The precise detection and segmentation of tumor lesions are very important for lung cancer computer-aided diagnosis.However,in PET/CT(Positron Emission Tomography/Computed Tomography)lung images,the lesion shapes are ...The precise detection and segmentation of tumor lesions are very important for lung cancer computer-aided diagnosis.However,in PET/CT(Positron Emission Tomography/Computed Tomography)lung images,the lesion shapes are complex,the edges are blurred,and the sample numbers are unbalanced.To solve these problems,this paper proposes a Multi-branch Cross-scale Interactive Feature fusion Transformer model(MCIF-Transformer Mask RCNN)for PET/CT lung tumor instance segmentation,The main innovative works of this paper are as follows:Firstly,the ResNet-Transformer backbone network is used to extract global feature and local feature in lung images.The pixel dependence relationship is established in local and non-local fields to improve the model perception ability.Secondly,the Cross-scale Interactive Feature Enhancement auxiliary network is designed to provide the shallow features to the deep features,and the cross-scale interactive feature enhancement module(CIFEM)is used to enhance the attention ability of the fine-grained features.Thirdly,the Cross-scale Interactive Feature fusion FPN network(CIF-FPN)is constructed to realize bidirectional interactive fusion between deep features and shallow features,and the low-level features are enhanced in deep semantic features.Finally,4 ablation experiments,3 comparison experiments of detection,3 comparison experiments of segmentation and 6 comparison experiments with two-stage and single-stage instance segmentation networks are done on PET/CT lung medical image datasets.The results showed that APdet,APseg,ARdet and ARseg indexes are improved by 5.5%,5.15%,3.11%and 6.79%compared with Mask RCNN(resnet50).Based on the above research,the precise detection and segmentation of the lesion region are realized in this paper.This method has positive significance for the detection of lung tumors.展开更多
Aiming at the land cover (features) recognition of outdoor sports venues (football field, basketball court, tennis court and baseball field), this paper proposed a set of object recognition methods and technical flow ...Aiming at the land cover (features) recognition of outdoor sports venues (football field, basketball court, tennis court and baseball field), this paper proposed a set of object recognition methods and technical flow based on Mask R-CNN. Firstly, through the preprocessing of high spatial resolution remote sensing imagery (HSRRSI) and collecting the artificial samples of outdoor sports venues, the training data set required for object recognition of land cover features was constructed. Secondly, the Mask R-CNN was used as the basic training model to be adapted to cope with outdoor sports venues. Thirdly, the recognition results were compared with the four object-oriented machine learning classification methods in eCognition®. The experiment results of effectiveness verification show that the Mask R-CNN is superior to traditional methods not only in technical procedures but also in outdoor sports venues (football field, basketball court, tennis court and baseball field) recognition results, and it achieves the precision of 0.8927, a recall of 0.9356 and an average precision of 0.9235. Finally, from the aspect of practical engineering application, using and validating the well-trained model, an empirical application experiment was performed on the HSRRSI of Xicheng and Daxing District of Beijing respectively, and the generalization ability of the trained model of Mask R-CNN was thoroughly evaluated.展开更多
Nowadays, asphalt road has dominated highways around the world. Among various defects of asphalt road, crackshave been paid more attention, since cracks often cause major engineering and personnel safety incidents. Cu...Nowadays, asphalt road has dominated highways around the world. Among various defects of asphalt road, crackshave been paid more attention, since cracks often cause major engineering and personnel safety incidents. Currentmanual crack inspection methods are time-consuming and labor-intensive, and most segmentation methods cannot detect cracks at the pixel level. This paper proposes an intelligent segmentation and measurement model basedon the modified Mask R-CNN algorithm to automatically and accurately detect asphalt road cracks. The modelproposed in this paper mainly includes a convolutional neural network (CNN), an optimized region proposalnetwork (RPN), a region of interest (RoI) Align layer, a candidate area classification network and a Mask branch offully convolutional network (FCN). The ratio and size of anchors in the RPN are adjusted to improve the accuracyand efficiency of segmentation. Soft non-maximum suppression (Soft-NMS) algorithm is developed to improvethe segmentation accuracy. A dataset including 8,689 images (512× 512 pixels) of asphalt cracks is established andthe road crack is manually marked. Transfer learning is used to initialize the model parameters in the trainingprocess. To optimize the model training parameters, multiple comparison experiments are performed, and the testresults show that the mean average precision (mAP) value and F1-score of the optimal trained model are 0.952 and0.949. Subsequently, the robustness verification test and comparative test of the trained model are conducted andthe topological features of the crack are extracted. Then, the damage area, length and average width of the crackare measured automatically and accurately at pixel level. More importantly, this paper develops an automatic crackdetection platform for asphalt roads to automatically extract the number, area, length and average width of cracks,which can significantly improve the crack detection efficiency for the road maintenance industry.展开更多
基金funded by National Natural Science Foundation of China No.62062003Ningxia Natural Science Foundation Project No.2023AAC03293.
