Abstract
Plenty of computer-aided blind-spot monitoring systems based on the classification model of the upper gastrointestinal sites are developed to enhance the quality of gastroscopy. However, the performance of the white light (WL) based model drops deeply while changing the light source to the special light (SL), a narrowed-spectrum technology. A naive solution is to collect as much data from SL as from WL, but it is hard and time-consuming. In this work, we propose a novel light adaptive module that is only trained by common labeled WL images and unlabeled SL images. Our proposed structure is a plug-in module including a light classification head and a reconstruction decoder. The light classification head is trained in an adversarial manner, which prevents the backbone network to extract light-related features. The reconstruction decoder facilitates the complete preservation of the extracted structural features. The result showed that the original classification model added with our proposed light adaptive module could significantly improve the classification performance under SL and keep the original accuracy under WL, which may help endoscopists achieve better gastroscopy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bisschops, R., et al.: Performance measures for upper gastrointestinal endoscopy: a European Society of Gastrointestinal Endoscopy (ESGE) Quality Improvement Initiative. Endoscopy 48, 843–864 (2016)
Rutter, M.D., Rees, C.J.: Quality in gastrointestinal endoscopy. Endoscopy 46, 526–528 (2014)
Wu, L., et al.: Randomised controlled trial of WISENSE, a real-time quality improving system for monitoring blind spots during esophagogastroduodenoscopy. Gut 68(12), 2161–2169 (2019)
Yao, L., et al.: A gastrointestinal endoscopy quality control system incorporated with deep learning improved endoscopist performance in a pretest and post-test trial. Clin. Transl. Gastroenterology 12(6) (2021)
East, J.E., et al.: Advanced endoscopic imaging: European Society of Gastrointestinal Endoscopy (ESGE) technology review. Endoscopy 48(11), 1029–1045 (2016)
Mahmood, F., Chen, R., Durr, N.J.: Unsupervised reverse domain adaptation for synthetic medical images via adversarial training. IEEE Trans. Med. Imaging 37(12), 2572–2581 (2018)
Ganin, Y., Lempitsky V.: Unsupervised domain adaptation by backpropagation. In: International Conference on Machine Learning, pp. 1180–1189. PMLR (2015)
Wang, M., Deng, W.: Deep visual domain adaptation: a survey. Neurocomputing 312, 135–153 (2018)
Tzeng, E., et al.: Simultaneous deep transfer across domains and tasks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4068–4076 (2015)
Li, Y., et al.: Revisiting batch normalization for practical domain adaptation. arXiv preprint arXiv:1603.04779(2016)
Liu, M.Y., Tuzel O.: Coupled generative adversarial networks. In: Advances in Neural Information Processing Systems, pp. 469–477 (2016)
Tzeng, E., et al.: Adversarial discriminative domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7167–7176 (2017)
Bousmalis, K., et al.: Domain separation networks. In: Advances in Neural Information Processing Systems, pp. 343–351 (2016)
Yi, Z., et al.: Dualgan: Unsupervised dual learning for image-to-image translation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2849–2857 (2017)
Peng, X., et al.: Domain agnostic learning with disentangled representations. In: International Conference on Machine Learning, pp. 5102–5112. PMLR (2019)
Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. Adv. Neural. Inf. Process. Syst. 32, 8026–8037 (2019)
Zeng, G., et al.: Semantic consistent unsupervised domain adaptation for cross-modality medical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 201–210 (2021)
Perone, C.S., et al.: Unsupervised domain adaptation for medical imaging segmentation with self-ensembling. Neuroimage 194, 1–11 (2019)
Deng, J., et al.: Imagenet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. (2009)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)
Li, Y., et al.: Adaptive batch normalization for practical domain adaptation. Pattern Recogn. 80, 109–117 (2018)
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
Abdelmoneim, R.S.E., Abdelmoety, A.A., Baddour, N., Salem, P., Metawea, M.: The classification of gastric antral vascular ectasia in cirrhotic patients by Versatile Intelligent Staining Technology. Egyptian Liver J. 12(1), 1–6 (2022)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980(2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Hao, X., Xu, X., Jiang, D., Zhou, G. (2022). Light Adaptation for Classification of the Upper Gastrointestinal Sites. In: Manfredi, L., et al. Imaging Systems for GI Endoscopy, and Graphs in Biomedical Image Analysis. ISGIE GRAIL 2022 2022. Lecture Notes in Computer Science, vol 13754. Springer, Cham. https://doi.org/10.1007/978-3-031-21083-9_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-21083-9_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-21082-2
Online ISBN: 978-3-031-21083-9
eBook Packages: Computer ScienceComputer Science (R0)