In this study, a variational model is proposed for filtering additive and multiplicative noise in wrapped phase maps. The model includes the Pythagorean identity, which is a fundamental requirement for phase maps, as well as the total variation regularizer to maintain discontinuities. We prove that our model is well-posed, compute the Euler-Lagrange equations, and present a fixed-point convergent algorithm for solving it. The quality of the proposed model is confirmed by conducting experiments on both synthetic and real data. Additionally, the implementation of the parallel fixed-point algorithm to accelerate the model's solution is presented. Implementations consist of OpenMP and CUDA execution on a multicore CPU and GPU, respectively. A comparison of the performance of parallel implementations with state-of-the-art methods is presented using synthetic and real data. According to the findings, our parallel implementations achieve speedups of 12x for multi-core CPUs and 125x for GPUs compared to the serial implementation.

This study introduces a technique for identifying the presence of the parasite Trypanosoma cruzi in video recordings, the primary cause of Chagas disease. Early diagnosis-especially during the acute phase-is vital to prevent serious complications. The primary contribution of this work is a computational algorithm capable of detecting the presence of Chagas parasites in capillary tubes containing blood samples. While prior algorithms relied on stained blood samples, this study employs unstained blood samples, utilizing the motility of living parasites for detection. The proposed approach combines optical flow estimation using Farneb & auml;ck's algorithm with a classification stage where several machine learning models were evaluated. Among these, the best performance in terms of accuracy was achieved by a convolutional neural network based on the ResNet-18 architecture. The dataset consists of 24 videos totaling 32 minutes of recording. The results demonstrate optimal performance, achieving a F1-score of 0.9383.

The comet assay is a versatile method used to determine the DNA damage in individual cells. The cells processed by this technique preserve the stable genetic material in the head of the comet and the unstable portion of DNA in the tail. The analysis of the resulting microscopic images from this test must be carried out by an expert, who must precisely determine the extent of DNA liberated from the head of the comet, since it is related to the level of damage. Since this is a time-consuming and very specialized task, the objective of this research is to develop a computational system, based on the use of a convolutional neural network, for the automatic classification of cells processed by comet assay according to the level of DNA damage they present.

Chagas disease, caused by Trypanosoma cruzi (T. cruzi), remains a significant public health challenge in Latin America. Traditional diagnostic methods relying on manual microscopy suffer from low sensitivity, subjective interpretation, and poor performance in suboptimal conditions. This study presents a novel computer vision framework integrating motion analysis with deep learning for automated T. cruzi detection in microscopic videos. Our motion-based detection pipeline leverages parasite motility as a key discriminative feature, employing frame differencing, morphological processing, and DBSCAN clustering across 23 microscopic videos. This approach effectively addresses limitations of static image analysis in challenging conditions including noisy backgrounds, uneven illumination, and low contrast. From motion-identified regions, 64×64 patches were extracted for classification. MobileNetV2 achieved superior performance with 99.63% accuracy, 100% precision, 99.12% recall, and an AUC-ROC of 1.0. Additionally, YOLOv5 and YOLOv8 models (Nano, Small, Medium variants) were trained on 43 annotated videos, with YOLOv5-Nano and YOLOv8-Nano demonstrating excellent detection capability on unseen test data. This dual-stage framework offers a practical, computationally efficient solution for automated Chagas diagnosis, particularly valuable for resource-constrained laboratories with poor imaging quality.

The timely and accurate identification of the Try-panosoma cruzi parasite is critical in the medical field, as it is the causal agent of Chagas disease. Our research aims to fill a significant gap in this area by employing a semi-supervised ensemble framework of neural networks for classifying microscopic images of the parasite. Our methodology stands out for its rigorous hyperparameter tuning, data augmentation approaches, and the use of an ensemble model comprising two main neural networks-Model A and Model B-guided by a Reference Model. Despite the constraints of a limited dataset, we applied our unique semi-supervised ensemble technique to multiple model architectures, including DenseNet121, VGG16, and ResNet50. Among these, the FPNDenseNet121 model demonstrated superior performance metrics, achieving an accuracy rate of $\mathbf{9 3. 7 5 \%}$, a precision value of 0.94, a recall rate of 0.94, and an F1-score of 0.94. These compelling results lay the groundwork for further advancements in the field of medical image classification, particularly in contexts with scarce labeled data.

Yucatan has a variety of plant species of melliferous importance. The honey produced in Yucatan has several special properties that make it one of the most demanded internationally. Analyzing the pollen grains present in honey is essential to determine its quality and identify its plants of origin. This study is a time-consuming process that must be carried out by highly trained palynologists. In this work, we propose an improved model based on a fully convolutional neural network for the automatic detection of pollen grains in microscopic images of four plant species of Yucatan to contribute to the analysis of the honey designation of origin.

