Implicancias de la inteligencia artificial en los métodos de imagen endovascular / Implications of Artificial Intelligence in Intravascular Imaging Methods

RESUMEN La angioplastia transluminal coronaria (ATC) es una de las principales estrategias de revascularización en pacientes con enfermedad coronaria aterosclerótica (ECA). Numerosos estudios respaldan la optimización de la ATC mediante métodos de imagen endovascular; sin embargo, estos métodos son subutilizados en la práctica clínica contemporánea y enfrentan desafíos en la interpretación de los datos obtenidos, por lo que la integración de la inteligencia artificial (IA) se vislumbra como una solución atractiva para promover y simplificar su uso. La IA se define como un programa computarizado que imita la capacidad del cerebro humano para recopilar y procesar datos. El aprendizaje de máquinas es una subdisciplina de la IA que implica la creación de algoritmos capaces de analizar grandes conjuntos de datos sin suposiciones previas, mientras que el aprendizaje profundo se centra en la construcción y entrenamiento de redes neuronales artificiales profundas y complejas. Así, se ha demostrado que la incorporación de sistemas de IA a los métodos de imagen endovascular incrementa la precisión de la ATC, disminuye el tiempo del procedimiento y la variabilidad interobservador en la interpretación de los datos obtenidos, promueve así una mayor adopción y facilita su utilización. El propósito de la presente revisión es destacar cómo los sistemas actuales basados en IA pueden desempeñar un papel fundamental en la interpretación de los datos generados por los métodos de imagen endovascular, lo que conduce a una mejora en la optimización de la ATC en pacientes con ECA.

ABSTRACT Percutaneous coronary intervention (PCI) is one of the primary revascularization strategies in patients with coronary artery disease (CAD). Several studies support the use of intravascular imaging methods to optimize PCI. However, these methods are underutilized in contemporary clinical practice and face challenges in data interpretation. Therefore, the incorporation of artificial intelligence (AI) is seen as an attractive solution to promote and simplify their use. AI can be defined as a computer program that mimics the human brain in its ability to collect and process data. Machine learning is a sub-discipline of AI that involves the creation of algorithms capable of analyzing large datasets without making prior assumptions, while deep learning focuses on the construction and training of deep and complex artificial neural networks. The incorporation of AI systems to intravascular imaging methods improves the accuracy of PCI, reduces procedure duration, and minimizes interobserver variability in data interpretation. This promotes their wider adoption and facilitates their use. The aim of this review is to highlight how current AI-based systems can play a key role in the interpretation of data generated by intravascular imaging methods and optimize PCI in patients with CAD.

Acute Coronary Syndrome with Non-Obstructive Plaque on Angiography and Features of Vulnerable Plaque on Intracoronary Optical Coherence Tomography.

Optical coherence tomography (OCT) has a high spatial resolution and is useful in identifying coronary lesions with high-risk features (vulnerable plaques). These plaques are strongly associated with acute coronary syndrome (ACS). In this report, we present the case of a 43-year-old male patient presenting with typical chest pain that began three hours prior to admission. The patient exhibited an elevation of the ST segments of the anterior and lateral walls. Invasive stratification revealed a 40% lesion in the middle segment of the left anterior descending (LAD) artery. The patient was given optimized clinical treatment as he had a nonobstructive lesion in the LAD at the time of angiography. During the treatment, the patient continued to complain of angina on exertion. A follow-up coronary angiography, along with OCT analysis of the middle-to-moderate lesion in the LAD, revealed a plaque predominantly rich in lipids with signs of vulnerability. A percutaneous coronary intervention was performed. The patient's recovery was uneventful, and he was discharged the day after the procedure. This case illustrates the evolution of intravascular imaging, particularly OCT, in the detection of vulnerable plaques.

Absorb bioresorbable vascular scaffold outcomes following implantation with routine intravascular imaging guidance.

OBJECTIVES: We sought to describe the outcomes of BVS use from a single-center experience in which scaffold implantation was guided by intravascular imaging (ultrasound and/or optical coherence tomography) to identify and treat mechanical factors potentially related to BVS failure. BACKGROUND: The Absorb bioresorbable vascular scaffold (BVS) has been associated with an unexpectedly high incidence of thrombosis. METHODS: Between 11/2014 and 10/2016, 100 patients were treated with BVS. Intravascular imaging assessment before and after BVS implantation was performed in all cases. RESULTS: Mean age was 58.1 years; 88% were male, 31% had diabetes, and 28% presented with acute coronary syndromes. A total of 171 lesions in 141 vessels were treated with 190 BVS (mean 1.9 scaffolds/patient). Further intervention following intravascular imaging to optimize BVS implantation was required in 31% of patients. Procedure success was 100%. All patients completed a 1-year follow-up. The 1-year rate of target lesion failure was 4%, and there were no cases (0%) of scaffold thrombosis, myocardial infarction, or death. CONCLUSIONS: In this real-world experience, the use of intravascular imaging to guide BVS implantation was associated with a high 1-year event-free survival rate, with no scaffold thrombosis.

