20 research outputs found
The art of selecting the ECG input in neural networks to classify heart diseases: a dual focus on maximizing information and reducing redundancy
Full text link[EN] Background and Objectives Accurate diagnosis of cardiovascular diseases often relies on the electrocardiogram (ECG). Since the cardiac vector is located within a three-dimensional space and the standard ECG comprises 12 projections or leads derived from it, redundant information is inherently present. This study aims to quantify this redundancy and its impact on classification tasks using Convolutional Neural Networks (CNNs) in cardiovascular diseases.Methods We employed signal theory and mutual information to introduce a novel redundancy metric and explored techniques for redundancy augmentation and reduction. This involved lead selection and transformation to evaluate the effects on neural network performance.Results Our findings indicate that optimizing input configurations through redundancy reduction techniques can enhance the performance of deep learning models in cardiovascular diagnostics, provided that the information is preserved and minimally distorted.Conclusion For the first time, this research has quantified the redundancy present in the input by validating various redundancy reduction techniques using a CNN. This discovery paves the way for advancing biomedical signal processing research, simplifying model complexity, and enhancing diagnostic performance in cardiovascular medicine within reduced lead systems, such as Holter monitors or wearables.The author(s) declare that financial support was received for the research, authorship, and/or publication of this article. This work has been supported by PID 2022-142514OB-I00 (National Research Program, Ministerio de Ciencia e Innovacion, Spanish Government) and CIBERCV CB16/11/00486 (Instituto de Salud Carlos III).Ramírez, E.; Ruiperez-Campillo, S.; Casado-Arroyo, R.; Merino, JL.; Vogt, JE.; Castells, F.; Millet Roig, J. (2024). The art of selecting the ECG input in neural networks to classify heart diseases: a dual focus on maximizing information and reducing redundancy. Frontiers in Physiology. 15. https://doi.org/10.3389/fphys.2024.1452829S1
Mini Peltier Cell Array System for the Generation of Controlled Local Epicardial Heterogeneities
Full text link[EN] The present study aims to design and fabricate a system capable of generating heterogeneities on the epicardial surface of an isolated rabbit heart perfused in a Langendorff system. The system consists of thermoelectric modules that can be independently controlled by the developed hardware, thereby allowing for the generation of temperature gradients on the epicardial surface, resulting in conduction slowing akin to heterogeneities of pathological origin. A comprehensive analysis of the system's viability was performed through modeling and thermal simulation, and its practicality was validated through preliminary tests conducted at the experimental cardiac electrophysiology laboratory of the University of Valencia. The design process involved the use of Fusion 360 for 3D designs, MATLAB/Simulink for algorithms and block diagrams, LTSpice and Altium Designer for schematic captures and PCB design, and the integration of specialized equipment for animal experimentation. The objective of the study was to efficiently capture epicardial recordings under varying conditions.Clinical relevance- The proposed system aims to induce local epicardial heterogeneities to generate labeled correct signals that can serve as a golden standard for improving algorithms that identify and characterize fibrotic substrates. This improvement will enhance the efficacy of ablation processes and potentially reduce the ablated surface area.This work was supported by PID2019-109547RB-I00 (National Research Program, Ministerio de Ciencia e Innovacion, Spanish Government) and CIBERCV CB16/11/00486 (Instituto de Salud Carlos III).Segarra, I.; Cebrián Ferriols, AJ.; Ruiperez-Campillo, S.; Tormos Ferrando, Á.; Chorro, FJ.; Castells, F.; Alberola, A.... (2023). Mini Peltier Cell Array System for the Generation of Controlled Local Epicardial Heterogeneities. IEEE. 1-4. https://doi.org/10.1109/EMBC40787.2023.10340369S1
Segmenting computed tomograms for cardiac ablation using machine learning leveraged by domain knowledge encoding
Full text link[EN] Background: Segmentation of computed tomography (CT) is important for many
clinical procedures including personalized cardiac ablation for the management of
cardiac arrhythmias. While segmentation can be automated by machine learning
(ML), it is limited by the need for large, labeled training data that may be difficult
to obtain. We set out to combine ML of cardiac CT with domain knowledge,
which reduces the need for large training datasets by encoding cardiac
geometry, which we then tested in independent datasets and in a prospective
study of atrial fibrillation (AF) ablation.
