Deep convolutional neural network applied to &lt;i&gt;Trypanosoma cruzi&lt;/i&gt; detection in blood samples

Pereira, André S.; Mazza, Leonardo O.; Pinto, Pedro Contreiras; Gomes, Jonas; Nedjah, Nadia; Vanzan, Daniel F.; Pyrrho, Alexandre dos Santos; Soares, José Agnelo

doi:10.1504/ijbic.2022.120749

Cited by 3 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Incorporating images from six additional slides, including thick blood samples, raised the accuracy to 95.4% on two further slides. Raster scans with overlapping windows efficiently reveal positive Trypanosoma cruzi occurrences in both blood smear and thick blood images, highlighting the method’s potential to boost Chagas disease detection [ 36 ]. In this study, an innovative approach was developed for the automatic detection of the Trypanosoma cruzi parasite in blood smears using machine learning techniques applied to mobile phone images.…”

Section: Related Workmentioning

confidence: 99%

Assessment of Deep Learning Models for Cutaneous Leishmania Parasite Diagnosis Using Microscopic Images

Abdelmula,

Mirzaei,

Güler

et al. 2023

Diagnostics

View full text Add to dashboard Cite

Cutaneous leishmaniasis (CL) is a common illness that causes skin lesions, principally ulcerations, on exposed regions of the body. Although neglected tropical diseases (NTDs) are typically found in tropical areas, they have recently become more common along Africa’s northern coast, particularly in Libya. The devastation of healthcare infrastructure during the 2011 war and the following conflicts, as well as governmental apathy, may be causal factors associated with this catastrophic event. The main objective of this study is to evaluate alternative diagnostic strategies for recognizing amastigotes of cutaneous leishmaniasis parasites at various stages using Convolutional Neural Networks (CNNs). The research is additionally aimed at testing different classification models employing a dataset of ultra-thin skin smear images of Leishmania parasite-infected people with cutaneous leishmaniasis. The pre-trained deep learning models including EfficientNetB0, DenseNet201, ResNet101, MobileNetv2, and Xception are used for the cutaneous leishmania parasite diagnosis task. To assess the models’ effectiveness, we employed a five-fold cross-validation approach to guarantee the consistency of the models’ outputs when applied to different portions of the full dataset. Following a thorough assessment and contrast of the various models, DenseNet-201 proved to be the most suitable choice. It attained a mean accuracy of 0.9914 along with outstanding results for sensitivity, specificity, positive predictive value, negative predictive value, F1-score, Matthew’s correlation coefficient, and Cohen’s Kappa coefficient. The DenseNet-201 model surpassed the other models based on a comprehensive evaluation of these key classification performance metrics.

show abstract

Section: Related Workmentioning

confidence: 99%

Assessment of Deep Learning Models for Cutaneous Leishmania Parasite Diagnosis Using Microscopic Images

Abdelmula,

Mirzaei,

Güler

et al. 2023

Diagnostics

View full text Add to dashboard Cite

show abstract

“…This approach is contrasts with traditional centralized training, where all separate local datasets are gathered to a center server for training model [11]. Compared to the traditional centralized machine learning methods [12], FL techniques can realize multiple federated agencies to build a unified model between the safe, efficient, and compliance of multi-source data applications of the ecological system [13][14][15]. Meanwhile, the performance of federated model is similar to that of the model trained through data integration.…”

Section: Introductionmentioning

confidence: 99%

A survey on federated learning: challenges and applications

Zhang

Lan

et al. 2022

Int. J. Mach. Learn. & Cyber.

167

View full text Add to dashboard Cite

y impact on human life [1][2][3]. As great progress has been made in AI technology in recent years, various application fields have stepped into intelligence [4,5]. On the road of AI development, models, computing power, chip performance, and other technical issues have been the focus of academic research, so that AI technology can continue to evolve. For machines to truly approach the level of human thought, they need to be trained with vast amounts of real data [6,7]. However, cloud computing power, data security, data silos and other risks will inevitably become constraints for AI to win user trust, collect private data, and achieve largescale implementation [8]. Therefore, it is an urgent need for a practical and effective technique to alleviate the above problems and make the AI full of vitality again. Under this background, the concept of "federated learning (FL) " came into being.The notion of FL is first proposed by Google in 2016, mainly to make android mobile phone users update models locally without revealing private personal data [9]. After then, Google implemented an application-oriented FL system. The designed FL system, which focused on running federated average (FedAvg) algorithms on mobile phones, can perform federated analytics and be applied to monitor statistics for large-scale cluster equipment without recording raw device data to the cloud server. FL is one of the most Zhihua Cui

show abstract

“…A previous study even used the HRV analysis with this entropy for Chagas disease [10], finding significant differences in different periods of the day between the groups of patients analyzed. Also, deep neural networks are widely used for disease detection, and Chagas disease has not been the exception [11][12][13][14] although they mostly involve image analysis. That is why the present work proposes a deep neural network that uses an analysis of heart rate variability based on the Approximate entropy of a database of patients with Chagas disease in order to create a highly efficient and noninvasive tool for early diagnosis of this disease.…”

Section: Introductionmentioning

confidence: 99%

Approximate Entropy and Densely Connected Neural Network in the Early Diagnostic of Patients with Chagas Disease

Rodriguez¹,

Ravelo-García²,

Alvarez³

et al. 2022

Computing in Cardiology Conference (CinC)

View full text Add to dashboard Cite

It is estimated that in the world there are between 6 and 8 million people infected with Chagas disease, mainly in endemic areas of 21 Latin American countries, and in recent years it is slowly becoming a health problem in more urban areas and countries. In that sense, developing diagnosis methods is primordial. That is why this work used a deep neural network to classify 292 subjects (volunteers and patients) composed of 83 health volunteers (Control group); 102 asymptomatic chagasic patients (CH1 group) and 107 seropositive chagasic patients with incipient heart disease (CH2 group). Approximate Entropy ApEn was calculated from the tachograms of the circadian profiles of 24 hours every 5 minutes (288 frames) of each subject, and part of this data were used to train the network. The classification work done by the deep neural network had 98% of accuracy and 98% of precision, validated with the ROC curve, whose AUC values were approximately the unit for each group. Taking into account the good performance, we can consider this deep neural network and approximate entropy as useful tools to have a good early diagnosis about Chagas disease and its cardiac compromise.

show abstract

Deep convolutional neural network applied to <i>Trypanosoma cruzi</i> detection in blood samples

Cited by 3 publications

References 0 publications

Assessment of Deep Learning Models for Cutaneous Leishmania Parasite Diagnosis Using Microscopic Images

Assessment of Deep Learning Models for Cutaneous Leishmania Parasite Diagnosis Using Microscopic Images

A survey on federated learning: challenges and applications

Approximate Entropy and Densely Connected Neural Network in the Early Diagnostic of Patients with Chagas Disease

Contact Info

Product

Resources

About