Fluke Eggs Detection and Classifcation Using Deep Convolution Neural Network
Article Sidebar
Main Article Content
Abstract
We present the experimental results of utilizing object detection to solve the problem of detecting and also classifying the parasite eggs in the fecal slides. We experimented with different detection techniques and different sizes of the backbone part. The trained models were evaluated using standard mean Average Precision (mAP) on the results from labeled data collected from the closed environment and also manual evaluation on the results from feld data collected from actual medical diagnoses that do not have accurate labels. On the lab data, VFNet achieved a very good 0.897 mAP at the Intersection over Union (IoU) of 0.7 thresholds but performed rather poorly in the classifcation part on the feld data. The relatively older technique Cascade Faster R-CNN had a little below average result in the lab data but had a very good classifcation accuracy on the feld data. The backbone part also had conflicting results on the lab data and feld data. The smaller backbones performed better in the lab data but lost to the bigger backbones on the feld data.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
เนื้อหาข้อมูล
References
F. Bray, J. Ferlay, I. Soerjomataram et al., “Global Cancer Statistics 2018: Globocan Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries,” CA: A Cancer Journal for Clinicians, vol. 68, no. 6, pp. 394–424, Sep. 2018.
J. M. Bruun, C. M. Kapel, and J. M. Carstensen. (2012, Jun. 21). Detection and Classifcation of Parasite Eggs for Use in Helminthic Therapy. [Online]. Available: https://ieeexplore.ieee.org/document/6235888
Y. S. Yang, D. K. Park, H. C. Kim et al. (2001, Jun. 2), Automatic Identification of Human Helminth Eggs on Microscopic Fecal Specimens Using Digital Image Processing and an Artifcial Neural Network. [Online]. Available: https:// pubmed.ncbi.nlm.nih.gov/11396601/
A. Akintayo, G. L. Tylka, A. K. Singh et al. (2021, Jul. 2). A Deep Learning Framework to Discern and Count Microscopic Nematode Eggs. [Online]. Available: https://www.nature.com/articles/s41598-018-27272-w
K. Chen, J. Wang, J. Pang et al. (2019, Jun. 15). MMDetection: Open MMLab Detection Toolbox and Benchmark. [Online]. Available: https://arxiv.org/abs/1906.07155
T. Y. Lin, M. Maire, S. Belongie et al. (2015, Jun. 15). Microsoft Coco: Common Objects in Context. [Online]. Available: https://cocodataset.org
K. He, X. Zhang, S. Ren et al. (2015, Jun. 15). Deep Residual Learning for Image Recognition. [Online]. Available: https://arxiv.org/abs/1512.03385
S. Xie, R. Girshick, P. Dollár et al. (2017, Jun. 20). Aggregated Residual Transformations for Deep Neural Networks. [Online]. Available: https://arxiv.org/abs/1611.05431
X. Zhu, H. Hu, S. Lin et al. (2018, Jun.21). Deformable Convnets V2: More Deformable, Better Results. [Online]. Available: https://arxiv.org/abs/1811
.11168
T. Y. Lin, P. Goyal, R. Girshick et al. (2018). Focal Loss for Dense Object Detection. [Online]. Available: https://arxiv.org/abs/1708.02002
J. Redmon and A. Farhadi. (2021, Jun. 20). Yolov3: An
Incremental Improvement. [Online]. Available: https://arxiv.org/abs/ 1804.02767
S. Ren, K. He, R. Girshick et al. (2021, Jun. 20). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. [Online]. Available: https://arxiv.org/abs/1506.01497
Z. Cai and N. Vasconcelos. (2021, Jun. 21). Cascade R-CNN: High Quality Object Detection and Instance Segmentation. [Online]. Available: http://dx.doi.org/10.1109/tpami.2019.2956516
N. Carion, F. Massa, G. Synnaeve et al. (2021, Jun. 20). End-to-end Object Detection with Transformers. [Online] Available: https://arxiv.org/abs/2005.
A. Vaswani, N. Shazeer, N. Parmar et al. (2021, Jun. 2). Attention is All You Need. [Online] Available: https://arxiv.org/abs/1706.03762
X. Zhu, W. Su, L. Lu et al. (2021, Jun. 21). Deformable Detr: Deformable Transformers for End-to-End Object Detection. [Online] Available: https://arxiv.org/abs/2010.04159
X. Li, W. Wang, L. Wu et al. (2021, Jul. 2). Generalized Focal Loss: Learning Qualifed and Distributed Bounding Boxes for Dense Object Detection. [Online] Available: https://arxiv.org/abs/2006.04388
H. Zhang, Y. Wang, F. Dayoub et al. (2021, Mar. 4).VarifocalNet:
An IoU-aware Dense Object Detector. [Online] Available: https://arxiv.org/
abs/2008.13367