Automated Detection and Cropping of Hyphae in Microscopic Images of Various Fungi

Fusarium oxysporum f. sp. cubense is a soil-borne fungi that has become a major threat to the current banana industry. The presence of this fungi can destroy entire plantations if not detected and stopped early enough. The purpose of this study is to create a Convolutional Neural Network (CNN) that...

Full description

Saved in:
Bibliographic Details
Main Authors: Cajucom, Luis Gabriel A, Abigan, Erinn Giannice T, Ong, Josh Daniel L, Abu, Patricia Angela R, Estuar, Ma. Regina Justina E
Format: text
Published: Archīum Ateneo 2021
Subjects:
Online Access:https://archium.ateneo.edu/discs-faculty-pubs/245
https://ieeexplore.ieee.org/document/9591115
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Ateneo De Manila University
id ph-ateneo-arc.discs-faculty-pubs-1244
record_format eprints
spelling ph-ateneo-arc.discs-faculty-pubs-12442022-01-28T07:56:02Z Automated Detection and Cropping of Hyphae in Microscopic Images of Various Fungi Cajucom, Luis Gabriel A Abigan, Erinn Giannice T Ong, Josh Daniel L Abu, Patricia Angela R Estuar, Ma. Regina Justina E Fusarium oxysporum f. sp. cubense is a soil-borne fungi that has become a major threat to the current banana industry. The presence of this fungi can destroy entire plantations if not detected and stopped early enough. The purpose of this study is to create a Convolutional Neural Network (CNN) that can detect hyphae in microscopic images. By detecting hyphae, the presence of fungi in the soil can be confirmed. To create a model that can detect hyphae, a dataset of various microscopic images of fungi was sorted into hyphae images and non-hyphae images (labeled as others). Four subsequent datasets were created from this, namely: (1) bright field, (2) dark field, (3) fluorescent, and (4) all microscopy techniques. Pretrained ResNet34 and ResNet152 models were used for each of the datasets and the use of heatmaps on these models was done to analyze how the models looked for hyphae. The ResNet34 model achieved accuracies of 86.38% for bright field, 87.31% for dark field, 88.37% for fluorescent, and 87.60% for all microscopy techniques. The ResNet152 model achieved accuracies of 87.97% for bright field, 86.79% for dark field, 89.37% for fluorescent, and 87.69% for all microscopy techniques. Additionally, to improve the accuracy even further, automated cropping using edge detection and contour detection was done on the datasets to create cropped photos of hyphae. This resulted in average test accuracies of 87.17% for bright field, 86.90% for dark field, 91.22% for fluorescent, and 89.99% for all microscopy techniques. Generally, fluorescent consistently performed the best, but the heatmaps generated from each model show that hyphae can also be detected using the other microscopy techniques. This study can act as a steppingstone for future studies involving the classification of fungi through hyphae and other features. 2021-01-01T08:00:00Z text https://archium.ateneo.edu/discs-faculty-pubs/245 https://ieeexplore.ieee.org/document/9591115 Department of Information Systems & Computer Science Faculty Publications Archīum Ateneo Fungi Heating systems Training Analytical models Microscopy Image edge detection Fluorescence Microscopy image analysis convolutional neural networks hyphae detection automated cropping Computer Sciences Databases and Information Systems Fungi Microbiology
institution Ateneo De Manila University
building Ateneo De Manila University Library
continent Asia
country Philippines
Philippines
content_provider Ateneo De Manila University Library
collection archium.Ateneo Institutional Repository
topic Fungi
Heating systems
Training
Analytical models
Microscopy
Image edge detection
Fluorescence
Microscopy image analysis
convolutional neural networks
hyphae detection
automated cropping
Computer Sciences
Databases and Information Systems
Fungi
Microbiology
spellingShingle Fungi
Heating systems
Training
Analytical models
Microscopy
Image edge detection
Fluorescence
Microscopy image analysis
convolutional neural networks
hyphae detection
automated cropping
Computer Sciences
Databases and Information Systems
Fungi
Microbiology
Cajucom, Luis Gabriel A
Abigan, Erinn Giannice T
Ong, Josh Daniel L
Abu, Patricia Angela R
Estuar, Ma. Regina Justina E
Automated Detection and Cropping of Hyphae in Microscopic Images of Various Fungi
description Fusarium oxysporum f. sp. cubense is a soil-borne fungi that has become a major threat to the current banana industry. The presence of this fungi can destroy entire plantations if not detected and stopped early enough. The purpose of this study is to create a Convolutional Neural Network (CNN) that can detect hyphae in microscopic images. By detecting hyphae, the presence of fungi in the soil can be confirmed. To create a model that can detect hyphae, a dataset of various microscopic images of fungi was sorted into hyphae images and non-hyphae images (labeled as others). Four subsequent datasets were created from this, namely: (1) bright field, (2) dark field, (3) fluorescent, and (4) all microscopy techniques. Pretrained ResNet34 and ResNet152 models were used for each of the datasets and the use of heatmaps on these models was done to analyze how the models looked for hyphae. The ResNet34 model achieved accuracies of 86.38% for bright field, 87.31% for dark field, 88.37% for fluorescent, and 87.60% for all microscopy techniques. The ResNet152 model achieved accuracies of 87.97% for bright field, 86.79% for dark field, 89.37% for fluorescent, and 87.69% for all microscopy techniques. Additionally, to improve the accuracy even further, automated cropping using edge detection and contour detection was done on the datasets to create cropped photos of hyphae. This resulted in average test accuracies of 87.17% for bright field, 86.90% for dark field, 91.22% for fluorescent, and 89.99% for all microscopy techniques. Generally, fluorescent consistently performed the best, but the heatmaps generated from each model show that hyphae can also be detected using the other microscopy techniques. This study can act as a steppingstone for future studies involving the classification of fungi through hyphae and other features.
format text
author Cajucom, Luis Gabriel A
Abigan, Erinn Giannice T
Ong, Josh Daniel L
Abu, Patricia Angela R
Estuar, Ma. Regina Justina E
author_facet Cajucom, Luis Gabriel A
Abigan, Erinn Giannice T
Ong, Josh Daniel L
Abu, Patricia Angela R
Estuar, Ma. Regina Justina E
author_sort Cajucom, Luis Gabriel A
title Automated Detection and Cropping of Hyphae in Microscopic Images of Various Fungi
title_short Automated Detection and Cropping of Hyphae in Microscopic Images of Various Fungi
title_full Automated Detection and Cropping of Hyphae in Microscopic Images of Various Fungi
title_fullStr Automated Detection and Cropping of Hyphae in Microscopic Images of Various Fungi
title_full_unstemmed Automated Detection and Cropping of Hyphae in Microscopic Images of Various Fungi
title_sort automated detection and cropping of hyphae in microscopic images of various fungi
publisher Archīum Ateneo
publishDate 2021
url https://archium.ateneo.edu/discs-faculty-pubs/245
https://ieeexplore.ieee.org/document/9591115
_version_ 1724079142055444480