Unsupervised summarisation of capsule endoscopy video

Iakovidis, Dimitris K.; Tsevas, Spyros; Maroulis, Dimitris; Polydorou, Andreas

doi:10.1109/is.2008.4670414

Cited by 21 publications

(17 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each frame of the video was visually inspected and annotated by two expert endoscopists, and two kinds of abnormal findings were identified in several sites of the small intestine; ulcers and phlebectasias. Following the approach we developed in [16] neighbourhoods of frames were extracted for each finding since each finding was visible in more than a single frame. Frame neighbourhoods exhibit very close similarity and were indicated by both experts without any interobserver variability, providing at the same time us with ground truth information.…”

Section: Resultsmentioning

confidence: 99%

“…Section II provides a description of the proposed methodology. Section III, presents the results of its experimental application on WCE video data with several amendments on the results provided in [16], and Section IV summarises the conclusions that can be derived from this study.…”

Section: Introductionmentioning

confidence: 98%

“…Computational approaches coping with the analysis of the WCE video include the development of special annotation tools to auto-bookmark abnormalities [3]; classification approaches that perform tissue discrimination either between normal and abnormal regions [4] or between different organs [5][6][7]; synergistic methodologies such as image registration techniques and L-G graphs for the detection of abnormal patterns in WCE images [8]; clustering techniques for blood detection [9]; neural network techniques for classification or detection of abnormal patterns [10,16]; intestinal motility assessment methodologies [13,15]; and other approaches that aim either to image enhancement [12] or to the rejection of invalid parts of the WCE video by performing intestinal juice detection [14].…”

Section: Introductionmentioning

confidence: 99%

“…To cope with this issue, we further investigate an effective computational approach that drastically reduces the video frames to be inspected enabling this way faster inspection of the video sequence [16]. The proposed approach applies an unsupervised methodology based on clustering and non-negative matrix factorization (NMF) [18] to summarize the WCE video by keeping the most representative frames from the whole examination.…”

Section: Introductionmentioning

confidence: 99%

“…The proposed summarization approach has been previously tested on a controlled dataset giving promising results [16]. However, no experimentation has taken place regarding the performance of the approach on real patient data.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Automatic frame reduction of Wireless Capsule Endoscopy video

Tsevas

Iakovidis

Maroulis

et al. 2008

2008 8th IEEE International Conference on BioInformatics and BioEngineering

Self Cite

View full text Add to dashboard Cite

Abstract-Wireless Capsule Endoscopy (WCE) is a noninvasive colour imaging technique that has been introduced for the screening of the gastrointestinal tract and especially the small intestine. WCE is performed by a wireless swallowable endoscopic capsule that transmits more than 50,000 video frames per examination. The visual inspection of the resulting video is a highly time-consuming task even for the experienced gastroenterologist. In this paper we propose a novel WCE video summarization approach which is subsequently evaluated using real world patient data. The proposed approach aims to the reduction of the number of the video frames to be visually inspected so as to enable significant reduction in the video assessment time. It is based on clustering using symmetric nonnegative matrix factorization initialized by the fuzzy c-means algorithm and supported by non-negative Lagrangian relaxation to extract a subset of video scenes containing the most representative frames from an entire examination. Real world patient data that display abnormal findings at several sites in the small intestine were annotated by expert gastroenterologists in order to experimentally evaluate the proposed approach. The results demonstrate that the suggested approach leads to significant reduction of the total number of frames in the input video without losing critical information related to the abnormal regions of the small intestine.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Automatic frame reduction of Wireless Capsule Endoscopy video

Tsevas

Iakovidis

Maroulis

et al. 2008

2008 8th IEEE International Conference on BioInformatics and BioEngineering

Self Cite

View full text Add to dashboard Cite

show abstract

MEMS and MEMS Package Assembly

Liu

2011

Modeling and Simulation for Microelectronic Packaging Assembly

View full text Add to dashboard Cite

Automatic Unsupervised Clustering of Videos of the Intracytoplasmic Sperm Injection (ICSI) Procedure

Storås

Riegler

Haugen

et al. 2022

Communications in Computer and Information Science

View full text Add to dashboard Cite

The in vitro fertilization procedure called intracytoplasmic sperm injection can be used to help fertilize an egg by injecting a single sperm cell directly into the cytoplasm of the egg. In order to evaluate, refine and improve the method in the fertility clinic, the procedure is usually observed at the clinic. Alternatively, a video of the procedure can be examined and labeled in a time-consuming process. To reduce the time required for the assessment, we propose an unsupervised method that automatically clusters video frames of the intracytoplasmic sperm injection procedure. Deep features are extracted from the video frames and form the basis for a clustering method. The method provides meaningful clusters representing different stages of the intracytoplasmic sperm injection procedure. The clusters can lead to more efficient examinations and possible new insights that can improve clinical practice. Further on, it may also contribute to improved clinical outcomes due to increased understanding about the technical aspects and better results of the procedure. Despite promising results, the proposed method can be further improved by increasing the amount of data and exploring other types of features.

show abstract

Unsupervised summarisation of capsule endoscopy video

Cited by 21 publications

References 11 publications

Automatic frame reduction of Wireless Capsule Endoscopy video

Automatic frame reduction of Wireless Capsule Endoscopy video

MEMS and MEMS Package Assembly

Automatic Unsupervised Clustering of Videos of the Intracytoplasmic Sperm Injection (ICSI) Procedure

Contact Info

Product

Resources

About