文摘The precise detection and segmentation of tumor lesions are very important for lung cancer computer-aided diagnosis.However,in PET/CT(Positron Emission Tomography/Computed Tomography)lung images,the lesion shapes are complex,the edges are blurred,and the sample numbers are unbalanced.To solve these problems,this paper proposes a Multi-branch Cross-scale Interactive Feature fusion Transformer model(MCIF-Transformer Mask RCNN)for PET/CT lung tumor instance segmentation,The main innovative works of this paper are as follows:Firstly,the ResNet-Transformer backbone network is used to extract global feature and local feature in lung images.The pixel dependence relationship is established in local and non-local fields to improve the model perception ability.Secondly,the Cross-scale Interactive Feature Enhancement auxiliary network is designed to provide the shallow features to the deep features,and the cross-scale interactive feature enhancement module(CIFEM)is used to enhance the attention ability of the fine-grained features.Thirdly,the Cross-scale Interactive Feature fusion FPN network(CIF-FPN)is constructed to realize bidirectional interactive fusion between deep features and shallow features,and the low-level features are enhanced in deep semantic features.Finally,4 ablation experiments,3 comparison experiments of detection,3 comparison experiments of segmentation and 6 comparison experiments with two-stage and single-stage instance segmentation networks are done on PET/CT lung medical image datasets.The results showed that APdet,APseg,ARdet and ARseg indexes are improved by 5.5%,5.15%,3.11%and 6.79%compared with Mask RCNN(resnet50).Based on the above research,the precise detection and segmentation of the lesion region are realized in this paper.This method has positive significance for the detection of lung tumors.
文摘Aiming at the land cover (features) recognition of outdoor sports venues (football field, basketball court, tennis court and baseball field), this paper proposed a set of object recognition methods and technical flow based on Mask R-CNN. Firstly, through the preprocessing of high spatial resolution remote sensing imagery (HSRRSI) and collecting the artificial samples of outdoor sports venues, the training data set required for object recognition of land cover features was constructed. Secondly, the Mask R-CNN was used as the basic training model to be adapted to cope with outdoor sports venues. Thirdly, the recognition results were compared with the four object-oriented machine learning classification methods in eCognition®. The experiment results of effectiveness verification show that the Mask R-CNN is superior to traditional methods not only in technical procedures but also in outdoor sports venues (football field, basketball court, tennis court and baseball field) recognition results, and it achieves the precision of 0.8927, a recall of 0.9356 and an average precision of 0.9235. Finally, from the aspect of practical engineering application, using and validating the well-trained model, an empirical application experiment was performed on the HSRRSI of Xicheng and Daxing District of Beijing respectively, and the generalization ability of the trained model of Mask R-CNN was thoroughly evaluated.
基金This research was funded by the National Key Research and Development Program of China(No.2017YFC1501204)the National Natural Science Foundation of China(No.51678536)+4 种基金the Guangdong Innovative and Entrepreneurial Research Team Program(2016ZT06N340)the Program for Science and Technology Innovation Talents in Universities of Henan Province(Grant No.19HASTIT043)the Outstanding Young Talent Research Fund of Zhengzhou University(1621323001)the Program for Innovative Research Team(in Science and Technology)in University of Henan Province(18IRTSTHN007)the Research on NonDestructive Testing(NDT)and Rapid Evaluation Technology for Grouting Quality of Prestressed Ducts(Contract No.HG-GCKY-01-002).The authors would like to thank for these financial supports.
文摘Nowadays, asphalt road has dominated highways around the world. Among various defects of asphalt road, crackshave been paid more attention, since cracks often cause major engineering and personnel safety incidents. Currentmanual crack inspection methods are time-consuming and labor-intensive, and most segmentation methods cannot detect cracks at the pixel level. This paper proposes an intelligent segmentation and measurement model basedon the modified Mask R-CNN algorithm to automatically and accurately detect asphalt road cracks. The modelproposed in this paper mainly includes a convolutional neural network (CNN), an optimized region proposalnetwork (RPN), a region of interest (RoI) Align layer, a candidate area classification network and a Mask branch offully convolutional network (FCN). The ratio and size of anchors in the RPN are adjusted to improve the accuracyand efficiency of segmentation. Soft non-maximum suppression (Soft-NMS) algorithm is developed to improvethe segmentation accuracy. A dataset including 8,689 images (512× 512 pixels) of asphalt cracks is established andthe road crack is manually marked. Transfer learning is used to initialize the model parameters in the trainingprocess. To optimize the model training parameters, multiple comparison experiments are performed, and the testresults show that the mean average precision (mAP) value and F1-score of the optimal trained model are 0.952 and0.949. Subsequently, the robustness verification test and comparative test of the trained model are conducted andthe topological features of the crack are extracted. Then, the damage area, length and average width of the crackare measured automatically and accurately at pixel level. More importantly, this paper develops an automatic crackdetection platform for asphalt roads to automatically extract the number, area, length and average width of cracks,which can significantly improve the crack detection efficiency for the road maintenance industry.
