ARTEFACT DETECTION AND SEGMENTATION BASED ON A DEEP LEARNING SYSTEM

Abstract

This paper presents the results of detection and segmentation of artefact from endoscopic video frames for EAD2020 competition. In this competition, a deep learning based system is applied, which is built upon RetinaNet. Since RetinaNet employs a one-stage method that lacks facilitating masks of segmented objects, inspired by the work of real-time instance segmentation, this system accomplishes object segmentation through two parallel branches to generate a set of prototype masks and to predict per-object mask coefficients respectively. Overall, top 7 (out of 32 entries) position was achieved in this competition on the leaderboard.

1. METHODS

Figure 1 illustrates the network system applied in this competition [ 1, 2, 3, 4, 5, 6, 7, 8, 9 ] built upon RetinaNet. It accomplishes object segmentation through two parallel strands (Prototype and Prediction coefficient), which are to generate a set of prototype masks and to predict per-object mask coefficients respectively. The backbone model of Resnet101 is applied for all three tasks.

2. RESULTS

Table 1 presents the final results submitted from this work whereas Table 2 gives the mAP for segmentation when 95% the overall classification accuracy was 63%. Although the results remain on the top 7, it is felt more enhancement is needed to further improve this model to improve its robustness.

3. REFERENCES

Copyright c 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

Model parameters

Epoch = 412, Threshold = 0.17 Epoch = 226, Threshold = 0.13

Scored

mAP at IoU thresholds 0.50 0.70 0.95 All 77.85 61.64 0.99 47.42 76.91 61.51 0.87 46.17 [2] Sharib Ali, Felix Zhou, Adam Bailey, Barbara Braden, James East, Xin Lu, and Jens Rittscher. A deep learning framework for quality assessment and restoration in video endoscopy. arXiv preprint arXiv:1904.07073, 2019. nizzaro, Jens Rittscher, Christian Daul, and James East. Endoscopy disease detection challenge 2020. arXiv preprint arXiv:2003.03376, 2020.

References

[4] Sharib Ali , Felix Zhou, Barbara Braden, Adam Bailey, Suhui Yang, Guanju Cheng, Pengyi Zhang, Xiaoqiong Li, Maxime Kayser , Roger D. Soberanis-Mukul , Shadi Albarqouni, Xiaokang Wang, Chunqing Wang , Seiryo Watanabe, Ilkay Oksuz, Qingtian Ning, Shufan Yang, Mohammad Azam Khan, Xiaohong W. Gao, Stefano Realdon, Maxim Loshchenov, Julia A. Schnabel , James E. East, Geroges Wagnieres, Victor B. Loschenov , Enrico Grisan, Christian Daul, Walter Blondel, and Jens Rittscher . An objective comparison of detection and segmentation algorithms for artefacts in clinical endoscopy . Scientific Reports , 10 , 2020 .

[5] T. Lin , P. Goyal , R. Girshick , K. He , and P. Dollr . Focal loss for dense object detection . In 2017 IEEE International Conference on Computer Vision (ICCV), pages 2999 - 3007 , 2017 .

[6] Ross Girshick , Jeff Donahue, Trevor Darrell, and Jitendra Malik . Rich feature hierarchies for accurate object detection and semantic segmentation . In Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, page 580587 , USA, 2014 . IEEE Computer Society.

[7] Wei Liu , Dragomir Anguelov, Dumitru Erhan, Christian Szegedy , Scott E . Reed, Cheng-Yang Fu , and Alexander C. Berg . Ssd: Single shot multibox detector . In ECCV (1) , volume 9905 of Lecture Notes in Computer Science, pages 21 - 37 . Springer, 2016 .

[8] Joseph Redmon , Santosh Kumar Divvala, Ross B. Girshick , and Ali Farhadi . You only look once: Unified, real-time object detection . 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , pages 779 - 788 , 2015 .

[9] Daniel Bolya , Chong Zhou, Fanyi Xiao, and Yong Jae Lee. Yolact: Real-time instance segmentation . In ICCV , 2019 .