1
|
Ramos JDS, Vieira IHP, Rocha WS, Esquerdo RP, Watanabe CYV, Zanchi FB. A transfer learning approach to identify Plasmodium in microscopic images. PLoS Comput Biol 2024; 20:e1012327. [PMID: 39102445 PMCID: PMC11326699 DOI: 10.1371/journal.pcbi.1012327] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/22/2024] [Revised: 08/15/2024] [Accepted: 07/15/2024] [Indexed: 08/07/2024] Open
Abstract
Plasmodium parasites cause Malaria disease, which remains a significant threat to global health, affecting 200 million people and causing 400,000 deaths yearly. Plasmodium falciparum and Plasmodium vivax remain the two main malaria species affecting humans. Identifying the malaria disease in blood smears requires years of expertise, even for highly trained specialists. Literature studies have been coping with the automatic identification and classification of malaria. However, several points must be addressed and investigated so these automatic methods can be used clinically in a Computer-aided Diagnosis (CAD) scenario. In this work, we assess the transfer learning approach by using well-known pre-trained deep learning architectures. We considered a database with 6222 Region of Interest (ROI), of which 6002 are from the Broad Bioimage Benchmark Collection (BBBC), and 220 were acquired locally by us at Fundação Oswaldo Cruz (FIOCRUZ) in Porto Velho Velho, Rondônia-Brazil, which is part of the legal Amazon. We exhaustively cross-validated the dataset using 100 distinct partitions with 80% train and 20% test for each considering circular ROIs (rough segmentation). Our experimental results show that DenseNet201 has a potential to identify Plasmodium parasites in ROIs (infected or uninfected) of microscopic images, achieving 99.41% AUC with a fast processing time. We further validated our results, showing that DenseNet201 was significantly better (99% confidence interval) than the other networks considered in the experiment. Our results support claiming that transfer learning with texture features potentially differentiates subjects with malaria, spotting those with Plasmodium even in Leukocytes images, which is a challenge. In Future work, we intend scale our approach by adding more data and developing a friendly user interface for CAD use. We aim at aiding the worldwide population and our local natives living nearby the legal Amazon's rivers.
Collapse
Affiliation(s)
- Jonathan da Silva Ramos
- Computer Science Department, Federal University of Rondônia (DACC/UNIR), Porto Velho, Rondônia, Brazil
| | - Ivo Henrique Provensi Vieira
- Laboratório de Bioinformática e Química Medicinal, Fundação Oswaldo Cruz Rondônia, Porto Velho, Rondônia, Brazil
- Instituto Nacional de Epidemiologia na Amazônia Ocidental (INCT-EPIAMO), Porto Velho, Rondônia, Brazil
| | - Wan Song Rocha
- Instituto Nacional de Epidemiologia na Amazônia Ocidental (INCT-EPIAMO), Porto Velho, Rondônia, Brazil
- Programa de Pós-Graduação em Biologia Experimental, Universidade Federal de Rondônia (PGBIOEXP/UNIR), Porto Velho, Rondônia, Brazil
| | - Rosimar Pires Esquerdo
- Laboratório de Bioinformática e Química Medicinal, Fundação Oswaldo Cruz Rondônia, Porto Velho, Rondônia, Brazil
| | | | - Fernando Berton Zanchi
- Laboratório de Bioinformática e Química Medicinal, Fundação Oswaldo Cruz Rondônia, Porto Velho, Rondônia, Brazil
- Instituto Nacional de Epidemiologia na Amazônia Ocidental (INCT-EPIAMO), Porto Velho, Rondônia, Brazil
- Programa de Pós-Graduação em Biologia Experimental, Universidade Federal de Rondônia (PGBIOEXP/UNIR), Porto Velho, Rondônia, Brazil
| |
Collapse
|
2
|
Gozalo AS, Robinson CK, Holdridge J, Franco Mahecha OL, Elkins WR. Overview of Plasmodium spp. and Animal Models in Malaria Research. Comp Med 2024. [PMID: 38902006 PMCID: PMC11373680 DOI: 10.30802/aalas-cm-24-000019] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/22/2024]
Abstract
Malaria is a parasitic disease caused by protozoan species of the genus Plasmodium and transmitted by female mosquitos of the genus Anopheles and other Culicidae. Most of the parasites of the genus Plasmodium are highly species specific with more than 200 species described affecting different species of mammals, birds, and reptiles. Plasmodium species strictly affecting humans are P. falciparum, P. vivax, P. ovale, and P. malariae. More recently, P. knowlesi and other nonhuman primate plasmodia were found to naturally infect humans. Currently, malaria occurs mostly in poor tropical and subtropical areas of the world, and in many of these countries it is the leading cause of illness and death. For