Percutaneous endovascular delivery of calcium chloride to the intact porcine carotid artery: A novel animal model of arterial calcification.

OBJECTIVE: The present study evaluated the effect of endovascular administration of calcium chloride to the carotid artery of swines, to create a model of arterial calcification. METHODS: Fifteen Large White pigs were used for the study. Via endovascular treatment, carotid arteries were exposed during 9 min to either calcium chloride (experimental artery) or saline (control artery) with the use of the TAPAS catheter. Intravascular ultrasound (IVUS) imaging was obtained at baseline, postprocedure and at 30 days. Optical coherence tomography (OCT) imaging was obtained in vitro after carotids were harvested. Longitudinally cut parallel arterial segments were placed in a system of delicate clamps and underwent uniaxial strain test. All arteries underwent histopathological examination. RESULTS: Calcium chloride treated segments showed extensive circumferential parietal calcification evident on both IVUS and OCT. Reduction in minimal lumen area on IVUS was evident in experimental arteries both at 24 hr and 30 days postprocedure. Histopathologic assessment (Von Kossa stain) confirmed medial calcification with mild intimal thickening. Biomechanical testing showed treated segments to have smaller breaking strength and less elastic deformation than controls. CONCLUSION: We developed a nonexpensive, reproducible model of early carotid medial calcification in pigs. Our model has the potential to help the development of research to unravel mechanisms underlying arterial calcification, the use of current or new devices to treat calcified lesions as well as to serve as an option for training interventionalists on the use of such devices.

Tomografía de coherencia óptica: Bases y aplicaciones de una nueva técnica de imagen intravascular

La angiografía es la técnica de referencia para el diagnóstico de la enfermedad arte rial coronaria. Sin embargo, la mayoría de los síndromes coronarios agudos involucran lesiones angiográficamente no significativas. Es también la técnica de elección para guiar la implantación de prótesis endovasculares y su seguimiento. La tomografía de coherencia óptica es una técnica de imagen interferométrica que penetra en los tejidos alrededor de 2-3 mm y ofrece una alta resolución axial. Es capaz de distinguir diferentes tipos de tejido, como fibroso, lipídico, necrótico o calcificado, reconoce características de las placas de ateroma que se han asociado con progresión rápida de la lesión y eventos clínicos adversos, como la delgada capa de fibroateroma, el espesor de la capa fibrosa, la infiltración de macrófagos y la formación de trombos. En la actualidad, existe un creciente interés en el valor de la tomografía de coherencia óptica en el área de intervención coronaria, donde la técnica ofrece ventajas significativas sobre las técnicas intravasculares de diagnóstico convencionales, como la ecografía intravascular. Su alta resolución permite reconocer las complicaciones periprocedimiento, como microdisección, malaposición e hiperplasia neointimal, haciendo de esta herramienta una de las técnicas más prometedoras en el diagnóstico intravascular.

Coronary angiography is the reference technique for the diagnosis of coronary disease. However, the majority of acute coronary syndromes involve angiographically non- significant lesions. It is also the technique of choice for guiding the implantation of endovascular prostheses and their later monitoring. Optical coherence tomography is an interferometric imaging technique that penetrates tissue approximately 2-3 mm and provides axial and lateral resolution. It is able to distinguish different tissue types, such as fibrous, lipid-rich, necrotic, or calcified tissue. Optical coherence tomography is able to recognize a variety of features of athe- rosclerotic plaques that have been associated with rapid lesion progression and clinical events, such as thin cap fibroatheroma, fibrous cap thickness, dense macrophage infiltration, and thrombus formation. Currently, there is growing interest in the value of optical coherence tomography in the area of coronary intervention, where the technique offers significant advantages over more widespread intravascular diagnostic techniques such as intravascular ultrasound. Its higher resolution permits to recognize periprocedural complications, such as microdissection of the coronary artery, stent malapposition, and neointimal hiperplasia, making this tool one of the most promising techniques in the intravascular diagnosis.

