Deep Learning aplicado en imágenes fotoacústicas para la Identificación del cáncer de seno / Deep Learning Applied in Photoacoustic Images for the Identification of Breast Cancer

La Imagen Fotoacústica (PAI por sus siglas en inglés), es una modalidad de imagen híbrida que fusiona la iluminación óptica y la detección por ultrasonido. Debido a que los métodos de imágenes ópticas puras no pueden mantener una alta resolución, la capacidad de lograr imágenes de contraste óptico de alta resolución en tejidos biológicos hace que la fotoacústica (PA por sus siglas en inglés) sea una técnica prometedora para varias aplicaciones de imágenes clínicas. En la actualidad el Aprendizaje Profundo (Deep Learning) tiene el enfoque más reciente en métodos basados en la PAI, donde existe una gran cantidad de aplicaciones en análisis de imágenes, en especial en el área del campo biomédico, como lo es la adquisición, segmentación y reconstrucciones de imágenes de tomografía computarizada. Esta revisión describe las últimas investigaciones en PAI y un análisis sobre las técnicas y métodos basados en Deep Learning, aplicado en diferentes modalidades para el diagnóstico de cáncer de seno(AU)

Photoacoustic Imaging (PAI) is a hybrid imaging modality that combines optical illumination and ultrasound detection. Because pure optical imaging methods cannot maintain high resolution, the ability to achieve high resolution optical contrast images in biological tissues makes Photoacoustic (PA) a promising technique for various clinical imaging applications. At present, Deep Learning has the most recent approach of methods based on PAI where there are a large number of applications in image analysis especially in the area of ​​the biomedical field, such as acquisition, segmentation and reconstructions of computed tomography imaging. This review describes the latest research in PAI and an analysis of the techniques and methods based on Deep Learning applied in different modalities for the diagnosis of breast cancer(AU)

Removal of calcium hydroxide from Weine Type II systems using photon-induced photoacoustic streaming, passive ultrasonic, and needle irrigation: a microcomputed tomography study

ABSTRACT Objective This study compared the effectiveness of Er:YAG laser-activated irrigation (PIPS), passive ultrasonic irrigation (PUI) with EndoUltra and standard needle irrigation (SNI) in the removal of calcium hydroxide [Ca(OH)2] from the mesial roots of Weine Type II mandibular molars. Material and Methods Thirty mandibular molars were screened by µCT for the presence of mesial roots with complex intra-canal anatomy and a common apical foramen. The teeth were enlarged to a standardized 25/.06 preparation and filled with Ca(OH)2 paste. Specimens were divided into three groups (n=10) according to the technique used for Ca(OH)2 removal: PIPS, at 15 Hz and 20 mJ using a 9 mm long, 600 µm diameter tip; PUI using a 15/.02 tip; and SNI (30 Ga. side-vented needle). Equal volumes of 8.25% NaOCl and 17% EDTA were used in all groups. µCT was used to measure the initial amount of Ca(OH)2 present and to assess the residual volume of Ca(OH)2 following each irrigation protocol. Data were analyzed using Tukey HSD and Kruskal-Wallis tests (α=5%). Results The mean volume of Ca(OH)2 before removal was significantly higher in the coronal third than in the middle and apical third (p<0.001). Ca(OH)2 was similarly removed from the coronal and middle thirds with the three methods used (p>0.05). PIPS (median 0%; IQR: 0-0) showed significant higher Ca(OH)2 removal in the apical third than PUI (median 100%, IQR: 85-100) and SNI (median 47%; IQR: 16-72) (p<0.001). Conclusions PIPS laser-activation was more effective for the removal of Ca(OH)2 from mesial roots of mandibular molars with Weine Type II canal configurations than PUI with EndoUltra and SNI.