ABSTRACT
The incidence of colorectal cancer (CRC) has increased worldwide, and early diagnosis is crucial to reduce mortality rates. Therefore, new noninvasive biomarkers for CRC are required. Recent studies have revealed an imbalance in the oral and gut microbiomes of patients with CRC, as well as impaired gut vascular barrier function. In the present study, the microbiomes of saliva, crevicular fluid, feces, and non-neoplastic and tumor intestinal tissue samples of 93 CRC patients and 30 healthy individuals without digestive disorders (non-CRC) were analyzed by 16S rRNA metabarcoding procedures. The data revealed that Parvimonas, Fusobacterium, and Bacteroides fragilis were significantly over-represented in stool samples of CRC patients, whereas Faecalibacterium and Blautia were significantly over-abundant in the non-CRC group. Moreover, the tumor samples were enriched in well-known periodontal anaerobes, including Fusobacterium, Parvimonas, Peptostreptococcus, Porphyromonas, and Prevotella. Co-occurrence patterns of these oral microorganisms were observed in the subgingival pocket and in the tumor tissues of CRC patients, where they also correlated with other gut microbes, such as Hungatella. This study provides new evidence that oral pathobionts, normally located in subgingival pockets, can migrate to the colon and probably aggregate with aerobic bacteria, forming synergistic consortia. Furthermore, we suggest that the group composed of Fusobacterium, Parvimonas, Bacteroides, and Faecalibacterium could be used to design an excellent noninvasive fecal test for the early diagnosis of CRC. The combination of these four genera would significantly improve the reliability of a discriminatory test with respect to others that use a single species as a unique CRC biomarker.
Subject(s)
Bacteroides , Biomarkers, Tumor , Colorectal Neoplasms , Feces , Fusobacterium , Humans , Colorectal Neoplasms/microbiology , Colorectal Neoplasms/diagnosis , Fusobacterium/isolation & purification , Fusobacterium/genetics , Male , Female , Bacteroides/isolation & purification , Bacteroides/genetics , Middle Aged , Feces/microbiology , Faecalibacterium/isolation & purification , Faecalibacterium/genetics , Aged , RNA, Ribosomal, 16S/genetics , Gastrointestinal Microbiome/genetics , Saliva/microbiology , AdultABSTRACT
Oral and intestinal samples from a cohort of 93 colorectal cancer (CRC) patients and 30 healthy controls (non-CRC) were collected for microbiome analysis. Saliva (28 non-CRC and 94 CRC), feces (30 non-CRC and 97 CRC), subgingival fluid (20 CRC), and tumor tissue samples (20 CRC) were used for 16S metabarcoding and/or RNA sequencing (RNAseq) approaches. A differential analysis of the abundance, performed with the ANCOM-BC package, adjusting the P-values by the Holm-Bonferroni method, revealed that Parvimonas was significantly over-represented in feces from CRC patients (P-value < 0.001) compared to healthy controls. A total of 11 Parvimonas micra isolates were obtained from the oral cavity and adenocarcinoma of CRC patients. Genome analysis identified a pair of isolates from the same patient that shared 99.2% identity, demonstrating that P. micra can translocate from the subgingival cavity to the gut. The data suggest that P. micra could migrate in a synergistic consortium with other periodontal bacteria. Metatranscriptomics confirmed that oral bacteria were more active in tumor than in non-neoplastic tissues. We suggest that P. micra could be considered as a CRC biomarker detected in non-invasive samples such as feces.
