Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 5 de 5
Filtrar
Mais filtros











Intervalo de ano de publicação
1.
Rev. argent. cardiol ; 92(1): 5-14, mar. 2024. tab, graf
Artigo em Espanhol | LILACS-Express | LILACS | ID: biblio-1559227

RESUMO

RESUMEN Introducción: El número creciente de estudios ecocardiográficos y la necesidad de cumplir rigurosamente con las recomendaciones de guías internacionales de cuantificación, ha llevado a que los cardiólogos deban realizar tareas sumamente extensas y repetitivas, como parte de la interpretación y análisis de cantidades de información cada vez más abrumadoras. Novedosas técnicas de machine learning (ML), diseñadas para reconocer imágenes y realizar mediciones en las vistas adecuadas, están siendo cada vez más utilizadas para responder a esta necesidad evidente de automatización de procesos. Objetivos: Nuestro objetivo fue evaluar un modelo alternativo de interpretación y análisis de estudios ecocardiográficos, basado fundamentalmente en la utilización de software de ML, capaz de identificar y clasificar vistas y realizar mediciones estandarizadas de forma automática. Material y métodos: Se utilizaron imágenes obtenidas en 2000 sujetos normales, libres de enfermedad, de los cuales 1800 fueron utilizados para desarrollar los algoritmos de ML y 200 para su validación posterior. Primero, una red neuronal convolucional fue desarrollada para reconocer 18 vistas ecocardiográficas estándar y clasificarlas de acuerdo con 8 grupos (stacks) temáticos. Los resultados de la identificación automática fueron comparados con la clasificación realizada por expertos. Luego, algoritmos de ML fueron desarrollados para medir automáticamente 16 parámetros de eco Doppler de evaluación clínica habitual, los cuales fueron comparados con las mediciones realizadas por un lector experto. Finalmente, comparamos el tiempo necesario para completar el análisis de un estudio ecocardiográfico con la utilización de métodos manuales convencionales, con el tiempo necesario con el empleo del modelo que incorpora ML en la clasificación de imágenes y mediciones ecocardiográficas iniciales. La variabilidad inter e intraobservador también fue analizada. Resultados: La clasificación automática de vistas fue posible en menos de 1 segundo por estudio, con una precisión de 90 % en imágenes 2D y de 94 % en imágenes Doppler. La agrupación de imágenes en stacks tuvo una precisión de 91 %, y fue posible completar dichos grupos con las imágenes necesarias en 99% de los casos. La concordancia con expertos fue excelente, con diferencias similares a las observadas entre dos lectores humanos. La incorporación de ML en la clasificación y medición de imágenes ecocardiográficas redujo un 41 % el tiempo de análisis y demostró menor variabilidad que la metodología de interpretación convencional. Conclusión: La incorporación de técnicas de ML puede mejorar significativamente la reproducibilidad y eficiencia de las interpretaciones y mediciones ecocardiográficas. La implementación de este tipo de tecnologías en la práctica clínica podría resultar en reducción de costos y aumento en la satisfacción del personal médico.


ABSTRACT Background: The growing number of echocardiographic tests and the need for strict adherence to international quantification guidelines have forced cardiologists to perform highly extended and repetitive tasks when interpreting and analyzing increasingly overwhelming amounts of data. Novel machine learning (ML) techniques, designed to identify images and perform measurements at relevant visits, are becoming more common to meet this obvious need for process automation. Objectives: Our objective was to evaluate an alternative model for the interpretation and analysis of echocardiographic tests mostly based on the use of ML software in order to identify and classify views and perform standardized measurements automatically. Methods: Images came from 2000 healthy subjects, 1800 of whom were used to develop ML algorithms and 200 for subsequent validation. First, a convolutional neural network was developed in order to identify 18 standard echocardiographic views and classify them based on 8 thematic groups (stacks). The results of automatic identification were compared to classification by experts. Later, ML algorithms were developed to automatically measure 16 Doppler scan parameters for regular clinical evaluation, which were compared to measurements by an expert reader. Finally, we compared the time required to complete the analysis of an echocardiographic test using conventional manual methods with the time needed when using the ML model to classify images and perform initial echocardiographic measurements. Inter- and intra-observer variability was also analyzed. Results: Automatic view classification was possible in less than 1 second per test, with a 90% accuracy for 2D images and a 94% accuracy for Doppler scan images. Stacking images had a 91% accuracy, and it was possible to complete the groups with any necessary images in 99% of cases. Expert agreement was outstanding, with discrepancies similar to those found between two human readers. Applying ML to echocardiographic imaging classification and measurement reduced time of analysis by 41% and showed lower variability than conventional reading methods. Conclusion: Application of ML techniques may significantly improve reproducibility and efficiency of echocardiographic interpretations and measurements. Using this type of technologies in clinical practice may lead to reduced costs and increased medical staff satisfaction.