Uso da tomografia de coerência ótica intracoronariana para caracterização precisa da aterosclerose / Uso de la tomografía de coherencia óptica intracoronaria para caracterización precisa de la aterosclerosis / Use of optical coherence tomography for accurate characterization of atherosclerosis

A Tomografia de Coerência Ótica (TCO) é uma nova tecnologia de imagem baseada em interferometria de baixa coerência que utiliza a dispersão de luz quase-infravermelha como uma fonte de sinal para fornecer imagens transversais vasculares com definição muito superior à de qualquer outra modalidade disponível. Com uma resolução espacial de até 10μm, a TCO fornece uma resolução 20 vezes maior do que o ultrassom intravascular (USIV), a modalidade atualmente mais utilizada para obter imagens intra-coronárias. A TCO tem uma capacidade de fornecer um entendimento das várias fases da doença aterosclerótica e a resposta vascular ao tratamento. Estudos tem mostrado a capacidade da TCO em detectar estruturas arteriais e ajudar na determinação de diferentes constituintes histológicos. Sua capacidade de distinguir diferentes graus de alterações ateroscleróticas e os vários tipos de placas, quando comparada à histologia, tem sido recentemente demonstrada com correlações inter e intra-observador aceitáveis para esses achados. A TCO fornece uma resolução endovascular excepcional em tempo real in vivo, que tem sido explorada para avaliar as estruturas vasculares e a resposta ao uso do equipamento. Embora a profundidade permaneça uma limitação para a caracterização de placa além de 2 mm através da TCO, uma resolução próxima à histológica pode ser obtida dentro do primeiro milímetro da parede do vaso, permitindo uma avaliação extraordinária das características e espessura da capa fibrosa. Além disso, a avaliação da cobertura de neoíntima, padrões de tecido para-haste e aposição de stent podem agora ser escrutinizados para hastes individuais na escala de mícrons, a assim chamada análise em nível de haste. A TCO levou a imagem intravascular ao nível de mícron na análise vascular in vivo e espera-se que breve se torne uma ferramenta valiosa e indispensável para cardiologistas em aplicações clínicas e de pesquisa.

Optical coherence tomography (OCT) is a novel imaging technology based on low-coherence interferometry that uses scattering of near-infrared light as a signal source to provide vascular cross-sectional imaging with definition far superior to any other available modality. With spatial resolution of up to 10μm, OCT provides 20-fold higher resolution than intravascular ultrasound (IVUS), currently the most used modality for intra-coronary imaging. OCT has the capacity to provide invaluable insight into the various phases of atherosclerotic disease and vascular response to therapeutics. Studies have shown the ability of OCT to detect arterial structures and assist in the determination of different histological constituents. Its capacity to distinguish different grades of atherosclerotic changes and the various types of plaques, as compared to histology, has recently been demonstrated with acceptable intra-observer and inter-observer correlations for these findings. OCT provides unrivaled real-time in vivo endovascular resolution, which has been exploited to assess the vascular structures and response to device deployment. While depth remains a limitation for OCT plaque characterization beyond 2-mm, near-histological resolution can be achieved within the first millimeter of the vessel wall allowing unique assessment of fibrous cap characteristics and thickness. In addition, assessment of neointimal coverage, para-strut tissue patterns and stent apposition can now be scrutinized for individual struts on the micron scale, the so-called strut-level analysis. OCT has propelled intravascular imaging into micron-level in vivo vascular analysis and is expected to soon become a valuable and indispensable tool for the cardiologists on both clinical and research applications.

La Tomografía de Coherencia Óptica (TCO) es una nueva tecnología de imagen basada en interferometría de baja coherencia que utiliza la dispersión de luz casi infrarroja como una fuente de señal para suministrar imágenes transversales vasculares con definición muy superior a la de cualquier otra modalidad disponible. Con una resolución espacial de hasta 10 μm, la TCO ofrece una resolución 20 veces mayor que la ecografía intravascular (EIV), la modalidad actualmente más utilizada para obtener imágenes intracoronarias. La TCO tiene capacidad de suministrar comprensión de las varias fases de la enfermedad aterosclerótica y la respuesta vascular al tratamiento. Estudios han mostrado la capacidad de la TCO para detectar estructuras arteriales y ayudar en la determinación de diferentes constituyentes histológicos. Su capacidad para distinguir diferentes grados de alteraciones ateroscleróticas y los varios tipos de placas, cuando se la compara con la histología, ha sido demostrada recientemente con correlaciones inter e intra observador aceptables para esos hallazgos. La TCO ofrece una resolución endovascular excepcional en tiempo real in vivo, que se ha explorado para evaluar las estructuras vasculares y la respuesta al auso del equipamiento. Aunque la profundida continúe siendo una limitación para la caracterización de placa más allá de 2 mm a través de la TCO, una resolución próxima a la histológica puede obtenerse dentro del primer milímetro de la pared del vaso, permitiendo una evaluación extraordnaria de las característica y espesor de la capa fibrosa. Además de ello, la evaluación de la cobertura de neoíntima, patrones de tejido para vástago y aposición de stent pueden ahora ser escrutados para vástagos individuales en la escala de micrones, el llamado análisis a nivel de vástago.