A frame reduction system based on a color structural similarity (CSS) method and Bayer images analysis for capsule endoscopy

Al-Shebani, Qasim; Premaratne, Prashan; McAndrew, Darryl J; Vial, Peter James; Abey, Shehan

doi:10.1016/j.artmed.2018.12.008

Cited by 9 publications

(8 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Of the redundant images, 79.09% were screened out without missing venous abnormalities, polyps, erythema, white spots, erosions, aphthous ulcers, diverticula, granules, redness, abnormal villi, paleness, hookworms, and bleeding. The image reduction ratio of the current color structural similarity (CSS) method [6] reaches 93.87% without missing the detection of bleeding lesions. The motion-estimate method [8] can remove 68% of redundant images, although there is no description of lesion retention.…”

Section: Resultsmentioning

confidence: 99%

“…Tsevas et al [3][4][5] applied the optical flow method to estimate the motion of the capsule and identify the backward redundant images among the capsule endoscopic images. Alexandros [6] used the Bayer image to reduce the dimensions of the original data and evaluated image similarity using local binary patterns (LBP) and the color structure similarity measurement method. Lee et al [7] proposed a similarity confidence function based on area segmentation and global mapping to identify the registration area of WCE images, so as to identify the similarity of adjacent image data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of Structural Similarity Analysis of Visually Salient Areas and Hierarchical Clustering in the Screening of Similar Wireless Capsule Endoscopic Images

Nie¹,

Yang

Peng³

et al. 2020

2020 2nd International Conference on Information Technology and Computer Application (ITCA)

View full text Add to dashboard Cite

Small intestinal capsule endoscopy is the mainstream method for inspecting small intestinal lesions, but a single small intestinal capsule endoscopy will produce 60,000-120,000 images, the majority of which are similar and have no diagnostic value. It takes 2-3 hours for doctors to identify lesions from these images. This is time-consuming and increases the probability of misdiagnosis and missed diagnosis since doctors are likely to experience visual fatigue while focusing on a large number of similar images for an extended period of time. In order to solve these problems, we proposed a similar wireless capsule endoscope (WCE) image screening method based on structural similarity analysis and the hierarchical clustering of visually salient sub-image blocks. The similarity clustering of images was automatically identified by hierarchical clustering based on the hue, saturation, value (HSV) spatial color characteristics of the images, and the keyframe images were extracted based on the structural similarity of the visually salient sub-image blocks, in order to accurately identify and screen out similar small intestinal capsule endoscopic images. Subsequently, the proposed method was applied to the capsule endoscope imaging workstation. After screening out similar images in the complete data gathered by the Type I OMOM Small Intestinal Capsule Endoscope from 52 cases covering 17 common types of small intestinal lesions, we obtained a lesion recall of 100% and an average similar image reduction ratio of 76%. With similar images screened out, the average play time of the OMOM image workstation was 18 minutes, which greatly reduced the time spent by doctors viewing the images.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Application of Structural Similarity Analysis of Visually Salient Areas and Hierarchical Clustering in the Screening of Similar Wireless Capsule Endoscopic Images

Nie¹,

Yang

Peng³

et al. 2020

2020 2nd International Conference on Information Technology and Computer Application (ITCA)

View full text Add to dashboard Cite

show abstract

“…Another interesting approach to reduce CE reading time was recently introduced. They proposed a CE frame reduction system based on a color structural similarity using color models for color texture and structural information, achieving a reduction ratio of 93.8% [ 25 ]. Although technical advances such as AI are expected to enhance the diagnostic yield of CE, there are some challenges relating to the SB preparation quality.…”

Section: Discussionmentioning

confidence: 99%

Development and Verification of a Deep Learning Algorithm to Evaluate Small-Bowel Preparation Quality

Nam

Lee

et al. 2021

Diagnostics

View full text Add to dashboard Cite

Capsule endoscopy (CE) quality control requires an objective scoring system to evaluate the preparation of the small bowel (SB). We propose a deep learning algorithm to calculate SB cleansing scores and verify the algorithm’s performance. A 5-point scoring system based on clarity of mucosal visualization was used to develop the deep learning algorithm (400,000 frames; 280,000 for training and 120,000 for testing). External validation was performed using additional CE cases (n = 50), and average cleansing scores (1.0 to 5.0) calculated using the algorithm were compared to clinical grades (A to C) assigned by clinicians. Test results obtained using 120,000 frames exhibited 93% accuracy. The separate CE case exhibited substantial agreement between the deep learning algorithm scores and clinicians’ assessments (Cohen’s kappa: 0.672). In the external validation, the cleansing score decreased with worsening clinical grade (scores of 3.9, 3.2, and 2.5 for grades A, B, and C, respectively, p < 0.001). Receiver operating characteristic curve analysis revealed that a cleansing score cut-off of 2.95 indicated clinically adequate preparation. This algorithm provides an objective and automated cleansing score for evaluating SB preparation for CE. The results of this study will serve as clinical evidence supporting the practical use of deep learning algorithms for evaluating SB preparation quality.

show abstract

“…To compare our proposed methodology with the previous works, we implemented three previous methods [10, 17, 19] on our dataset. An unsupervised mining‐based video summarisation method was proposed in [10].…”

Section: Discussionmentioning

confidence: 99%

“…A representative keyframe was extracted from each state based on the highest state‐conditional probability of the corresponding saliency vector. Al‐Shebani et al [19] proposed a frame reduction system based on various colour models using Bayer images for colour texture and a modified local binary pattern for structural information. This approach reduced reviewing time by omitting the images with high similarity of information.…”

Section: Introductionmentioning

confidence: 99%

Integrated system for automatic detection of representative video frames in wireless capsule endoscopy using adaptive sliding window singular value decomposition

Biniaz

Abdolali

Zoroofi

2020

IET Image Processing

View full text Add to dashboard Cite

A frame reduction system based on a color structural similarity (CSS) method and Bayer images analysis for capsule endoscopy

Cited by 9 publications

References 24 publications

Application of Structural Similarity Analysis of Visually Salient Areas and Hierarchical Clustering in the Screening of Similar Wireless Capsule Endoscopic Images

Application of Structural Similarity Analysis of Visually Salient Areas and Hierarchical Clustering in the Screening of Similar Wireless Capsule Endoscopic Images

Development and Verification of a Deep Learning Algorithm to Evaluate Small-Bowel Preparation Quality

Integrated system for automatic detection of representative video frames in wireless capsule endoscopy using adaptive sliding window singular value decomposition

Contact Info

Product

Resources

About