2.
Eur Heart J Cardiovasc Imaging ; 25(6): 754-761, 2024 05 31.
Artigo em Inglês | MEDLINE | ID: mdl-38243591

RESUMO

AIMS: Although impaired left ventricular (LV) global longitudinal strain (GLS) with apical sparing is a feature of cardiac amyloidosis (CA), its diagnostic accuracy has varied across studies. We aimed to determine the ability of apical sparing ratio (ASR) and most common echocardiographic parameters to differentiate patients with confirmed CA from those with clinical and/or echocardiographic suspicion of CA but with this diagnosis ruled out. METHODS AND RESULTS: We identified 544 patients with confirmed CA and 200 controls (CTRLs) as defined above (CTRL patients). Measurements from transthoracic echocardiograms were performed using artificial intelligence software (Us2.AI, Singapore) and audited by an experienced echocardiographer. Receiver operating characteristic curve analysis was used to evaluate the diagnostic performance and optimal cut-offs for the differentiation of CA patients from CTRL patients. Additionally, a group of 174 healthy subjects (healthy CTRL) was included to provide insight on how patients and healthy CTRLs differed echocardiographically. LV GLS was more impaired (-13.9 ± 4.6% vs. -15.9 ± 2.7%, P < 0.0005), and ASR was higher (2.4 ± 1.2 vs. 1.7 ± 0.9, P < 0.0005) in the CA group vs. CTRL patients. Relative wall thickness and ASR were the most accurate parameters for differentiating CA from CTRL patients [area under the curve (AUC): 0.77 and 0.74, respectively]. However, even with the optimal cut-off of 1.67, ASR was only 72% sensitive and 66% specific for CA, indicating the presence of apical sparing in 32% of CTRL patients and even in 6% healthy subjects. CONCLUSION: Apical sparing did not prove to be a CA-specific biomarker for accurate identification of CA, when compared with clinically similar CTRLs with no CA.


Assuntos
Amiloidose , Ecocardiografia , Humanos , Feminino , Masculino , Amiloidose/diagnóstico por imagem , Pessoa de Meia-Idade , Ecocardiografia/métodos , Idoso , Cardiomiopatias/diagnóstico por imagem , Estudos de Casos e Controles , Disfunção Ventricular Esquerda/diagnóstico por imagem , Disfunção Ventricular Esquerda/fisiopatologia , Estudos Retrospectivos , Curva ROC
3.
Eur Heart J Cardiovasc Imaging ; 24(5): 664-677, 2023 04 24.
Artigo em Inglês | MEDLINE | ID: mdl-36056824

