Persona: Carmona Suárez, Enrique J.
Cargando...
Dirección de correo electrónico
ORCID
0000-0002-7487-745X
Fecha de nacimiento
Proyectos de investigación
Unidades organizativas
Puesto de trabajo
Apellidos
Carmona Suárez
Nombre de pila
Enrique J.
Nombre
6 resultados
Resultados de la búsqueda
Mostrando 1 - 6 de 6
Publicación Semantic-guided generative latent diffusion augmentation approaches for improving the neovascularization diagnosis in OCT-A imaging(ELSEVIER, 2025-01-13) Iglesias Morís, Daniel; Moura, Joaquim de; Novo, Jorge; Ortega, Marcos; Carmona Suárez, Enrique J.Age-related Macular Degeneration (AMD) presents an enormous challenge in Western Societies due to the increase in life expectancy. AMD is characterized for causing Macular Neovascularization. Optical Coherence Tomography Angiography (OCT-A) represents an advanced method to help find evidence of the disease. In this context, deep learning algorithms are suitable to make a screening of the disease. However, biomedical imaging domains are usually affected by the data scarcity issue. The mitigation of this problem can be achieved with the support of generative latent diffusion models. This represents a powerful strategy to artificially augment the cardinality of the original dataset. In this work, we present a novel fully automatic methodology to generate OCT-A images, guided by semantic information, to reduce the impact of data scarcity and to enable an accurate neovascularization diagnosis. The evaluation has been performed with a specific dataset composed of two different fields of view commonly used by clinicians. The results demonstrate a top accuracy of 96.50% 1.37%, using 3 × 3 scans, and 95.79% 1.44%, when using 6 × 6 scans. The proposed methodology has great potential to be extrapolated to other imaging modalities and domains.Publicación Modeling, localization, and segmentation of the foveal avascular zone on retinal OCT-angiography images(IEEE, 2020-08-17) Díaz González, Macarena; Novo, Jorge; Ortega, Marcos; Carmona Suárez, Enrique J.The Foveal Avascular Zone (FAZ) is a capillary-free area that is placed inside the macula and its morphology and size represent important biomarkers to detect different ocular pathologies such as diabetic retinopathy, impaired vision or retinal vein occlusion. Therefore, an adequate and precise segmentation of the FAZ presents a high clinical interest. About to this, Angiography by Optical Coherence Tomography (OCT-A) is a non-invasive imaging technique that allows the expert to visualize the vascular and avascular foveal zone. In this work, we present a robust methodology composed of three stages to model, localize, and segment the FAZ in OCT-A images. The first stage is addressed to generate two FAZ normality models: superficial and deep plexus. The second one uses the FAZ model as a template to localize the FAZ center. Finally, in the third stage, an adaptive binarization is proposed to segment the entire FAZ region. A method based on this methodology was implemented and validated in two OCT-A image subsets, presenting the second subset more challenging pathological conditions than the first. We obtained localization success rates of 100% and 96% in the first and second subsets, respectively, considering a success if the obtained FAZ center is inside the FAZ area segmented by an expert clinician. Complementary, the Dice score and other indexes (Jaccard index and Hausdorff distance) are used to measure the segmentation quality, obtaining competitive average values in the first subset: 0.84 ± 0.01 (expert 1) and 0.85 ± 0.01 (expert 2). The average Dice score obtained in the second subset was also acceptable (0.70 ± 0.17), even though the segmentation process is more complex in this case.Publicación Simultaneous segmentation of the optic disc and fovea in retinal images using evolutionary algorithms(Springer, 2021-03) Molina Casado, José María; Carmona Suárez, Enrique J.In this work, we present a new methodology to simultaneously segment anatomical structures in medical images. Additionally, this methodology is instantiated in a method that is used to simultaneously segment the optic disc (OD) and fovea in retinal images. The OD and fovea are important anatomical structures that must be previously identified in any image-based computer-aided diagnosis system dedicated to diagnosing retinal pathologies that cause vision problems. Basically, the simultaneous segmentation method uses an OD-fovea model and an evolutionary algorithm. On the one hand, the model is built using the intra-structure relational knowledge, associated with each structure, and the inter-structure relational knowledge existing between both and other retinal structures. On the other hand, the evolutionary algorithm (differential evolution) allows us to automatically adjust the instance parameters that best approximate the OD-fovea model in a given retinal image. The method is evaluated in the MESSIDOR public database. Compared with other recent segmentation methods in the related literature, competitive segmentation results are achieved. In particular, a sensitivity and specificity of 0.9072 and 0.9995 are respectively obtained for the OD. Considering a success when the distance between the detected and actual center is less than or equal to η times the OD radius, the success rates obtained for the