RESUMO
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.
Assuntos
Microscopia , Humanos , Microscopia/métodos , Plasmodium falciparum/patogenicidade , Plasmodium vivax , Biologia Computacional/métodos , Malária/parasitologia , Plasmodium , Aprendizado Profundo , Bases de Dados Factuais , Processamento de Imagem Assistida por Computador/métodos , Malária Falciparum/parasitologia , Diagnóstico por Computador/métodosRESUMO
PURPOSE: To evaluate the use of the latest generation smartphone camera in performing arterial microanastomosis in rats. METHODS: Ten Wistar rats were divided into 2 groups and underwent anastomosis of the right carotid artery with the aid of magnification from a microscope (group M) and a smartphone camera (group S), to compare patency in 72 hours, as well as to measure the weight of the animals, diameter of the carotid arteries and anastomosis time. RESULTS: There was no statistical difference between the weight of the animals or the diameter of the carotid arteries. There was a statistical difference for the time spent on anastomoses, which was greater in group S, with higher rates of thrombosis (p < 0.05). CONCLUSIONS: Although our patency and anastomosis time results were statistically lower in the smartphone group, there was success in some cases. As the segment continues to progress, it is likely that the results will improve in line with the evolution of camera technology.
Assuntos
Anastomose Cirúrgica , Artérias Carótidas , Microscopia , Microcirurgia , Ratos Wistar , Smartphone , Animais , Microcirurgia/instrumentação , Microcirurgia/métodos , Microscopia/instrumentação , Microscopia/métodos , Anastomose Cirúrgica/instrumentação , Anastomose Cirúrgica/métodos , Artérias Carótidas/cirurgia , Masculino , Fatores de Tempo , Grau de Desobstrução Vascular , Ratos , Reprodutibilidade dos TestesRESUMO
In recent decades, many studies have been published on the use of automatic smear microscopy for diagnosing pulmonary tuberculosis (TB). Most of them deal with a preliminary step of the diagnosis, the bacilli detection, whereas sputum smear microscopy for diagnosis of pulmonary TB comprises detecting and reporting the number of bacilli found in at least 100 microscopic fields, according to the 5 grading scales (negative, scanty, 1+, 2+ and 3+) endorsed by the World Health Organization (WHO). Pulmonary TB diagnosis in bright-field smear microscopy, however, depends upon the attention of a trained and motivated technician, while the automated TB diagnosis requires little or no interpretation by a technician. As far as we know, this work proposes the first automatic method for pulmonary TB diagnosis in bright-field smear microscopy, according to the WHO recommendations. The proposed method comprises a semantic segmentation step, using a deep neural network, followed by a filtering step aiming to reduce the number of false positives (false bacilli): color and shape filtering. In semantic segmentation, different configurations of encoders are evaluated, using depth-wise separable convolution layers and channel attention mechanism. The proposed method was evaluated with a large, robust, and annotated image dataset designed for this purpose, consisting of 250 testing sets, 50 sets for each of the 5 TB diagnostic classes. The following performance metrics were obtained for automatic pulmonary TB diagnosis by smear microscopy: mean precision of 0.894, mean recall of 0.896, and mean F1-score of 0.895.
Assuntos
Mycobacterium tuberculosis , Tuberculose Pulmonar , Humanos , Microscopia/métodos , Tuberculose Pulmonar/diagnóstico por imagem , Redes Neurais de Computação , Sensibilidade e EspecificidadeRESUMO
Dye application for parasite highlighting in the Ova and Parasite exam is a common practice in parasitology diagnosis. Methods: A scoping review investigated how staining solutions interact with parasite structures. After screening 1334 papers, 35 met eligibility criteria. Results: Differentiating background from foreground in the fecal smear under light microscopy is the core of the research on this topic. Refractivity, unevenness of staining, size and temperature were explored to enhance staining protocols. Cryptosporidium spp. and Microsporidia were the main studied species. Conclusion: Studies on diagnostic efficacy outperform those that elucidate the physical-chemical interaction between dyes and parasites. An alternative approach involves technicians using computational tools to reduce subjectivity in fecal smear interpretation, deviating from conventional methods.
