X-ray computed tomography(CT)has been an important technology in paleontology for several decades.It helps researchers to acquire detailed anatomical structures of fossils non-destructively.Despite its widespread appl...X-ray computed tomography(CT)has been an important technology in paleontology for several decades.It helps researchers to acquire detailed anatomical structures of fossils non-destructively.Despite its widespread application,developing an efficient and user-friendly method for segmenting CT data continues to be a formidable challenge in the field.Most CT data segmentation software operates on 2D interfaces,which limits flexibility for real-time adjustments in 3D segmentation.Here,we introduce Curves Mode in Drishti Paint 3.2,an open-source tool for CT data segmentation.Drishti Paint 3.2 allows users to manually or semi-automatically segment the CT data in both 2D and 3D environments,providing a novel solution for revisualizing CT data in paleontological studies.展开更多
文摘X-ray computed tomography(CT)has been an important technology in paleontology for several decades.It helps researchers to acquire detailed anatomical structures of fossils non-destructively.Despite its widespread application,developing an efficient and user-friendly method for segmenting CT data continues to be a formidable challenge in the field.Most CT data segmentation software operates on 2D interfaces,which limits flexibility for real-time adjustments in 3D segmentation.Here,we introduce Curves Mode in Drishti Paint 3.2,an open-source tool for CT data segmentation.Drishti Paint 3.2 allows users to manually or semi-automatically segment the CT data in both 2D and 3D environments,providing a novel solution for revisualizing CT data in paleontological studies.
文摘目的:探讨机器学习结合CT影像组学特征构建模型预测2型糖尿病(type 2 diabetes mellitus,T2DM)患者椎体脆性骨折的准确性。方法:回顾性收集140例(新发椎体脆性骨折的T2DM患者70例,对照组70例)患者CT图像和临床资料。另收集18例(椎体脆性骨折的T2DM患者16例,对照组2例)患者的前次CT图像和临床资料作为外部验证集。应用单因素分析、Pearson相关分析、最小冗余度最大相关度算法、二元logistic回归分析和最小绝对值收缩和选择算子模型筛选出最佳特征。基于支持向量机、多层感知器、极端梯度提升(eXtreme Gradient Boosting,XGBoost)构建预测模型。应用受试者工作特征曲线下面积(area under the curve,AUC)对模型效能进行评估。结果:从每例患者的CT图像中提取了1037个影像组学特征,然后精简为14个影像组学特征。17个临床特征中性别、年龄、体质指数是预测结果的独立因素。其中XGBoost分类器表现最好,训练集中XGBoost模型的AUC分别为1.000、0.929、1.000;测试集中分别为0.954、0.862、0.969。结论:基于临床及影像组学特征构建的XGBoost模型可作为预测T2DM患者椎体脆性骨折的一种无创性辅助工具。