more than 100 y, animal models, have played a major role in our understanding of malaria biology. Avian Plasmodium species were the first to be used as models to study human malaria. Malaria parasite biology and immunity were first studied using mainly P. gallinaceum and P. relictum. Rodent malarias, particularly P. berghei and P. yoelii, have been used extensively as models to study malaria in mammals. Several species of Plasmodium from nonhuman primates have been used as surrogate models to study human malaria immunology, pathogenesis, candidate vaccines, and treatments. Plasmodium cynomolgi, P. simiovale, and P. fieldi are important models for studying malaria produced by P. vivax and P. ovale, while P. coatneyi is used as a model for studying severe malaria. Other nonhuman primate malarias used in research are P. fragile, P. inui, P. knowlesi, P. simium, and P. brasilianum. Very few nonhuman primate species can develop an infection with human malarias. Macaques in general are resistant to infection with P. falciparum, P. vivax, P. malariae, and P. ovale. Only apes and a few species of New World monkeys can support infection with human malarias. Herein we review the most common, and some less common, avian, reptile, and mammal plasmodia species used as models to study human malaria.
Collapse
Affiliation(s)
- Alfonso S Gozalo
- Comparative Medicine Branch, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Bethesda, Maryland
| | - Christen K Robinson
- Comparative Medicine Branch, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Bethesda, Maryland
| | - Julie Holdridge
- Comparative Medicine Branch, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Bethesda, Maryland
| | - Olga L Franco Mahecha
- Comparative Medicine Branch, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Bethesda, Maryland
| | - William R Elkins
- Comparative Medicine Branch, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Bethesda, Maryland
| |
Collapse
|
3
|
Kittichai V, Sompong W, Kaewthamasorn M, Sasisaowapak T, Naing KM, Tongloy T, Chuwongin S, Thanee S, Boonsang S. A novel approach for identification of zoonotic trypanosome utilizing deep metric learning and vector database-based image retrieval system. Heliyon 2024; 10:e30643. [PMID: 38774068 PMCID: PMC11107104 DOI: 10.1016/j.heliyon.2024.e30643] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/10/2023] [Revised: 04/28/2024] [Accepted: 05/01/2024] [Indexed: 05/24/2024] Open
Abstract
Trypanosomiasis, a significant health concern in South America, South Asia, and Southeast Asia, requires active surveys to effectively control the disease. To address this, we have developed a hybrid model that combines deep metric learning (DML) and image retrieval. This model is proficient at identifying Trypanosoma species in microscopic images of thin-blood film examinations. Utilizing the ResNet50 backbone neural network, a trained-model has demonstrated outstanding performance, achieving an accuracy exceeding 99.71 % and up to 96 % in recall. Acknowledging the necessity for automated tools in field scenarios, we demonstrated the potential of our model as an autonomous screening approach. This was achieved by using prevailing convolutional neural network (CNN) applications, and vector database based-images returned by the KNN algorithm. This achievement is primarily attributed to the implementation of the Triplet Margin Loss function as 98 % of precision. The robustness of the model demonstrated in five-fold cross-validation highlights the ResNet50 neural network, based on DML, as a state-of-the-art CNN model as AUC >98 %. The adoption of DML significantly improves the performance of the model, remaining unaffected by variations in the dataset and rendering it a useful tool for fieldwork studies. DML offers several advantages over conventional classification model to manage large-scale datasets with a high volume of classes, enhancing scalability. The model has the capacity to generalize to novel classes that were not encountered during training, proving particularly advantageous in scenarios where new classes may consistently emerge. It is also well suited for applications requiring precise recognition, especially in discriminating between closely related classes. Furthermore, the DML exhibits greater resilience to issues related to class imbalance, as it concentrates on learning distances or similarities, which are more tolerant to such imbalances. These contributions significantly make the effectiveness and practicality of DML model, particularly in in fieldwork research.
