our recent work aimed at improving and adapting machine learning algorithms to automatically classify nanoscience images acquired by the Scanning Electron Microscope(SEM).This is done by coupling supervised and unsupervised learning approaches.We first investigate supervised learning on a ten-category data set of images and compare the performance of the different models in terms of training accuracy.Then,we reduce the dimensionality of the features through autoencoders to perform unsupervised learning on a subset of images in a selected range of scales(from 1μm to 2μm).Finally,we compare different clustering methods to uncover intrinsic structures in the images.
文摘Colon cancer is the third most commonly diagnosed cancer in the world.Most colon AdenoCArcinoma(ACA)arises from pre-existing benign polyps in the mucosa of the bowel.Thus,detecting benign at the earliest helps reduce the mortality rate.In this work,a Predictive Modeling System(PMS)is developed for the classification of colon cancer using the Horizontal Voting Ensemble(HVE)method.Identifying different patterns inmicroscopic images is essential to an effective classification system.A twelve-layer deep learning architecture has been developed to extract these patterns.The developedHVE algorithm can increase the system’s performance according to the combined models from the last epochs of the proposed architecture.Ten thousand(10000)microscopic images are taken to test the classification performance of the proposed PMS with the HVE method.The microscopic images obtained from the colon tissues are classified intoACAor benign by the proposed PMS.Results prove that the proposed PMS has∼8%performance improvement over the architecture without using the HVE method.The proposed PMS for colon cancer reduces the misclassification rate and attains 99.2%of sensitivity and 99.4%of specificity.The overall accuracy of the proposed PMS is 99.3%,and without using the HVE method,it is only 91.3%.