What is this article about? Coloring parasites during fecal exams has been widely used to find parasites in human feces. We searched for articles that could help us to answer the question: 'How do dyes give color to parasites?'. Then, we filtered the information from a total of 1334 articles to 35.What were the results? Cryptosporidium spp. and Microsporidia are microbes that can be seen only through a microscope. Researchers were interested in these two species in the last 40 years. Differentiating parasites from dirt on a glass slide is the main problem researchers are trying to solve. The way the light goes through parasites under a microscope, variation of staining, size and temperature of dyes have been explored to identify what gives better results in coloring protocols.What do the results of the study mean? Little is known about the chemical interaction between dyes and parasites. On the other hand, there are many studies on how good coloring methods are and comparing protocols. An alternative to the conventional approaches in staining parasites is the use of computational tools to reduce doubt in the exam interpretation by technicians.
Assuntos
Corantes , Fezes , Parasitologia , Coloração e Rotulagem , Fezes/parasitologia , Coloração e Rotulagem/métodos , Humanos , Parasitologia/métodos , Corantes/química , Animais , Cryptosporidium/isolamento & purificação , Microsporídios/isolamento & purificação , Microscopia/métodos , Parasitos/isolamento & purificaçãoRESUMO
PURPOSE: The aim of this study was to evaluate the efficacy of artificial intelligence-derived morphometric parameters in characterizing Fuchs corneal endothelial dystrophy (FECD) from specular microscopy images. METHODS: This cross-sectional study recruited patients diagnosed with FECD, who underwent ophthalmologic evaluations, including slit-lamp examinations and corneal endothelial assessments using specular microscopy. The modified Krachmer grading scale was used for clinical FECD classification. The images were processed using a convolutional neural network for segmentation and morphometric parameter estimation, including effective endothelial cell density, guttae area ratio, coefficient of variation of size, and hexagonality. A mixed-effects model was used to assess relationships between the FECD clinical classification and measured parameters. RESULTS: Of 52 patients (104 eyes) recruited, 76 eyes were analyzed because of the exclusion of 26 eyes for poor quality retroillumination photographs. The study revealed significant discrepancies between artificial intelligence-based and built-in microscope software cell density measurements (1322 ± 489 cells/mm 2 vs. 2216 ± 509 cells/mm 2 , P < 0.001). In the central region, guttae area ratio showed the strongest correlation with modified Krachmer grades (0.60, P < 0.001). In peripheral areas, only guttae area ratio in the inferior region exhibited a marginally significant positive correlation (0.29, P < 0.05). CONCLUSIONS: This study confirms the utility of CNNs for precise FECD evaluation through specular microscopy. Guttae area ratio emerges as a compelling morphometric parameter aligning closely with modified Krachmer clinical grading. These findings set the stage for future large-scale studies, with potential applications in the assessment of irreversible corneal edema risk after phacoemulsification in FECD patients, as well as in monitoring novel FECD therapies.
