RAt-CapsNet: A Deep Learning Network Utilizing Attention and Regional Information for Abnormality Detection in Wireless Capsule Endoscopy

Alam, Md. Jahin; Rashid, Rifat Bin; Fattah, Shaikh Anowarul; Saquib, Mohammad

doi:10.1109/jtehm.2022.3198819

Cited by 12 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a related research case, we analyzed research progress by year through the examination of anatomical landmark data captured via a wireless capsule endoscope. Table 1 illustrates the research progress over the years based on anatomical landmark data collected using wireless capsule endoscopes [14,[29][30][31][32][33][34][35][36][37]. Research to date has used a variety of CNN models.…”

Section: Related Research and Model Selectionmentioning

confidence: 99%

See 1 more Smart Citation

Color-Transfer-Enhanced Data Construction and Validation for Deep Learning-Based Upper Gastrointestinal Landmark Classification in Wireless Capsule Endoscopy

Kim,

Cho,

Park

et al. 2024

Diagnostics

View full text Add to dashboard Cite

While the adoption of wireless capsule endoscopy (WCE) has been steadily increasing, its primary application remains limited to observing the small intestine, with relatively less application in the upper gastrointestinal tract. However, there is a growing anticipation that advancements in capsule endoscopy technology will lead to a significant increase in its application in upper gastrointestinal examinations. This study addresses the underexplored domain of landmark identification within the upper gastrointestinal tract using WCE, acknowledging the limited research and public datasets available in this emerging field. To contribute to the future development of WCE for gastroscopy, a novel approach is proposed. Utilizing color transfer techniques, a simulated WCE dataset tailored for the upper gastrointestinal tract is created. Using Euclidean distance measurements, the similarity between this color-transferred dataset and authentic WCE images is verified. Pioneering the exploration of anatomical landmark classification with WCE data, this study integrates similarity evaluation with image preprocessing and deep learning techniques, specifically employing the DenseNet169 model. As a result, utilizing the color-transferred dataset achieves an anatomical landmark classification accuracy exceeding 90% in the upper gastrointestinal tract. Furthermore, the application of sharpen and detail filters demonstrates an increase in classification accuracy from 91.32% to 94.06%.

show abstract

Section: Related Research and Model Selectionmentioning

confidence: 99%

“…Research to date has used a variety of CNN models. However, several studies have shown wide and inconsistent limits in accuracy [14,[30][31][32][33][34][35][36]. The performance of these models can vary depending on the characteristics of each dataset.…”

Section: Related Research and Model Selectionmentioning

confidence: 99%

Color-Transfer-Enhanced Data Construction and Validation for Deep Learning-Based Upper Gastrointestinal Landmark Classification in Wireless Capsule Endoscopy

Kim,

Cho,

Park

et al. 2024

Diagnostics

View full text Add to dashboard Cite

show abstract

“…In [17], the authors proposed Failure to detect gastrointestinal (GI) tract diseases early can have severe consequences, including the development of cancer and even death. Traditional procedures for detecting these diseases are often painful and cannot cover the entire GI tract.…”

Section: Literature Surveymentioning

confidence: 99%

Relative Scrutiny of Different Capsule Network Architectures

Thiyagarajan,

Thenmozhi

2023

Recent Trends in Data Science and Its Applications

View full text Add to dashboard Cite

The integration of computer vision and machine learning techniques has led to significant advancements in pattern recognition and image categorization. One of the most sophisticated machine learning techniques for encoding features based on hierarchical relationships is the capsule network. Unlike convolutional neural networks (CNNs), which lose much spatial location information and require extensive training data, capsule networks use inverted graphics and a network of capsules to represent objects as separate pieces and establish their interconnections. This paper aims to present an overview of various capsule network architecture designs employed in different applications, highlighting their pros and cons. The objective is to provide readers with a comprehensive understanding of the current state-of-the-art capsule network topologies.

show abstract

“…A performance evaluation was conducted using 271 detectable findings in 35 cases, with a sensitivity and specificity of 93.4% and 97.8%, respectively. Alam et al (2022) proposed Rat-CapsNet with regional information and attention mechanisms to classify abnormalities from WCE video data as normal, ulcers, erosions, blood, angiectasias, and lymphangiectasias. A mean computational accuracy of 98.51% for binary classes and over 95.65% for multi-classes was obtained using the public dataset Kvasir-Capsule.…”

Section: Introductionmentioning

confidence: 99%

Automated classification of ulcerative lesions in small intestine using densenet with channel attention and residual dilated blocks

Guo,

Xu,

Liu

et al. 2024

Phys. Med. Biol.

View full text Add to dashboard Cite

Objective: Ulceration of the small intestine, which has a high incidence, includes Crohn's disease (CD), intestinal tuberculosis (ITB), primary small intestinal lymphoma (PSIL), cryptogenic multifocal ulcerous stenosing enteritis (CMUSE), and non-specific ulcer (NSU). However, the ulceration morphology can easily be misdiagnosed through enteroscopy. Approach: In this study, DRCA-DenseNet169, which is based on DenseNet169, with residual dilated blocks and a channel attention block, is proposed to identify CD, ITB, PSIL, CMUSE, and NSU intelligently. In addition, a novel loss function that incorporates dynamic weights is designed to enhance the precision of imbalanced datasets with limited samples. DRCA-Densenet169 was evaluated using 10883 enteroscopy images, including 5375 ulcer images and 5508 normal images, which were obtained from the Shanghai Changhai Hospital. Main results: DRCA-Densenet169 achieved an overall accuracy of 85.27%±0.32%, a weighted-precision of 83.99%±2.47%, a weighted-recall of 84.36%±0.88% and a weighted-F1-score of 84.07%±2.14%. Significance: The results demonstrate that DRCA-Densenet169 has high recognition accuracy and strong robustness in identifying different types of ulcers when obtaining immediate and preliminary diagnoses.

show abstract

RAt-CapsNet: A Deep Learning Network Utilizing Attention and Regional Information for Abnormality Detection in Wireless Capsule Endoscopy

Cited by 12 publications

References 26 publications

Color-Transfer-Enhanced Data Construction and Validation for Deep Learning-Based Upper Gastrointestinal Landmark Classification in Wireless Capsule Endoscopy

Color-Transfer-Enhanced Data Construction and Validation for Deep Learning-Based Upper Gastrointestinal Landmark Classification in Wireless Capsule Endoscopy

Relative Scrutiny of Different Capsule Network Architectures

Automated classification of ulcerative lesions in small intestine using densenet with channel attention and residual dilated blocks

Contact Info

Product

Resources

About