Challenges of Radiology education in the era of artificial intelligence.

Artificial intelligence is a branch of computer science that is generating great expectations in medicine and particularly in radiology. Artificial intelligence will change not only the way we practice our profession, but also the way we teach it and learn it. Although the advent of artificial intelligence has led some to question whether it is necessary to continue training radiologists, there seems to be a consensus in the recent scientific literature that we should continue to train radiologists and that we should teach future radiologists about artificial intelligence and how to exploit it. The acquisition of competency in artificial intelligence should start in medical school, be consolidated in residency programs, and be maintained and updated during continuing medical education. This article aims to describe some of the challenges that artificial intelligencve can pose in the different stages of training in radiology, from medical school through continuing medical education.

Challenges of Radiology education in the era of artificial intelligence. / Retos de la formación en radiología en la era de la inteligencia artificial.

Artificial intelligence is a branch of computer science that is generating great expectations in medicine and particularly in radiology. Artificial intelligence will change not only the way we practice our profession, but also the way we teach it and learn it. Although the advent of artificial intelligence has led some to question whether it is necessary to continue training radiologists, there seems to be a consensus in the recent scientific literature that we should continue to train radiologists and that we should teach future radiologists about artificial intelligence and how to exploit it. The acquisition of competency in artificial intelligence should start in medical school, be consolidated in residency programs, and be maintained and updated during continuing medical education. This article aims to describe some of the challenges that artificial intelligencve can pose in the different stages of training in radiology, from medical school through continuing medical education.

[Response prediction for chronic migraine preventive treatment by gray matter morphometry in magnetic resonance imaging: a pilot study]. / Predicción de la respuesta al tratamiento preventivo en migraña crónica mediante la medición de la sustancia gris en resonancia magnética: estudio piloto.

INTRODUCTION: Topiramate is the only oral preventative with level of evidence I for the treatment of chronic migraine. AIM: To evaluate gray matter parameters, obtained with magnetic resonance imaging (MRI), as biomarkers of the response to topiramate in chronic migraine patients. PATIENTS AND METHODS: The sample was composed by 57 chronic migraine patients, screened for first time in a Headache Unit due to chronic migraine. MRI acquisitions were performed at a 3 T unit. Afterwards, topiramate preventive treatment began. Response and tolerability were evaluated after three months, defining response as at least 50% reduction in headache days per month. We included patients that tolerated topiramate. T1- and diffusion-weighted MRI were processed to obtain gray matter (68 cortical and 16 subcortical regions) descriptive parameters. A logistic regression model was employed for the predictive assessment. RESULTS: Forty-two patients tolerated the treatment and were analyzed, responding 23 of them (54.7%). The final prediction model was built with gray matter parameters with significant results. In this model, higher left cuneus curvature and right insula area values were associated with a higher probability of response, while higher right inferior parietal cortex volume and left superior temporal gyrus area values were associated with a lower probability. The accuracy of the predictive model was 95%. CONCLUSION: The gray matter parameters may be useful biomarkers of preventive treatment response with topiramate in chronic migraine.

TITLE: Predicción de la respuesta al tratamiento preventivo en migraña crónica mediante la medición de la sustancia gris en resonancia magnética: estudio piloto.Introducción. El topiramato es el único tratamiento preventivo oral con nivel de evidencia I para la migraña crónica. Objetivo. Evaluar los parámetros de la sustancia gris, obtenidos mediante resonancia magnética, como marcadores de respuesta al tratamiento con topiramato en pacientes con migraña crónica. Pacientes y métodos. La muestra se compuso de 57 pacientes con migraña crónica atendidos por primera vez en una unidad de cefaleas como consecuencia de migraña crónica, a los que se realizó una resonancia magnética de 3 T. Posteriormente, se inició el tratamiento preventivo con topiramato. Se evaluaron la respuesta y la tolerancia a los tres meses y se definió respuesta como disminución de al menos un 50% en el número de días de cefalea al mes. Mediante procesamiento de imágenes de resonancia magnética ponderadas en T1 y difusión, se obtuvieron los parámetros de la sustancia gris (68 estructuras corticales y 16 subcorticales). Se obtuvo un modelo de regresión logística para la valoración predictiva. Resultados. Se analizó a 42 pacientes que toleraron el tratamiento, con respuesta terapéutica en 23 de ellos (54,7%). El modelo final de predicción se construyó con parámetros de la sustancia gris con resultados significativos. En dicho modelo, a mayor curvatura del cúneo izquierdo y área de la ínsula derecha, mayor probabilidad de respuesta, y menor probabilidad a mayor volumen de la corteza inferior parietal derecha y área del giro temporal superior izquierdo. La precisión del modelo predictivo fue del 95%. Conclusión. Los parámetros de la sustancia gris pueden ser marcadores útiles de respuesta al tratamiento preventivo con topiramato en la migraña crónica.