Conference Paper2024Cited by 6

Mycological Examination of Microscopic Fungi Images with Deep Learning and Gradient Weighted Class Activation Mapping Visualization

Md. Safirur Rashid, Md. Samin Morshed, Muhammad Usama Islam, Sami Rashid, Asif Mahmud, Ashraful Islam

IEEE 2024 International Advances in Science & Engineering Technology (ASET) Multi-Conferences

IEEE, pp. 01-08

DOI: 10.1109/aset60340.2024.10708690URL

Abstract

Fungal species classification is an important task with broad implications for medicine, agriculture, and ecology. Even though they work well, traditional identification techniques frequently take a lot of time, knowledge, and resources. In order to improve the effectiveness and precision of fungal classification, this work explores the use of deep learning techniques, more especially transfer learning with pre-trained Convolutional Neural Networks (CNNs). Using six well-known pre-trained models, namely ResNet-50, ResNet-101, VGG16, VGG19, InceptionV3, and InceptionV4,we modify them to categorize pictures from the DeFungi dataset, which is a varied compilation of images featuring fungal species. Our approach comprises a thorough comparative analysis based on metrics for F1 score, accuracy, and precision to assess how well these models perform in the identification of fungal species. The outcomes show that there is a lot of promise for using these trained models in mycology, with some models exhibiting better performance that might facilitate the creation of automated systems for fungal identification. This work not only advances the field of biological classification by illuminating the strengths and weaknesses of different CNN architectures for fungal classification, but it also emphasizes how crucial it is to use cutting-edge AI methods to tackle biological problems. ResNet-101 was the most accurate with accuracy result of 93 percentile of the six pre-trained models that were examined (ResNet-50, ResNet-101, VGG16, VGG19, InceptionV3, and InceptionV4).Other evaluation metrics including precision was 0.93, recall was 0.90, and F1 score was 0.91. Our results point to a promising direction for future research in automated fungal classification and provide insightful information for researchers and practitioners wishing to use machine learning in the identification and study of fungal species.

Keywords

  • pre-trained convolutional neural networks
  • ResNet-101
  • Grad-CAM
  • transfer learning
  • CNN architecture comparison

CCDS Authors

Muhammad Usama Islam, PhD
Muhammad Usama Islam

Muhammad Usama Islam, PhD

  • Collaborator, HCI Wing

Assistant Professor

+1 more affiliation

Metro State University

Sami Rashid
Sami Rashid

Sami Rashid

  • Intern, CCDS

Research Interests

Machine Learning

Asif Mahmud
Asif Mahmud

Asif Mahmud

  • Co-Director, IPT Wing

Lecturer

Department of Computer Science and Engineering

Independent University, Bangladesh

Ashraful Islam, PhD
Ashraful Islam

Ashraful Islam, PhD

  • Center Director, CCDS
  • Director, HCI Wing

Assistant Professor

Department of Computer Science and Engineering

Independent University, Bangladesh (IUB)

Published at

CHI, UIST, UbiComp, IJCNN, ICIP, HCII, ICDMW, BLP, IEEE Internet of Things Journal, JMIR, JMIR Human Factors, JMIR Formative Research, IEEE Access, Smart Agricultural Technology, Diabetes Research and Clinical Practice, PLOS ONE

Research Interests

Human-Computer Interaction, AI for Social Good, AI for Public Health, AI for Impact

