Informative frame classification for endoscopy video

JungHwan Oh, Sae Hwang, JeongKyu Lee, Wallapak Tavanapong, Johnny Wong, Piet C. de Groen

Research output: Contribution to journalArticle

66 Citations (Scopus)

Abstract

Advances in video technology allow inspection, diagnosis and treatment of the inside of the human body without or with very small scars. Flexible endoscopes are used to inspect the esophagus, stomach, small bowel, colon, and airways, whereas rigid endoscopes are used for a variety of minimal invasive surgeries (i.e., laparoscopy, arthroscopy, endoscopic neurosurgery). These endoscopes come in various sizes, but all have a tiny video camera at the tip. During an endoscopic procedure, the tiny video camera generates a video signal of the interior of the human organ, which is displayed on a monitor for real-time analysis by the physician. However, many out-of-focus frames are present in endoscopy videos because current endoscopes are equipped with a single, wide-angle lens that cannot be focused. We need to distinguish the out-of-focus frames from the in-focus frames to utilize the information of the out-of-focus and/or the in-focus frames for further automatic or semi-automatic computer-aided diagnosis (CAD). This classification can reduce the number of images to be viewed by a physician and to be analyzed by a CAD system. We call an out-of-focus frame a non-informative frame and an in-focus frame an informative frame. The out-of-focus frames have characteristics that are different from those of in-focus frames. In this paper, we propose two new techniques (edge-based and clustering-based) to classify video frames into two classes, informative and non-informative frames. However, because intensive specular reflections reduce the accuracy of the classification we also propose a specular reflection detection technique, and use the detected specular reflection information to increase the accuracy of informative frame classification. Our experimental studies indicate that precision, sensitivity, specificity, and accuracy for the specular reflection detection technique and the two informative frame classification techniques are greater than 90% and 95%, respectively.

Original languageEnglish (US)
Pages (from-to)110-127
Number of pages18
JournalMedical Image Analysis
Volume11
Issue number2
DOIs
StatePublished - Apr 2007

Fingerprint

Endoscopy
Endoscopes
Computer aided diagnosis
Video cameras
Physicians
Laparoscopy
Arthroscopy
Neurosurgery
Human Body
Lenses
Esophagus
Cicatrix
Cluster Analysis
Stomach
Colon
Surgery
Technology
Sensitivity and Specificity
Inspection
Therapeutics

Keywords

  • Clustering
  • Colonoscopy
  • Endoscopy
  • Frame classification
  • Specular reflection detection
  • Texture

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging
  • Medicine (miscellaneous)
  • Computer Science (miscellaneous)

Cite this

Oh, J., Hwang, S., Lee, J., Tavanapong, W., Wong, J., & de Groen, P. C. (2007). Informative frame classification for endoscopy video. Medical Image Analysis, 11(2), 110-127. https://doi.org/10.1016/j.media.2006.10.003

Informative frame classification for endoscopy video. / Oh, JungHwan; Hwang, Sae; Lee, JeongKyu; Tavanapong, Wallapak; Wong, Johnny; de Groen, Piet C.

In: Medical Image Analysis, Vol. 11, No. 2, 04.2007, p. 110-127.

Research output: Contribution to journalArticle

Oh, J, Hwang, S, Lee, J, Tavanapong, W, Wong, J & de Groen, PC 2007, 'Informative frame classification for endoscopy video', Medical Image Analysis, vol. 11, no. 2, pp. 110-127. https://doi.org/10.1016/j.media.2006.10.003
Oh J, Hwang S, Lee J, Tavanapong W, Wong J, de Groen PC. Informative frame classification for endoscopy video. Medical Image Analysis. 2007 Apr;11(2):110-127. https://doi.org/10.1016/j.media.2006.10.003
Oh, JungHwan ; Hwang, Sae ; Lee, JeongKyu ; Tavanapong, Wallapak ; Wong, Johnny ; de Groen, Piet C. / Informative frame classification for endoscopy video. In: Medical Image Analysis. 2007 ; Vol. 11, No. 2. pp. 110-127.
@article{567de4e062a843e6ae5df63a4f9e3e82,
title = "Informative frame classification for endoscopy video",
abstract = "Advances in video technology allow inspection, diagnosis and treatment of the inside of the human body without or with very small scars. Flexible endoscopes are used to inspect the esophagus, stomach, small bowel, colon, and airways, whereas rigid endoscopes are used for a variety of minimal invasive surgeries (i.e., laparoscopy, arthroscopy, endoscopic neurosurgery). These endoscopes come in various sizes, but all have a tiny video camera at the tip. During an endoscopic procedure, the tiny video camera generates a video signal of the interior of the human organ, which is displayed on a monitor for real-time analysis by the physician. However, many out-of-focus frames are present in endoscopy videos because current endoscopes are equipped with a single, wide-angle lens that cannot be focused. We need to distinguish the out-of-focus frames from the in-focus frames to utilize the information of the out-of-focus and/or the in-focus frames for further automatic or semi-automatic computer-aided diagnosis (CAD). This classification can reduce the number of images to be viewed by a physician and to be analyzed by a CAD system. We call an out-of-focus frame a non-informative frame and an in-focus frame an informative frame. The out-of-focus frames have characteristics that are different from those of in-focus frames. In this paper, we propose two new techniques (edge-based and clustering-based) to classify video frames into two classes, informative and non-informative frames. However, because intensive specular reflections reduce the accuracy of the classification we also propose a specular reflection detection technique, and use the detected specular reflection information to increase the accuracy of informative frame classification. Our experimental studies indicate that precision, sensitivity, specificity, and accuracy for the specular reflection detection technique and the two informative frame classification techniques are greater than 90{\%} and 95{\%}, respectively.",
keywords = "Clustering, Colonoscopy, Endoscopy, Frame classification, Specular reflection detection, Texture",
author = "JungHwan Oh and Sae Hwang and JeongKyu Lee and Wallapak Tavanapong and Johnny Wong and {de Groen}, {Piet C.}",
year = "2007",
month = "4",
doi = "10.1016/j.media.2006.10.003",
language = "English (US)",
volume = "11",
pages = "110--127",
journal = "Medical Image Analysis",
issn = "1361-8415",
publisher = "Elsevier",
number = "2",

