Detection of gastrointestinal tract disorders using deep learning methods from colonoscopy images and videos

Aliyi, Salih; Dese, Kokeb; Raj, Hakkins

doi:10.1016/j.sciaf.2023.e01628

Cited by 9 publications

(9 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, the selection of hyperparameters, including depth and width of CNN, is also a difficult task in identifying upper gastrointestinal disorders, including ulcers and bleeding. The detection of GIT disease using colonoscopy is a current area of research, and deep learning has consistently been crucial in its diagnosis 24,25 …”

Section: Literature Reviewmentioning

confidence: 99%

“…The detection of GIT disease using colonoscopy is a current area of research, and deep learning has consistently been crucial in its diagnosis. 24,25 In conclusion, the classification of gastrointestinal diseases is an important aspect of medical research, and several research papers have been published in this area. These papers describe the classification of various gastrointestinal diseases based on their clinical, histological, and molecular characteristics.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

CG‐Net: A novel CNN framework for gastrointestinal tract diseases classification

Siddiqui,

Akram,

Ashraf

et al. 2024

Int J Imaging Syst Tech

View full text Add to dashboard Cite

The classification of medical images has had a significant influence on the diagnostic techniques and therapeutic interventions. Conventional disease diagnosis procedures require a substantial amount of time and effort to accurately diagnose. Based on global statistics, gastrointestinal cancer has been recognized as a major contributor to cancer‐related deaths. The complexities involved in resolving gastrointestinal tract (GIT) ailments arise from the need for elaborate methods to precisely identify the exact location of the problem. Therefore, doctors frequently use wireless capsule endoscopy to diagnose and treat GIT problems. This research aims to develop a robust framework using deep learning techniques to effectively classify GIT diseases for therapeutic purposes. A CNN based framework, in conjunction with the feature selection method, has been proposed to improve the classification rate. The proposed framework has been evaluated using various performance measures, including accuracy, recall, precision, F1 measure, mean absolute error, and mean squared error.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

CG‐Net: A novel CNN framework for gastrointestinal tract diseases classification

Siddiqui,

Akram,

Ashraf

et al. 2024

Int J Imaging Syst Tech

View full text Add to dashboard Cite

show abstract

“…The use of machine-learning methods also makes it possible to identify the pathology of the genitourinary system [1]. Image segmentation based on machine-learning models and neural networks makes it possible to identify and classify diseases of the gastrointestinal tract [10][11][12][13]. In terms of identification studies, possible heart diseases based on clinical data in different patients were considered in [14], but their application in practice relies on the complexity of the data and the presence of correlations between them.…”

Section: Related Workmentioning

confidence: 99%

“…The listed methods have a high resource intensity in terms of the applied software and hardware. Summarizing the results [1][2][3][4][5][6][7][8][9][10][11][12][13][14], it is advisable to note that with almost all the methods, there is no possibility of automating the detection of pathology or deviations in the functioning of a particular organ (Table 1). In the table, a «+» sign indicates the presence of this property from the column header in the method from the first column in this source, «−» its absence.…”

Section: Related Workmentioning

confidence: 99%

“…Diseases of the gastrointestinal tract − [10-13] + [11,12]/− [10,13] + [10][11][12][13] − [10][11][12][13] Detection of cardiovascular diseases − [15] + [15] + [15] + [15] Existing methods are usually limited to considering the pathology of only one of the body's systems. As a rule, the methods for detecting combined pathology are not considered in studies .…”

Section: Automation Of Pathology Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Method for Detecting Pathology of Internal Organs Using Bioelectrography

Shichkina,

Fatkieva,

Sychev

et al. 2024

Diagnostics

View full text Add to dashboard Cite

This article considers the possibility of using the bioelectrography method to identify the pathology of internal organs. It is shown that with the currently existing methods, there is no possibility of the automatic detection of diseases or abnormalities in the functioning of a particular organ, or of the definition of combined pathology. It has been revealed that the use of various classifiers makes it possible to expand the field of pathology and choose the most optimal method for determining a particular disease. Based on this, a method for detecting the pathology of internal organs is developed, as well as a software package that allows the detection of diseases of the internal organs based on the bioelectrography results. Machine-learning models such as logistic regression, decision tree, random forest, xgboost, KNN, SVM and HyperTab are used for this purpose. HyperTab, logistic regression and xgboost turn out to be the best among them for this task, achieving a performance according to the f1-score metric in the order of 60–70%. The use of the developed method will, in practice, allow us to switch to combining various machine-learning models for the identification of certain diseases, as well as for the identification of combined pathology, which will help solve the problem of detecting pathology during screening studies and lead to a reduction in the burden on the staff of medical institutions.

show abstract

Advancements in Polyp Detection: A Developed Single Shot Multibox Detector Approach

Belabbes,

Oukdach,

Souaidi

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The significant challenge in detecting polyps in wireless capsule endoscopy and colonoscopy images lies in identifying the small ones. This detection task exhibits variability related to multiple characteristics such as color, shape, texture, morphology and size. In recent times, a lot of research has been done on the detection of polyps using the one-or two-stage method. Nevertheless, their real-world application demands significant computational power and memory resources, resulting in a trade-off between speed and improved precision. This study proposes Small Polyp Detection (SPDNet) for identifying small polyp regions in frames from wireless capsule endoscopy (WCE) and colonoscopy. Considering the foundational architecture is centered on balancing precision and speed. Extensive exploration was conducted to understand and address this trade-off. Applying deep transfer learning involves transferring knowledge to polyp images, allowing the extraction of exceptionally representative features and contextual information using the singleshot detector. Medical imaging applications are areas where the SSD has showcased its efficiency, but its limited detection capability for small polyp areas persists. Initially, the latest layers of the original backbone network VGG-16 of the SSD were modified. Subsequently, the feature maps from different layers and scales were adjusted to match their sizes. A branch block and concatenation module were introduced to integrate the feature maps from different layers, which were delivered to the next layer. Following this, a transition block generated new pyramidal layers. Then, in the middle of SPDNet, attention was applied. Finally, the multibox received the feature maps to generate the ultimate detection results, culminating in the refined feature map. The experimental results demonstrated a notable enhancement in the proposed method for detecting small polyp regions, achieving an encouraging mean average precision (mAP) of 94.32% and an F1-score of 91.37%. Moreover, the model showcased efficiency by demanding less computational time.

show abstract

Detection of gastrointestinal tract disorders using deep learning methods from colonoscopy images and videos

Cited by 9 publications

References 20 publications

CG‐Net: A novel CNN framework for gastrointestinal tract diseases classification

CG‐Net: A novel CNN framework for gastrointestinal tract diseases classification

Method for Detecting Pathology of Internal Organs Using Bioelectrography

Advancements in Polyp Detection: A Developed Single Shot Multibox Detector Approach

Contact Info

Product

Resources

About