RESUMO

AIMS: The 2010 Task Force Criteria (TFC) require that both right ventricular (RV) regional wall-motion abnormalities (WMA) and specific RV size cut-offs be met in order to fulfil one of the major criterion for arrhythmogenic right ventricular cardiomyopathy (ARVC) diagnosis. Currently, 2D echocardiography (2DE) and cardiovascular magnetic resonance imaging (cMRI) are used to determine if these criteria are met. Little is known about the diagnostic value of 3D echocardiography (3DE) in ARVC. The aim of this study was to determine whether a combination of 2DE-3DE is non-inferior to the currently used 2DE-cMRI combination in the diagnosis of patients with ARVC. METHODS AND RESULTS: Thirty-nine individuals (47±15 years) with suspected ARVC underwent evaluation of the RV with cMRI, 2DE, and 3DE. 3DE and cMRI were independently used to obtain RV volumes, ejection fraction (EF) and determine the presence of segmental RV WMA. Studies were blindly classified as meeting criteria for ARVC in accordance with the 2010 TFC. Kappa statistics were used to test the concordance between 2DE-cMRI and 2DE-3DE approaches. Using the 2DE-cMRI approach, 3/39 were not affected, 5/39 possible, 8/39 borderline, and 23/39 definite ARVC. The proposed 2DE-3DE approach yielded 5/39 not affected, 7/39 possible, 8/39 borderline, and 19/39 definite diagnoses. The two approaches were highly concordant (k = 0.71; 95% confidence interval: 0.44-0.84). Although 3DE underestimated RV volumes in comparison with cMRI, interfering, in some instances with the fulfilment of a major criterion, it was able to identify more RV WMA (28/39) than 2DE (11/39), with a detection-rate comparable to cMRI (33/39) highlighting a unique advantage. CONCLUSION: The combination of 2DE-3DE for ARVC diagnosis is comparable to the conventional 2DE-cMRI approach. 3DE should be performed in all suspected ARVC patients to aide in the detection of WMA.


Assuntos
Displasia Arritmogênica Ventricular Direita , Ecocardiografia Tridimensional , Humanos , Ventrículos do Coração/diagnóstico por imagem , Ecocardiografia Tridimensional/métodos , Imageamento por Ressonância Magnética/métodos , Ecocardiografia/métodos
4.
Ginecol. obstet. Méx ; 87(8): 549-554, ene. 2019. graf
Artigo em Espanhol | LILACS-Express | LILACS | ID: biblio-1286658

RESUMO

Resumen ANTECEDENTES: Las anomalías de posición fetal se asocian con la deficiente evolución de trabajo de parto. El ultrasonido durante el trabajo de parto es una herramienta complementaria para confirmar los hallazgos obtenidos en la exploración vaginal y definir el tipo de anomalía de posición fetal. CASOS CLÍNICOS: Caso 1: Paciente de 24 años, primigesta, con 41 semanas de embarazo y ruptura prematura de membranas. Ingresó al área de tococirugía por completar la dilatación y borramiento cervical, sin evolución del trabajo de parto durante 120 minutos. El ultrasonido transabdominal suprapúbico reportó el signo de estrabismo. El embarazo finalizó por cesárea y se corroboró la anomalía fetal de posición occipito-posterior. Caso 2: Paciente de 29 años, primigesta, con 39 semanas de embarazo e hipertensión gestacional, quien completó la dilatación y borramiento cervical y durante 120 minutos no hubo descenso del polo cefálico. A la exploración vaginal se detectó variedad de posición fetal occipito-transversa. El ultrasonido transabdominal suprapúbico mostró el signo de estrabismo. El embarazo finalizó mediante cesárea y la evolución para la madre y su hijo fue satisfactoria. CONCLUSIONES: La ecografía es un estudio efectivo para la detección de anomalías de posición, pues disminuye las complicaciones materno-fetales asociadas con trabajo de parto extendido. Sin embargo, reportar la experiencia de solo dos casos no podría tener validez para sustentar dicha afirmación.