Collapse
Affiliation(s)
- Veerayuth Kittichai
- Faculty of Medicine, King Mongkut's Institute of Technology Ladkrabang, Thailand
| | - Weerachat Sompong
- Faculty of Medicine, King Mongkut's Institute of Technology Ladkrabang, Thailand
| | - Morakot Kaewthamasorn
- Veterinary Parasitology Research Unit, Faculty of Veterinary Science, Chulalongkorn University, Bangkok, Thailand
| | - Thanyathep Sasisaowapak
- College of Advanced Manufacturing Innovation, King Mongkut's Institute of Technology Ladkrabang, Thailand
| | - Kaung Myat Naing
- College of Advanced Manufacturing Innovation, King Mongkut's Institute of Technology Ladkrabang, Thailand
| | - Teerawat Tongloy
- College of Advanced Manufacturing Innovation, King Mongkut's Institute of Technology Ladkrabang, Thailand
| | - Santhad Chuwongin
- College of Advanced Manufacturing Innovation, King Mongkut's Institute of Technology Ladkrabang, Thailand
| | - Suchansa Thanee
- Veterinary Parasitology Research Unit, Faculty of Veterinary Science, Chulalongkorn University, Bangkok, Thailand
| | - Siridech Boonsang
- Department of Electrical Engineering, Faculty of Engineering, King Mongkut's Institute of Technology Ladkrabang, Thailand
| |
Collapse
|
4
|
Yan WL, Sun HT, Zhao YC, Hou XW, Zhang M, Zhao Q, Elsheikha HM, Ni HB. Global prevalence of Plasmodium infection in wild birds: A systematic review and meta-analysis. Res Vet Sci 2024; 168:105136. [PMID: 38183894 DOI: 10.1016/j.rvsc.2024.105136] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/02/2023] [Revised: 12/28/2023] [Accepted: 01/01/2024] [Indexed: 01/08/2024]
Abstract
Avian malaria is a vector-borne parasitic disease caused by Plasmodium infection transmitted to birds by mosquitoes. The aim of this systematic review was to analyze the global prevalence of malaria and risk factors associated with infection in wild birds. A systematic search of the databases CNKI, WanFang, VIP, PubMed, and ScienceDirect was performed from database inception to 24 February 2023. The search identified 3181 retrieved articles, of which 52 articles met predetermined inclusion criteria. Meta-analysis was performed using the random-effects model. The estimated pooled global prevalence of Plasmodium infection in wild birds was 16%. Sub-group analysis showed that the highest prevalence was associated with adult birds, migrant birds, North America, tropical rainforest climate, birds captured by mist nets, detection of infection by microscopy, medium quality studies, and studies published after 2016. Our study highlights the need for more understanding of Plasmodium prevalence in wild birds and identifying risk factors associated with infection to inform future infection control measures.
Collapse
Affiliation(s)
- Wei-Lan Yan
- College of Veterinary Medicine, Qingdao Agricultural University, Qingdao 266109, Shandong Province, PR China; College of Life Science, Changchun Sci-Tech University, Shuangyang 130600, Jilin Province, PR China
| | - He-Ting Sun
- Center of Prevention and Control Biological Disaster, State Forestry and Grassland Administration, Shenyang 110034, Liaoning Province, PR China
| | - Yi-Chen Zhao
- Academy of Forestry Inventory and Planning, National Forestry and Grassland Administration, Beijing 100714, PR China
| | - Xin-Wen Hou
- College of Veterinary Medicine, Qingdao Agricultural University, Qingdao 266109, Shandong Province, PR China
| | - Miao Zhang
- College of Veterinary Medicine, Qingdao Agricultural University, Qingdao 266109, Shandong Province, PR China
| | - Quan Zhao
- College of Life Science, Changchun Sci-Tech University, Shuangyang 130600, Jilin Province, PR China.
