• Corpus ID: 84177838

Bleeding Classification of Enhanced Wireless Capsule Endoscopy Images using Deep Convolutional Neural Network

@inproceedings{Osdiana2018BleedingCO,
  title={Bleeding Classification of Enhanced Wireless Capsule Endoscopy Images using Deep Convolutional Neural Network},
  author={Osdiana and Hahril and tsushi and Aito and Kinobu and himizu and Abariah and Aharun},
  year={2018}
}
ROSDIANA SHAHRIL1, ATSUSHI SAITO2, AKINOBU SHIMIZU2 AND SABARIAH BAHARUN3 1Faculty of Computer Systems & Software Engineering Universiti Malaysia Pahang Pahang, Malaysia 2Tokyo University of Agriculture and Technology Tokyo,Japan 3 Malaysia-Japan International Institute of Technology Universiti Teknologi Malaysia Kuala Lumpur, Malaysia E-mail: {rosdiana}@ump.edu.my; {a-saito}@go.tuat.ac.jp;{simiz}@cc.tuat.ac.jp ; {sabariahb}@utm.my 

Figures and Tables from this paper

Automated Small Intestine Bleeding Detection Using Wireless Capusle Endocscopy Images
TLDR
An efficient automated detection of small intestine bleeding using Neural Networks is proposed and obtained 98.6% of average accuracy with CNN resnet-50 with 6 features only, as compared with CNN Goglenet, Alexnet and Softmax.
Image Aided Recognition of Wireless Capsule Endoscope Based on the Neural Network
  • B. Lu
  • Medicine, Computer Science
  • 2022
TLDR
The accuracy of the neural network model constructed in this study is 97.69%, which can effectively distinguish normal, benign lesions, and malignant tumors.
Image Aided Recognition of Wireless Capsule Endoscope Based on the Neural Network
  • B. Lu
  • Computer Science, Medicine
    Journal of healthcare engineering
  • 2022
TLDR
This research hopes to provide a reference for the application of neural network algorithms in the field of endoscopic images and proves that the neural network algorithm can effectively assist the endoscopist's diagnosis and improve the diagnosis efficiency.
Endoscopy Artefact Detection by Deep Transfer Learning of Baseline Models
TLDR
A simple baseline could achieve state-of-the-art performance in detecting artefacts in endoscopy using faster region-based convolutional neural networks and the combination of EfficientDet-D2 with suitable data augmentation and pre-trained parameters during fine-tuning training to detect the artefacts.
A deep learning framework combined with word embedding to identify DNA replication origins
TLDR
This paper develops sequence segmentation methods, and employs the word embedding technique, ‘Word2vec’, to convert gene sequences into word vectors, thereby grasping the inner correlations of gene sequences with different lengths and making a useful high throughput tool for genome analysis.

References

SHOWING 1-10 OF 28 REFERENCES
A convolutional neural network approach for abnormality detection in Wireless Capsule Endoscopy
TLDR
A technique to automate the abnormality detection in WCE images by split the image into several patches and extract features pertaining to each block using a convolutional neural network (CNN) to increase their generality while overcoming the drawbacks of manually crafted features.
A study on automated segmentation of blood regions in Wireless Capsule Endoscopy images using fully convolutional networks
  • Xiao JiaM. Meng
  • Computer Science
    2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)
  • 2017
TLDR
A new approach for automated segmentation of blood regions in WCE images via a deep learning strategy that achieves comparable or better performance than the state-of-the-art methods.
Gastrointestinal bleeding detection in wireless capsule endoscopy images using handcrafted and CNN features
  • Xiao JiaM. Meng
  • Computer Science
    2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
  • 2017
TLDR
A new approach for WCE bleeding detection that combines handcrafted (HC) features and convolutional neural network (CNN) features is presented and a smaller-scale CNN architecture is constructed to lower the computational cost.
A hybrid convolutional neural networks with extreme learning machine for WCE image classification
TLDR
A WCE classification system by a hybrid CNN with Extreme Learning Machine (ELM) is proposed, which constructs the CNN as a data-driven feature extractor and the cascaded ELM as a strong classifier instead of the conventional used full-connection classifier in deep CNN classification system.
Hookworm Detection in Wireless Capsule Endoscopy Images With Deep Learning
TLDR
A novel deep hookworm detection framework is proposed for WCE images, which simultaneously models visual appearances and tubular patterns of hookworms, and significantly outperforms the state-of-the-art approaches.
An automatic bleeding detection scheme in wireless capsule endoscopy based on histogram of an RGB-indexed image
TLDR
From extensive experimentation on real time WCE video recordings, it is found that the proposed automatic bleeding image detection method can accurately detect bleeding images with high sensitivity and specificity.
Detection and classification of bleeding using statistical color features for wireless capsule endoscopy images
TLDR
This approach focuses on various color features in HSV color space to differentiate between bleeding and non-bleeding frames and shows that proposed method for feature and classification is quite effective and achieve high performance classifier.
Exploring transfer learning for gastrointestinal bleeding detection on small-size imbalanced endoscopy images.
  • Xiuli LiHao ZhangXiaolu ZhangHao LiuGuotong Xie
  • Computer Science
    Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference
  • 2017
TLDR
This paper explored transfer learning for gastrointestinal bleeding detection on small-size imbalanced endoscopy images, and showed how image representations learned with CNN on large-scale annotated datasets can be efficiently transferred to other tasks with limited amount of training data.
Computer-Aided Bleeding Detection in WCE Video
TLDR
A new method for rapid bleeding detection in the WCE video is proposed that group pixels through superpixel segmentation to reduce the computational complexity while maintaining high diagnostic accuracy.
Machine learning techniques for bleeding detection in capsule endoscopy
  • H. PannuPriyanka Jarial
  • Computer Science
    2017 International Conference on Computing Methodologies and Communication (ICCMC)
  • 2017
TLDR
Major state-of-the-art techniques for bleeding detection in WCE have been studied comprehensively along with their comparative analysis in this survey.
...
...