Methods: We mathematically represented atrial anatomy with simple geometric
shapes and derived a model to parse cardiac structures in a small set of N=6
digital hearts. The model, termed ¿virtual dissection,¿ was used to train ML to
segment cardiac CT in N = 20 patients, then tested in independent datasets and
in a prospective study.
Results: In independent test cohorts (N = 160) from 2 Institutions with different CT
scanners, atrial structures were accurately segmented with Dice scores of 96.7% in
internal (IQR: 95.3%¿97.7%) and 93.5% in external (IQR: 91.9%¿94.7%) test data,
with good agreement with experts (r = 0.99; p < 0.0001). In a prospective study
of 42 patients at ablation, this approach reduced segmentation time by 85%
(2.3 ± 0.8 vs. 15.0 ± 6.9 min, p < 0.0001), yet provided similar Dice scores to
experts (93.9% (IQR: 93.0%¿94.6%) vs. 94.4% (IQR: 92.8%¿95.7%), p = NS).
Conclusions: Encoding cardiac geometry using mathematical models greatly
accelerated training of ML to segment CT, reducing the need for large training
sets while retaining accuracy in independent test data. Combining ML with
domain knowledge may have broad applications.Research reported in this publication was supported by grants from the National Institutes of Health under award numbers R01 HL149134 and R01 HL83359.Feng, R.; Deb, B.; Ganesan, P.; Tjong, FV..; Rogers, AJ.; Ruiperez-Campillo, S.; Somani, S.... (2023). Segmenting computed tomograms for cardiac ablation using machine learning leveraged by domain knowledge encoding. Frontiers in Cardiovascular Medicine. 10. https://doi.org/10.3389/fcvm.2023.1189293S1
Vector field heterogeneity as a novel omnipolar mapping metric for functional substrate characterization in scar-related ventricular tachycardias
No full textISSN:1547-5271ISSN:1556-3871ISSN:1556-387
Evaluation and assessment of clique arrangements for the estimation of omnipolar electrograms in high density electrode arrays: an experimental animal model study
Full text linkISSN:2662-4737ISSN:2662-4729ISSN:2662-472
Multimodal explainable artificial intelligence identifies patients with non-ischaemic cardiomyopathy at risk of lethal ventricular arrhythmias
No full textISSN:2045-232
La dimensión performativa del juego taurino popular y profesional, una interpretación. Dimensión Antropológica Vol. 59 Año 20 (2013) septiembre-diciembre
No full textAbad Molina, Javier, “Experiencia estética y arte de participación: juego, símbolo y celebración”, en Salomé Díaz Rodríguez y Susana Montemayor Ruiz (eds.), La educación artística como instrumento de integración intercultural y social, Madrid, Ministerio de Educación-Secretaría General Técnica, 2007, pp. 37-76.Aguilar y Prado, Iacinto de, Escrito Historico de las solemnes fiestas que la Antiquisima y Noble Ciudad de Pamplona cabeça del Nobilísimo Reyno de Navarra a hecho en honra y comemoracion del gloriosissimo S. Fermin, Pamplona, impreso por Carlos de Labàyen, 1628.Alenda y Mira, Jenaro, Relaciones de solemnidades y fiestas públicas de España, Madrid, Sucesores de Rivadeneyra, 1903.Bahr, Wolfgang, “La ganadería de toros de lidia en Tlaxcala”, en Comunicaciones, núm. 3, Fundación Alemana para la Investigación Científica, Puebla, 1971.Barthes, Roland, Del deporte y los hombres, Madrid, Paidós (El arco de Ulises), 2008.Bennassar, Bartolomé, Historia de la tauromaquia, una sociedad del espectáculo, trad. de Denise Lavezzi Revel-Chion, Valencia, Real Maestranza de Caballería de Ronda/Pre-Textos, 2000.Bergamín, José, Obra taurina, Madrid, Consejo Superior de Investigaciones Científicas, 2008.Caillois, Roger, Los juegos y los hombres, la máscara y el vértigo (trad. de Jorge Ferreiro), México, FCE (Popular, 344), 1986.Campos Cañizares, José, El toreo caballeresco en la época de Felipe IV: técnicas y significado-sociocultural, Sevilla, Fundación Real Maestranza de Caballería de Sevilla/Fundación de Estudios Taurinos/Universidad de Sevilla (Tauromaquias, 9), 2007.Carlson, Marvin, “What is Performance?”, en Henry Bial (ed.), The Performance Studies Reader, Nueva York, Routledge, 2004, pp. 70-75.Cordero del Campillo, Miguel, Crónicas de Indias, ganadería, medicina y veterinaria, Salamanca, Junta de Castilla y León/Consejería de Educación y Cultura (Estudios