}

TY - JOUR

T1 - Informative frame classification for endoscopy video

AU - Oh, JungHwan

AU - Hwang, Sae

AU - Lee, JeongKyu

AU - Tavanapong, Wallapak

AU - Wong, Johnny

AU - de Groen, Piet C.

PY - 2007/4

Y1 - 2007/4

N2 - Advances in video technology allow inspection, diagnosis and treatment of the inside of the human body without or with very small scars. Flexible endoscopes are used to inspect the esophagus, stomach, small bowel, colon, and airways, whereas rigid endoscopes are used for a variety of minimal invasive surgeries (i.e., laparoscopy, arthroscopy, endoscopic neurosurgery). These endoscopes come in various sizes, but all have a tiny video camera at the tip. During an endoscopic procedure, the tiny video camera generates a video signal of the interior of the human organ, which is displayed on a monitor for real-time analysis by the physician. However, many out-of-focus frames are present in endoscopy videos because current endoscopes are equipped with a single, wide-angle lens that cannot be focused. We need to distinguish the out-of-focus frames from the in-focus frames to utilize the information of the out-of-focus and/or the in-focus frames for further automatic or semi-automatic computer-aided diagnosis (CAD). This classification can reduce the number of images to be viewed by a physician and to be analyzed by a CAD system. We call an out-of-focus frame a non-informative frame and an in-focus frame an informative frame. The out-of-focus frames have characteristics that are different from those of in-focus frames. In this paper, we propose two new techniques (edge-based and clustering-based) to classify video frames into two classes, informative and non-informative frames. However, because intensive specular reflections reduce the accuracy of the classification we also propose a specular reflection detection technique, and use the detected specular reflection information to increase the accuracy of informative frame classification. Our experimental studies indicate that precision, sensitivity, specificity, and accuracy for the specular reflection detection technique and the two informative frame classification techniques are greater than 90% and 95%, respectively.

AB - Advances in video technology allow inspection, diagnosis and treatment of the inside of the human body without or with very small scars. Flexible endoscopes are used to inspect the esophagus, stomach, small bowel, colon, and airways, whereas rigid endoscopes are used for a variety of minimal invasive surgeries (i.e., laparoscopy, arthroscopy, endoscopic neurosurgery). These endoscopes come in various sizes, but all have a tiny video camera at the tip. During an endoscopic procedure, the tiny video camera generates a video signal of the interior of the human organ, which is displayed on a monitor for real-time analysis by the physician. However, many out-of-focus frames are present in endoscopy videos because current endoscopes are equipped with a single, wide-angle lens that cannot be focused. We need to distinguish the out-of-focus frames from the in-focus frames to utilize the information of the out-of-focus and/or the in-focus frames for further automatic or semi-automatic computer-aided diagnosis (CAD). This classification can reduce the number of images to be viewed by a physician and to be analyzed by a CAD system. We call an out-of-focus frame a non-informative frame and an in-focus frame an informative frame. The out-of-focus frames have characteristics that are different from those of in-focus frames. In this paper, we propose two new techniques (edge-based and clustering-based) to classify video frames into two classes, informative and non-informative frames. However, because intensive specular reflections reduce the accuracy of the classification we also propose a specular reflection detection technique, and use the detected specular reflection information to increase the accuracy of informative frame classification. Our experimental studies indicate that precision, sensitivity, specificity, and accuracy for the specular reflection detection technique and the two informative frame classification techniques are greater than 90% and 95%, respectively.

KW - Clustering

KW - Colonoscopy

KW - Endoscopy

KW - Frame classification

KW - Specular reflection detection

KW - Texture

UR - http://www.scopus.com/inward/record.url?scp=33847631274&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33847631274&partnerID=8YFLogxK

U2 - 10.1016/j.media.2006.10.003

DO - 10.1016/j.media.2006.10.003

M3 - Article

C2 - 17329146

AN - SCOPUS:33847631274

VL - 11

SP - 110

EP - 127

JO - Medical Image Analysis

JF - Medical Image Analysis

SN - 1361-8415

IS - 2

ER -