An Automatic Bleeding Frame and Region Detection Scheme for Wireless Capsule Endoscopy Videos Based on Interplane Intensity Variation Profile in Normalized RGB Color Space

Kundu, Amit Kumar; Fattah, Shaikh Anowarul; Rizve, Mamshad Nayeem

doi:10.1155/2018/9423062

Cited by 29 publications

(23 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the major challenge here is to propose a unified scheme for ROI extraction of WCE images from any disease class, as different diseases show different characteristics in terms of their color patterns. For example, in [13], an ROI is extracted based on offline research for bleeding identification before computing features, where the ROI extraction parameters are static for all images. The static parameters may not extract ROI with significant precision when different variants of the same disease are available in the training set, even may not extract precise ROI from images of other diseases.…”

Section: B Salient Roi Extraction From M-lda Modelsmentioning

confidence: 99%

“…As a result, researchers became motivated to develop computer-aided methods to detect the GI diseases for reducing the burden of the physicians [1]. With the exception of a few, most research efforts are concentrated on dealing with detecting only one type of disease where bleeding, being the most common GI disease, has received the most attention [3]- [13]. There are a few schemes that focus on ulcer or tumor detection from WCE videos [14]- [21].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multiple Linear Discriminant Models for Extracting Salient Characteristic Patterns in Capsule Endoscopy Images for Multi-Disease Detection

Kundu

Fattah

Wahid

2020

IEEE J. Transl. Eng. Health Med.

Self Cite

View full text Add to dashboard Cite

Background: Computer-aided disease detection schemes from wireless capsule endoscopy (WCE) videos have received great attention by the researchers for reducing physicians' burden due to the time-consuming and risky manual review process. While single disease classification schemes are greatly dealt by the researchers in the past, developing a unified scheme which is capable of detecting multiple gastrointestinal (GI) diseases is very challenging due to the highly irregular behavior of diseased images in terms of color patterns. Method: In this paper, a computer-aided method is developed to detect multiple GI diseases from WCE videos utilizing linear discriminant analysis (LDA) based region of interest (ROI) separation scheme followed by a probabilistic model fitting approach. Commonly in training phase, as pixel-labeled images are available in small number, only the image-level annotations are used for detecting diseases in WCE images, whereas pixel-level knowledge, although a major source for learning the disease characteristics, is left unused. In view of learning the characteristic disease patterns from pixel-labeled images, a set of LDA models are trained which are later used to extract the salient ROI from WCE images both in training and testing stages. The intensity patterns of ROI are then modeled by a suitable probability distribution and the fitted parameters of the distribution are utilized as features in a supervised cascaded classification scheme. Results: For the purpose of validation of the proposed multi-disease detection scheme, a set of pixel-labeled images of bleeding, ulcer and tumor are used to extract the LDA models and then, a large WCE dataset is used for training and testing. A high level of accuracy is achieved even with a small number of pixel-labeled images. Conclusion: Therefore, the proposed scheme is expected to help physicians in reviewing a large number of WCE images to diagnose different GI diseases.

show abstract

Section: B Salient Roi Extraction From M-lda Modelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Multiple Linear Discriminant Models for Extracting Salient Characteristic Patterns in Capsule Endoscopy Images for Multi-Disease Detection

Kundu

Fattah

Wahid

2020

IEEE J. Transl. Eng. Health Med.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Around 2393, annotated bleeding and non-bleeding images have been used to analyze the proposed method, which is available in [19]. In [20], they offer a bleeding detection technique using 2300 WCE images, though 2393 images have been used in the proposed method.…”

Section: Methodsmentioning

confidence: 99%

Small intestine bleeding detection using color threshold and morphological operation in WCE images

