1
|
Martins GL, Ferreira DS, Carneiro CM, Nogueira-Paiva NC, Bianchi AGC. Trajectory-driven computational analysis for element characterization in Trypanosoma cruzi video microscopy. PLoS One 2024; 19:e0304716. [PMID: 38829872 PMCID: PMC11146708 DOI: 10.1371/journal.pone.0304716] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/19/2023] [Accepted: 05/14/2024] [Indexed: 06/05/2024] Open
Abstract
Optical microscopy videos enable experts to analyze the motion of several biological elements. Particularly in blood samples infected with Trypanosoma cruzi (T. cruzi), microscopy videos reveal a dynamic scenario where the parasites' motions are conspicuous. While parasites have self-motion, cells are inert and may assume some displacement under dynamic events, such as fluids and microscope focus adjustments. This paper analyzes the trajectory of T. cruzi and blood cells to discriminate between these elements by identifying the following motion patterns: collateral, fluctuating, and pan-tilt-zoom (PTZ). We consider two approaches: i) classification experiments for discrimination between parasites and cells; and ii) clustering experiments to identify the cell motion. We propose the trajectory step dispersion (TSD) descriptor based on standard deviation to characterize these elements, outperforming state-of-the-art descriptors. Our results confirm motion is valuable in discriminating T. cruzi of the cells. Since the parasites perform the collateral motion, their trajectory steps tend to randomness. The cells may assume fluctuating motion following a homogeneous and directional path or PTZ motion with trajectory steps in a restricted area. Thus, our findings may contribute to developing new computational tools focused on trajectory analysis, which can advance the study and medical diagnosis of Chagas disease.
Collapse
Affiliation(s)
- Geovani L. Martins
- Postgraduate Program in Computer Science, Federal University of Ouro Preto, Ouro Preto, MG, Brazil
- Department of Computing, Federal University of Ouro Preto, Ouro Preto, MG, Brazil
| | - Daniel S. Ferreira
- Department of Computing, Federal Institute of Education, Science, and Technology of Ceará, Maracanaú, CE, Brazil
| | - Claudia M. Carneiro
- Nucleus of Biological Sciences Research, Federal University of Ouro Preto, Ouro Preto, MG, Brazil
- Department of Clinical Analysis, Federal University of Ouro Preto, Ouro Preto, MG, Brazil
| | - Nivia C. Nogueira-Paiva
- Nucleus of Biological Sciences Research, Federal University of Ouro Preto, Ouro Preto, MG, Brazil
| | - Andrea G. C. Bianchi
- Postgraduate Program in Computer Science, Federal University of Ouro Preto, Ouro Preto, MG, Brazil
- Department of Computing, Federal University of Ouro Preto, Ouro Preto, MG, Brazil
| |
Collapse
|
2
|
Rada L, Kumar P, Martin-Gonzalez A, Brito-Loeza C. Chagas parasite classification in blood sample images using different machine learning architectures. Med Biol Eng Comput 2024; 62:195-206. [PMID: 37758871 DOI: 10.1007/s11517-023-02926-8] [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: 03/01/2023] [Accepted: 09/05/2023] [Indexed: 09/29/2023]
Abstract
Chagas disease is a life-threatening illness mainly found in Latin America. Early identification and diagnosis of Chagas disease are critical for reducing the death rate of individuals since cures and treatments are available at the acute stage. In this work, we test and compare several deep learning classification models on smear blood sample images for the task of Chagas parasite classification. Our experiments showed that the best classification model is a deep learning architecture based on a residual network together with separable convolution blocks as feature extractors and using a support vector machine algorithm as the classifier in the final layer. This optimized model, we named Res2_SVM, with a reduced number of parameters, achieved an accuracy of [Formula: see text], precision of [Formula: see text], recall of [Formula: see text], and F1-score of [Formula: see text] on our test dataset, overcoming other machine learning models.