ABSTRACT
Introduction: Elevated plasma levels of extracellular vesicles have been associated with impaired placentation, angiogenesis imbalance, intravascular inflammation, and endothelial dysfunction in women with preeclampsia, thus suggesting that circulating vesicles may be a good therapeutic target for the treatment of the disease. Recently, statins have been considered a potential treatment for the prevention of preeclampsia because of their pleiotropic effects, including the improvement of endothelial dysfunction and inhibition of inflammatory responses. However, the effects of these drugs on circulating vesicles concentration in women at risk of preeclampsia have not been established. Herein, we aimed to assess the effects of pravastatin on circulating extracellular vesicle generation in women at high risk of term preeclampsia. Methods: In a sample of 68 singleton pregnant women participating in the multicenter, double-blind, placebo-controlled STATIN trial (Nº EducraCT 2016-005206-19 ISRCTN), 35 women received a placebo and 33 women received a 20 mg/day dose of pravastatin for approximately 3 weeks (from 35 to 37 weeks of gestation until delivery). Large extracellular vesicles were characterized and quantified by flow cytometry using annexin V and cell-specific antibodies directed against platelet, endothelial, leukocyte, and syncytiotrophoblast cell surface markers. Results: In women who received the placebo, a significant increase in the plasma levels of large extracellular vesicles from platelets (34%, p < 0.01), leukocytes (33%, p < 0.01), monocytes (60%, p < 0.01), endothelial cells (40%, p < 0.05), and syncytiotrophoblast cells (22%, p < 0.05) were observed. However, treatment with pravastatin significantly reduced the plasma levels of large extracellular vesicles from platelets (42%, p < 0.001), leukocytes (25%, p < 0.001), monocytes (61%, p < 0.001), endothelial cells (69%, p < 0.001), activated endothelial cells (55%, p < 0.001), and syncytiotrophoblast cells (44%, p < 0.001). Discussion: These results indicate that pravastatin reduces the levels of activated cell-derived membrane vesicles from the maternal vasculature, blood, and placental syncytiotrophoblast of women at high risk of term preeclampsia, suggesting that this statin may be beneficial in reducing endothelial dysfunction and pro-inflammatory and pro-coagulatory state characteristics of the disease.
ABSTRACT
Toxoplasmosis chorioretinitis is commonly diagnosed by an ophthalmologist through the evaluation of the fundus images of a patient. Early detection of these lesions may help to prevent blindness. In this article we present a data set of fundus images labeled into three categories: healthy eye, inactive and active chorioretinitis. The dataset was developed by three ophthalmologists with expertise in toxoplasmosis detection using fundus images. The dataset will be of great use to researchers working on ophthalmic image analysis using artificial intelligence techniques for the automatic detection of toxoplasmosis chorioretinitis.
ABSTRACT
The hypothalamic-pituitary-adrenocortical axis can translate, through glucocorticoid secretion, the prenatal environment to development to produce phenotypes that match prevailing environmental conditions. However, whether developmental plasticity is modulated by the interaction between circulating glucocorticoids and receptor expression remains unclear. Here, we tested whether covariation between plasma corticosterone (CORT) and glucocorticoid receptor gene (Nr3c1) expression in blood underlies embryonic developmental programming in yellow-legged gulls (Larus michahellis). We examined variations in circulating levels of CORT and the expression and DNA methylation patterns of Nr3c1 in response to two ecologically relevant prenatal factors: adult alarm calls (a cue of predator presence) and changes in prenatal light environment (a cue of competitive disadvantage). We then determined whether embryonic development and postnatal phenotypes were associated with CORT levels and Nr3c1 expression, and explored direct and indirect relationships between the prenatal environment, hormone-receptor covariation, and postnatal phenotypes. Prenatal exposure to alarm calls increased CORT levels and up-regulated Nr3c1 expression in gull chicks, while exposure to light cues reduced both hormone levels and receptor expression. Chicks prenatally exposed to alarm calls showed altered DNA methylation profiles in the Nr3c1 regulatory region, but patterns varied throughout the breeding season and between years. Moreover, our results suggest a negative relationship between DNA methylation and expression in Nr3c1 , at least at specific CpG sites. The interplay between circulating CORT and Nr3c1 expression affected embryo developmental timing and vocalizations, as well as hatchling mass and fitness-relevant behaviours. These findings provide a link between prenatal inputs, glucocorticoid function and phenotypic outcomes, suggesting that hormone-receptor interaction may underlie developmental programming in free-living animals.