Assuntos
Inteligência Artificial , Endotélio Corneano , Distrofia Endotelial de Fuchs , Microscopia , Humanos , Estudos Transversais , Masculino , Feminino , Distrofia Endotelial de Fuchs/diagnóstico , Endotélio Corneano/patologia , Endotélio Corneano/diagnóstico por imagem , Idoso , Contagem de Células , Pessoa de Meia-Idade , Microscopia/métodos , Idoso de 80 Anos ou mais , Redes Neurais de ComputaçãoRESUMO
Objetivos: Evaluar mediante microscopia quirúrgica la presencia del segundo conducto mesiovestibular (MV2) en el piso de la cámara pulpar de los primeros molares superiores, determinar su abordabilidad, establecer el calibre de lima que llegó al tercio apical y tipificar radiovisiográficamente su morfología se-gún la clasificación de Weine. Materiales y métodos: Se utilizaron 48 primeros molares superiores huma-nos extraídos. Sé tomaron radiovisografías preope-ratorias (Carestream 5200) en sentido orto radial y mesio-distal. Se realizó apertura y se localizó entra-da del MV2 con microscopio quirúrgico (Newton MEC XXI, Argentina) a 16 x. Se cateterizó MV1 y MV2 con limas tipo K #10 y #15 (Dentsply Maillefer). Se cortó raíz distovestibular para mejorar visualización ra-diovisográfica. Se tomó conductometria en sentido mesio-distal para establecer la tipología. Se compa-raron frecuencias y porcentajes mediante test de Chi-cuadrado con corrección de Yates, prueba exac-ta de Fisher y test z para diferencia de proporcio-nes. Se calcularon intervalos de confianza 95% para porcentajes mediante método score de Wilson. Re-sultados: El 54% (26 casos) presentó MV2. De los 26 MV2, el 77% (20 casos) fueron abordables, porcen-taje significativamente mayor al 23% no abordable (z=3,62; P<0,05). Al hacer cateterismo, hubo asocia-ción significativa entre tipo de conducto (MV1 y MV2) y calibre de lima que llegó al tercio apical (Chi-cua-drado=29,12; gl=1; P<0,05). La tipología I (58%) fue significativamente mayor que las tipologías II (21%) y III (21%) (P<0,05 para ambas comparaciones). Con-clusión: El alto porcentaje de piezas que presentó MV2 evidencia la importancia clínica de detectarlo y tratarlo correctamente. Dado el alto porcentaje de piezas donde fue abordable, se concluye que el clíni-co debe tener conocimiento, destreza y la tecnología necesaria para poder abordarlo. Si bien la tipología I (58%) fue la más encontrada, cuando el MV2 termina en foramen independiente (tipo III), su omisión puede conducir al fracaso del tratamiento (AU))
Objectives: To evaluate by surgical microscopy the presence of second mesiobuccal canal (MB2) in the pulp chamber floor of the maxillary first molars, determine its approachability, establish the caliber of the file that reached the apical third, and radiographically typify its morphology according to Weine Ìs classification. Materials and methods: 48 extracted human maxillary first molars were used. Preoperative radiovisographies (Carestream 5200) were taken in ortho-radial and mesio-distal direction. Coronal access was made and the entrance of MB2 was located with a surgical microscope (Newton MEC XXI, Argentina) at 16x. MB1 and MB2 were catheterized with K files #10 and #15 (Dentsply Maillefer). Distobuccal root was cut to improve radiovisographic visualization. Conductometry was taken in mesio-distal direction to establish the typology. Frequencies and percentages were compared using Chi-square test with Yates correction, Fisher's exact test and z test for difference in proportions. 95% confidence intervals were calculated for percentages using Wilson score method. Results: 54% (26 cases) presented MB2. Of the 26 MB2, 77% (20 cases) were approachable, a significantly higher percentage than those not approachable (z=3.62; P<0.05). When performing catheterization, there was a significant association between type of canal (MB1 and MB2) and file caliber that reached the apical third (Chi-square=29.12; df=1; P<0.05). Typology I (58%) was significantly higher than typologies II (21%) and III (21%) (P<0.05 for both comparisons). Conclusion: The high percentage of specimens that showed MB2 evidence the clinical importance of detecting and treating it correctly. Given the percentage of pieces where it was approachable (77%), it is concluded that the clinician must have the knowledge, skill and necessary technology to be able to approach it. Although typology I (58%) was the most found, when MB2 ends an independent foramen (type III), its omission can lead to treatment failure (AU)
Assuntos