Collapse
Affiliation(s)
- Lavdie Rada
- Faculty of Engineering and Natural Sciences, Bahcesehir University, Istanbul, Turkey.
| | - Preet Kumar
- Faculty of Engineering and Natural Sciences, Bahcesehir University, Istanbul, Turkey
| | - Anabel Martin-Gonzalez
- Computational Learning and Imaging Research, Universidad Autónoma de Yucatán, Mérida, Yucatán, México
| | - Carlos Brito-Loeza
- Computational Learning and Imaging Research, Universidad Autónoma de Yucatán, Mérida, Yucatán, México
| |
Collapse
|
3
|
Morais MCC, Silva D, Milagre MM, de Oliveira MT, Pereira T, Silva JS, Costa LDF, Minoprio P, Junior RMC, Gazzinelli R, de Lana M, Nakaya HI. Automatic detection of the parasite Trypanosoma cruzi in blood smears using a machine learning approach applied to mobile phone images. PeerJ 2022; 10:e13470. [PMID: 35651746 PMCID: PMC9150695 DOI: 10.7717/peerj.13470] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/04/2021] [Accepted: 04/29/2022] [Indexed: 01/14/2023] Open
Abstract
Chagas disease is a life-threatening illness caused by the parasite Trypanosoma cruzi. The diagnosis of the acute form of the disease is performed by trained microscopists who detect parasites in blood smear samples. Since this method requires a dedicated high-resolution camera system attached to the microscope, the diagnostic method is more expensive and often prohibitive for low-income settings. Here, we present a machine learning approach based on a random forest (RF) algorithm for the detection and counting of T. cruzi trypomastigotes in mobile phone images. We analyzed micrographs of blood smear samples that were acquired using a mobile device camera capable of capturing images in a resolution of 12 megapixels. We extracted a set of features that describe morphometric parameters (geometry and curvature), as well as color, and texture measurements of 1,314 parasites. The features were divided into train and test sets (4:1) and classified using the RF algorithm. The values of precision, sensitivity, and area under the receiver operating characteristic (ROC) curve of the proposed method were 87.6%, 90.5%, and 0.942, respectively. Automating image analysis acquired with a mobile device is a viable alternative for reducing costs and gaining efficiency in the use of the optical microscope.
Collapse
Affiliation(s)
- Mauro César Cafundó Morais
- Hospital Israelita Albert Einstein, São Paulo, Brazil,Scientific Platform Pasteur-University of São Paulo (SPPU), Universidade de São Paulo, Sao Paulo, SP, Brazil,Department of Clinical and Toxicological Analysis, School of Pharmaceutical Sciences, Universidade de São Paulo, Sao Paulo, SP, Brazil
| | - Diogo Silva
- Department of Clinical and Toxicological Analysis, School of Pharmaceutical Sciences, Universidade de São Paulo, Sao Paulo, SP, Brazil
| | - Matheus Marques Milagre
- Departamento de Análises Clínicas (DEACL), Programa de Pós-graduação em Ciências Farmacêuticas (CiPHARMA), Universidade Federal de Ouro Preto, Ouro Preto, MG, Brazil
| | | | - Thaís Pereira
- Laboratório de Imunopatologia, Instituto René Rachou, Fundação Oswaldo Cruz, Universidade Federal de Minas Gerais, Belo Horizonte, MG, Brazil
| | - João Santana Silva
- Fiocruz- Bi-Institutional Translational Medicine Project, FIOCRUZ/SP, Ribeirão Preto, SP, Brazil
| | - Luciano da F. Costa
- São Carlos Institute of Physics (DFCM- IFSC), Universidade de São Paulo, São Carlos, SP, Brazil
| | - Paola Minoprio
- Scientific Platform Pasteur-University of São Paulo (SPPU), Universidade de São Paulo, Sao Paulo, SP, Brazil
| | | | - Ricardo Gazzinelli
- Laboratório de Imunopatologia, Instituto René Rachou, Fundação Oswaldo Cruz, Universidade Federal de Minas Gerais, Belo Horizonte, MG, Brazil
| | - Marta de Lana
- Departamento de Análises Clínicas (DEACL), Programa de Pós-graduação em Ciências Farmacêuticas (CiPHARMA), Universidade Federal de Ouro Preto, Ouro Preto, MG, Brazil,Núcleo de Pesquisas em Ciências Biológicas (NUPEB), Universidade Federal de Ouro Preto, Ouro Preto, MG, Brazil
| | - Helder I. Nakaya
- Hospital Israelita Albert Einstein, São Paulo, Brazil,Scientific Platform Pasteur-University of São Paulo (SPPU), Universidade de São Paulo, Sao Paulo, SP, Brazil,Department of Clinical and Toxicological Analysis, School of Pharmaceutical Sciences, Universidade de São Paulo, Sao Paulo, SP, Brazil,Center of Research in Inflammatory Diseases (CRID), Universidade de São Paulo, Ribeirão Preto, SP, Brazil
| |
Collapse
|
4
|
Ojeda-Pat A, Martin-Gonzalez A, Brito-Loeza C, Ruiz-Piña H, Ruz-Suarez D. Effective residual convolutional neural network for Chagas disease parasite segmentation. Med Biol Eng Comput 2022; 60:1099-1110. [DOI: 10.1007/s11517-022-02537-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/23/2021] [Accepted: 01/17/2022] [Indexed: 10/19/2022]
|
5
|
Martins GL, Ferreira DS, Ramalho GLB. Collateral motion saliency-based model for Trypanosoma cruzi detection in dye-free blood microscopy. Comput Biol Med 2021; 132:104220. [PMID: 33799216 DOI: 10.1016/j.compbiomed.2021.104220] [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: 09/14/2020] [Revised: 01/11/2021] [Accepted: 01/12/2021] [Indexed: 10/22/2022]
Abstract
The motion performed by some protozoa is a crucial visual stimulus in microscopy analysis, especially when they have almost imperceptible morphological characteristics. Microorganisms can be distinguished through the interactions of their locomotion with neighboring elements, as observed in some parasitological analysis of Trypanosoma cruzi. In dye-free blood microscopy, the low contrast of this parasite makes it difficult to detect them. Thus, the parasite's interaction with the neighborhood, such as collisions with blood cells and shocks during the escape of confinements in cell clumps, generates collateral motions that assist its detection. Assuming that the collateral motion of the parasite can be sufficiently noticeable to overcome the dynamic contexts of inspection, we propose a novel computational approach that is based on motion saliency. We estimate motion in microscopy videos using dense optical flow and we investigate vestiges in saliency maps that could characterize the collateral motion of parasites. Our biological-inspired method shows that the parasite's collateral motion is a relevant feature for T. cruzi detection. Therefore, our computational model is a promising aid in the research and medical diagnosis of Chagas disease.
Collapse
Affiliation(s)
- Geovani L Martins
- Programa de Pós-Graduação em Ciência da Computação, Instituto Federal de Educação Ciência e Tecnologia (IFCE), Fortaleza, Ceará, Brazil; Laboratório de Processamento de Imagens, Sinais e Computação Aplicada (LAPISCO), Fortaleza, Ceará, Brazil.
| | - Daniel S Ferreira
- Departamento de Computação, Instituto Federal de Educação, Ciência e Tecnologia (IFCE), Maracanaú, Ceará, Brazil; Departamento de Engenharia de Teleinformática, Universidade Federal do Ceará (UFC), Fortaleza, Ceará, Brazil
| | - Geraldo L B Ramalho
- Programa de Pós-Graduação em Ciência da Computação, Instituto Federal de Educação Ciência e Tecnologia (IFCE), Fortaleza, Ceará, Brazil; Laboratório de Processamento de Imagens, Sinais e Computação Aplicada (LAPISCO), Fortaleza, Ceará, Brazil
| |
Collapse
|
6
|
Boniface PK, Ferreira EI. Flavonoids as efficient scaffolds: Recent trends for malaria, leishmaniasis, Chagas disease, and dengue. Phytother Res 2019; 33:2473-2517. [PMID: 31441148 DOI: 10.1002/ptr.6383] [Citation(s) in RCA: 22] [Impact Index Per Article: 4.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/13/2018] [Revised: 04/04/2019] [Accepted: 04/13/2019] [Indexed: 12/21/2022]
Abstract
