The potential of improving disease detection and treatment planning comes with accurate and fully automatic algorithms for brain tumor segmentation.Glioma, a type of brain tumor, can appear at different locations with...The potential of improving disease detection and treatment planning comes with accurate and fully automatic algorithms for brain tumor segmentation.Glioma, a type of brain tumor, can appear at different locations with different shapes and sizes. Manual segmentation of brain tumor regions is not only timeconsuming but also prone to human error, and its performance depends on pathologists’ experience. In this paper, we tackle this problem by applying a fully convolutional neural network SegNet to 3 D data sets for four MRI modalities(Flair, T1, T1 ce, and T2)for automated segmentation of brain tumor and subtumor parts, including necrosis, edema, and enhancing tumor. To further improve tumor segmentation, the four separately trained SegNet models are integrated by post-processing to produce four maximum feature maps by fusing the machine-learned feature maps from the fully convolutional layers of each trained model. The maximum feature maps and the pixel intensity values of the original MRI modalities are combined to encode interesting information into a feature representation.Taking the combined feature as input, a decision tree(DT) is used to classify the MRI voxels into different tumor parts and healthy brain tissue. Evaluating the proposed algorithm on the dataset provided by the Brain Tumor Segmentation 2017(BraTS 2017)challenge, we achieved F-measure scores of 0.85, 0.81,and 0.79 for whole tumor, tumor core, and enhancing tumor, respectively.Experimental results demonstrate that using SegNet models with 3 D MRI datasets and integrating the four maximum feature maps with pixel intensity values of the original MRI modalities has potential to perform well on brain tumor segmentation.展开更多
The segmentation of brain tumor plays an important role in diagnosis, treatment planning, and surgical simulation. The precise segmentation of brain tumor can help clinicians obtain its location, size, and shape infor...The segmentation of brain tumor plays an important role in diagnosis, treatment planning, and surgical simulation. The precise segmentation of brain tumor can help clinicians obtain its location, size, and shape information. We propose a fully automatic brain tumor segmentation method based on kernel sparse coding. It is validated with 3D multiple-modality magnetic resonance imaging(MRI). In this method, MRI images are pre-processed first to reduce the noise, and then kernel dictionary learning is used to extract the nonlinear features to construct five adaptive dictionaries for healthy tissues, necrosis, edema, non-enhancing tumor, and enhancing tumor tissues. Sparse coding is performed on the feature vectors extracted from the original MRI images, which are a patch of m×m×m around the voxel. A kernel-clustering algorithm based on dictionary learning is developed to code the voxels. In the end, morphological filtering is used to fill in the area among multiple connected components to improve the segmentation quality. To assess the segmentation performance, the segmentation results are uploaded to the online evaluation system where the evaluation metrics dice score, positive predictive value(PPV), sensitivity, and kappa are used. The results demonstrate that the proposed method has good performance on the complete tumor region(dice: 0.83; PPV: 0.84; sensitivity: 0.82), while slightly worse performance on the tumor core(dice: 0.69; PPV: 0.76; sensitivity: 0.80) and enhancing tumor(dice: 0.58; PPV: 0.60; sensitivity: 0.65). It is competitive to the other groups in the brain tumor segmentation challenge. Therefore, it is a potential method in differentiation of healthy and pathological tissues.展开更多
The semantic segmentation of a brain tumor is the essential stage in medical treatment planning. Due to the different characteristics of tumors, one of the main difficulties in image segmentation is the severe imbalan...The semantic segmentation of a brain tumor is the essential stage in medical treatment planning. Due to the different characteristics of tumors, one of the main difficulties in image segmentation is the severe imbalance between classes. Also, a dataset with imbalanced classes is a common problem in multimodal 3D brain MRIs. Despite these problems, most studies in brain tumor segmentation are biased toward the overrepresented tumor class (majority class) and ignore the small size tumor class (minority class). In this paper, we propose an improved loss function Weighted Focal Loss (WFL), based on 3D U-Net to enhance the prediction of brain tumor segmentation. Using our proposed loss function (WFL) solves the imbalance between classes and the imbalance between weights by giving higher weights to the minority and lower weights to the majority. After assigning these weights to different pixel values, our work is able to resolve pixel degradation, which is one of the limitations of the loss function during model training. Based on our experiments, the proposed function (WFL) on the 3D U-Net model for high-grade glioma (HGG) and low-grade glioma (LGG) in the Brain Tumor Segmentation Challenge (BraTS) 2019 dataset has shown promising results for tumor core (TC), whole tumor (WT) and enhanced tumor (ET) with average dice scores of HGG: 0.830, 0.913, 0.815 and Dice scores of LGG for TC: 0.731, WT: 0.775 and ET: 0.685. Moreover, we deployed our training on BraTS 2020 in which we obtained mean Dice scores of HGG: TC: 0.843, WT: 0.892, ET: 0.871 and Dice scores of LGG: 0.7501, 0.7985, 0.6103 for TC, WT and ET, respectively.展开更多
Background Brain tumor segmentation from magnetic resonance imaging （MRI） is an important step toward surgical planning,treatment planning,monitoring of therapy.However,manual tumor segmentation commonly used in cli...Background Brain tumor segmentation from magnetic resonance imaging （MRI） is an important step toward surgical planning,treatment planning,monitoring of therapy.However,manual tumor segmentation commonly used in clinic is time-consuming and challenging,and none of the existed automated methods are highly robust,reliable and efficient in clinic application.An accurate and automated tumor segmentation method has been developed for brain tumor segmentation that will provide reproducible and objective results close to manual segmentation results.Methods Based on the symmetry of human brain,we employed sliding-window technique and correlation coefficient to locate the tumor position.At first,the image to be segmented was normalized,rotated,denoised,and bisected.Subsequently,through vertical and horizontal sliding-windows technique in turn,that is,two windows in the left and the right part of brain image moving simultaneously pixel by pixel in two parts of brain image,along with calculating of correlation coefficient of two windows,two windows with minimal correlation coefficient were obtained,and the window with bigger average gray value is the location of tumor and the pixel with biggest gray value is the locating point of tumor.At last,the segmentation threshold was decided by the average gray value of the pixels in the square with center at the locating point and 10 pixels of side length,and threshold segmentation and morphological operations were used to acquire the final tumor region.Results The method was evaluated on 3D FSPGR brain MR images of 10 patients.As a result,the average ratio of correct location was 93.4％ for 575 slices containing tumor,the average Dice similarity coefficient was 0.77 for one scan,and the average time spent on one scan was 40 seconds.Conclusions An fully automated,simple and efficient segmentation method for brain tumor is proposed and promising for future clinic use.Correlation coefficient is a new and effective feature for tumor location.展开更多
文摘The potential of improving disease detection and treatment planning comes with accurate and fully automatic algorithms for brain tumor segmentation.Glioma, a type of brain tumor, can appear at different locations with different shapes and sizes. Manual segmentation of brain tumor regions is not only timeconsuming but also prone to human error, and its performance depends on pathologists’ experience. In this paper, we tackle this problem by applying a fully convolutional neural network SegNet to 3 D data sets for four MRI modalities(Flair, T1, T1 ce, and T2)for automated segmentation of brain tumor and subtumor parts, including necrosis, edema, and enhancing tumor. To further improve tumor segmentation, the four separately trained SegNet models are integrated by post-processing to produce four maximum feature maps by fusing the machine-learned feature maps from the fully convolutional layers of each trained model. The maximum feature maps and the pixel intensity values of the original MRI modalities are combined to encode interesting information into a feature representation.Taking the combined feature as input, a decision tree(DT) is used to classify the MRI voxels into different tumor parts and healthy brain tissue. Evaluating the proposed algorithm on the dataset provided by the Brain Tumor Segmentation 2017(BraTS 2017)challenge, we achieved F-measure scores of 0.85, 0.81,and 0.79 for whole tumor, tumor core, and enhancing tumor, respectively.Experimental results demonstrate that using SegNet models with 3 D MRI datasets and integrating the four maximum feature maps with pixel intensity values of the original MRI modalities has potential to perform well on brain tumor segmentation.
基金Project supported by the National Natural Science Foundation of China(No.31200746)the Zhejiang Provincial Key Research and Development Plan,China(No.2015C03023)the‘521’Talent Project of ZSTU,China
文摘The segmentation of brain tumor plays an important role in diagnosis, treatment planning, and surgical simulation. The precise segmentation of brain tumor can help clinicians obtain its location, size, and shape information. We propose a fully automatic brain tumor segmentation method based on kernel sparse coding. It is validated with 3D multiple-modality magnetic resonance imaging(MRI). In this method, MRI images are pre-processed first to reduce the noise, and then kernel dictionary learning is used to extract the nonlinear features to construct five adaptive dictionaries for healthy tissues, necrosis, edema, non-enhancing tumor, and enhancing tumor tissues. Sparse coding is performed on the feature vectors extracted from the original MRI images, which are a patch of m×m×m around the voxel. A kernel-clustering algorithm based on dictionary learning is developed to code the voxels. In the end, morphological filtering is used to fill in the area among multiple connected components to improve the segmentation quality. To assess the segmentation performance, the segmentation results are uploaded to the online evaluation system where the evaluation metrics dice score, positive predictive value(PPV), sensitivity, and kappa are used. The results demonstrate that the proposed method has good performance on the complete tumor region(dice: 0.83; PPV: 0.84; sensitivity: 0.82), while slightly worse performance on the tumor core(dice: 0.69; PPV: 0.76; sensitivity: 0.80) and enhancing tumor(dice: 0.58; PPV: 0.60; sensitivity: 0.65). It is competitive to the other groups in the brain tumor segmentation challenge. Therefore, it is a potential method in differentiation of healthy and pathological tissues.
文摘The semantic segmentation of a brain tumor is the essential stage in medical treatment planning. Due to the different characteristics of tumors, one of the main difficulties in image segmentation is the severe imbalance between classes. Also, a dataset with imbalanced classes is a common problem in multimodal 3D brain MRIs. Despite these problems, most studies in brain tumor segmentation are biased toward the overrepresented tumor class (majority class) and ignore the small size tumor class (minority class). In this paper, we propose an improved loss function Weighted Focal Loss (WFL), based on 3D U-Net to enhance the prediction of brain tumor segmentation. Using our proposed loss function (WFL) solves the imbalance between classes and the imbalance between weights by giving higher weights to the minority and lower weights to the majority. After assigning these weights to different pixel values, our work is able to resolve pixel degradation, which is one of the limitations of the loss function during model training. Based on our experiments, the proposed function (WFL) on the 3D U-Net model for high-grade glioma (HGG) and low-grade glioma (LGG) in the Brain Tumor Segmentation Challenge (BraTS) 2019 dataset has shown promising results for tumor core (TC), whole tumor (WT) and enhanced tumor (ET) with average dice scores of HGG: 0.830, 0.913, 0.815 and Dice scores of LGG for TC: 0.731, WT: 0.775 and ET: 0.685. Moreover, we deployed our training on BraTS 2020 in which we obtained mean Dice scores of HGG: TC: 0.843, WT: 0.892, ET: 0.871 and Dice scores of LGG: 0.7501, 0.7985, 0.6103 for TC, WT and ET, respectively.
文摘Background Brain tumor segmentation from magnetic resonance imaging （MRI） is an important step toward surgical planning,treatment planning,monitoring of therapy.However,manual tumor segmentation commonly used in clinic is time-consuming and challenging,and none of the existed automated methods are highly robust,reliable and efficient in clinic application.An accurate and automated tumor segmentation method has been developed for brain tumor segmentation that will provide reproducible and objective results close to manual segmentation results.Methods Based on the symmetry of human brain,we employed sliding-window technique and correlation coefficient to locate the tumor position.At first,the image to be segmented was normalized,rotated,denoised,and bisected.Subsequently,through vertical and horizontal sliding-windows technique in turn,that is,two windows in the left and the right part of brain image moving simultaneously pixel by pixel in two parts of brain image,along with calculating of correlation coefficient of two windows,two windows with minimal correlation coefficient were obtained,and the window with bigger average gray value is the location of tumor and the pixel with biggest gray value is the locating point of tumor.At last,the segmentation threshold was decided by the average gray value of the pixels in the square with center at the locating point and 10 pixels of side length,and threshold segmentation and morphological operations were used to acquire the final tumor region.Results The method was evaluated on 3D FSPGR brain MR images of 10 patients.As a result,the average ratio of correct location was 93.4％ for 575 slices containing tumor,the average Dice similarity coefficient was 0.77 for one scan,and the average time spent on one scan was 40 seconds.Conclusions An fully automated,simple and efficient segmentation method for brain tumor is proposed and promising for future clinic use.Correlation coefficient is a new and effective feature for tumor location.
