TY - JOUR
T1 - Classification of fungal genera from microscopic images using artificial intelligence
AU - Rahman, Md Arafatur
AU - Clinch, Madelyn
AU - Reynolds, Jordan
AU - Dangott, Bryan
AU - Meza Villegas, Diana M.
AU - Nassar, Aziza
AU - Hata, D. Jane
AU - Akkus, Zeynettin
N1 - Publisher Copyright:
© 2023
PY - 2023/1
Y1 - 2023/1
N2 - Microscopic image examination is fundamental to clinical microbiology and often used as the first step to diagnose fungal infections. In this study, we present classification of pathogenic fungi from microscopic images using deep convolutional neural networks (CNN). We trained well-known CNN architectures such as DenseNet, Inception ResNet, InceptionV3, Xception, ResNet50, VGG16, and VGG19 to identify fungal species, and compared their performances. We collected 1079 images of 89 fungi genera and split our data into training, validation, and test datasets by 7:1:2 ratio. The DenseNet CNN model provided the best performance among other CNN architectures with overall accuracy of 65.35% for top 1 prediction and 75.19% accuracy for top 3 predictions for classification of 89 genera. The performance is further improved (>80%) after excluding rare genera with low sample occurrence and applying data augmentation techniques. For some particular fungal genera, we obtained 100% prediction accuracy. In summary, we present a deep learning approach that shows promising results in prediction of filamentous fungi identification from culture, which could be used to enhance diagnostic accuracy and decrease turnaround time to identification.
AB - Microscopic image examination is fundamental to clinical microbiology and often used as the first step to diagnose fungal infections. In this study, we present classification of pathogenic fungi from microscopic images using deep convolutional neural networks (CNN). We trained well-known CNN architectures such as DenseNet, Inception ResNet, InceptionV3, Xception, ResNet50, VGG16, and VGG19 to identify fungal species, and compared their performances. We collected 1079 images of 89 fungi genera and split our data into training, validation, and test datasets by 7:1:2 ratio. The DenseNet CNN model provided the best performance among other CNN architectures with overall accuracy of 65.35% for top 1 prediction and 75.19% accuracy for top 3 predictions for classification of 89 genera. The performance is further improved (>80%) after excluding rare genera with low sample occurrence and applying data augmentation techniques. For some particular fungal genera, we obtained 100% prediction accuracy. In summary, we present a deep learning approach that shows promising results in prediction of filamentous fungi identification from culture, which could be used to enhance diagnostic accuracy and decrease turnaround time to identification.
KW - Artificial intelligence
KW - Convolutional neural network
KW - Fungal genera classification
KW - Mycology
UR - http://www.scopus.com/inward/record.url?scp=85153606053&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85153606053&partnerID=8YFLogxK
U2 - 10.1016/j.jpi.2023.100314
DO - 10.1016/j.jpi.2023.100314
M3 - Article
AN - SCOPUS:85153606053
SN - 2229-5089
VL - 14
JO - Journal of Pathology Informatics
JF - Journal of Pathology Informatics
M1 - 100314
ER -