Raiz Dentária/anatomia & histologia , Cavidade Pulpar/anatomia & histologia , Raiz Dentária/diagnóstico por imagem , Interpretação Estatística de Dados , Radiografia Dentária Digital/métodos , Cavidade Pulpar/diagnóstico por imagem , Microscopia/métodos , Odontometria/métodosRESUMO
BACKGROUND: In tissues and organisms, the coordination of neighboring cells is essential to maintain their properties and functions. Therefore, knowing which cells are adjacent is crucial to understand biological processes that involve physical interactions among them, e.g. cell migration and proliferation. In addition, some signaling pathways, such as Notch or extrinsic apoptosis, are highly dependent on cell-cell communication. While this is straightforward to obtain from membrane images, nuclei labelling is much more ubiquitous for technical reasons. However, there are no automatic and robust methods to find neighboring cells based only on nuclear markers. RESULTS: In this work, we describe Nfinder, a method to assess the cell's local neighborhood from images with nuclei labeling. To achieve this goal, we approximate the cell-cell interaction graph by the Delaunay triangulation of nuclei centroids. Then, links are filtered by automatic thresholding in cell-cell distance (pairwise interaction) and the maximum angle that a pair of cells subtends with shared neighbors (non-pairwise interaction). We systematically characterized the detection performance by applying Nfinder to publicly available datasets from Drosophila melanogaster, Tribolium castaneum, Arabidopsis thaliana and C. elegans. In each case, the result of the algorithm was compared to a cell neighbor graph generated by manually annotating the original dataset. On average, our method detected 95% of true neighbors, with only 6% of false discoveries. Remarkably, our findings indicate that taking into account non-pairwise interactions might increase the Positive Predictive Value up to + 11.5%. CONCLUSION: Nfinder is the first robust and automatic method for estimating neighboring cells in 2D and 3D based only on nuclear markers and without any free parameters. Using this tool, we found that taking non-pairwise interactions into account improves the detection performance significantly. We believe that using our method might improve the effectiveness of other workflows to study cell-cell interactions from microscopy images. Finally, we also provide a reference implementation in Python and an easy-to-use napari plugin.
Assuntos
Arabidopsis , Drosophila melanogaster , Animais , Caenorhabditis elegans , Microscopia/métodos , Núcleo Celular/metabolismo , Algoritmos , Processamento de Imagem Assistida por Computador/métodosRESUMO
INTRODUCTION: Digital cytopathology is being progressively implemented in centres worldwide, but impediments such as the three-dimensionality of specimens and the size of scanned images have prevented its use from becoming widespread. This study aimed to validate the use of digital whole slide image scanning of cytopathology samples for routine sign-out. METHODS: Specimens were scanned using the Leica Aperio GT 450 System. The following sample types were used: liquid-based cytology, direct conventional smears from fine needle aspirates and cytospins. Cases were validated by the same pathologist who originally rendered the conventional diagnosis, with a washout of at least 3 months. Final digital diagnoses were compared to the original analogical diagnoses, and cases were considered concordant up to a one-degree difference between the original and digital diagnoses. Reasons for the unsuccessful scanning of slides were also noted. The technical procedures followed the College of American Pathologists' guidelines for digital pathology validation. RESULTS: A total of 730 slides from 383 cases (337 female, 51 male; median age 42) were successfully scanned. These cases consisted of the following sample types: 81 (21.1%) conventional smears, 240 (62.7%) liquid-based cytology samples and 62 (16.2%) cytospins. There were only five discordant cases, with a 98.7% agreement between original and digital diagnoses using the difference rate of up to one degree. Seventy-seven slides (10.5%) had to be rescanned due to technical problems. The main reasons for unsuccessful scanning were paucicellular samples (44; 57.1%), the thickness of the smears (18; 23.4%) and issues with the coverslip (15; 19.5%). CONCLUSION: Cytological specimens can be successfully scanned and used for digital pathology, with excellent agreement with the original diagnoses.
