Morphologic Identification of Clinically Encountered Moulds Using a Residual Neural Network

Overview

Journal Front Microbiol

Specialty Microbiology

Date 2022 Oct 31

PMID 36312928

Authors

Ran Jing

Xiang-Long Yin

Xiu-Li Xie

He-Qing Lian

Jin Li

Ge Zhang

Wen-Hang Yang

Tian-Shu Sun

Ying-Chun Xu

Affiliations

Soon will be listed here.

Abstract

The use of morphology to diagnose invasive mould infections in China still faces substantial challenges, which often leads to delayed diagnosis or misdiagnosis. We developed a model called XMVision Fungus AI to identify mould infections by training, testing, and evaluating a ResNet-50 model. Our research achieved the rapid identification of nine common clinical moulds: complex, complex, complex, complex, , , , spp., and spp. In our study, the adaptive image contrast enhancement enabling XMVision Fungus AI as a promising module by effectively improve the identification performance. The overall identification accuracy of XMVision Fungus AI was up to 93.00% (279/300), which was higher than that of human readers. XMVision Fungus AI shows intrinsic advantages in the identification of clinical moulds and can be applied to improve human identification efficiency through training. Moreover, it has great potential for clinical application because of its convenient operation and lower cost. This system will be suitable for primary hospitals in China and developing countries.

References

Ho C, Jean N, Hogan C, Blackmon L, Jeffrey S, Holodniy M . Rapid identification of pathogenic bacteria using Raman spectroscopy and deep learning. Nat Commun. 2019; 10(1):4927. PMC: 6960993. DOI: 10.1038/s41467-019-12898-9. View

Ren S, He K, Girshick R, Sun J . Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Trans Pattern Anal Mach Intell. 2016; 39(6):1137-1149. DOI: 10.1109/TPAMI.2016.2577031. View

Kaliamurthy J, Kalavathy C, Nelson Jesudasan C, Thomas P . Keratitis due to Chaetomium sp. Case Rep Ophthalmol Med. 2012; 2011:696145. PMC: 3350250. DOI: 10.1155/2011/696145. View

Balajee S, Borman A, Brandt M, Cano J, Cuenca-Estrella M, Dannaoui E . Sequence-based identification of Aspergillus, fusarium, and mucorales species in the clinical mycology laboratory: where are we and where should we go from here?. J Clin Microbiol. 2008; 47(4):877-84. PMC: 2668331. DOI: 10.1128/JCM.01685-08. View

McCoy D, DePestel D, Carver P . Primary antifungal prophylaxis in adult hematopoietic stem cell transplant recipients: current therapeutic concepts. Pharmacotherapy. 2009; 29(11):1306-25. DOI: 10.1592/phco.29.11.1306. View

Ledoux M, Guffroy B, Nivoix Y, Simand C, Herbrecht R . Invasive Pulmonary Aspergillosis. Semin Respir Crit Care Med. 2020; 41(1):80-98. DOI: 10.1055/s-0039-3401990. View

Balajee S, Houbraken J, Verweij P, Hong S, Yaghuchi T, Varga J . Aspergillus species identification in the clinical setting. Stud Mycol. 2008; 59:39-46. PMC: 2275201. DOI: 10.3114/sim.2007.59.05. View

Anita , Yadav A . An Intelligent Model for the Detection of White Blood Cells using Artificial Intelligence. Comput Methods Programs Biomed. 2020; 199:105893. DOI: 10.1016/j.cmpb.2020.105893. View

Yu X, Kang C, Guttery D, Kadry S, Chen Y, Zhang Y . ResNet-SCDA-50 for Breast Abnormality Classification. IEEE/ACM Trans Comput Biol Bioinform. 2020; 18(1):94-102. DOI: 10.1109/TCBB.2020.2986544. View

10.

Wang Z, Zhang L, Zhao M, Wang Y, Bai H, Wang Y . Deep Neural Networks Offer Morphologic Classification and Diagnosis of Bacterial Vaginosis. J Clin Microbiol. 2020; 59(2). PMC: 8111127. DOI: 10.1128/JCM.02236-20. View

11.

Sh Y, Liu B, Zhang J, Zhou Y, Hu Z, Zhang X . Application of Artificial Intelligence Modeling Technology Based on Fluid Biopsy to Diagnose Alzheimer's Disease. Front Aging Neurosci. 2021; 13:768229. PMC: 8679840. DOI: 10.3389/fnagi.2021.768229. View

12.

Li Y, Wang H, Zhao Y, Xu Y, Hsueh P . Evaluation of the Bruker Biotyper Matrix-Assisted Laser Desorption/Ionization Time-of-Flight Mass Spectrometry System for Identification of Species Directly from Growth on Solid Agar Media. Front Microbiol. 2017; 8:1209. PMC: 5489701. DOI: 10.3389/fmicb.2017.01209. View

13.

Lefler E, Haim S, Merzbach D . Evaluation of direct microscopic examination versus culture in the diagnosis of superficial fungal infections. Mykosen. 1981; 24(2):102-6. DOI: 10.1111/j.1439-0507.1981.tb01841.x. View

14.

Zhang J, Wang X, Ni G, Liu J, Hao R, Liu L . Fast and accurate automated recognition of the dominant cells from fecal images based on Faster R-CNN. Sci Rep. 2021; 11(1):10361. PMC: 8121882. DOI: 10.1038/s41598-021-89863-4. View

15.

Su Y, Li D, Chen X . Lung Nodule Detection based on Faster R-CNN Framework. Comput Methods Programs Biomed. 2020; 200:105866. DOI: 10.1016/j.cmpb.2020.105866. View

16.

Esteva A, Kuprel B, Novoa R, Ko J, Swetter S, Blau H . Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017; 542(7639):115-118. PMC: 8382232. DOI: 10.1038/nature21056. View

17.

Peng Y, Zhang Q, Xu C, Shi W . MALDI-TOF MS for the rapid identification and drug susceptibility testing of filamentous fungi. Exp Ther Med. 2019; 18(6):4865-4873. PMC: 6895777. DOI: 10.3892/etm.2019.8118. View

18.

Ma H, Yang J, Chen X, Jiang X, Su Y, Qiao S . Deep convolutional neural network: a novel approach for the detection of Aspergillus fungi via stereomicroscopy. J Microbiol. 2021; 59(6):563-572. DOI: 10.1007/s12275-021-1013-z. View

19.

Jing R, Yang W, Xiao M, Li Y, Zou G, Wang C . Species identification and antifungal susceptibility testing of Aspergillus strains isolated from patients with otomycosis in northern China. J Microbiol Immunol Infect. 2021; 55(2):282-290. DOI: 10.1016/j.jmii.2021.03.011. View

20.

Gong Y, Li C, Wang C, Li J, Ding M, Chen D . Epidemiology and Mortality-Associated Factors of Invasive Fungal Disease in Elderly Patients: A 20-Year Retrospective Study from Southern China. Infect Drug Resist. 2020; 13:711-723. PMC: 7061722. DOI: 10.2147/IDR.S242187. View