References

  1. 1.Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jon Shlens, Zbigniew Wojna. (2016). Rethinking the Inception Architecture for Computer Vision. , 2818–2826[10.1109/cvpr.2016.308]
  2. 2.Sinno Jialin Pan, Qiang Yang. (2009). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359[10.1109/tkde.2009.191]
  3. 3.Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, Dhruv Batra. (2017). Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. , 618–626[10.1109/iccv.2017.74]
  4. 4.Fuzhen Zhuang, Zhiyuan Qi, Keyu Duan, Dongbo Xi, Yongchun Zhu, Hengshu Zhu, Hui Xiong, Qing He. (2020). A Comprehensive Survey on Transfer Learning. Proceedings of the IEEE, 109(1), 43–76[10.1109/jproc.2020.3004555]
  5. 5.Chuanqi Tan, Fuchun Sun, Tao Kong, Wenchang Zhang, Chao Yang, Chunfang Liu. (2018). A Survey on Deep Transfer Learning. Lecture notes in computer science, 270–279[10.1007/978-3-030-01424-7_27]
  6. 6.(2000). Measurement Reliability and Validity. Psychology Press eBooks, 319–338[10.4324/9781410605337-29]
  7. 7.Shuteng Niu, Yongxin Liu, Jian Wang, Houbing Song. (2020). A Decade Survey of Transfer Learning (2010–2020). IEEE Transactions on Artificial Intelligence, 1(2), 151–166[10.1109/tai.2021.3054609]
  8. 8.Sheldon Mascarenhas, Mukul Agarwal. (2021). A comparison between VGG16, VGG19 and ResNet50 architecture frameworks for Image Classification. , 96–99[10.1109/centcon52345.2021.9687944]
  9. 9.Monika Bansal, Munish Kumar, Monika Sachdeva, Ajay Mittal. (2021). Transfer learning for image classification using VGG19: Caltech-101 image data set. Journal of Ambient Intelligence and Humanized Computing, 14(4), 3609–3620[10.1007/s12652-021-03488-z]
  10. 10.Manali Shaha, Meenakshi M. Pawar. (2018). Transfer Learning for Image Classification. 2018 Second International Conference on Electronics, Communication and Aerospace Technology (ICECA), 656–660[10.1109/iceca.2018.8474802]
  11. 11.Sabbir Ahmed, Md. Bakhtiar Hasan, Tasnim Ahmed, Md. Redwan Karim Sony, Md. Hasanul Kabir. (2022). Less is More: Lighter and Faster Deep Neural Architecture for Tomato Leaf Disease Classification. IEEE Access, 10, 68868–68884[10.1109/access.2022.3187203]
  12. 12.Qian Xiang, Xiaodan Wang, Rui Li, Guoling Zhang, Jie Lai, Qingshuang Hu. (2019). Fruit Image Classification Based on MobileNetV2 with Transfer Learning Technique. Proceedings of the 3rd International Conference on Computer Science and Application Engineering, 1–7[10.1145/3331453.3361658]
  13. 13.Carlos Ferreira, Tânia Melo, Patrick Sousa, Maria Inês Meyer, Elham Shakibapour, Pedro Costa, Aurélio Campilho. (2018). Classification of Breast Cancer Histology Images Through Transfer Learning Using a Pre-trained Inception Resnet V2. Lecture notes in computer science, 763–770[10.1007/978-3-319-93000-8_86]
  14. 14.Bartosz Zieliński, Agnieszka Sroka-Oleksiak, Dawid Rymarczyk, Adam Piekarczyk, Monika Brzychczy‐Włoch. (2020). Deep learning approach to describe and classify fungi microscopic images. PLoS ONE, 15(6), e0234806[10.1371/journal.pone.0234806]
  15. 15.Md. Samin Morshed, Sabbir Ahmed, Tasnim Ahmed, Muhammad Usama Islam, Asif Rahman. (2022). Fruit Quality Assessment with Densely Connected Convolutional Neural Network. , 1–4[10.1109/icece57408.2022.10088873]
  16. 16.Asaduzzaman Herok, Sabbir Ahmed. (2023). Cotton Leaf Disease Identification Using Transfer Learning. , 158–162[10.1109/icict4sd59951.2023.10303323]
  17. 17.Esraa Hassan, Fatma M. Talaat, Samah A. Gamel, Samir Abdelrazek, Ahsan Aziz, Yunyoung Nam, Nora El-Rashidy. (2023). Robust Deep Learning Model for Black Fungus Detection Based on Gabor Filter and Transfer Learning. Computer Systems Science and Engineering, 47(2), 1507–1525[10.32604/csse.2023.037493]
  18. 18.Md. Sahidullah, Nasim Mahmud Nayan, Md. Samin Morshed, Mohammad Mobarak Hossain, Muhammad Usama Islam. (2023). Date Fruit Classification with Machine Learning and Explainable Artificial Intelligence. International Journal of Computer Applications, 184(50), 1–5[10.5120/ijca2023922617]
  19. 19.Sheikh Iftekhar Ahmed, A. H. M. Osama Haque. (2023). Microscopic Fungi Classification Using Vision Transformer Guided by Transfer Learning Approach. , 1–6[10.1109/iccit60459.2023.10441604]
  20. 20.María Alejandra Vanegas Álvarez, Leticia Sopó, Camilo Javier Pineda Sopo, Farshid Hajati, Soheil Gheisari. (2022). P456 Defungi: direct mycological examination of microscopic fungi images. Medical Mycology, 60(Supplement_1)[10.1093/mmy/myac072.p456]

Cited By

  1. 1.Mohsin Hossain, Mohammad Khairul Islam, Machbah Uddin, Farah Jahan, Md. Shafiul Alam Chowdhury, Md. Ahadullah. (2026). Explainable deep learning techniques for microscopic fungi classification using a learnable threshold-based ReLULeaky activation function and transfer learning. Journal of Pathology Informatics, 22, 100683[10.1016/j.jpi.2026.100683]
  2. 2.Fatma Z. Chebaani, Sara R. Noumeur, Ibtissam K. Bedaida, Stefan Stiller, Masahiro Ryo. (2026). Fungal identification using artificial intelligence: limitations of single-modality and prospects for multimodal strategies. Mycological Progress, 25(1)[10.1007/s11557-026-02169-5]
  3. 3.Seerat Singla, N. Suman Kumar, Nishant Bhandari, Kiran Sharma, Anjali, Amita Shukla. (2026). An Xception-Based Deep Learning Framework for Microscopic Fungi Image Classification. OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry (OTCON), 1–6[10.1109/otcon69332.2026.11629815]
  4. 4.Vimalenthiran Thusani, Rajendran Nirthika. (2026). DeFungi Image Classification with Image Enhancement and Feature Fusion. International Conference on Advanced Research in Computing (ICARC), 1–6[10.1109/icarc68737.2026.11453592]
  5. 5.Riya K, Christy James Jose. (2025). CBAM-Enhanced EfficientNet for Interpretable Microscopic Fungal Classification. International Conference on Smart Computing and Communications (ICSCC), 1–5[10.1109/icscc66177.2025.11233764]
  6. 6.Arafat Rahman, Mrityunjoy Gain, Md Shohanur Rahman, Sudip Kumar Saha, Apurba Adhikary, Anupam Kumar Bairagi, Avi Deb Raha. (2025). Enhancing Microscopic Fungi Classification through Advanced Pretraining in Deep Learning Models. International Conference on Electrical, Computer and Communication Engineering, 1–6[10.1109/ecce64574.2025.11013811]
← All publications