In this proposal, our objective is to create a neural network for the discovery of models using compartmental models as systems of Ordinary Differential Equations (ODEs), employing Graph-Supported Neural Networks (GSNN). We design the GSNN as a graph of transition functions of the structure of the model to ensure that the three properties of the ODE solution are satisfied: additivity to one, positivity, and boundness. Rather than directly estimating the solution, these neural networks approximate the transition functions. We present theoretical evidence substantiating that our GSNN maintains these properties, along with approximation outcomes from both simulated and real-world data. These outcomes demonstrate that our GSNN outperforms the non-graph-supported approach for these issues, with instances where it even surpasses full model-based solutions and Recurrent Neural Networks. Furthermore, an evolutionary algorithm successfully generated a consistent model using the data, offering a comprehensive framework for neural network-based model discovery in these scenarios.

Chagas disease, caused by the Trypanosoma cruzi parasite, poses a significant health threat, particularly in Latin America, with millions affected globally. This research introduces a novel approach using deep learning techniques for the automated detection of Trypanosoma cruzi in blood smear images provided by Zoonoses Laboratory (CIR) in Mexico. Advanced deep learning architectures like Faster RCNN, RetinaNet, YOLOv8, and FCOS have been adapted, trained, and compared with each other in terms of the detection accuracy of each image. Our selection of those models is based on their ability to swiftly and accurately detect anomalies, measured through rigorous assessment using pivotal metrics like Mean Average Precision (mAP) across varying Intersection over Union (IoU) thresholds. Notably, the YOLOv8 model has showcased outstanding performance, boasting a remarkable mAP score of 0.951 for parasite detection and localisation. Specifically, YOLOv8 outperforms with a leading mAP of 0.951 at 50

This paper describes a methodology to analyse the complexity of HeLa cells as observed with electron microscopy, in particular the relationship between mitochondria and the roughness of the nuclear envelope as reflected by the invaginations of the surface. For this purpose, several mitochondria segmentation algorithms were quantitatively compared, namely: Topology, Image Processing, Topology and Image Processing, and Deep Learning, which provided the highest accuracy. The invaginations were successfully segmented with one image processing algorithm. Metrics were extracted for both structures and correlations between the mitochondria and invaginations were explored for 25 segmented cells. It was found that there was a positive correlation between the volume of invaginations and the volume of mitochondria, and negative correlations between the number and the mean volume of mitochondria, and between the volume of the cytoplasm and the aspect ratio of mitochondria. These results suggest that there is a relationship between the shape of a cell, its nucleus and its mitochondria; as well as a relationship between the number of mitochondria and their shapes. Whilst these results were obtained from a single cell line and a relatively small number of cells, they encourage further study as the methodology proposed can be easily applied to other cells and settings. Code and data are freely available. HeLa images are available from http://dx.doi.org/10.6019/EMPIAR-10094, code from https://github.com/reyesaldasoro/MitoEM, and segmented nuclei, cells, invaginations and mitochondria from https://github.com/reyesaldasoro/HeLa_Cell Data.

This study aimed to determine the feasibility of applying machine-learning methods to assess the progression of chronic kidney disease (CKD) in patients with coronavirus disease (COVID-19) and acute renal injury (AKI). The study was conducted on patients aged 18 years or older who were diagnosed with COVID-19 and AKI between April 2020 and March 2021, and admitted to a second-level hospital in Mérida, Yucatán, México. Of the admitted patients, 47.92% died and 52.06% were discharged. Among the discharged patients, 176 developed AKI during hospitalization, and 131 agreed to participate in the study. The study’s results indicated that the area under the receiver operating characteristic curve (AUC-ROC) for the four models was 0.826 for the support vector machine (SVM), 0.828 for the random forest, 0.840 for the logistic regression, and 0.841 for the boosting model. Variable selection methods were utilized to enhance the performance of the classifier, with the SVM model demonstrating the best overall performance, achieving a classification rate of 99.8% ± 0.1 in the training set and 98.43% ± 1.79 in the validation set in AUC-ROC values. These findings have the potential to aid in the early detection and management of CKD, a complication of AKI resulting from COVID-19. Further research is required to confirm these results.

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 98.48% , precision of 100.0% , recall of 97.20% , and F1-score of 98.58% on our test dataset, overcoming other machine learning models.

This paper presents a parallel implementation of a fixed-point algorithm for wrapped phase denoising. The model based on total variation efficiently estimates discontinuous phase maps and further incorporates the Pythagorean trigonometric identity between the real and imaginary parts of the phase map, enhancing the quality of the restored phase. In this work, two parallel C/C++ implementations of the sequential version of algorithms were developed. The implementations include execution in a multi-core CPU and a GPU using OpenMP and CUDA, respectively. We show performance comparisons of the parallel implementations with advanced methods using synthetic and experimental data. Results show that our parallel implementations achieve speedups over the serial implementation of 12× for multi-core CPU and 110× for GPU.

