The week's pick
Random Articles
Reseach Article
Multi-Object Detection and Localization of Artefacts in Endoscopy Images
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 184 - Number 33 |
| Year of Publication: 2022 |
| Authors: Madhura Prakash M., Krishnamurthy G.N. |
10.5120/ijca2022922422
|
Madhura Prakash M., Krishnamurthy G.N. . Multi-Object Detection and Localization of Artefacts in Endoscopy Images. International Journal of Computer Applications. 184, 33 ( Oct 2022), 28-33. DOI=10.5120/ijca2022922422
Abstract
In this era the Artificial Intelligence (AI) combined with computer vision techniques are seamlessly applied across various domains. The medical image analysis domain is also gaining the advantage of the AI solutions. The medical domain requires real-time analysis of the images and videos being generated for providing automatic assistance to the experts. Artefacts Artefact are image features that do not represent any original scene but occur due to a quirk of the modality itself. The presence of artefacts in Images or video frames poses a challenge for efficient analysis to extract the relevant information. The actual information in the image for understanding the given scene usually lies behind the presence of these artefacts. Examples of artefacts include distortion, blurring, occlusion by other objects and so on. The presence of these in an image must be identified and in the case of video analysis, the frames without the presence of with minimal presence of artefacts must be considered for analysis. Endoscopy is a procedure that involves both diagnosis and therapeutic solutions in various inner regions of human body. Analyzing the image data generated by this procedure using AI based solution can provide an assistance to the medical experts. The work focuses on providing deep-learning based result based on the standard YOLO V3 model for artefact detection and localization on the endoscopy frames has been proposed. The proposed model has achieved a mean average precision (mAP) of 0.76 and an Intersection of Union (IoU) of 0.63 by training the model on the images from the widely available Endoscopy Artefact Detection (EAD) dataset.
References
- Ali, Sharib; Zhou, Felix; Daul, Christian; Braden, Barbara; Bailey, Adam; East, James; Realdon, Stefano; Georges, Wagnieres; Loshchenov, Maxim; Blondel, Walter; Grisan, Enrico; Rittscher, Jens (2019), “Endoscopy Artefact Detection (EAD) Dataset”, Mendeley Data, V1, doi: 10.17632/c7fjbxcgj9.1
- Sharib Ali, Felix Zhou, Adam Bailey, Barbara Braden, James E. East, Xin Lu, Jens Rittscher, A deep learning framework for quality assessment and restoration in video endoscopy, Medical Image Analysis, Volume 68, 2021,101900, ISSN 1361-8415, https://doi.org/10.1016/j.media.2020.101900.
- Zhang YY, Xie D. Detection and segmentation of multi-class artifacts in endoscopy. J Zhejiang Univ Sci B. 2019 Dec.;20(12):1014-1020. doi: 10.1631/jzus.B1900340. PMID: 31749348; PMCID: PMC6885408.
- Ali S, Zhou F, Braden B, Bailey A, Yang S, Cheng G, Zhang P, Li X, Kayser M, Soberanis-Mukul RD, Albarqouni S, Wang X, Wang C, Watanabe S, Oksuz I, Ning Q, Yang S, Khan MA, Gao XW, Realdon S, Loshchenov M, Schnabel JA, East JE, Wagnieres G, Loschenov VB, Grisan E, Daul C, Blondel W, Rittscher J. An objective comparison of detection and segmentation algorithms for artefacts in clinical endoscopy. Sci Rep. 2020 Feb 17;10(1):2748. doi: 10.1038/s41598-020-59413-5. PMID: 32066744; PMCID: PMC7026422.
- Sharib Ali, et al, Deep learning for detection and segmentation of artefact and disease instances in gastrointestinal endoscopy, Medical Image Analysis, Volume 70, 2021, 102002, ISSN 1361 8415,https://doi.org/10.1016/j.media.2021.102002.
- Yang, Suhui and Guanju Cheng. “ENDOSCOPIC ARTEFACT DETECTION AND SEGMENTATION WITH DEEP CONVOLUTIONAL NEURAL NETWORK.” (2019).
- Yin, TK., Huang, KL., Chiu, SR. et al. Endoscopy Artefact Detection by Deep Transfer Learning of Baseline Models. J Digit Imaging (2022). https://doi.org/10.1007/s10278-022-00627-6
- Jadhav, Suyog & Bamba, Udbhav & Chavan, Arnav & Tiwari, Rishabh & Raj, Aryan. (2020). Multi-Plateau Ensemble for Endoscopic Artefact Segmentation and Detection.
- Redmon, Joseph & Farhadi, Ali. (2018). YOLOv3: An Incremental Improvement.
- J. Deng, W. Dong, R. Socher, L. -J. Li, Kai Li and Li Fei-Fei, "ImageNet: A large-scale hierarchical image database," 2009 IEEE Conference on Computer Vision and Pattern Recognition, 2009, pp. 248-255, doi: 10.1109/CVPR.2009.5206848.
- Subramanian, Anand and Koushik Srivatsan. “Exploring Deep Learning Based Approaches for Endoscopic Artefact Detection and Segmentation.” EndoCV@ISBI (2020).
- Oksuz, I., Clough, J. R., Clough, J. R., & Schnabel, J. A. (2019). Artefact detection in video endoscopy using retinanet and focal loss function. CEUR Workshop Proceedings, 2366. https://doi.org/http://ceur-ws.org/Vol-2366/
- Khan, M. A., & Choo, J. (2019). Multi-class artefact detection in video endoscopy via convolution neural networks. CEUR Workshop Proceedings, 2366.
- Sulik, L., Krejcar, O., Selamat, A., Mashinchi, R., Kuca, K. (2015). Determining of Blood Artefacts in Endoscopic Images Using a Software Analysis. In: Núñez, M., Nguyen, N., Camacho, D., Trawiński, B. (eds) Computational Collective Intelligence. Lecture Notes in Computer Science (), vol 9330. Springer, Cham. https://doi.org/10.1007/978-3-319-24306-1_38
- N. Kirthika and B. Sargunam, "YOLOv4 for Multi-class Artefact Detection in Endoscopic Images," 2021 3rd International Conference on Signal Processing and Communication (ICPSC), 2021, pp. 73-77, doi: 10.1109/ICSPC51351.2021.9451761.
- F. Artunc and I. Oksuz, "An Ensemble Approach for Automatic Artefact Detection on Gastroendoscopy Images," 2021 6th International Conference on Computer Science and Engineering (UBMK), 2021, pp. 741-746, doi: 10.1109/UBMK52708.2021.9558919.
Index Terms
Keywords