Digital images are used for evaluation and diagnosis of a diabetic foot ulcer. Selecting the wound region (segmentation) in an image is a preliminary step for subsequent analysis. Most of the time, manual segmentation isn't very reliable because specialists could have different opinions over the ulcer border. This fact encourages researchers to find and test different automatic segmentation techniques. This paper presents a computer-aided ulcer region segmentation algorithm for diabetic foot images. The proposed algorithm has two stages: ulcer region segmentation, and post-processing of segmentation results. For the first stage, a trained machine learning model was selected to classify pixels inside the ulcer's region, after a comparison of five learning models. Exhaustive experiments have been performed with our own annotated dataset from images of Cuban patients. The second stage is needed because of the presence of some misclassified pixels. To solve this, we applied the DBSCAN clustering algorithm, together with dilation, and closing morphological operators. The best-trained model after the post-processing stage was the logistic regressor (Jaccard Index $0.81$, accuracy $0.94$, recall $0.86$, precision $0.91$, and F1 score $0.88$). The trained model was sensitive to irrelevant objects in the scene, but the patient foot. Physicians found these results promising to measure the lesion area and to follow-up the ulcer healing process over treatments, reducing errors.
This contribution presents a wavelet-based algorithm to detect patterns in images. A two-dimensional extension of the DST-II is introduced to construct adapted wavelets using the equation of the tensor product corresponding to the diagonal coefficients in the 2D discrete wavelet transform. A 1D filter was then estimated that meets finite energy conditions, vanished moments, orthogonality, and four new detection conditions. These allow, when performing the 2D transform, for the filter to detect the pattern by taking the diagonal coefficients with values of the normalized similarity measure, defined by Guido, as greater than 0.7, and . The positions of these coefficients are used to estimate the position of the pattern in the original image. This strategy has been used successfully to detect artificial patterns and localize mass-like abnormalities in digital mammography images. In the case of the latter, high sensitivity and positive predictive value in detection were achieved but not high specificity or negative predictive value, contrary to what occurred in the 1D strategy. This means that the proposed detection algorithm presents a high number of false negatives, which can be explained by the complexity of detection in these types of images.
23 January 2024 in Revista de Matemática: Teoría y Aplicaciones
A methodology is presented for calculating the effective elastic properties of periodic multi-phase composites made of an anisotropic linear elastic matrix reinforced with a periodical distribution of unidirectional fibers and exhibiting spring-type imperfect contacts at the interfaces. The periodicity cell contains any finite number of parallel fibers and exhibits arbitrary cross-section. Fibers also exhibit arbitrary cross-sections and are made of a different anisotropic linear elastic material each. The methodology uses asymptotic homogenization (AH) to obtain the mathematical expressions of the effective properties and to formulate the so-called local problems on the periodicity cell on whose solutions the effective properties depend on. In order to deal with the discontinuities arising from the spring-type interfaces, the local problems are then restated via domain decomposition (DD) in a way allowing for an iterative resolution scheme in which the solution of the problem to be solve in each iteration is obtained via finite elements (FE). Results in the examples are obtained via a computational implementation of the methodology based on the FreeFEM open-source software, which allows for the variational formulation of the iteration problem to be dealt with directly.