Variational models for inverse problems are mainly based on the choice of the regularizer, whose goal is to give the solutions some desirable property. Total Variation, one of the most popular regularizer for image restoration, is induced by the Euclidean gradient operator and promotes piece-wise constant solutions. In this paper, we present a new regularizer for color image restoration, which is induced by a generalization of the Dirac operator. This new regularizer also encourages the gradients of the three color components of the solutions to be aligned, which is actually a property of natural images. This property is also encoded when the regularizer is induced by a Riemannian gradient, for a well-chosen Riemannian metric, but with a different mathematical formulation. Then, we compare the different regularizers by combining them with the Deep Image Prior model, this latter assuming that the restored image is the output of a neural network. Experiments on denoising and deblurring show that the proposed Dirac operator provides better results than the Euclidean and Riemannian gradient operators.

This paper presents a variational model for the denoising of wrapped phase images. By enforcing the required Pythagorean trigonometric identity between the real and imaginary components of the signal, this model improves the signal-to-noise ratio of the restored signal. To preserve phase map discontinuities, the model is based on total variation. The existence and uniqueness of the model’s solution are demonstrated using standard techniques. In addition, the convergence of a rapid fixed-point method to determine the numerical solution is demonstrated. Experiments on both synthetic and actual patterns validate the model’s performance.

Considered a neglected tropical pathology, Chagas disease is responsible for thousands of deaths per year and it is caused by the parasite Trypanosoma cruzi. Since many infected people can remain asymptomatic, a fast diagnosis is necessary for proper intervention. Parasite microscopic observation in blood samples is the gold standard method to diagnose Chagas disease in its initial phase; however, this is a time-consuming procedure, requires expert intervention, and there is currently no efficient method to automatically perform this task. Therefore, we propose an efficient residual convolutional neural network, named Res2Unet, to perform a semantic segmentation of Trypanosoma cruzi parasites, with an active contour loss and improved residual connections, whose design is based on Heun's method for solving ordinary differential equations. The model was trained on a dataset of 626 blood sample images and tested on a dataset of 207 images. Validation experiments report that our model achieved a Dice coefficient score of 0.84, a precision value of 0.85, and a recall value of 0.82, outperforming current state-of-the-art methods. Since Chagas disease is a severe and silent illness, our computational model may benefit health care providers to give a prompt diagnose for this worldwide affection.

The mean curvature (MC)-based image denoising and image deblurring models are used to enhance the quality of the denoised images and deblurred images respectively. These models are very efficient in removing staircase effect, preserving edges and other nice properties. However, high order derivatives appear in the Euler–Lagrange equations of the MC-based models which create problems in developing an efficient numerical algorithm. To overcome this difficulty, we present a robust and efficient Two-Level method for MC-based image denoising and image deblurring models. The Two-Level method consists of solving one small problem and one large problem. The small problem is a nonlinear system, having high order derivative, on Level I (image having small number of pixels). The large problem is one less expensive system, having low order derivative, on Level II (image having large number of pixels). The derivation of the optimal regularization parameter of Level II is studied and formula is presented. Numerical experiments on digital images are presented to exhibit the performance of the Two-Level method.

In this paper, we analyze and evaluate suitable preconditioning techniques to improve the performance of the L-p-norm phase unwrapping method. We consider five preconditioning techniques commonly found in the literature, and analyze their performance with different sizes of wrapped-phase maps.

The single cell gel electrophoresis assay, which is also referred to as the comet assay, is a quantitative method by which visual evidence of DNA damage in individual cells may be measured. Since this assay is sensitive and simple to perform, it is widely used in several areas including human biomonitoring, genotoxicology, and ecological monitoring. In the last decades, various computer systems have implemented segmentation algorithms based on traditional threshold techniques rather than efficient deep learning methods to automatically identify cells in comet assay output images. This paper presents a fully convolutional neural network based system, named U-NetComet, to automate comets segmentation, minimizing user interaction and providing reproducible measurements. A comparison of our method with a commercial system has been performed, and results showed that our system is more efficient and reliable.

In this paper, we present a parallel implementation of a fixed-point algorithm for finding the solution of the total variation model for phase demodulation. The total variation model is efficient in estimating discontinuous phase maps, background illumination, and amplitude modulation from a single fringe pattern. The implementations include execution in a multi-core CPU and a GPU using OpenMP and CUDA, respectively. We show performance comparisons of the parallel implementations with 64-bit and 32-bit precision floating-point numbers using synthetic and real experimental data. Results show that our parallel implementations achieve speedups over the serial implementation of 9x for multi-core CPU and 103x for GPU.

In this work, we present a methodology for the semiautomatic segmentation of left ventricle of the hearth of mice in echocardiographic images of the murine model for Chagas disease. The methodology presented is based on the active contour model with shape prior. We will show through experimental results the good performance of the model and discuss pros and cons of the methodology.