A deep contrastive learning-based image retrieval system for automatic detection of infectious cattle diseases
Abstract Anaplasmosis, which is caused by Anaplasma spp. and transmitted by tick bites, is one of the most serious livestock animal diseases worldwide, causing significant economic losses as well as public health issues. Anaplasma marginale, a gram-negative intracellular obligate bacterium, can caus...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-01-01
|
| Series: | Journal of Big Data |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40537-024-01057-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559401775759360 |
|---|---|
| author | Veerayuth Kittichai Morakot Kaewthamasorn Apinya Arnuphaprasert Rangsan Jomtarak Kaung Myat Naing Teerawat Tongloy Santhad Chuwongin Siridech Boonsang |
| author_facet | Veerayuth Kittichai Morakot Kaewthamasorn Apinya Arnuphaprasert Rangsan Jomtarak Kaung Myat Naing Teerawat Tongloy Santhad Chuwongin Siridech Boonsang |
| author_sort | Veerayuth Kittichai |
| collection | DOAJ |
| description | Abstract Anaplasmosis, which is caused by Anaplasma spp. and transmitted by tick bites, is one of the most serious livestock animal diseases worldwide, causing significant economic losses as well as public health issues. Anaplasma marginale, a gram-negative intracellular obligate bacterium, can cause disease in cattle and other ruminants. Because of the insufficient quality of the slides, a microscopic diagnostic procedure is time-consuming and challenging to diagnose. Intra- and inter-rater variation is frequently imposed on by technicians who are underqualified and unexperienced. Alternatively, algorithms could support local employees in tracking disease transmission and quick action, especially in Thailand where this cattle disease is common. As a result, the study intends to create an automated tool based on a deep neural network linked with an image-retrieval procedure for recognizing infections in microscopic pictures. The Resnext-50 model, which serves as the embedding space’s backbone and is optimized by Triplet-Margin loss, outperforms, with averaged accuracy and specificity ratings of 91.30 percent and 92.83 percent, respectively. The model’s performance was also improved by a fine-tuned procedure between k-nearest neighbor and its normalized distance of each data point, including precision of 0.833 ± 0.134, specificity of 0.930 ± 0.054, recall of 0.838 ± 0.118, and accuracy of 0.915 ± 0.025, respectively. Five-fold cross-validation confirms that the trained model using the optimal k-nearest neighbor (kNN) for the image-based retrieval system, involving 12 images, prevents overfitting via dataset variations indicating areas under the receiver operating curve rankings ranging from 0.917 to 0.922. The image retrieval technique demonstrated in this research is a prototype for a variety of applications. The findings may aid in the early diagnosis of anaplasmosis infections in remote areas without access to veterinary care or costly molecular diagnostic tools. |
| format | Article |
| id | doaj-art-ee7d9cb93fc84e4dbec3ea5fddd66803 |
| institution | Kabale University |
| issn | 2196-1115 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Journal of Big Data |
| spelling | doaj-art-ee7d9cb93fc84e4dbec3ea5fddd668032025-01-05T12:33:02ZengSpringerOpenJournal of Big Data2196-11152025-01-0112112510.1186/s40537-024-01057-7A deep contrastive learning-based image retrieval system for automatic detection of infectious cattle diseasesVeerayuth Kittichai0Morakot Kaewthamasorn1Apinya Arnuphaprasert2Rangsan Jomtarak3Kaung Myat Naing4Teerawat Tongloy5Santhad Chuwongin6Siridech Boonsang7Faculty of Medicine, King Mongkut’s Institute of Technology LadkrabangCenter of Excellence in Veterinary Parasitology, Department of Pathology, Faculty of Veterinary Science, Chulalongkorn UniversityCenter of Excellence in Veterinary Parasitology, Department of Pathology, Faculty of Veterinary Science, Chulalongkorn UniversityFaculty of Science and Technology, Suan Dusit UniversityCollege of Advanced Manufacturing Innovation, King Mongkut’s Institute of Technology LadkrabangCollege of Advanced Manufacturing Innovation, King Mongkut’s Institute of Technology LadkrabangCollege of Advanced Manufacturing Innovation, King Mongkut’s Institute of Technology LadkrabangDepartment of Electrical Engineering, School of Engineering, King Mongkut’s Institute of Technology LadkrabangAbstract Anaplasmosis, which is caused by Anaplasma spp. and transmitted by tick bites, is one of the most serious livestock animal diseases worldwide, causing significant economic losses as well as public health issues. Anaplasma marginale, a gram-negative intracellular obligate bacterium, can cause disease in cattle and other ruminants. Because of the insufficient quality of the slides, a microscopic diagnostic procedure is time-consuming and challenging to diagnose. Intra- and