Unknown

Dataset Information

0

Automated frame selection process for high-resolution microendoscopy.


ABSTRACT: 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.

SUBMITTER: Ishijima A 

PROVIDER: S-EPMC4412137 | biostudies-literature | 2015 Apr

REPOSITORIES: biostudies-literature

altmetric image

Publications

Automated frame selection process for high-resolution microendoscopy.

Ishijima Ayumu A   Schwarz Richard A RA   Shin Dongsuk D   Mondrik Sharon S   Vigneswaran Nadarajah N   Gillenwater Ann M AM   Anandasabapathy Sharmila S   Richards-Kortum Rebecca R  

Journal of biomedical optics 20150401 4


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 consi  ...[more]

Similar Datasets

| S-EPMC10721617 | biostudies-literature
| S-EPMC4504008 | biostudies-literature
| S-EPMC2795438 | biostudies-literature
| S-EPMC5836883 | biostudies-literature
| S-EPMC4547689 | biostudies-literature
| S-EPMC5658369 | biostudies-literature
| S-EPMC3065245 | biostudies-literature
| S-EPMC4767323 | biostudies-literature
| S-EPMC3494281 | biostudies-literature
| S-EPMC5381332 | biostudies-literature