fovea are 97.3% and 99.0% for η = 1=2 and η = 1 and, respectively. The segmentation average time per image is 29.35 s.Publicación Introducing modularity and homology in grammatical evolution to address the analog electronic circuit design problem(IEEE, 2020-08-24) Castejón, Federico; Carmona Suárez, Enrique J.We present a new approach based on grammatical evolution (GE) aimed at addressing the analog electronic circuit design problem. In the new approach, called multi-grammatical evolution (MGE), a chromosome is a variable-length codon string that is divided into as many partitions as subproblems result from breaking down the original optimization problem: circuit topology and component sizing in our case. This leads to a modular approach where the solution of each subproblem is encoded and evolved in a partition of the chromosome. Additionally, each partition is decoded according to a specific grammar and the final solution to the original problem emerges as an aggregation result associated with the decoding process of the different partitions. Modularity facilitates the encoding and evolution of the solution in each subproblem. On the other way, homology helps to reduce the potentially destructive effect associated with standard crossover operators normally used in GE-based approaches. Seven analog circuit designs are addressed by an MGE-based method and the obtained results are compared to those obtained by different methods based on GE and other evolutionary paradigms. A simple parsimony mechanism was also introduced to ensure compliance with design specifications and reduce the number of components of the circuits obtained. We can conclude that our method obtains competitive results in the seven circuits analyzed.Publicación Deformable registration of multimodal retinal images using a weakly supervised deep learning approach(Springer, 2023-03-28) Martínez Río, Javier; Cancelas, Daniel; Novo, Jorge; Ortega, Marcos; Carmona Suárez, Enrique J.There are different retinal vascular imaging modalities widely used in clinical practice to diagnose different retinal pathologies. The joint analysis of these multimodal images is of increasing interest since each of them provides common and complementary visual information. However, if we want to facilitate the comparison of two images, obtained with different techniques and containing the same retinal region of interest, it will be necessary to make a previous registration of both images. Here, we present a weakly supervised deep learning methodology for robust deformable registration of multimodal retinal images, which is applied to implement a method for the registration of fluorescein angiography (FA) and optical coherence tomography angiography (OCTA) images. This methodology is strongly inspired by VoxelMorph, a general unsupervised deep learning framework of the state of the art for deformable registration of unimodal medical images. The method was evaluated in a public dataset with 172 pairs of FA and superficial plexus OCTA images. The degree of alignment of the common information (blood vessels) and preservation of the non-common information (image background) in the transformed image were measured using the Dice coefficient (DC) and zero-normalized cross-correlation (ZNCC), respectively. The average values of the mentioned metrics, including the standard deviations, were DC = 0.72 ± 0.10 and ZNCC = 0.82 ± 0.04. The time required to obtain each pair of registered images was 0.12 s. These results outperform rigid and deformable registration methods with which our method was compared.Publicación Robust multimodal registration of fluorescein angiography and optical coherence tomography angiography images using evolutionary algorithms(Elsevier, 2021-07) Martínez Río, Javier; Cancelas, Daniel; Novo, Jorge; Ortega, Marcos; Carmona Suárez, Enrique J.Optical coherence tomography angiography (OCTA) and fluorescein angiography (FA) are two different vascular imaging modalities widely used in clinical practice to diagnose and grade different relevant retinal pathologies. Although each of them has its advantages and disadvantages, the joint analysis of the images produced by both techniques to analyze a specific area of the retina is of increasing interest, given that they provide common and complementary visual information. However, in order to facilitate this analysis task, a previous registration of the pair of FA and OCTA images is desirable in order to superimpose their common areas and focus the gaze on the regions of interest. Normally, this task is manually carried out by the expert clinician, but it turns out to be tedious and time-consuming. Here, we present a three-stage methodology for robust multimodal registration of FA and superficial plexus OCTA images. The first one is a preprocessing stage devoted to reducing the noise and segmenting the main vessels in both types of images. The second stage uses the vessel information to do an approximate registration based on template matching. Lastly, the third stage uses an evolutionary algorithm based on differential evolution to refine the previous registration and obtain the optimal registration. The method was evaluated in a dataset with 172 pairs of FA and OCTA images, obtaining a success rate of 98.8%. The best mean execution time of the method was less than 5 s per image.