Quantitative analysis ofex vivocolorectal epithelium using an automated feature extraction algorithm for microendoscopy image data

Abstract

Quantitative analysis of ex vivo colorectal epithelium using an automated feature extraction algorithm for microendoscopy image data," J. Med. Imag. 3(2), 024502 (2016), doi: 10.1117/1.JMI.3.2.024502. Abstract. Qualitative screening for colorectal polyps via fiber bundle microendoscopy imaging has shown promising results, with studies reporting high rates of sensitivity and specificity, as well as low interobserver variability with trained clinicians. A quantitative image quality control and image feature extraction algorithm (QFEA) was designed to lessen the burden of training and provide objective data for improved clinical efficacy of this method. After a quantitative image quality control step, QFEA extracts field-of-view area, crypt area, crypt circularity, and crypt number per image. To develop and validate this QFEA, a training set of microendoscopy images was collected from freshly resected porcine colon epithelium. The algorithm was then further validated on ex vivo image data collected from eight human subjects, selected from clinically normal appearing regions distant from grossly visible tumor in surgically resected colorectal tissue. QFEA has proven flexible in application to both mosaics and individual images, and its automated crypt detection sensitivity ranges from 71 to 94% despite intensity and contrast variation within the field of view. It also demonstrates the ability to detect and quantify differences in grossly normal regions among different subjects, suggesting the potential efficacy of this approach in detecting occult regions of dysplasia.

Fluorescein as a topical fluorescent contrast agent for quantitative microendoscopic inspection of colorectal epithelium

“…The microendoscopy system has been previously described [6,29], and consists of a 455nm LED (Philips, USA), a filter set (Chroma Tech, USA), monochrome camera (Flea 3, USB 3.0, Point Grey Research Inc., CA), a 10x objective (NA 0.25, Olympus, Japan), and a fiber bundle image guide comprised of 50,000 fibers with 3.5µm center to center spacing (FIGH-50-1100N fiber, Myriad Fiber Imaging Tech, Inc., USA) with customized ends. The distal end has a modified SMA connector with rounded edges, to reduce the risk of tissue tearing as well as protect the fiber from chipping.…”

“…Proflavine hemisulfate was prepared at a concentration of 0.01% (w/v) in 1x phosphate buffered saline (PBS) [29]. Fluorescein salt solution was prepared at 0.05% (w/v) in 1x PBS.…”

“…We have previously developed a custom image feature quantification algorithm (QFEA) for automated crypt detection and quantification of crypt morphology in microendoscopic images of proflavine-stained colorectal tissue [29]. This algorithm was designed to detect, segment, and quantify area and circularity of crypt shapes in microendoscopic images, and calculated automated crypt detection sensitivity at the crypt level by comparing if the algorithm detected a crypt at the position that the trained observer visually detected a crypt [29].…”

“…This algorithm was designed to detect, segment, and quantify area and circularity of crypt shapes in microendoscopic images, and calculated automated crypt detection sensitivity at the crypt level by comparing if the algorithm detected a crypt at the position that the trained observer visually detected a crypt [29]. We have optimized this algorithm for images of fluorescein-stained colorectal tissue, and compared the crypt detection sensitivity of the algorithm for proflavine versus fluorescein-stained epithelium, as described below.…”

“…Automated image analysis provides an objective, replicable output to lessen the burden of training for clinicians. Our previous work has shown that the automated detection sensitivity of crypt structures in images of proflavine-stained colorectal epithelium using a custom algorithm ranges from 71 to 94% [29]. In addition, preliminary quantification of crypt area and circularity suggest that crypt quantification may provide an unbiased metric for aiding clinicians using fluorescence microendoscopy systems [26,30].…”