Endemic in 149 tropical and subtropical countries, neglected tropical diseases (NTDs) affect more than 1 billion people annually with over 500,000 deaths. Among the NTDs, some of the most severe consist of leishmaniasis, Chagas disease, and dengue. The impact of the combined NTDs closely rivals that of malaria. According to the World Health Organization, 216 million cases of malaria were reported in 2016 with 445,000 deaths. Current treatment options are associated with various limitations including widespread drug resistance, severe adverse effects, lengthy treatment duration, unfavorable toxicity profiles, and complicated drug administration procedures. Flavonoids are a class of compounds that has been the subject of considerable scientific interest. New developments of flavonoids have made promising advances for the potential treatment of malaria, leishmaniasis, Chagas disease, and dengue, with less toxicity, high efficacy, and improved bioavailability. This review summarizes the current standings of the use of flavonoids to treat malaria and neglected diseases such as leishmaniasis, Chagas disease, and dengue. Natural and synthetic flavonoids are leading compounds that can be used for developing antiprotozoal and antiviral agents. However, detailed studies on toxicity, pharmacokinetics, and mechanisms of action of these compounds are required to confirm the in vitro pharmacological claims of flavonoids for pharmaceutical applications. HIGHLIGHTS: In the current review, we have tried to compile recent discoveries on natural and synthetic flavonoids as well as their implication in the treatment of malaria, leishmaniasis, Chagas disease, and dengue. A total of 373 (220 natural and 153 synthetic) flavonoids have been evaluated for antimalarial, antileishmanial, antichagasic, and antidengue activities. Most of these flavonoids showed promising results against the above diseases. Reports on molecular modeling of flavonoid compounds to the disease target indicated encouraging results. Flavonoids can be prospected as potential leads for drug development; however, more rigorously designed studies on toxicity and pharmacokinetics, as well as the quantitative structure-activity relationship studies of these compounds, need to be addressed.
Collapse
Affiliation(s)
- Pone Kamdem Boniface
- Department of Pharmacy, Faculty of Pharmaceutical Sciences, University of São Paulo, São Paulo, Brazil
| | - Elizabeth Igne Ferreira
- Department of Pharmacy, Faculty of Pharmaceutical Sciences, University of São Paulo, São Paulo, Brazil
| |
Collapse
|
7
|
Uc-Cetina V, Brito-Loeza C, Ruiz-Piña H. Chagas parasite detection in blood images using AdaBoost. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE 2015; 2015:139681. [PMID: 25861375 PMCID: PMC4377374 DOI: 10.1155/2015/139681] [Citation(s) in RCA: 14] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 10/17/2014] [Revised: 02/20/2015] [Accepted: 02/20/2015] [Indexed: 11/18/2022]
Abstract
The Chagas disease is a potentially life-threatening illness caused by the protozoan parasite, Trypanosoma cruzi. Visual detection of such parasite through microscopic inspection is a tedious and time-consuming task. In this paper, we provide an AdaBoost learning solution to the task of Chagas parasite detection in blood images. We give details of the algorithm and our experimental setup. With this method, we get 100% and 93.25% of sensitivity and specificity, respectively. A ROC comparison with the method most commonly used for the detection of malaria parasites based on support vector machines (SVM) is also provided. Our experimental work shows mainly two things: (1) Chagas parasites can be detected automatically using machine learning methods with high accuracy and (2) AdaBoost + SVM provides better overall detection performance than AdaBoost or SVMs alone. Such results are the best ones known so far for the problem of automatic detection of Chagas parasites through the use of machine learning, computer vision, and image processing methods.
Collapse
Affiliation(s)
- Víctor Uc-Cetina
- Facultad de Matemáticas, Universidad Autónoma de Yucatán, Anillo Periférico Norte, Tablaje Catastral, 13615 Mérida, YUC, Mexico
| | - Carlos Brito-Loeza
- Facultad de Matemáticas, Universidad Autónoma de Yucatán, Anillo Periférico Norte, Tablaje Catastral, 13615 Mérida, YUC, Mexico
| | - Hugo Ruiz-Piña
- Centro de Investigaciones Regionales Dr. Hideyo Noguchi, Universidad Autónoma de Yucatán, Avenida, Itzáes No. 490 x 59, Colonia Centro, 97000 Mérida, YUC, Mexico
| |
Collapse
|