Subject(s)
Charadriiformes , Glucocorticoids , Animals , Charadriiformes/genetics , Gene Expression , Corticosterone , Receptors, Glucocorticoid/metabolism , Phenotype , DNA Methylation , Chickens/genetics , Embryonic DevelopmentABSTRACT
INTRODUCTION: To date, no pancreatic stump closure technique has been shown to be superior to any other in distal pancreatectomy. Although several studies have shown a trend towards better results in transection using a radiofrequency device (radiofrequency-assisted transection (RFT)), no randomised trial for this purpose has been performed to date. Therefore, we designed a randomised clinical trial, with the hypothesis that this technique used in distal pancreatectomies is superior in reducing clinically relevant postoperative pancreatic fistula (CR-POPF) than mechanical closures. METHODS AND ANALYSIS: TRANSPAIRE is a multicentre randomised controlled trial conducted in seven Spanish pancreatic centres that includes 112 patients undergoing elective distal pancreatectomy for any indication who will be randomly assigned to RFT or classic stapler transections (control group) in a ratio of 1:1. The primary outcome is the CR-POPF percentage. Sample size is calculated with the following assumptions: 5% one-sided significance level (α), 80% power (1-ß), expected POPF in control group of 32%, expected POPF in RFT group of 10% and a clinically relevant difference of 22%. Secondary outcomes include postoperative results, complications, radiological evaluation of the pancreatic stump, metabolomic profile of postoperative peritoneal fluid, survival and quality of life. Follow-ups will be carried out in the external consultation at 1, 6 and 12 months postoperatively. ETHICS AND DISSEMINATION: TRANSPAIRE has been approved by the CEIM-PSMAR Ethics Committee. This project is being carried out in accordance with national and international guidelines, the basic principles of protection of human rights and dignity established in the Declaration of Helsinki (64th General Assembly, Fortaleza, Brazil, October 2013), and in accordance with regulations in studies with biological samples, Law 14/2007 on Biomedical Research will be followed. We have defined a dissemination strategy, whose main objective is the participation of stakeholders and the transfer of knowledge to support the exploitation of activities. REGISTRATION DETAILS: ClinicalTrials.gov Registry (NCT04402346).
Subject(s)
Pancreatectomy , Humans , Multicenter Studies as Topic , Pancreas/surgery , Pancreatectomy/adverse effects , Pancreatectomy/methods , Pancreatic Fistula/etiology , Pancreatic Fistula/prevention & control , Postoperative Complications/etiology , Quality of Life , Randomized Controlled Trials as Topic , Risk FactorsABSTRACT
Androgens are a group of steroid hormones that have long been proposed as a mechanism underpinning intergenerational plasticity. In birds, maternally allocated egg testosterone, one of the main androgens in vertebrates, affects a wide variety of offspring phenotypic traits but the mechanisms underlying this form of intergenerational plasticity are not yet well understood. Recent in vitro and animal model studies have shown that telomerase expression and activity are important targets of androgen signaling. The telomerase enzyme is known for its repair function on telomeres, the DNA-protein complexes at the ends of chromosomes that are involved in genomic integrity and cell aging. However, the role of maternal testosterone in influencing offspring telomerase levels in natural populations and its consequences on telomere length and potentially on offspring development is still unknown. Here, by experimentally modifying the level of egg testosterone in a natural population of yellow-legged gull (Larus michahellis), we show that chicks hatched from testosterone-treated eggs had higher average levels of telomerase and faster growth than controls during the first week of life. While testosterone-treated chicks also tended to have longer telomeres than controls at hatching this difference disappeared by day 6 of age. Overall, our results suggest that maternal testosterone may have a potential adaptive value by promoting offspring growth and presumably telomerase levels, as this enzyme plays other important physiological functions (e.g., stress resistance, cell signaling, or tissue genesis) besides telomere lengthening. Nonetheless, our knowledge of the potential adaptive function of telomerase in natural populations is scarce and so the potential pathways linking maternal hormones, offspring telomerase, and fitness should be further investigated.
ABSTRACT
Oxidative and inflammatory stress, angiogenic imbalance, and endothelial dysfunction are pathophysiological mechanisms occurring in pre-eclampsia (PE) that may persist over time and predispose women to a higher risk of cardiovascular disease (CVD) in the future. However, there is little evidence on the vascular function of women at risk of PE who have not developed the disease. The main objective of this research is to study factors and biomarkers involved in endothelial dysfunction related to oxidative stress, angiogenic disbalance, and inflammation in women at high risk of term PE who do not develop the disease. An observational, analytical, retrospective, and descriptive study was carried out in a selected sample of 68 high-risk and 57 non-risk of term PE participants in the STATIN study (FFIS/2016/02/ST EUDRACT No: 2016-005206-19). A significant increase in mean arterial pressure (MAP) levels and oxidative stress biomarkers (uric acid, homocysteine, and total serum antioxidant capacity) was found. Biomarkers of inflammation (interleukin-6 and growth differentiation factor 15) and endothelial function (asymmetric dimethylarginine) were significantly elevated in the group at risk of pre-eclampsia. A significative dependence relationship was also established between MAP and interleukin-6 and uric acid. These results suggest that women at high risk of term PE may represent pregnancies with pre-existing maternal risk factors for CVD, manifested by the own cardiovascular overload of pregnancy. A better understanding of maternal cardiovascular function in pregnancy would allow the improved prediction of CVD late in life in women.
