ABSTRACT
The intelligent gastrointestinal image classification based on computer-aided diagnosis not only alleviates the shortage of endoscopist's missed diagnosis and misdiagnosis but also reduces the heavy diagnostic tasks to help prevent the deterioration of gastric diseases into gastric cancer. In our research work, we propose to use the Inception-Resnet-v2 with attention mechanism based on transfer learning to predict three-class anomalies of the gastrointestinal endoscopic imagery. Our model achieves a promising classification performance with 92.5% accuracy, 98.46% precision and 99.89% recall.
- C. Gamage, I. Wijesinghe, C. Chitraranjan and I. Perera, ”GI-Net: Anomalies Classification in Gastrointestinal Tract through Endoscopic Imagery with Deep Learning,” 2019 Moratuwa Engineering Research Conference (MERCon), Moratuwa, Sri Lanka, 2019, pp. 66-71.Google ScholarCross Ref
- Zhao Shengbing, Qian Wei, Bai Yu, Li Zhaoshen. Application research progress of artificial intelligence in the field of digestive endoscopy [J].Chinese Journal of digestive endoscopy, 2019 (04): 293-296.Google Scholar
- Li Xia, Wu Lianlian, Yu Honggang. Application of artificial intelligence gastroscopy in blind area monitoring and autonomous image acquisition [J]. Chinese Journal of Gastroenterology, 2019 (04): 240-245.Google Scholar
- Wang Zhijie, Gao Jie, Meng Xixi, Yang Ting, Wang Zeyuan, Chen Xingchun, Wang Dong, Li Zhaoshen. Application of artificial intelli- gence technology based on deep learning in the diagnosis of early gastric cancer [J]. Chinese Journal of digestive endoscopy, 2018,35 (08):551-556.Google Scholar
- Satoki Shichijo, Shuhei Nomura, Kazuharu Aoyama, Yoshitaka Nishikawa, Motoi Miura,Takahide Shinagawa,Hirotoshi Takiyama,Tetsuya Tanimoto, Soichiro Ishihara,Keigo Matsuo,Tomohiro Tada. Application of Convolutional Neural Networks in the Diagnosis of Helicobacter pylori Infection Based on Endoscopic Images[J]. EBioMedicine,2017,25.Google Scholar
- Younghak Shin, Balasingham I. Comparison of hand-craft feature based SVM and CNN based deep learning framework for automatic polyp classification. Annu Int Conf IEEE Eng Med Biol Soc. 2017 Jul;2017:3277-3280. doi: 10.1109/EMBC.2017.8037556. PMID: 29060597.Google Scholar
- Val´erio, M. T., Gomes, S., Salgado, M., Oliveira, H. P., & Cunha, A. (2019). Lesions Multiclass Classification in Endoscopic Capsule Frames. Procedia Computer Science, 164, 637-645.Google Scholar
- R. Zhang Automatic Detection and Classification of Colorectal Polyps by Transferring Low-Level CNN Features from Nonmedical Domain. IEEE Journal of Biomedical and Health Informatics,2017, 21:41-47.Google Scholar
- C. Gamage, I. Wijesinghe, C. Chitraranjan and I. Perera, ”GI-Net: Anomalies Classification in Gastrointestinal Tract through Endoscopic Imagery with Deep Learning,” 2019 Moratuwa Engineering Research Conference (MERCon), Moratuwa, Sri Lanka, 2019, pp. 66-71, doi: 10.1109/MERCon.2019.8818929.Google ScholarCross Ref
- The kvasir dataset, [online] Available: https://datasets.simula.no/kvasir/.Google Scholar
- ¨Ozt¨urk, ¸Saban, and Umut ¨Ozkaya. ”Gastrointestinal tract classification using improved LSTM based CNN.” Multimedia Tools and Applications 79.39 (2020): 28825-28840.Google Scholar
- McGuire, Shelley. ”World cancer report 2014. Geneva, Switzerland: World Health Organization, international agency for research on cancer, WHO Press, 2015.” Advances in nutrition 7.2 (2016): 418-419.Google ScholarCross Ref
- Wimmer, G., Tamaki, T., Tischendorf, J. J., H¨afner, M., Yoshida, S., Tanaka, S., & Uhl, A. (2016). Directional wavelet based features for colonic polyp classification. Medical image analysis, 31, 16–36.Google Scholar
- C. Szegedy , ”Going deeper with convolutions,” 2015 IEEE Con- ference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 2015, pp. 1-9.Google Scholar
- Szegedy, C., Ioffe, S., & Vanhoucke, V. Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning.Google Scholar
- Woo, S., Park, J., Lee, J. Y., & Kweon, I. S. (2018). Cbam: Convolutional block attention module. In Proceedings of the European conference on computer vision (ECCV) (pp. 3-19).Google Scholar
Recommendations
Convolutional‐capsule network for gastrointestinal endoscopy image classification
AbstractAutomated diagnosis of digestive tract diseases from gastrointestinal endoscopy images is of high importance for improving the diagnosis accuracy and efficiency. The current mainstream methods for image classification of digestive tract ...
An Automated Model using Deep Convolutional Neural Network for Retinal Image Classification to Detect Diabetic Retinopathy
ICCA 2020: Proceedings of the International Conference on Computing AdvancementsDiabetic Retinopathy is considered as one of the significant reasons for vision impairment. Its identification involves detecting the presence of some features in retinal fundus images by clinicians which is a time and resource consuming procedure and a ...
The Classification of Hypertensive Retinopathy using Convolutional Neural Network
Changes in the retina of the eyes may occur due to high blood pressure, hypertensive retinopathy (HR) is a type of eye disease in which there is a change of the blood vessels of the eyes in the eye retina caused by arterial hypertension. HR signs occur ...
Comments