FecalNet: Automated detection of visible components in human feces using deep learning.
Fecal components
FecalNet
automatic identification
deep learning
neural network
Journal
Medical physics
ISSN: 2473-4209
Titre abrégé: Med Phys
Pays: United States
ID NLM: 0425746
Informations de publication
Date de publication:
Sep 2020
Sep 2020
Historique:
received:
31
03
2020
revised:
16
06
2020
accepted:
17
06
2020
pubmed:
26
6
2020
medline:
15
5
2021
entrez:
26
6
2020
Statut:
ppublish
Résumé
To automate the detection and identification of visible components in feces for early diagnosis of gastrointestinal diseases, we propose FecalNet, a method using multiple deep neural networks. FecalNet uses the ResNet152 residual network to extract and learn the characteristics of visible components in fecal microscopic images, acquire feature maps in combination with the feature pyramid network, apply the full convolutional network to classify and locate the fecal components, and implement the improved focal loss function to reoptimize the classification results. This allowed the complete automation of the detection and identification of the visible components in feces. We validated this method using a fecal database of 1,122 patients. The results indicated a mean average precision (mAP) of 92.16% and an average recall (AR) of 93.56%. The average precision (AP) and AR of erythrocyte, leukocyte, intestinal mucosal epithelial cells, hookworm eggs, ascarid eggs, and whipworm eggs were 92.82% and 93.38%, 93.99% and 96.11%, 90.71% and 92.41%, 89.95% and 93.88%, 96.90% and 91.21%, and 88.61% and 94.37%, respectively. The average times required by the GPU and the CPU to analyze a fecal microscopic image are approximately 0.14 and 1.02 s, respectively. FecalNet can automate the detection and identification of visible components in feces. It also provides a detection and identification framework for detecting several other types of cells in clinical practice.
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
4212-4222Subventions
Organisme : Shenzhen Science and Technology Project
ID : JCYJ20170302152605463
Organisme : Shenzhen Science and Technology Project
ID : JCYJ20170306123423907
Organisme : Shenzhen Science and Technology Project
ID : JCYJ20180507182025817
Organisme : National Natural Science Foundation of China-Shenzhen Joint Fund Project
ID : U1713220
Informations de copyright
© 2020 American Association of Physicists in Medicine.
Références
Burri E, Beglinger C. Faecal calprotectin - a useful tool in the management of inflammatory bowel disease. Swiss Med Wkly. 2012;142:w13557.
Marie C, Petri WA Jr. Amoebic dysentery. BMJ Clin Evid. 2013;2013:0918.
Nath R, Saikia L, Choudhury G, Sharma D. Drug resistant Shigella flexneri in & around Dibrugarh, north-east India. Indian J Med Res. 2013;137:183-186.
Bethony J, Brooker S, Albonico M, et al. Soil-transmitted helminth infections: ascariasis, trichuriasis, and hookworm. Lancet. 2006;367:1521-1532.
Guerrant RL, Oria RB, Moore SR, Oria MO, Lima AA. Malnutrition as an enteric infectious disease with long-term effects on child development. Nutr Rev. 2008;66:487-505.
Hall A, Hewitt G, Tuffrey V, Silva ND. A review and meta-analysis of the impact of intestinal worms on child growth and nutrition. Matern Child Nutr. 2008;4:118-236.
Stephenson LS, Latham MC, Ottesen EA. Malnutrition and parasitic helminth infections. Parasitology. 2000;121:23-38.
Garcia LS. Diagnostic medical parasitology. LWW. 2007;27:707-708.
Avci D, Varol A. An expert diagnosis system for classification of human parasite eggs based on multi-class SVM. Expert Syst Appl. 2009;36:43-48.
Zhang J, Lin Y, Liu Y, et al. Cascaded-automatic segmentation for Schistosoma japonicum eggs in images of fecal samples. Comput Biol Med. 2014;52:18-27.
Kumar R, Vázquez-Reina A, Pfister H. Radon-like features and their application to connectomics. IEEE. 2010;2010:186-193.
Liu L, Lei H, Zhang J, et al. Automatic identification of human erythrocytes in microscopic fecal specimens. J Med Syst. 2015;39:146.
Li Z, Gong H, Zhang W, et al. A robust and automatic method for human parasite egg recognition in microscopic images. Parasitol Res. 2015;114:3807-3813.
Wang W, Si MM, Chen FQ, Liu H, Jing XM. Study on recognition method of label-free red and white cell using fecal microscopic image. ICBCB 2018: Proceedings of the 2018 6th International Conference on Bioinformatics and Computational Biology; 2018:95-100.
Tchinda BS, Noubom M, Tchiotsop D, Valerie LD, Didier W. Towards an automated medical diagnosis system for intestinal parasitosis. Inform Med Unlocked. 2019;16:100238.
Wang XZ, Liu L, Du XH, et al. Leukocyte recognition in human fecal samples using texture features. J Opt Soc Am A. 2018;35:1941-1948.
Li C, Xu C, Gui C, Fox MD. Distance regularized level set evolution and its application to image segmentation. IEEE Trans Image Process. 2010;19:3243-3254.
Chandrasiri S, Samarasinghe P. Morphology based automatic disease analysis through evaluation of red blood cells. ISMS. 2014;318-323.
Du X, Liu L, Wang X, et al. Automatic classification of cells in microscopic fecal images using convolutional neural networks. Biosci Rep. 2019;39:BSR20182100.
Zhang J, Zhong Y, Wang XZ, et al. Computerized detection of leukocytes in microscopic leukorrhea images. Med Phys. 2017;44:4620-4629.
Wang YP, Cao YP. Human peripheral blood leukocyte classification method based on convolutional neural network and data augmentation. Med Phys. 2020;47:142-151.
Li YN, Zheng R, Wu YZ, et al. A low-cost, automated parasite diagnostic system via a portable, robotic microscope and deep learning. J Biophotonics. 2019;12:e201800410.
Lin TY, Goyal P, Girshick R, He K, Dollar P. Focal loss for dense object detection. IEEE Trans Pattern Anal Mach Intell. 2017;99:2999-3007.
He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. IEEE. 2016;1063-6919.
Lin TY, Dollár P, Girshick R, He K, Hariharan B, Belongie S. Feature Pyramid networks for object detection. IEEE; 2016:936-944.
Shelhamer E, Long J, Darrell T. Fully convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell. 2017;39:640-651.
Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. ICLR. 2015;2014:1409-1556.
Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions. IEEE open access; 2015:1-9.
Fukui A, Park DH, Yang D, Rohrbach A, Darrell T, Rohrbach M. Multimodal compact bilinear pooling for visual question answering and visual grounding. EMNLP; 2016.
Kingma D, Ba J. Adam: a method for stochastic optimization. Comput Sci; 2014;1412: 2333-9721.
Joseph R, Ali F. YOLOv3: An Incremental Improvement. Comput Sci; 2018.