Assuntos
Citologia , Microscopia , Masculino , Humanos , Feminino , Adulto , Microscopia/métodos , CitodiagnósticoRESUMO
O dano capilar causado pelo descolorimento oxidativo é muito intenso, sendo que dois fatores são responsáveis por essa ação: primeiro, a ação direta e danosa do oxidante em diversas estruturas capilares e segundo, o dano oxidativo primário facilita o dano causado por outros agentes físicos (luz, temperatura) e químicos (tensoativos), que comumente tem ação nos cabelos. Desenvolver conceitos e tecnologias que possam tornar o oxidante específico para a melanina e por conseguinte efetuando o descolorimento sem causar danos ao fio é extremamente desejável. Neste trabalho buscaremos entender de que forma a luz visível pode aumentar a ação do oxidante sem danificar o fio colateralmente. O objetivo principal deste trabalho é demonstrar que é possível utilizar a luz visível, que é absorvida pela melanina, para tornar esse pigmento mais suscetível ao agente oxidante e desta forma, permitir que o descolorimento seja realizado com concentrações pequenas de oxidante. Também almejamos desenvolver métodos de análises por microscopia ótica de fluorescência e de reflexão para mensurar o dano nas estruturas dos fios processados com oxidante e na presença ou ausência da luz
The capillary damage caused by oxidative discoloration is very intense, and two factors are responsible for this action: first, the direct and harmful action of the oxidant on several capillary structures and second, the primary oxidative damage facilitates the damage caused by other physical agents (light, temperature) and chemicals (surfactants), which commonly have action on the hair. Developing concepts and technologies that can make the oxidant specific to melanin and therefore discoloring without causing damage to the hair is extremely desirable. In this work we will try to understand how visible light can increase the oxidant's action without damaging the wire collaterally. The main objective of this work is to demonstrate that it is possible to use visible light, which is absorbed by melanin, to make this pigment more susceptible to the oxidizing agent and, thus, to allow the discoloration to be carried out with small concentrations of oxidizer. We also aim to develop methods of analysis by optical fluorescence and reflection microscopy to measure the damage to the structures of the threads processed with oxidizer and in the presence or absence of light
Assuntos
Oxidação , Descolorantes de Cabelo/efeitos adversos , Luz/efeitos adversos , Melaninas/agonistas , Compostos Químicos , Fluorescência , Cabelo , Microscopia/métodosRESUMO
OBJECTIVES: The aim of this study was to evaluate the mineral content, expressed by calcium (Ca) and phosphate (P), in dental enamel exposed to bleaching agents using micro-computed tomography (micro-CT), scanning electron microscopy (SEM), energy dispersive spectroscopy (EDS), and atomic force microscopy (AFM). METHODS: Sixty bovine dental enamel specimens were randomly divided into three groups (n=20): HP35ca (bleached using 35% hydrogen peroxide with Ca); HP35wca (bleached using 35% hydrogen peroxide without Ca); and control (without bleaching). Five specimens from each group were used for SEM and EDS analyses, 10 specimens were used for AFM analysis, and the remaining five specimens were used for micro-CT analysis. The pH of the gels was measured using a pH meter. The EDS and micro-CT data were analyzed using one-way ANOVA and Pearson's correlation test. The AFM data were analyzed using one-way ANOVA (α=0.05). RESULTS: The weight percentages of Ca and P obtained using EDS were similar between the bleached and control groups. Small, superficial changes were observed by SEM in the HP35wca group. The HP35ca group showed similar patterns to the control group. AFM results showed no significant changes in the enamel roughness in any of the tested groups. No significant difference in the volume or depth of structural enamel loss was found between gels with and without Ca. No mineral loss was observed in the dentin substrate. The EDS and micro-CT analysis data exhibited a high correlation (p<0.001). CONCLUSION: The addition of Ca to the bleaching gel had no beneficial effect on the bleached tooth enamel in terms of composition, mineral loss, and surface roughness. Micro-CT results exhibited a high correlation with the EDS results.