首页> 外文会议>Machine learning in medical imaging >Computer-Aided Detection of Polyps in CT Colonography with Pixel-Based Machine Learning Techniques

【24h】

Computer-Aided Detection of Polyps in CT Colonography with Pixel-Based Machine Learning Techniques

机译：基于像素的机器学习技术在计算机辅助结肠镜中息肉的计算机辅助检测

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

Pixel/voxel-based machine-learning techniques have been developed for classification between polyp regions of interest (ROIs) and non-polyp ROIs in computer-aided detection (CADe) of polyps in CT colonography (CTC). Although 2D/3D ROIs can be high-dimensional, they may reside in a lower dimensional manifold. We investigated the manifold structure of 2D CTC ROIs by use of the Laplacian eigenmaps technique. We compared a support vector machine (SVM) classifier with the Laplacian eigenmaps-based dimensionality-reduced ROIs with massive-training support vector regression (MTSVR) in reduction of false positive (FP) detections. The Laplacian eigenmaps-based SVM classifier removed 16.0% (78/489) of FPs without any loss of polyps in a leave-one-lesion-out cross-validation test, whereas the MTSVR removed 49.9% (244/489); thus, yielded a 96.6% by-polyp sensitivity at an FP rate of 2.4 (254/106) per patient.

机译：已经开发了基于像素/体素的机器学习技术，用于在计算机结肠成像（CTC）息肉的计算机辅助检测（CADe）中对息肉感兴趣区域（ROI）和非息肉ROI之间进行分类。尽管2D / 3D ROI可以是高维的，但它们可以驻留在较低维的流形中。我们使用拉普拉斯特征图技术研究了二维CTC ROI的流形结构。我们将支持向量机（SVM）分类器与基于Laplacian特征图的降维ROI与大规模训练支持向量回归（MTSVR）进行了比较，以减少假阳性（FP）检测。基于Laplacian特征图的SVM分类器在留一病灶交叉验证测试中去除了16.0％（78/489）的FP，而息肉没有任何损失，而MTSVR去除了49.9％（244/489）。因此，每位患者的FP率为2.4（254/106），息肉敏感性为96.6％。

著录项

来源
《Machine learning in medical imaging》|2011年|p.360-367|共8页
会议地点 Toronto(CA);Toronto(CA);Toronto(CA);Toronto(CA)
作者
Jian-Wu Xu; Kenji Suzuki;
展开▼
作者单位

Department of Radiology, The University of Chicago 5841 South Maryland Avenue, Chicago, IL 60637;

Department of Radiology, The University of Chicago 5841 South Maryland Avenue, Chicago, IL 60637;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类医用物理学;
关键词
colorectal cancer; computer-aided detection; manifold learning; pixel-based machine learning; support vector machines;

机译：大肠癌；计算机辅助检测；综合学习；基于像素的机器学习；支持向量机;

相似文献

外文文献
中文文献
专利

1. Adaptive kernel based multiple kernel learning for computer-aided polyp detection in CT colonography [J] . Ming Ma, Lihong Li, Hao Han, Geometry, Imaging and Computing . 2015,第1期

机译：基于自适应核的多核学习技术在CT结肠造影中进行计算机辅助息肉检测
2. CT colonography: Effect of computer-aided detection of colonic polyps as a second and concurrent reader for general radiologists with moderate experience in CT colonography [J] . MangT., BogoniL., AnandV.X., European radiology . 2014,第7期

机译：CT结肠造影：计算机辅助检测结肠息肉的效果，作为对具有CT结肠造影中度经验的普通放射科医生的辅助阅读器
3. CT colonography computer-aided polyp detection: Effect on radiologist observers of polyp identification by CAD on both the supine and prone scans. [J] . Summers RM, Liu J, Rehani B, Academic radiology . 2010,第8期

机译：CT结肠造影计算机辅助息肉检测：仰卧和俯卧扫描对CAD识别息肉的放射学观察者的影响。
4. Computer-Aided Detection of Polyps in CT Colonography with Pixel-Based Machine Learning Techniques [C] . Jian-Wu Xu, Kenji Suzuki International Workshop on Machine Learning in Medical Imaging . 2011

机译：基于像素的机器学习技术的CT主影中息肉的计算机辅助检测
5. Solar activity detection and prediction using image processing and machine learning techniques [D] . Fu, Gang 2007

机译：利用图像处理和机器学习技术进行太阳活动检测和预测
6. CT Colonography Computer-Aided Polyp Detection: Effect on Radiologist Observers of Polyp Identification by CAD on Both the Supine and Prone Scans [O] . Ronald M. Summers, Jiamin Liu, Bhavya Rehani, -1

机译：CT上校生计算机辅助息肉检测：对仰卧和俯卧扫描的CAD对息肉识别的放射科医师观察者的影响
7. CT colonography: Advanced computer-aided detection scheme utilizing MTANNs for detection of “missed” polyps in a multicenter clinical trial [O] . Suzuki, Kenji, Rockey, Don C., Dachman, Abraham H. 2009

机译：CT结肠造影：在多中心临床试验中，利用MTANN进行计算机辅助检测的先进方案，用于检测“缺失”息肉

Computer-Aided Detection of Polyps in CT Colonography with Pixel-Based Machine Learning Techniques

摘要

著录项

相似文献

相关主题

期刊订阅