ABSTRACT
Panoramic images are one of the most requested exams by dentists for allowing the visualization of the entire mouth. Interpreting X-ray images is a time-consuming task in which misdiagnoses can occur due to the inexperience or fatigue of professionals. In this work, we applied different image enhancement techniques as a pre-processing step to determine which image features correlate with improvements in teeth detection in panoramic images using deep learning architectures. We contrasted the performance of five object-detection architectures using 300 panoramic images of a public dataset. We evaluated the enhancement in the pre-processing step and the detection performance. Quality and detection metrics were considered, and the cross-correlation between them was computed for every object-detection method contemplated. We observe the dependence of the detection performance with some image enhancement techniques, especially those that introduce less noise and preserve the global contrast of the image.
Subject(s)
Deep Learning , Tooth , Benchmarking , Radiography, Panoramic , X-RaysABSTRACT
Due to the presence of high glucose levels, diabetes mellitus (DM) is a widespread disease that can damage blood vessels in the retina and lead to loss of the visual system. To combat this disease, called Diabetic Retinopathy (DR), retinography, using images of the fundus of the retina, is the most used method for the diagnosis of Diabetic Retinopathy. The Deep Learning (DL) area achieved high performance for the classification of retinal images and even achieved almost the same human performance in diagnostic tasks. However, the performance of DL architectures is highly dependent on the optimal configuration of the hyperparameters. In this article, we propose the use of Neuroevolutionary Algorithms to optimize the hyperparameters corresponding to the DL model for the diagnosis of DR. The results obtained prove that the proposed method outperforms the results obtained by the classical approach.
Subject(s)
Diabetes Mellitus , Diabetic Retinopathy , Algorithms , Diabetic Retinopathy/diagnostic imaging , Diagnostic Techniques, Ophthalmological , Fundus Oculi , Humans , Retina/diagnostic imagingABSTRACT
The purpose of this study was to examine relationships among instructor autonomy support for student learning, and students' motivational characteristics, learning approaches, perceptions of career competence and life satisfaction. Participated 1048 students from Spanish universities with ages between 18, and 57 years. A Structural equation modeling revealed a relationship between instructor autonomy support for student learning with students' basic psychological need satisfaction. As a result, students' basic need satisfaction was related to their intrinsic motivation, and to a deeper learning approach. These educational outcomes contributed to explain students'perceived professional competence, and life satisfaction. These findings highlight the importance of student choice, and decision-making in the learning process as a means to facilitating deeper learning, stronger feelings of professional competence, and enhanced well-being.
Subject(s)
Motivation , Personal Satisfaction , Humans , Personal Autonomy , Professional Competence , Students/psychology , UniversitiesABSTRACT
This paper presents a data set with information on meteorological data and electricity consumption in the department of Alto Paraná, Paraguay. The meteorological data were registered every three hours at the Aeropuerto Guarani, Department of Alto Paraná, which belongs to the Dirección Nacional de Aeronáutica Civil of Paraguay. The final data consists of a total of 22.445 records of temperature, relative humidity, wind speed and atmospheric pressure. On the other hand, the electrical energy consumption data set contains a total of 1.848.947 records, all of them coming from the one hundred and fifteen feeders located throughout the Alto Paraná region of Paraguay. Electrical energy consumption data was provided by Administración Nacional de Electricidad (ANDE). The analysis of this data can yield insights regarding the energy consumption in the area.
ABSTRACT
BACKGROUND: Primary prevention strategies for asthma are lacking. Its inception probably starts in utero and/or during the early postnatal period as the developmental origins of health and disease (DOHaD) paradigm suggests. OBJECTIVES: The main objective of Nutrition in Early Life and Asthma (NELA) cohort study is to unravel whether the following factors contribute causally to the developmental origins of asthma: (1) maternal obesity/adiposity and foetal growth; (2) maternal and child nutrition; (3) outdoor air pollution; (4) endocrine disruptors; and (5) maternal psychological stress. Maternal and offspring biological samples are used to assess changes in offspring microbiome, immune system, epigenome and volatilome as potential mechanisms influencing disease susceptibility. POPULATION: Randomly selected pregnant women from three health areas of Murcia, a south-eastern Mediterranean region of Spain, who fulfilled the inclusion criteria were invited to participate at the time of the follow-up visit for routine foetal anatomy scan at 19-22 weeks of gestation, at the Maternal-Fetal Medicine Unit of the "Virgen de la Arrixaca" University Clinical Hospital over a 36-month period, from March 2015 to April 2018. DESIGN: Prospective, population-based, maternal-child, birth cohort study. METHODS: Questionnaires on exposures and outcome variables were administered to mothers at 20-24 gestation week; 32-36 gestation week; and delivery. Children were surveyed at birth, 3 and 18 months of age and currently at 5 years. Furthermore, physical examinations were performed; and different measurements and biological samples were obtained at these time points. PRELIMINARY RESULTS: Among the 1350 women invited to participate, 738 (54%) were finally enrolled in the study and 720 of their children were eligible at birth. The adherence was high with 612 children (83%) attending the 3 months' visit and 532 children (72%) attending the 18 months' visit. CONCLUSION: The NELA cohort will add original and unique knowledge to the developmental origins of asthma.