| | - Hany M Elsheikha
- Faculty of Medicine and Health Sciences, School of Veterinary Medicine and Science, University of Nottingham, Sutton Bonington Campus, Loughborough, UK.
| | - Hong-Bo Ni
- College of Veterinary Medicine, Qingdao Agricultural University, Qingdao 266109, Shandong Province, PR China
| |
Collapse
|
5
|
Liu J, Zhang C, Shan Z. Application of Artificial Intelligence in Orthodontics: Current State and Future Perspectives. Healthcare (Basel) 2023; 11:2760. [PMID: 37893833 PMCID: PMC10606213 DOI: 10.3390/healthcare11202760] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/24/2023] [Revised: 10/11/2023] [Accepted: 10/16/2023] [Indexed: 10/29/2023] Open
Abstract
In recent years, there has been the notable emergency of artificial intelligence (AI) as a transformative force in multiple domains, including orthodontics. This review aims to provide a comprehensive overview of the present state of AI applications in orthodontics, which can be categorized into the following domains: (1) diagnosis, including cephalometric analysis, dental analysis, facial analysis, skeletal-maturation-stage determination and upper-airway obstruction assessment; (2) treatment planning, including decision making for extractions and orthognathic surgery, and treatment outcome prediction; and (3) clinical practice, including practice guidance, remote care, and clinical documentation. We have witnessed a broadening of the application of AI in orthodontics, accompanied by advancements in its performance. Additionally, this review outlines the existing limitations within the field and offers future perspectives.
Collapse
Affiliation(s)
- Junqi Liu
- Division of Paediatric Dentistry and Orthodontics, Faculty of Dentistry, The University of Hong Kong, Hong Kong SAR, China;
| | - Chengfei Zhang
- Division of Restorative Dental Sciences, Faculty of Dentistry, The University of Hong Kong, Hong Kong SAR, China;
| | - Zhiyi Shan
- Division of Paediatric Dentistry and Orthodontics, Faculty of Dentistry, The University of Hong Kong, Hong Kong SAR, China;
| |
Collapse
|
6
|
Semi-supervised graph learning framework for apicomplexan parasite classification. Biomed Signal Process Control 2023. [DOI: 10.1016/j.bspc.2022.104502] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/23/2022]
|
7
|
Simultaneous phenotyping of five Rh red blood cell antigens on a paper-based analytical device combined with deep learning for rapid and accurate interpretation. Anal Chim Acta 2022; 1207:339807. [DOI: 10.1016/j.aca.2022.339807] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/24/2022] [Revised: 04/01/2022] [Accepted: 04/02/2022] [Indexed: 11/21/2022]
|
8
|
A deep learning model (FociRad) for automated detection of γ-H2AX foci and radiation dose estimation. Sci Rep 2022; 12:5527. [PMID: 35365702 PMCID: PMC8975967 DOI: 10.1038/s41598-022-09180-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/26/2021] [Accepted: 03/18/2022] [Indexed: 11/08/2022] Open
Abstract
DNA double-strand breaks (DSBs) are the most lethal form of damage to cells from irradiation. γ-H2AX (phosphorylated form of H2AX histone variant) has become one of the most reliable and sensitive biomarkers of DNA DSBs. However, the γ-H2AX foci assay still has limitations in the time consumed for manual scoring and possible variability between scorers. This study proposed a novel automated foci scoring method using a deep convolutional neural network based on a You-Only-Look-Once (YOLO) algorithm to quantify γ-H2AX foci in peripheral blood samples. FociRad, a two-stage deep learning approach, consisted of mononuclear cell (MNC) and γ-H2AX foci detections. Whole blood samples were irradiated with X-rays from a 6 MV linear accelerator at 1, 2, 4 or 6 Gy. Images were captured using confocal microscopy. Then, dose-response calibration curves were established and implemented with unseen dataset. The results of the FociRad model were comparable with manual scoring. MNC detection yielded 96.6% accuracy, 96.7% sensitivity and 96.5% specificity. γ-H2AX foci detection showed very good F1 scores (> 0.9). Implementation of calibration curve in the range of 0-4 Gy gave mean absolute difference of estimated doses less than 1 Gy compared to actual doses. In addition, the evaluation times of FociRad were very short (< 0.5 min per 100 images), while the time for manual scoring increased with the number of foci. In conclusion, FociRad was the first automated foci scoring method to use a YOLO algorithm with high detection performance and fast evaluation time, which opens the door for large-scale applications in radiation triage.
