VGG19-DeFungi: A Novel Approach for Direct Fungal Infection Detection Using VGG19 and Microscopic Images

Asadi Amiri, Sekine; Mohammady, Fatemeh

doi:10.22044/jadm.2024.14731.2575

Document Type : Technical Paper

Authors

Department of Computer Engineering, Faculty of Engineering and Technology, University of Mazandaran, Babolsar, Iran.

https://doi.org/10.22044/jadm.2024.14731.2575

Abstract

Fungal infections, capable of establishing in various tissues and organs, are responsible for many human diseases that can lead to serious complications. The initial step in diagnosing fungal infections typically involves the examination of microscopic images. Direct microscopic examination using potassium hydroxide is commonly employed as a screening method for diagnosing superficial fungal infections. Although this type of examination is quicker than other diagnostic methods, the evaluation of a complete sample can be time-consuming. Moreover, the diagnostic accuracy of these methods may vary depending on the skill of the practitioner and does not guarantee full reliability. This paper introduces a novel approach for diagnosing fungal infections using a modified VGG19 deep learning architecture. The method incorporates two significant changes: replacing the Flatten layer with Global Average Pooling (GAP) to reduce feature count and model complexity, thereby enhancing the extraction of significant features from images. Additionally, a Dense layer with 1024 neurons is added post-GAP, enabling the model to better learn and integrate these features. The Defungi microscopic dataset was used for training and evaluating the model. The proposed method can identify fungal diseases with an accuracy of 97%, significantly outperforming the best existing method, which achieved an accuracy of 92.49%. This method not only significantly outperforms existing methods, but also, given its high accuracy, is valuable in the field of diagnosing fungal infections. This work demonstrates that the use of deep learning in diagnosing fungal diseases can lead to a substantial improvement in the quality of health services.

Keywords

Main Subjects

H.5. Image Processing and Computer Vision

References

[1] TM. Butt, C. Jackson and N. Magan N, "Fungi as biocontrol agents: progress problems and potential," 2001.

[2] CL. Duddington, "Microorganisms as allies. The industrial use of fungi and bacteria", 1961.

[3] P. Badiee and Z. Hashemizadeh, "Opportunistic invasive fungal infections," diagnosis & clinical management. Indian Journal of Medical Research. vol. 139, no. 2, pp. 195–204, 2014.

[4] D. Huang, D. He and L. Gong, "A prediction model for hospital mortality in patients with severe community-acquired pneumonia and chronic obstructive pulmonary disease," Respiratory Research. vol. 23, no. 1, pp. 250, 2022.

[5] T. Lahmer, PM. Peçanha-Pietrobom, RM. Schmid and AL. Colombo, "Invasive fungal infections in acute and chronic liver impairment," a systematic review. Mycoses. vol. 65, no. 2, pp.140151, 2022.

[6] M. Esheli, B. Thissera, HR. El-Seedi and ME. Rateb, "Fungal metabolites in human health and diseases—an overview," Encyclopedia. vol. 2, no. 3, pp.1590-1601, 2022.

[7] M. Nucci and KA. Marr, "Emerging fungal diseases," Clinical Infectious Diseases. vol. 41, no. 4, pp. 521–526, 2005.

[8] ML. Rodrigues and JD. Nosanchuk, "Fungal diseases as neglected pathogens: a wakeup call to public health officials," Advances in Clinical Immunology, Medical Microbiology, COVID-19, and Big Data, 2021.

[9] PP. Bosshard, "Incubation of fungal cultures: how long is long enough?" Mycoses. vol. 54, no .5, pp. e539-e545, 2011.

[10] M. Pihet, N. Clément and C. Kauffmann-Lacroix, "Diagnosis of dermatophytosis: an evaluationof direct examinationusing MycetColor®and MycetFluo," Diagnostic Microbiology and Infectious Disease. vol. 83, no. 2, pp.170-174, 2015.

[11] R. Robert and M. Pihet, "Conventional methods for the diagnosis of dermatophytosis," Mycopathologia. vol. 166, no. 6, pp. 295-306, 2008.

[12] S. Jiang, Y. Chen, S. Han, L. Lv and L. Li, "Next-generation sequencing applications for the study of fungal pathogens," Microorganisms. vol. 10, no. 10, pp. 1882, 2022.

[13] G. De-Pascale and M. Tumbarello, "Fungal infections in the ICU," Current Opinion in Critical Care. Curr. vol. 21, no. 5, pp. 421-429, 2015.

[14] PG. Pappas, MS. Lionakis, MC. Arendrup, L. Ostrosky-Zeichner and BJ. Kullberg, "Invasive candidiasis. Invasive candidiasis," Nature Reviews Disease Primers. vol. 4, no. 1, pp. 1-20, 2018.

[15] S. Cuervo, F. Bolanos, M. Vallejo and AC. Mesa-Arango, "Fusarium species identification by means of digital signal processing". In 2019 IEEE 4th Colombian Conference on Automatic Control (CCAC). pp. 1-5, 2019.

[16] B. Zielinski, A. Sroka-Oleksiak, D. Rymarczyk, A. Piekarczyk and M. Brzychczy-Wloch, "Deep learning approach to describe and classify fungi microscopic images," PloS one. 15-6: e0234806, 2020.

[17] C. J. P. Sopo, F. Hajati and S. Gheisari, "DeFungi: direct mycological examination of microscopic fungi images," arXiv preprint, 2021.

[18] S. Rawat, B. Bisht, V. Bisht, N. Rawat and A. Rawat, "MeFunX: A novel meta-learning-based deep learning architecture to detect fungal infection directly from microscopic images," Franklin Ope. pp.100069, 2024.

[19] M. Li, , R. Xu, Z. Yang, W.Hong, W, X. An and Y.Yeh, "Optimization approach of berth-quay crane-truck allocation by the tide, environment and uncertainty factors based on chaos quantum adaptive seagull optimization algorithm," Applied Soft Computing. pp. 111197, 2024.‏

[20] S. Ahmed and A. Haque, "Microscopic Fungi Classification Using Vision Transformer Guided by Transfer Learning Approach," In 2023 26th International Conference on Computer and Information Technology (ICCIT). pp. 1-6, 2023.

[21] M.Rahman, M.Clinch, J. Reynolds, B. Dangott, D. Villegas and A. Nassar, "Classification of fungal genera from microscopic images using artificial intelligence,". Journal of Pathology Informatics. pp. 100314, 2023.‏

[22] Iicio labmicologia. 2023 July 15. https://www.leticiasopomicologia.com/.

[23] S Asadi Amiri, M. Nasrolahzadeh, Z. Mohamadpoory, A. Movahedinia and A. Zare, "A Novel Method for Fish Spoilage Detection based on Fish Eye Images using Deep Convolutional Inception-ResNet-v2," Journal of AI and Data Mining. vol. 12, no.1, pp. 105-113, 2024.‏

VGG19-DeFungi: A Novel Approach for Direct Fungal Infection Detection Using VGG19 and Microscopic Images

References

References

Volume 12, Issue 2April 2024Pages 305-314

Volume 12, Issue 2
April 2024
Pages 305-314