inter-rater variation is frequently imposed on by technicians who are underqualified and unexperienced. Alternatively, algorithms could support local employees in tracking disease transmission and quick action, especially in Thailand where this cattle disease is common. As a result, the study intends to create an automated tool based on a deep neural network linked with an image-retrieval procedure for recognizing infections in microscopic pictures. The Resnext-50 model, which serves as the embedding space’s backbone and is optimized by Triplet-Margin loss, outperforms, with averaged accuracy and specificity ratings of 91.30 percent and 92.83 percent, respectively. The model’s performance was also improved by a fine-tuned procedure between k-nearest neighbor and its normalized distance of each data point, including precision of 0.833 ± 0.134, specificity of 0.930 ± 0.054, recall of 0.838 ± 0.118, and accuracy of 0.915 ± 0.025, respectively. Five-fold cross-validation confirms that the trained model using the optimal k-nearest neighbor (kNN) for the image-based retrieval system, involving 12 images, prevents overfitting via dataset variations indicating areas under the receiver operating curve rankings ranging from 0.917 to 0.922. The image retrieval technique demonstrated in this research is a prototype for a variety of applications. The findings may aid in the early diagnosis of anaplasmosis infections in remote areas without access to veterinary care or costly molecular diagnostic tools.https://doi.org/10.1186/s40537-024-01057-7AnaplasmosisAutomatic toolsDeep neural networkDeep contrastive learningTriplet margin lossAn image retrieval procedure |
| spellingShingle | Veerayuth Kittichai Morakot Kaewthamasorn Apinya Arnuphaprasert Rangsan Jomtarak Kaung Myat Naing Teerawat Tongloy Santhad Chuwongin Siridech Boonsang A deep contrastive learning-based image retrieval system for automatic detection of infectious cattle diseases Journal of Big Data Anaplasmosis Automatic tools Deep neural network Deep contrastive learning Triplet margin loss An image retrieval procedure |
| title | A deep contrastive learning-based image retrieval system for automatic detection of infectious cattle diseases |
| title_full | A deep contrastive learning-based image retrieval system for automatic detection of infectious cattle diseases |
| title_fullStr | A deep contrastive learning-based image retrieval system for automatic detection of infectious cattle diseases |
| title_full_unstemmed | A deep contrastive learning-based image retrieval system for automatic detection of infectious cattle diseases |
| title_short | A deep contrastive learning-based image retrieval system for automatic detection of infectious cattle diseases |
| title_sort | deep contrastive learning based image retrieval system for automatic detection of infectious cattle diseases |
| topic | Anaplasmosis Automatic tools Deep neural network Deep contrastive learning Triplet margin loss An image retrieval procedure |
| url | https://doi.org/10.1186/s40537-024-01057-7 |
| work_keys_str_mv | AT veerayuthkittichai adeepcontrastivelearningbasedimageretrievalsystemforautomaticdetectionofinfectiouscattlediseases AT morakotkaewthamasorn adeepcontrastivelearningbasedimageretrievalsystemforautomaticdetectionofinfectiouscattlediseases AT apinyaarnuphaprasert adeepcontrastivelearningbasedimageretrievalsystemforautomaticdetectionofinfectiouscattlediseases AT rangsanjomtarak adeepcontrastivelearningbasedimageretrievalsystemforautomaticdetectionofinfectiouscattlediseases AT kaungmyatnaing adeepcontrastivelearningbasedimageretrievalsystemforautomaticdetectionofinfectiouscattlediseases AT teerawattongloy adeepcontrastivelearningbasedimageretrievalsystemforautomaticdetectionofinfectiouscattlediseases AT santhadchuwongin adeepcontrastivelearningbasedimageretrievalsystemforautomaticdetectionofinfectiouscattlediseases AT siridechboonsang adeepcontrastivelearningbasedimageretrievalsystemforautomaticdetectionofinfectiouscattlediseases AT veerayuthkittichai deepcontrastivelearningbasedimageretrievalsystemforautomaticdetectionofinfectiouscattlediseases AT morakotkaewthamasorn deepcontrastivelearningbasedimageretrievalsystemforautomaticdetectionofinfectiouscattlediseases AT apinyaarnuphaprasert deepcontrastivelearningbasedimageretrievalsystemforautomaticdetectionofinfectiouscattlediseases AT rangsanjomtarak deepcontrastivelearningbasedimageretrievalsystemforautomaticdetectionofinfectiouscattlediseases AT kaungmyatnaing deepcontrastivelearningbasedimageretrievalsystemforautomaticdetectionofinfectiouscattlediseases AT teerawattongloy deepcontrastivelearningbasedimageretrievalsystemforautomaticdetectionofinfectiouscattlediseases AT santhadchuwongin deepcontrastivelearningbasedimageretrievalsystemforautomaticdetectionofinfectiouscattlediseases AT siridechboonsang deepcontrastivelearningbasedimageretrievalsystemforautomaticdetectionofinfectiouscattlediseases |