de la historia de la ciencia y de la técnica, 18), 2001.Dewey, John, El arte como experiencia (trad. de Samuel Ramos), México, FCE (secc. de Obras de Filosofía), 1949.Dubatti, Jorge, Filosofía del teatro, convivio, experiencia, subjetividad, Buenos Aires, Atuel, 2007, vol. 1.Galindo Villavicencio, Xóchitl, “Juegos con toros: de la dehesa castellana a la Cuenca de México (performance y representación)”, tesis de doctorado, Salamanca, Facultad de Ciencias Sociales-Universidad de Salamanca, 2011.Geist, Ingrid, “Encuentros oblicuos entre el ritual y el teatro”, en Ingrid Geist (ed.), Antropología del ritual: Victor Turner (trad. de Magdalena Uribe Jiménez e Ingrid Geist), México, enah-inah, 2002, pp. 145-188.Huizinga, Johan, Homo ludens, Madrid, Alianza/Emecé (El Libro de Bolsillo), 1972.____________, El otoño de la Edad Media, Madrid, Alianza, 1996.Mora Ledesma, Ma. Isabel, “‘Vámonos con todo y chivas’, sistemas de supervivencia en las culturas ganaderas del norte de San Luis Potosí”, en Revista del Colegio de San Luis, Nueva Época, año 1, núm. 1, enero-junio de 2011, pp. 49-68.Romano Garrido, Ricardo, “El espectáculo y el drama de la violencia. Los toreros del carnaval y la huamantlada en el volcán de la Malinche”, tesis de doctorado, FFYL/IIA-UNAM, 2011.Saumade, Frédéric, Las tauromaquias europeas. La forma y la historia, un enfoque antropológico (trad. de Adela Fábregas García), Sevilla, Fundación Real Maestranza de Caballería de Sevilla/Fundación de Estudios Taurinos de la Universidad de Sevilla/Universidad de Granada (Tauromaquias, 8), 2006.____________, Maçatl- Les transformations mexicaines des jeux taurins, Bourdeaux, Presses Universitaires de Bourdeaux, 2008.Savater, Fernando, Tauroética, Madrid, Turpial, 2010.Schechner, Richard, Essays on Performance Theory 1970-1976, Nueva York, Drama Books Specialists (Publishers), 1977.____________, Performance Theory, Londres, Routledge, 2003.____________, Performance Studies: An Introduction, Nueva York, Routledge, 2006.Tudela de la Orden, José, Historia de la ganadería hispanoamericana (Homenaje en su centenario), Madrid, Instituto de Cooperación Iberoamericana/Ediciones de Cultura Hispánica/Agencia Española de Cooperación Internacional, 1993.Turner, Victor, “Social Dramas and Ritual Metaphors”, en Dramas, Fields and Methaphors. Symbolic Action in Human Society, Nueva York, Cornell University Press, 1974, pp. 23-59.____________, “The Anthropology of Performance”, en Victor Turner, On the Edge of the Bush: Anthropology as Experience, Arizona, University of Arizona Press, 1985.____________, The Anthropology of Performance, Nueva York, Performing Arts Journal Publications, 1988.____________, “La antropología del performance”, en Ingrid Geist (ed.), Antropología del ritual: Victor Turner (trad. de Magdalena Uribe Jiménez e Ingrid Geist), México, ENAH-INAH, 2002, pp. 72-98.Wulf, Christoph, “Teorías y prácticas del performativo”, en Antropología: historia, cultura, filosofía (trad. de Daniel Barreto González), México/
Barcelona, Anthropos/UAM-I, 2008.Se propone una interpretación de la corrida de toros profesionalizada y del juego taurino popular denominado “encierro”. Como caso particular mexicano se analiza el ejemplo de la Huamantlada en Tlaxcala. Ambos casos, a partir de la focalización en las acciones inmediatas que ocurren durante el desarrollo del espectáculo. En cada uno de los ejemplos proponemos que es posible apreciar procesos de escenificación performativos que nos permiten analizarlos como eventos que crean y comunican experiencias mientras son ejecutados
Microresonators for organic semiconductor and fluidic lasers
No full textThis thesis describes a number of studies of microstructured optical resonators,
designed with the aim of enhancing the performance of organic semiconductor lasers
and exploring potential applications. The methodology involves the micro-engineering
of the photonic environment in order to modify the pathways of the emitted light and
control the feedback mechanism. The research focuses on designing new organic
microstructures using established semi-analytical and numerical methods, developing fabrication techniques using electron-beam lithography, and optically characterising the resulting structures.
