Detección de fibrosis en imágenes de cine de resonancia cardíaca mediante el uso de técnicas de inteligencia artificial / Fibrosis detection on MR-Cine images by using artificial intelligence techniques

RESUMEN Introducción: Las técnicas de inteligencia artificial han demostrado tener un gran potencial en el área de la cardiología, especialmente para identificar patrones imperceptibles para el ser humano. En este sentido, dichas técnicas parecen ser las adecuadas para identificar patrones en la textura del miocardio con el objetivo de identificar y cuantificar la fibrosis. Objetivos: Proponer un nuevo método de inteligencia artificial para identificar fibrosis en imágenes cine de resonancia cardíaca. Materiales y métodos: Se realizó un estudio retrospectivo observacional en 75 sujetos del Sanatorio San Carlos de Bariloche. El método propuesto analiza la textura del miocardio en las imágenes cine CMR (resonancia magnética cardíaca) mediante el uso de una red neuronal convolucional que determinar el daño local del tejido miocárdico. Resultados: Se observó una precisión del 89% para cuantificar el daño tisular local en el conjunto de datos de validación y de un 70% para el conjunto de prueba. Además, el análisis cualitativo realizado muestra una alta correlación espacial en la localización de la lesión. Conclusiones: El método propuesto permite identificar espacialmente la fibrosis únicamente utilizando la información de los estudios de cine de resonancia magnética nuclear, mostrando el potencial de la técnica propuesta para cuantificar la viabilidad miocárdica en un futuro o estudiar la etiología de las lesiones.

ABSTRACT Background: Artificial intelligence techniques have demonstrated great potential in cardiology, especially to detect imperceptible patterns for the human eye. In this sense, these techniques seem to be adequate to identify patterns in the myocardial texture which could lead to characterize and quantify fibrosis. Purpose: The aim of this study was to postulate a new artificial intelligence method to identify fibrosis in cine cardiac magnetic resonance (CMR) imaging. Methods: A retrospective observational study was carried out in a population of 75 subjects from a clinical center of San Carlos de Bariloche. The proposed method analyzes the myocardial texture in cine CMR images using a convolutional neural network to determine local myocardial tissue damage. Results: An accuracy of 89% for quantifying local tissue damage was observed for the validation data set and 70% for the test set. In addition, the qualitative analysis showed a high spatial correlation in lesion location. Conclusions: The postulated method enables to spatially identify fibrosis using only the information from cine nuclear magnetic resonance studies, demonstrating the potential of this technique to quantify myocardial viability in the future or to study the etiology of lesions.

Factores asociados a placa blanda en pacientes con score de calcio igual a cero / Factors Associated with Non-calcified Plaques in Patients with Coronary Artery Calcium Score of Zero

RESUMEN Introducción: El score de calcio es una prueba utilizada en la estratificación de riesgo de pacientes asintomáticos. Aunque la enfermedad coronaria puede producirse en ausencia de calcificaciones, no se han descripto afecciones asociadas a la presencia de placa blanda en este contexto, más allá de la presencia de síntomas. Objetivos: Determinar asociaciones entre la presencia de placa blanda y variables independientes en pacientes con un score de calcio de cero. Material y métodos: Se incluyeron pacientes consecutivos con un score de calcio de 0 unidades Agatston que se hubieran realizado, además, una angiotomografía coronaria. Se determinaron asociaciones a partir de análisis univariado. Se calculó la sensibilidad, especificidad, VPN, VPP, +LR y -LR. Resultados: Se incluyeron en el estudio 93 pacientes. El 10% (n = 9) presentaron placa blanda. La ergometría positiva se asoció a placas de cualquier gravedad (OR 6,5; IC del 95%: 1,3-33, p = 0,02). Esta asociación persistió para placas no graves cuando se combinó la ergometría positiva con perfusión miocárdica SPECT o ecocardiograma estrés negativos para isquemia (OR 12,4 IC 95% 1,5-101, p = 0,02). La sensibilidad y la especificidad del infradesnivel del ST para placa blanda de cualquier nivel de gravedad fue del 44,4% y del 86%, respectivamente. El VPN fue del 94% y el VPP del 25%, LR+ fue de 3,11 y LR- fue de 0,65. Conclusiones: El infradesnivel del ST se asociaría a la presencia de placa blanda en pacientes sin calcificaciones coronarias, incluso en contexto de perfusión miocárdica o motilidad parietal en esfuerzo normales (enfermedad no obstructiva).

ABSTRACT Background: The coronary artery calcium score is used for risk stratification in asymptomatic patients. Although coronary artery disease can occur in the absence of coronary artery calcifications, no conditions associated with the presence of soft non-calcified plaques have been described in this scenario, beyond the presence of symptoms. Objectives: The aim of this study was to determine the associations between non-calcified plaques and independent variables in patients with coronary artery calcium score of zero. Methods: Consecutive patients with coronary artery score of zero Agatston units who also underwent computed tomography coronary angiography were included in the study. Univariate logistic regression analysis was used to find associations. (15) Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), positive likelihood ratio (LH+) and negative likelihood ratio (LH-) were calculated. Results: Among a total of 93 patients, 10% (n=9) presented non-calcified plaque. A positive exercise stress test was associated with plaques of any degree of severity (OR 6.5; 95% CI, 1.3-33, p=0.02). This association persisted for non-severe plaques when the positive exercise stress test was combined with a negative myocardial perfusion SPECT or stress echocardiography for ischemia (OR, 12.4; 95% CI 1.5-101, p=0.02). Sensitivity and specificity of ST-segment depression for non-calcified plaque of any degree of severity was 44.4% and 86%, respectively, with NPV of 94%, PPV of 25%, LR+ of 3.11 and LR- of 0.65. Conclusions: ST-segment depression could be associated with non-calcified plaques in patients without coronary artery calcifications, even with normal exercise stress myocardial perfusion or wall motion (non-obstructive disease).

Ventricular-arterial coupling assessment using gated single-photon emission computed tomography: relationship with reserve pulse pressure and repolarization abnormalities.

AIMS: In patients with normal myocardial perfusion, ST-segment depression and reserve pulse pressure (rPP) can identify patients at higher risk of cardiovascular events. We aimed to explore the prevalence of impaired ventricular-arterial coupling (VAc) in patients with normal myocardial perfusion imaging and its relationship with ST-segment depression and rPP. METHODS AND RESULTS: The present study included consecutive patients with normal myocardial perfusion imaging by single-photon emission computed tomography and ST-segment depression. Stroke volume, end-systolic pressure, arterial elastance (Ea), ventricular elastance (Ev), and VAc (Ea/Ev) were estimated both at rest and during stress. The difference between stress and rest (ΔVAc) was calculated. A positive ΔVAc was considered an impaired ΔVAc (iVAc). RESULTS: A total of 92 patients were prospectively included. iVAc was identified in 44 (59%) patients with ST-segment depression compared with 3 (16%) patients with normal repolarization (P=0.001). A higher incidence of abnormal rPP was identified in patients with ST-segment depression compared with the control group (61 vs. 16%, P=0.0001). ST-segment depression was identified as the only independent predictor of iVAc (adjusted OR 7.5; 95% CI 1.9-30.0, P=0.004). CONCLUSION: Noninvasive assessment of VAc is feasible with gated single-photon emission computed tomography and appears to be related to ST-segment depression and reserve rPP.