Novel deep learning method for coronary artery tortuosity detection through coronary angiography.

Coronary artery tortuosity is usually an undetected condition in patients undergoing coronary angiography. This condition requires a longer examination by the specialist to be detected. Yet, detailed knowledge of the morphology of coronary arteries is essential for planning any interventional treatment, such as stenting. We aimed to analyze coronary artery tortuosity in coronary angiography with artificial intelligence techniques to develop an algorithm capable of automatically detecting this condition in patients. This work uses deep learning techniques, in particular, convolutional neural networks, to classify patients into tortuous or non-tortuous based on their coronary angiography. The developed model was trained both on left (Spider) and right (45°/0°) coronary angiographies following a fivefold cross-validation procedure. A total of 658 coronary angiographies were included. Experimental results demonstrated satisfactory performance of our image-based tortuosity detection system, with a test accuracy of (87 ± 6)%. The deep learning model had a mean area under the curve of 0.96 ± 0.03 over the test sets. The sensitivity, specificity, positive predictive values, and negative predictive values of the model for detecting coronary artery tortuosity were (87 ± 10)%, (88 ± 10)%, (89 ± 8)%, and (88 ± 9)%, respectively. Deep learning convolutional neural networks were found to have comparable sensitivity and specificity with independent experts' radiological visual examination for detecting coronary artery tortuosity for a conservative threshold of 0.5. These findings have promising applications in the field of cardiology and medical imaging.

Artificial intelligence to estimate wine volume from single-view images.

In this paper, we present a method to determine the volume of wine in different types of glass liquid containers from a single-view image. The proposed model predicts red wine volume from a photograph of the glass containing the wine. Experimental results demonstrated satisfactory performance of our image-based wine measurement system, with a Mean Absolute Error lower than 10 mL . To train and evaluate our system, we introduced the WineGut_BrainUp dataset, a new dataset of glasses of wine that contains 24305 laboratory images, including a wide range of containers, volumes of wine, backgrounds, object distances, angles and lightning, with or without calibration object. The proposed methodology is a suitable analytical tool for automate measurement of red wine volume. Indeed, it has potential real life applications in diet monitoring and wine consumption studies.

Estudio de intervención no aleatorizado sobre evolución postquirúrgica en pacientes tratadas con terapia neural tras mamoplastia de aumento vía axilar / Non-randomized intervention study on postoperative evolution in patients who underwent neural therapy after transaxillary breast augmentation

Antecedentes y objetivo: Durante nuestra práctica clínica nos hemos encontrado algo limitados por el pensamiento y tratamiento de la medicina convencional. Por circunstancias personales hemos entrado en contacto con terapias complementarias ampliamente aplicadas en muchos países a la población general en contextos de medicina general, fisioterapia, medicina interna, y hemos pensado introducir estas técnicas en nuestra práctica diaria y estudiar cómo impactan en nuestros pacientes. Se conoce por terapia neural a la técnica que emplea un anestésico local en muy bajas concentraciones con la finalidad de restaurar el potencial transmembrana de la neurona que se ha perdido por inflamación, cicatriz, infección, etc. La ausencia patológica de potencial transmembrana de la neurona ocasiona que, al no poderse transmitir el impulso nervioso fisiológico, la inflamación o patología a tratar perduren en el tiempo. Por así decirlo, el anestésico local logra un reinicio del normal funcionamiento del sistema nervioso, que afecta a todo el organismo. El presente trabajo estudia la evolución postquirúrgica de las pacientes tras mamoplastia de aumento vía axilar en función de si se les realizó o no terapia neural como tratamiento coadyuvante. Material y Método: Realizamos un estudio de intervención no aleatorizado midiendo la presencia o no de dolor y la presencia o no y grado de encapsulamiento periprotésico según la clasificación de Baker durante los 12 meses siguientes a una mamoplastia de aumento vía axilar, y el consumo de fármacos (Nervobión(R), Accolate(R)) para dichas dolencias según si se les realizó o no terapia neural después de dicha intervención quirúrgica. La muestra estuvo compuesta por 178 mujeres con un rango de edad entre 17 y 52 años (media de 28.34 años) El grupo de tratamiento recibió procaína al 0.33% en la cicatriz cutánea axilar y trayecto por el que pasó la prótesis durante la cirugía. Este tratamiento se inició desde la primera cura y en las visitas sucesivas si la paciente lo requirió, con una media de 4 sesiones de terapia neural por paciente. Utilizamos el paquete estadístico Statistica versión 8.0 para el análisis de tablas de contingencia 2 por 2 mediante X2. Resultados: De las 178 pacientes incluidas en el estudio (con 8 pérdidas), llevamos a cabo tratamiento convencional en 101 y terapia neural coadyuvante en 69, comprobando una mejoría significativa de la evolución postquirúrgica en las pacientes tratadas con terapia neural, mientas que las no tratadas requirieron más medicación postquirúrgica. Conclusiones: A pesar de que la limitación principal de nuestro estudio es el tipo de diseño: estudio de intervención sin aleatorización, en nuestra experiencia, el uso de la terapia neural puede recomendarse como tratamiento coadyuvante para disminuir la contractura capsular y el dolor postquirúrgico en pacientes sometidas a mamoplastia de aumento vía axilar

Background and Objective: During our clinical practice we have found some limitations by the thoughts and treatments of conventional medicine. Due to personal circumstances we got in contact with complementary therapies widely applied in many countries to the general population in contexts of general medicine, physiotherapy, internal medicine, so we thought to introduce these techniques to our daily practice and study how it affected our patients. Neural therapy is a technique that uses local anesthetic in very low concentrations in order to restore the membrane potential of the neuron, lost by inflammation, scar, infection, etc. This pathological membrane potential of the neuron causes an absence of transmission of physiological nervous impulse, so that inflammation or pathology to be treated lasts over time. Somehow, the local anesthetic achieves a reset in the nervous system to restart physiological function of the entire organism. The present study observes the postoperative evolution of the patients after an axillary augmentation mammoplasty, depending on if they were treated with neural therapy as adjuvant treatment or not. Methods: We performed a non-randomized intervention study in which the presence or absence of pain and the presence or not and degree of periprosthetic encapsulation following Baker's scale, was measured after transaxillary breast augmentation, and the use of drugs (Nervobión(R) and Accolate(R)) depending on if they received or not neural therapy as coadjuvant. The sample consisted of 178 women with an age range between 17 and 52 years (average of 28.34 years). The treatment group received 0.33% procaine in the axillary skin scar and the path through which the prosthesis passed during surgery. This treatment was started from the first cure and in the successive visits if the patient required it, with an average of 4 sessions of neural therapy per patient. We used the statistical package Statistica version 8.0 for the analysis of contingency tables 2 by 2 through X2. Results: Of the 178 patients included in the study (with 8 losses), we carried out conventional treatment in 101 and coadjuvant neural therapy in 69, verifying a significant improvement in postoperative evolution in patients treated with neural therapy, while the untreated ones required more postsurgical medication. Conclusions: Although the main limitation of our study is the type of design: intervention study without randomization, in our experience, the use of neural therapy can be recommended as a coadjuvant treatment to reduce capsular contracture and postoperative pain in patients undergoing axillary augmentation mammoplasty