Polyp Detection and Segmentation from Video Capsule Endoscopy: A Review

Prasath, V. B. Surya

doi:10.3390/jimaging3010001

Cited by 56 publications

(26 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the domain of polyp detection, Mamonov et al [23] presented an automated method with 81 % sensitivity per polyp at a specicity level of 90 %. A review of polyp detection and segmentation from video capsule endoscopy was published in 2017 [24]. Many successful methods can be found that are still relying on the traditional recognition approach that is based, for example, on the Gabor texture features and the K-means clustering [14] or the scale-invariant feature transform and the complete local binary pattern [37].…”

Section: Related Workmentioning

confidence: 99%

Comparison of Deep Learning-Based Recognition Techniques for Medical and Biomedical Images

Majtner

Nadimi

2019

Computer Analysis of Images and Patterns

View full text Add to dashboard Cite

The recognition and classication of medical and biomedical images typically suer from the problem of a low number of annotated samples. This comes along with the problem of ecient training of the current deep learning frameworks. Therefore, many researchers opt for various techniques which could substitute the traditional training of convolutional neural networks (CNN) from scratch. In this article, we are comparing multiple of these methods, including transfer learning and using the CNNs as feature extractors. The paper contains results on two datasets with dierent modalities and three dierent CNN architectures. We demonstrate the high eectiveness of transfer learning and suggest that, in some cases, it is worth retraining more layers at the end of the network for achieving higher accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

Comparison of Deep Learning-Based Recognition Techniques for Medical and Biomedical Images

Majtner

Nadimi

2019

Computer Analysis of Images and Patterns

View full text Add to dashboard Cite

show abstract

“…In gastroenterology, AI methods have been explored from both the classical model-driven and deep learning paradigms [20]. While the majority of work has focused on the detection or delineation of diseased regions [5,14,27], on the measurement of structural size [10] or the 3D navigation within the endoluminal organs [12,15,25], relatively little research effort has been invested into the classification of different endoscopic viewpoints that need to be viewed to complete an examination.…”

Section: Introductionmentioning

confidence: 99%

Deep learning-based anatomical site classification for upper gastrointestinal endoscopy

Bano

Ahmad

et al. 2020

Int J CARS

View full text Add to dashboard Cite

Purpose Upper gastrointestinal (GI) endoscopic image documentation has provided an efficient, low-cost solution to address quality control for endoscopic reporting. The problem is, however, challenging for computer-assisted techniques, because different sites have similar appearances. Additionally, across different patients, site appearance variation may be large and inconsistent. Therefore, according to the British and modified Japanese guidelines, we propose a set of oesophagogastroduodenoscopy (EGD) images to be routinely captured and evaluate its efficiency for deep learning-based classification methods. Methods A novel EGD image dataset standardising upper GI endoscopy to several steps is established following landmarks proposed in guidelines and annotated by an expert clinician. To demonstrate the discrimination of proposed landmarks that enable the generation of an automated endoscopic report, we train several deep learning-based classification models utilising the well-annotated images. Results We report results for a clinical dataset composed of 211 patients (comprising a total of 3704 EGD images) acquired during routine upper GI endoscopic examinations. We find close agreement between predicted labels using our method and the ground truth labelled by human experts. We observe the limitation of current static image classification scheme for EGD image classification. Conclusion Our study presents a framework for developing automated EGD reports using deep learning. We demonstrate that our method is feasible to address EGD image classification and can lead towards improved performance and additionally qualitatively demonstrate its performance on our dataset.

show abstract

“…Other methods concentrate on classifying different organs [28] and lesion detection [29] in WCE images. A survey paper [30,31] on video capsule endoscopy provides a better understanding of various models incorporating the detection and segmentation of polyps in the literature. However, all these methods performed polyp detection or the classification of frame-wise polyp presence.…”

Section: Introductionmentioning

confidence: 99%

Region-Based Automated Localization of Colonoscopy and Wireless Capsule Endoscopy Polyps

Sornapudi

Meng

2019

Applied Sciences

View full text Add to dashboard Cite

The early detection of polyps could help prevent colorectal cancer. The automated detection of polyps on the colon walls could reduce the number of false negatives that occur due to manual examination errors or polyps being hidden behind folds, and could also help doctors locate polyps from screening tests such as colonoscopy and wireless capsule endoscopy. Losing polyps may result in lesions evolving badly. In this paper, we propose a modified region-based convolutional neural network (R-CNN) by generating masks around polyps detected from still frames. The locations of the polyps in the image are marked, which assists the doctors examining the polyps. The features from the polyp images are extracted using pre-trained Resnet-50 and Resnet-101 models through feature extraction and fine-tuning techniques. Various publicly available polyp datasets are analyzed with various pertained weights. It is interesting to notice that fine-tuning with balloon data (polyp-like natural images) improved the polyp detection rate. The optimum CNN models on colonoscopy datasets including CVC-ColonDB, CVC-PolypHD, and ETIS-Larib produced values (F1 score, F2 score) of (90.73, 91.27), (80.65, 79.11), and (76.43, 78.70) respectively. The best model on the wireless capsule endoscopy dataset gave a performance of (96.67, 96.10). The experimental results indicate the better localization of polyps compared to recent traditional and deep learning methods.

show abstract

Polyp Detection and Segmentation from Video Capsule Endoscopy: A Review

Cited by 56 publications

References 68 publications

Comparison of Deep Learning-Based Recognition Techniques for Medical and Biomedical Images

Comparison of Deep Learning-Based Recognition Techniques for Medical and Biomedical Images

Deep learning-based anatomical site classification for upper gastrointestinal endoscopy

Region-Based Automated Localization of Colonoscopy and Wireless Capsule Endoscopy Polyps

Contact Info

Product

Resources

About