Transfer Learning Approach for the Classification of Conidial Fungi (Genus Aspergillus) Thru Pre-trained Deep Learning Models

Mital, Matt Ervin; Tobias, Rogelio Ruzcko; Villaruel, Herbert V.; Maningo, Jose Martin Z.; Billones, Robert Kerwin C.; Vicerra, Ryan Rhay P.; Dadios, Elmer P.

doi:10.1109/tencon50793.2020.9293803

Cited by 16 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It enables rapid analysis of large image datasets, facilitating timely and informed decisions in healthcare and agriculture. Automated classification mitigates the risk of human error and supports research by providing consistent, reproducible results, which is critical for understanding disease patterns and contributing to public health efforts [7,8,10,11].…”

Section: Wwwdergiparkgovtr/tdfdmentioning

confidence: 99%

Classification of Microscopic Fungi Images Using Vision Transformers for Enhanced Detection of Fungal Infections

Gümüş

2024

Türk Doğa Ve Fen Dergisi

View full text Add to dashboard Cite

Fungi play a pivotal role in our ecosystem and human health, serving as both essential contributors to environmental sustainability and significant agents of disease. The importance of precise fungi detection cannot be overstated, as it underpins effective disease management, agricultural productivity, and the safeguarding of global food security. This research explores the efficacy of vision transformer-based architectures for the classification of microscopic fungi images of various fungal types to enhance the detection of fungal infections. The study compared the pre-trained base Vision Transformer (ViT) and Swin Transformer models, evaluating their capability in feature extraction and fine-tuning. The incorporation of transfer learning and fine-tuning strategies, particularly with data augmentation, significantly enhances model performance. Utilizing a comprehensive dataset with and without data augmentation, the study reveals that Swin Transformer, particularly when fine-tuned, exhibits superior accuracy (98.36%) over ViT model (96.55%). These findings highlight the potential of vision transformer-based models in automating and refining the diagnosis of fungal infections, promising significant advancements in medical imaging analysis.

show abstract

Section: Wwwdergiparkgovtr/tdfdmentioning

confidence: 99%

Classification of Microscopic Fungi Images Using Vision Transformers for Enhanced Detection of Fungal Infections

Gümüş

2024

Türk Doğa Ve Fen Dergisi

View full text Add to dashboard Cite

show abstract

“…In some preliminary reports, the CNN transfer learning model has been successfully applied to diagnose filamentous fungi. Most of the previous reports focused only on the genus Aspergillus and used macroscopic patterns ( 32 , 33 ). Microscopic morphologies’ characteristics are critical for accurately identifying filamentous fungi and are a crucial determining factor for fungus identification since macroscopic patterns might be similar between different (species or genera) of fungi.…”

Section: Introductionmentioning

confidence: 99%

Attention-Guided Transfer Learning for Identification of Filamentous Fungi Encountered in the Clinical Laboratory

Huang

Wang

et al. 2023

Microbiol Spectr

View full text Add to dashboard Cite

This study utilizes transfer learning with CNNs to classify fungal genera and identify Aspergillus species using microscopic images from touch-tape preparation and lactophenol cotton blue staining. The training and test data sets included 4,108 images with representative microscopic morphology for each genus, and a soft attention mechanism was incorporated to enhance classification accuracy.

show abstract

“…The motivation behind this research lies in addressing the need for an efficient, reliable, and automated method to classify microscopic fungi [11] responsible for superficial infections.…”

Section: Introductionmentioning

confidence: 99%

Detection of Fungal Infections from Microscopic Fungal Images Using Deep Learning Techniques

CINAR,

TASPINAR

2023

icat

View full text Add to dashboard Cite

Fungal infections, due to their diverse manifestations and varying characteristics, present significant challenges in medical diagnosis. This study delves into applying deep-learning techniques for detecting fungal infections from microscopic fungal images. By harnessing the power of Convolutional Neural Networks (CNNs), we propose an approach that employs transfer learning to accurately classify different fungal species. The dataset comprises microscopic images of various fungal types, and to enhance model performance, we utilize data augmentation techniques. Furthermore, we aim to boost performance by fine-tuning the model's layers. Initially starting at 84.38% accuracy, our experimental results progressively reached high values of 95.35% and 97.19%. These results underscore the effectiveness of our deep learning approach in precisely identifying and classifying fungal infections. This success holds promising potential to aid medical professionals in timely and accurate diagnoses. The findings presented in this study contribute to ongoing research in medical image analysis and drive advancements in the field of automated disease detection.

show abstract

Transfer Learning Approach for the Classification of Conidial Fungi (Genus Aspergillus) Thru Pre-trained Deep Learning Models

Cited by 16 publications

References 11 publications

Classification of Microscopic Fungi Images Using Vision Transformers for Enhanced Detection of Fungal Infections

Classification of Microscopic Fungi Images Using Vision Transformers for Enhanced Detection of Fungal Infections

Attention-Guided Transfer Learning for Identification of Filamentous Fungi Encountered in the Clinical Laboratory

Detection of Fungal Infections from Microscopic Fungal Images Using Deep Learning Techniques

Contact Info

Product

Resources

About