Subject(s)
Asthma , Birth Cohort , Asthma/epidemiology , Cohort Studies , Female , Humans , Infant, Newborn , Nutritional Status , Pregnancy , Prospective StudiesABSTRACT
It is often assumed that the transfer of maternal glucocorticoids (GCs; e.g., corticosterone or cortisol) to offspring is an inevitable cost associated with adverse or stressful conditions experienced by mothers. However, recent evidence indicates that maternal GCs may adaptively programme particular physiological and molecular pathways during development to enhance offspring fitness. In this context, an important mechanism through which maternal GCs may lastingly affect offspring phenotypic quality and survival is via effects on embryo telomerase activity and so on offspring postnatal telomere length. Here, using a field experimental design for which we manipulated the corticosterone content in yellow-legged gull (Larus michahellis) eggs, we show that embryos from corticosterone-injected eggs not only had a higher telomerase activity but also longer telomeres just after hatching. A complementary analysis further revealed that gull hatchlings with longer telomeres had a higher survival probability during the period when most of the chick mortality occurs. Given the important role that telomere length and its restoring mechanisms have on ageing trajectories and disease risk, our findings provide a new mechanistic link by which mothers may presumably shape offspring life-history trajectories and phenotype.
Subject(s)
Charadriiformes , Telomerase , Animals , Corticosterone/pharmacology , Telomere/genetics , Embryonic Development/geneticsABSTRACT
In the automatic diagnosis of ocular toxoplasmosis (OT), Deep Learning (DL) has arisen as a powerful and promising approach for diagnosis. However, despite the good performance of the models, decision rules should be interpretable to elicit trust from the medical community. Therefore, the development of an evaluation methodology to assess DL models based on interpretability methods is a challenging task that is necessary to extend the use of AI among clinicians. In this work, we propose a novel methodology to quantify the similarity between the decision rules used by a DL model and an ophthalmologist, based on the assumption that doctors are more likely to trust a prediction that was based on decision rules they can understand. Given an eye fundus image with OT, the proposed methodology compares the segmentation mask of OT lesions labeled by an ophthalmologist with the attribution matrix produced by interpretability methods. Furthermore, an open dataset that includes the eye fundus images and the segmentation masks is shared with the community. The proposal was tested on three different DL architectures. The results suggest that complex models tend to perform worse in terms of likelihood to be trusted while achieving better results in sensitivity and specificity.
ABSTRACT
In many animals, recent evidence indicates that the gut microbiome may be acquired during early development, with possible consequences on newborns' health. Thus, it has been hypothesized that a healthy microbiome protects telomeres and genomic integrity against cellular stress. However, the link between the early acquired microbiome and telomere dynamics has not hitherto been investigated. In birds, this link may also be potentially modulated by the transfer of maternal glucocorticoids, since these substances dysregulate microbiome composition during postnatal development. Here, we examined the effect of the interplay between the microbiome and stress hormones on the telomere length of yellow-legged gull hatchlings by using a field experiment in which we manipulated the corticosterone content in eggs. We found that the hatchling telomere length was related to microbiome composition, but this relationship was not affected by the corticosterone treatment. Hatchlings with a microbiome dominated by potential commensal bacteria (i.e. Catellicoccus and Cetobacterium) had larger telomeres, suggesting that an early establishment of the species-specific microbiome during development may have important consequences on offspring health and survival.
