目的:运用强化学习!多分类器集成!降维方法等最新计算机技术,结合细胞病理知识,设计制作/智能化肺癌细胞病理图像诊断系统0"方法:采集细胞图像,运用基于强化学习的图像分割法将细胞区域从背景中分离出来 运用基于样条和改进2方法对重叠细胞进行分离和重构 提取40个细胞特征用于贝叶斯!支持向量机!紧邻和决策树4种分类器,集成产生肺癌细胞分类结果 建立肺癌细胞病理图库,运用基于等降维方法对细胞进行比对,给予未定型癌细胞分类"结果:/智能化肺癌细胞病理诊断系统0应用于临床随机1200例肺部病灶穿刺细胞学涂片,肺癌识别诊断率94180 ,假阳性率1185 ,假阴性率3135 ,肺癌分类识别率82190 ,核异型细胞识别率74120 "结论:/智能化肺癌早期细胞病理诊断系统0对肺癌细胞涂片诊断率高,克服了肺癌细胞病理诊断过程中取检细胞数量少,重叠细胞识别率低,涂片背景及染色差异等干扰因素,可辅助临床肺部病灶的穿刺细胞病理诊断"-Objective Design and develop a intelligent cytopathological lung cancer diagnosing system(ICLCDS)　utilizing the latest computer technologies(including Reinforcement Lcaming　Multiple Classifier Fusion and Dimcnsionality Reduction)　and the cy-topathological knowledge on lung canccrcclls Methods We got information ofcclls and segregated cell regions in a slice image using an magi scgmcntouon a址orithm Sascd on　reinforcement lcaming　 including rcconstmction of overlapped cell area Sascd on B一Spline and improved dcBoor-Cox Mcthoc}　We comSincd multiple classifiers　 including Baycsian classific:Support Vector Machine(SVM)

classific　 K-Ncarcst NcighSour( KNN)　and Decision c classific　 to achieve an accurate result of cytopathological lung cancer diag-nosis Results Experimental results on 1 200 cases randomly selected we as follows　the accurate diagnosis rate for lung cancer idcn-tification was the false positive rate was 1. 8`J /c‘the false negative rate was 3. 3`J /c‘the type class相关搜索： lung
cancer
cancer
采集
lung
KNN
classifier
分类
knn
and
svm
强化学习
图像
分割
Cancer
using
SVM
in
matlab