Collapse
|
9
|
Basran PS, Appleby RB. The unmet potential of artificial intelligence in veterinary medicine. Am J Vet Res 2022; 83:385-392. [PMID: 35353711 DOI: 10.2460/ajvr.22.03.0038] [Citation(s) in RCA: 13] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022]
Abstract
Veterinary medicine is a broad and growing discipline that includes topics such as companion animal health, population medicine and zoonotic diseases, and agriculture. In this article, we provide insight on how artificial intelligence works and how it is currently applied in veterinary medicine. We also discuss its potential in veterinary medicine. Given the rapid pace of research and commercial product developments in this area, the next several years will pose challenges to understanding, interpreting, and adopting this powerful and evolving technology. Artificial intelligence has the potential to enable veterinarians to perform tasks more efficiently while providing new insights for the management and treatment of disorders. It is our hope that this will translate to better quality of life for animals and those who care for them.
Collapse
Affiliation(s)
- Parminder S Basran
- Department of Clinical Sciences, College of Veterinary Medicine, Cornell University, Ithaca, NY
| | - Ryan B Appleby
- Department of Clinical Studies, Ontario Veterinary College, University of Guelph, Guelph, ON, Canada
| |
Collapse
|
10
|
Chousangsuntorn C, Tongloy T, Chuwongin S, Boonsang S. A Deep Learning System for Recognizing and Recovering Contaminated Slider Serial Numbers in Hard Disk Manufacturing Processes. SENSORS 2021; 21:s21186261. [PMID: 34577468 PMCID: PMC8472306 DOI: 10.3390/s21186261] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 07/26/2021] [Revised: 09/07/2021] [Accepted: 09/15/2021] [Indexed: 11/16/2022]
Abstract
This paper outlines a system for detecting printing errors and misidentifications on hard disk drive sliders, which may contribute to shipping tracking problems and incorrect product delivery to end users. A deep-learning-based technique is proposed for determining the printed identity of a slider serial number from images captured by a digital camera. Our approach starts with image preprocessing methods that deal with differences in lighting and printing positions and then progresses to deep learning character detection based on the You-Only-Look-Once (YOLO) v4 algorithm and finally character classification. For character classification, four convolutional neural networks (CNN) were compared for accuracy and effectiveness: DarkNet-19, EfficientNet-B0, ResNet-50, and DenseNet-201. Experimenting on almost 15,000 photographs yielded accuracy greater than 99% on four CNN networks, proving the feasibility of the proposed technique. The EfficientNet-B0 network outperformed highly qualified human readers with the best recovery rate (98.4%) and fastest inference time (256.91 ms).
Collapse
Affiliation(s)
- Chousak Chousangsuntorn
- Department of Electrical Engineering, School of Engineering, Faculty of Engineering, King Mongkut’s Institute of Technology Ladkrabang, Bangkok 10520, Thailand;
| | - Teerawat Tongloy
- Center of Industrial Robot and Automation (CiRA), College of Advanced Manufacturing Innovation, King Mongkut’s Institute of Technology Ladkrabang, Bangkok 10520, Thailand; (T.T.); (S.C.)
| | - Santhad Chuwongin
- Center of Industrial Robot and Automation (CiRA), College of Advanced Manufacturing Innovation, King Mongkut’s Institute of Technology Ladkrabang, Bangkok 10520, Thailand; (T.T.); (S.C.)
| | - Siridech Boonsang
- Department of Electrical Engineering, School of Engineering, Faculty of Engineering, King Mongkut’s Institute of Technology Ladkrabang, Bangkok 10520, Thailand;
- Correspondence:
| |
Collapse
|