Subject(s)
Charadriiformes , Gastrointestinal Microbiome , Animals , Corticosterone , Telomere , Telomere ShorteningABSTRACT
This article presents a database containing 757 color fundus images acquired at the Department of Ophthalmology of the Hospital de Clínicas, Facultad de Ciencias Médicas (FCM), Universidad Nacional de Asunción (UNA), Paraguay. Firstly, the retinal images were acquired with a clinical procedure presented in this paper. The acquisition of the retinographies was made through the Visucam 500 camera of the Zeiss brand. Next, two expert ophthalmologists have classified the dataset. These data can help physicians and researchers in the detection of cases of Non-Proliferative Diabetic Retinopathy (NPDR) and Proliferative Diabetic Retinopathy (PDR), in their different stages. The dataset generated will be useful for ophthalmologists and researchers to work on automatic detection algorithms for Diabetic Retinopathy (DR).
ABSTRACT
In wild animals, telomere attrition during early development has been linked with several fitness disadvantages throughout life. Telomerase enzyme can elongate telomeres, but it is generally assumed that its activity is suppressed in most somatic tissues upon birth. However, recent evidence suggests that this may not be the case for long-lived bird species. We have therefore investigated whether telomerase activity is maintained during the postnatal growth period in a wild yellow-legged gull (Larus michahellis) population. Our results indicate that telomerase activity is not negligible in the blood cells, but activity levels sharply decline from hatching to fledging following a similar pattern to the reduction observed in telomere length. Our results further suggest that the observed variation in telomere length may be the result of a negative effect of fast growth on telomerase activity, thus providing a new mechanism through which growth rates may affect telomere dynamics and potentially life-history trajectories.
Subject(s)
Charadriiformes/growth & development , Telomerase , Telomere , Animals , Animals, Wild , Telomerase/genetics , Telomere/genetics , Telomere ShorteningABSTRACT
Panoramic dental radiography is one of the most used images of the different dental specialties. This radiography provides information about the anatomical structures of the teeth. The correct evaluation of these radiographs is associated with a good quality of the image obtained. In this study, 598 patients were consecutively selected to undergo dental panoramic radiography at the Department of Radiology of the Faculty of Dentistry, Universidad Nacional de Asunción. Contrast enhancement techniques are used to enhance the visual quality of panoramic dental radiographs. Specifically, this article presents a new algorithm for contrast, detail and edge enhancement of panoramic dental radiographs. The proposed algorithm is called Multi-Scale Top-Hat transform powered by Geodesic Reconstruction for panoramic dental radiography enhancement (MSTHGR). This algorithm is based on multi-scale mathematical morphology techniques. The proposal extracts multiple features of brightness and darkness, through the reconstruction of the marker (obtained by the Top-Hat transformation by reconstruction) starting from the mask (obtained by the classic Top-Hat transformation). The maximum characteristics of brightness and darkness are added to the dental panoramic radiography. In this way, the contrast, details and edges of the panoramic radiographs of teeth are improved. For the tests, MSTHGR was compared with the following algorithms: Geodesic Reconstruction Multiscale Morphology Contrast Enhancement (GRMMCE), Histogram Equalization (HE), Brightness Preserving Bi-Histogram Equalization (BBHE), Dual Sub-Image Histogram Equalization (DSIHE), Minimum Mean Brightness Error Bi-Histogram Equalization (MMBEBHE), Quadri-Histogram Equalization with Limited Contrast (QHELC), Contrast-Limited Adaptive Histogram Equalization (CLAHE) and Gamma Correction (GC). Experimentally, the numerical results show that the MSTHGR obtained the best results with respect to the Contrast Improvement Ratio (CIR), Entropy (E) and Spatial Frequency (SF) metrics. This indicates that the algorithm performs better local enhancements on panoramic radiographs, improving their details and edges.
Subject(s)
Radiographic Image Enhancement , Tooth , Algorithms , Humans , Image Enhancement , Radiography, Panoramic , Tooth/diagnostic imagingABSTRACT
Ocular toxoplasmosis (OT) is commonly diagnosed through the analysis of fundus images of the eye by a specialist. Despite Deep Learning being widely used to process and recognize pathologies in medical images, the diagnosis of ocular toxoplasmosis(OT) has not yet received much attention. A predictive computational model is a valuable time-saving option if used as a support tool for the diagnosis of OT. It could also help diagnose atypical cases, being particularly useful for ophthalmologists who have less experience. In this work, we propose the use of a deep learning model to perform automatic diagnosis of ocular toxoplasmosis from images of the eye fundus. A pretrained residual neural network is fine-tuned on a dataset of samples collected at the medical center of Hospital de Clínicas in Asunción, Paraguay. With sensitivity and specificity rates equal to 94% and 93%,respectively, the results show that the proposed model is highly promising. In order to replicate the results and advance further in this area of research, an open data set of images of the eye fundus labeled by ophthalmologists is made available.