Abstract BACKGROUND: The anomalies of the position are the cause of failure in the task of labor. The ultrasound during labor is a complementary tool to confirm the clinical findings in the vaginal examination and define the type of position abnormality. OBJECTIVE: to report on the use of ultrasound during abnormal labor, such as the detection of the position abnormality. CLINICAL CASES: Case 1: 24-year-old patient with 41 weeks of gestation (SDG) and premature rupture of membranes, entered the area of tochosurgery to complete the dilation and cervical neck, nevertheless worked and delivery for 120 minutes . A suprapubic transabdominal ultrasound was performed, finding a sign of strabismus, the resolution was by caesarean section and an occipito-posterior position anomaly was corroborated. Case 2: 29-year-old patient with 39 SDG and gestational hypertension, it is deduced from the labor, the cervical neck was dilated and for 120 minutes, there was no decrease of the cephalic pole, a variety of occipito place -transverse, suprapubic transabdominal ultrasound was performed, finding a sign of strabismus. The pregnancy ended by caesarean section and the evolution for the mother and her child was satisfactory. CONCLUSIONS: Ultrasound is an effective study for the detection of position abnormalities, since it reduces maternal-fetal complications associated with extended labor. However, reporting the experience of only two cases could not be valid to support this assertion.

5.
Ginecol. obstet. Méx ; 87(3): 202-207, ene. 2019. graf
Artigo em Espanhol | LILACS-Express | LILACS | ID: biblio-1250020

RESUMO

Resumen ANTECEDENTES: Los leiomiomas y el embarazo se relacionan con complicaciones impredecibles; incluso su incidencia se ha incrementado, debido al retraso de la primera gestación y conforme avanza la edad de la madre, su asociación con hemorragia posparto y alto riesgo de histerectomía obstétrica aumentan la morbilidad y mortalidad. CASO CLÍNICO: Paciente de 30 años, sin control prenatal y embarazo clínicamente de término, que acudió a urgencias por dolor obstétrico y sangrado transvaginal. En la exploración física reveló el primer periodo de trabajo de parto, 9 cm de dilatación, altura de presentación -4 según los planos De Lee; se palpó el borde placentario a nivel cervical, acompañado de sangrado transvaginal moderado, rojo rutilante. Se activó el código mater y se preparó para cesárea, por placenta previa sangrante. Durante la intervención quirúrgica se comprobó el diagnóstico y la tumoración, que inició en la cara posterior, en el segmento uterino inferior, y finalizó en la zona cervical, con múltiples vasos de neoformación sangrantes y atonía uterina secundaria, circunstancias que condicionaron hemorragia importante. Se efectuó la histerectomía obstétrica y nació una niña de 3145 g, talla 51 cm, Capurro de 41 semanas de gestación y Apgar 7/9. La pérdida hemática total fue de 2000 cc; permaneció cuatro días en estancia hospitalaria y la madre y su hijo se dieron de alta del hospital sin complicaciones. CONCLUSIÓN: La relación entre miomatosis uterina y embarazo incrementa el riesgo de complicaciones maternas. El seguimiento ecográfico y el control prenatal determinan su repercusión durante la evolución del embarazo y el parto. En estos casos es importante considerar el tratamiento conservador.


Abstract BACKGROUND: Leiomyomas and gestation are an association with unpredictable complications, in which their incidence is increased by the delay of the first gestation and as maternal age advances, its relationship with postpartum hemorrhage and high risk of obstetric hysterectomy increases maternal morbidity and mortality proportionally. CLINICAL CASE: A 30-year-old patient without prenatal care and a clinically terminal pregnancy, who attended the emergency department due to obstetric pain and transvaginal bleeding. Physical examination revealed first labor, 9cm of dilation, height of presentation -4 according to plans From Lee, placental edge was palpated at the cervical level, accompanied by moderate transvaginal bleeding, bright red, mater code is activated and prepared for cesarean section, for bleeding placenta, during the surgical event, corroborates diagnosis and tumor that starts on the face posterior, lower uterine segment and ends at the cervical level, with multiple vessels of bleeding neoformation and secondary uterine atony, causing significant hemorrhage, obstetric hysterectomy was performed, a new born with sex female woman with a weight of 3145 g, size 51cm, Capurro 41 weeks of gestation was obtained, Apgar 7/9, the total blood loss was 2000 cc, 4 days of inpatient hospital stay, the binomial without complications was graduated. CONCLUSION: The association of uterine myomatosis and pregnancy increase the risk of maternal complications, adequate ultrasound monitoring and prenatal control, determine the repercussion during the evolution of pregnancy and childbirth, conservative management should always be considered.

SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA