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
Objective:The image data of intracerebral hematoma in hypertensive intracerebral hemorrhage(HICH)patients were obtained by three-dimensional(3D)spiral computed tomography(CT)scan in this study to provide a basis for c...Objective:The image data of intracerebral hematoma in hypertensive intracerebral hemorrhage(HICH)patients were obtained by three-dimensional(3D)spiral computed tomography(CT)scan in this study to provide a basis for clinical minimally invasive surgery and the development and research of related surgical instruments.Methods:From June 2020 to March 2022,33 patients with supratentorial HICH admitted to the Department of Neurosurgery,the First Affiliated Hospital,Zhejiang University,School of Medicine were selected.All patients underwent 3D spiral CT scanning.Multiplanar reconstruction(MPR)was used to reconstruct along any plane to obtain coronal,sagittal,cross-sectional,or arbitrary angle reconstructed images.Then,we observed and measured relevant data indicators on these three planes by measuring tools.Results:All hemorrhage sites of these 33 HICH patients were basal ganglia hemorrhage,including left basal ganglia hemorrhage in 13 cases and right basal ganglia hemorrhage in 20 cases.It was also found that basal ganglia hematomas were usually elliptical,and the anteroposterior diameter was significantly larger than the transverse diameter,almost twice the size of the transverse diameter[(62±10)mm vs.(35±9)mm,P<0.05].Although the depth of the hematoma on the transfrontal(sagittal)approach was significantly greater than that on the transtemporal(transverse)approach[(100±15)mm vs.(59±14)mm,P<0.05],the angle of the hematoma on the transfrontal approach was significantly smaller than that on the transtemporal approach[(37±11)°vs.(70±17)°,P<0.05],which was conducive to improving the clearance rate of the hematoma.Conclusion:During neuroendoscopic surgery for HICH patients,different lengths of the tubular port should be selected according to the transfrontal or transtemporal surgical approach to meet the needs of hematoma removal.展开更多
基金This work was supported by the National Natural Science Foundation of China （No.20673107）, the National Key Basic Research Special Foundation of China （No.2007CB815203）, and the Knowledge Innovation Foundation of the Chinese Academy of Science （No.KJCX2-SW-H08）.
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.
基金This work was supported by the Project of Zhejiang Medical Science and Technology Plan[2020PY044].
文摘Objective:The image data of intracerebral hematoma in hypertensive intracerebral hemorrhage(HICH)patients were obtained by three-dimensional(3D)spiral computed tomography(CT)scan in this study to provide a basis for clinical minimally invasive surgery and the development and research of related surgical instruments.Methods:From June 2020 to March 2022,33 patients with supratentorial HICH admitted to the Department of Neurosurgery,the First Affiliated Hospital,Zhejiang University,School of Medicine were selected.All patients underwent 3D spiral CT scanning.Multiplanar reconstruction(MPR)was used to reconstruct along any plane to obtain coronal,sagittal,cross-sectional,or arbitrary angle reconstructed images.Then,we observed and measured relevant data indicators on these three planes by measuring tools.Results:All hemorrhage sites of these 33 HICH patients were basal ganglia hemorrhage,including left basal ganglia hemorrhage in 13 cases and right basal ganglia hemorrhage in 20 cases.It was also found that basal ganglia hematomas were usually elliptical,and the anteroposterior diameter was significantly larger than the transverse diameter,almost twice the size of the transverse diameter[(62±10)mm vs.(35±9)mm,P<0.05].Although the depth of the hematoma on the transfrontal(sagittal)approach was significantly greater than that on the transtemporal(transverse)approach[(100±15)mm vs.(59±14)mm,P<0.05],the angle of the hematoma on the transfrontal approach was significantly smaller than that on the transtemporal approach[(37±11)°vs.(70±17)°,P<0.05],which was conducive to improving the clearance rate of the hematoma.Conclusion:During neuroendoscopic surgery for HICH patients,different lengths of the tubular port should be selected according to the transfrontal or transtemporal surgical approach to meet the needs of hematoma removal.