Control of the feedback mechanism in conjugated polymer lasers is first investigated by studying Distributed Feedback or photonic crystal resonators based on a square feedback lattice. This study identified the diffraction to free space radiation as a major source of loss in current microstructured resonator designs. By cancelling the coupling to free space through the use of different feedback symmetries and diffraction orders, a threshold reduction by almost an order of magnitude is demonstrated.
The introduction of mid-gap defect photonic states in an otherwise uniformly periodic
structure was studied in Distributed Bragg Reflector (DBR) resonators. This enabled
GaN diode pumped polymer lasers to be demonstrated, indicating that the transition
from complex excitation sources to more compact systems is possible. Devices for
potential applications in the field of optical communications are also explored by
demonstrating a polymer DBR laser based on silicon. In this way, the potential for
integrating conjugated polymers with silicon photonics is confirmed.
Photonic crystal fibres, which have a periodic microstructure in the transverse
direction, are explored as an alternative means for controlling the optical properties of organic lasers. Fluidic fibre organic lasers were demonstrated as efficient sources with good spectral purity. In these devices, mechanisms to tune the emission wavelength
were explored and the origin of the frequency selection mechanism was investigated.The author received a Wingate Scholarship for the Si experiments
Comparing Phenotypes for Acute and Long-Term Response to Atrial Fibrillation Ablation Using Machine Learning
No full textBACKGROUND: It is difficult to identify patients with atrial fibrillation (AF) most likely to respond to ablation. While any arrhythmia patient may recur after acutely successful ablation, AF is unusual in that patients may have long-term arrhythmia freedom despite a lack of acute success. We hypothesized that acute and chronic AF ablation outcomes may reflect distinct physiology and used machine learning of multimodal data to identify their phenotypes. METHODS: We studied 561 consecutive patients in the Stanford AF ablation registry (66±10 years, 28% women, 67% nonparoxysmal), from whom we extracted 72 data features of electrograms, electrocardiogram, cardiac structure, lifestyle, and clinical variables. We compared 6 machine learning models to predict acute and long-term end points after ablation and used Shapley explainability analysis to contrast phenotypes. We validated our results in an independent external population of n=77 patients with AF. RESULTS: The 1-year success rate was 69.5%, and the acute termination rate was 49.6%, which correlated poorly on a patient-by-patient basis (φ coefficient=0.08). The best model for acute termination (area under the curve=0.86, Random Forest) was more predictive than for long-term outcomes (area under the curve=0.67, logistic regression; P<0.001). Phenotypes for long-term success reflected clinical and lifestyle features, while phenotypes for AF termination reflected electrical features. The need for AF induction predicted both phenotypes. The external validation cohort showed similar results (area under the curve=0.81 and 0.64, respectively) with similar phenotypes. CONCLUSIONS: Long-term and acute responses to AF ablation reflect distinct clinical and electrical physiology, respectively. This de-linking of phenotypes raises the question of whether long-term success operates through factors such as attenuated AF progression. There remains an urgent need to develop procedural predictors of long-term AF ablation success.</p
Revisiting Automatic Data Curation for Vision Foundation Models in Digital Pathology
No full textVision foundation models (FMs) are accelerating the development of digital pathology algorithms and transforming biomedical research. These models learn, in a self-supervised manner, to represent histological features in highly heterogeneous tiles extracted from whole-slide images (WSIs) of real-world patient samples. The performance of these FMs is significantly influenced by the size, diversity, and balance of the pre-training data. Yet, data selection has been primarily guided by expert knowledge at the WSI level, focusing on factors such as disease classification and tissue types, while largely overlooking the granular details available at the tile level. In this paper, we investigate the potential of unsupervised automatic data curation at the tile-level, taking into account 350 million tiles. Specifically, we apply hierarchical clustering trees to pre-extracted tile embeddings, allowing us to sample balanced datasets uniformly across the embedding space of the pretrained FM. We further show that these datasets are subject to a trade-off between size and balance, potentially compromising the quality of representations learned by FMs. We propose tailored batch sampling strategies to mitigate this effect. We demonstrate the effectiveness of our method through improved performance on a diverse range of clinically relevant downstream tasks.LTS