Mamun

Hossain

Ping

et al. 2021

IJECE

View full text Add to dashboard Cite

<span>Wireless capsule endoscopy (WCE) is a significant modern technique for observing the whole gastroenterological tract to diagnose various diseases like bleeding, ulcer, tumor, Crohn's disease, polyps etc in a non-invasive manner. However, it will make a substantial onus for physicians like human oversight errors with time consumption for manual checking of a vast amount of image frames. These problems motivate the researchers to employ a computer-aided system to classify the particular information from the image frames. Therefore, a computer-aided system based on the color threshold and morphological operation has been proposed in this research to recognize specified bleeding images from the WCE. Besides, A unique classifier, quadratic support vector machine (QSVM) has been employed for classifying the bleeding and non-bleeding images with the statistical feature vector in HSV color space. After extensive experiments on clinical data, 95.8% accuracy, 95% sensitivity, 97% specificity, 80% precision, 99% negative predicted value and 85% F1 score has been achieved, which outperforms some of the existing methods in this regard. It is expected that this methodology would bring a significant contribution to the WCE technology. </span>

show abstract

“…Moreover, utilizing the whole image increases computational burden. Hence, in [13], some preliminary POI are selected for feature extraction rather than to utilize the whole image. However, the POI extraction criteria are fixed for all image and applicable only for bleeding POI extraction.…”

Section: A Pixels Of Interest (Poi) Extractionmentioning

confidence: 99%

Least Square Saliency Transformation of Capsule Endoscopy Images for PDF Model Based Multiple Gastrointestinal Disease Classification

2020

Self Cite

View full text Add to dashboard Cite

Wireless capsule endoscopy (WCE) is an effective video technology to diagnose gastrointestinal (GI) diseases, such as bleeding, ulcer, and tumor. In order to avoid a tedious manual review process of long duration WCE video recordings, automatic disease detection schemes have received significant attention from the researchers. In particular, instead of the conventional approach of dealing with a single disease, developing a unified scheme, which is capable of detecting multiple GI diseases, is getting more importance while being challenging. In this paper, a unified computer-aided scheme is developed for detecting multiple GI diseases from WCE videos based on a proposed least-square saliency transformation (LSST) followed by a probabilistic model-fitting approach. Commonly in the training phase, image-level labeling of images is used, as pixel-level annotations are available only for a small number of images. In view of utilizing the knowledge from pixel-level annotated diseased images, an LSST scheme is proposed to extract a set of optimum prior coefficient-vectors which is later used to capture the salient pixels of interest (POI) in a larger WCE image dataset that do not have pixel-annotations. The intensity distributions of salient POI are modeled by a suitable probability density function (PDF) and the fitted PDF parameters are utilized as features in the proposed supervised hierarchical classification scheme. A large number of WCE images obtained from publicly available WCE videos are used for performance evaluation and it is found that the result obtained by the proposed method outperforms the results obtained in case of some state-of-the-art methods. INDEX TERMS Multiple gastrointestinal disease detection, K-means clustering, least square saliency transformation, quadratic programming, support vector machine. The associate editor coordinating the review of this manuscript and approving it for publication was Derek Abbott. as bleeding is the most common GI disease [3]-[14]. The reported automatic bleeding detection schemes are mainly based on suspected blood indicator [3], histogram-based features [4]-[7], statistical features [8], block-based approaches [7], [9], features from salient points [11], [15] and deep learning framework [12]. In [14], the active and inactive bleeding subgroups are classified based on histogram features and then, separately fed to different fully connected neural networks for bleeding region segmentation. On the other side, automatic ulcer detection schemes are proposed based on convolutional neural network (CNN) based architecture [16], completed local binary patterns (LBP), and laplacian

show abstract

An Automatic Bleeding Frame and Region Detection Scheme for Wireless Capsule Endoscopy Videos Based on Interplane Intensity Variation Profile in Normalized RGB Color Space

Cited by 29 publications

References 24 publications

Multiple Linear Discriminant Models for Extracting Salient Characteristic Patterns in Capsule Endoscopy Images for Multi-Disease Detection

Multiple Linear Discriminant Models for Extracting Salient Characteristic Patterns in Capsule Endoscopy Images for Multi-Disease Detection

Small intestine bleeding detection using color threshold and morphological operation in WCE images

Least Square Saliency Transformation of Capsule Endoscopy Images for PDF Model Based Multiple Gastrointestinal Disease Classification

Contact Info

Product

Resources

About