Automated frame selection process for high-resolution microendoscopy
Automated frame selection process for high-resolution microendoscopy
复制标题
DOI：
10.1117/1.jbo.20.4.046014
复制
发表时间：
2015-04-01
影响因子：
3.5
通讯作者：
Richards-Kortum, Rebecca
中科院分区：
文献类型：
--
作者：
Ishijima, Ayumu;Schwarz, Richard A.;Richards-Kortum, Rebecca
我们开发了一种针对高分辨率显微内窥镜视频序列的自动帧选择算法。该算法从短视频序列中快速选择具有最小运动伪影的代表性帧，从而实现了在护理点处的全自动图像分析。通过定量比较自动帧选择和手动帧选择获得的诊断相关图像特征和诊断分类结果，对该算法进行了评估。分析中使用了由100个口腔部位和167个食道部位的活体视频序列组成的数据集。口腔部位受试者操作特征曲线下面积分别为0.78(自动选择)和0.82(手动选择)，食道部位分别为0.93(自动选择)和0.92(手动选择)。在护理地点实施全自动高分辨率显微内窥镜有可能减少在低资源环境下准确诊断癌症前期和癌症所需的活组织检查数量，因为标准组织学分析的基础设施和人员可能有限。(C)作者。由SPIE在知识共享署名3.0未移植许可下发布。
We developed an automated frame selection algorithm for high-resolution microendoscopy video sequences. The algorithm rapidly selects a representative frame with minimal motion artifact from a short video sequence, enabling fully automated image analysis at the point-of-care. The algorithm was evaluated by quantitative comparison of diagnostically relevant image features and diagnostic classification results obtained using automated frame selection versus manual frame selection. A data set consisting of video sequences collected in vivo from 100 oral sites and 167 esophageal sites was used in the analysis. The area under the receiver operating characteristic curve was 0.78 (automated selection) versus 0.82 (manual selection) for oral sites, and 0.93 (automated selection) versus 0.92 (manual selection) for esophageal sites. The implementation of fully automated high-resolution microendoscopy at the point-of-care has the potential to reduce the number of biopsies needed for accurate diagnosis of precancer and cancer in low-resource settings where there may be limited infrastructure and personnel for standard histologic analysis. (C) The Authors. Published by SPIE under a Creative Commons Attribution 3.0 Unported License.