RESUMEN
AIM: The purpose of this study was to automatically extract myocardial regions from transaxial single-photon emission computed tomography (SPECT) images using deep learning to reduce the effects of extracardiac activity, which has been problematic in cardiac nuclear imaging. METHOD: Myocardial region extraction was performed using two deep neural network architectures, U-Net and U-Net ++, and 694 myocardial SPECT images manually labeled with myocardial regions were used as the training data. In addition, a multi-slice input method was introduced during the learning session while taking the relationships to adjacent slices into account. Accuracy was assessed using Dice coefficients at both the slice and pixel levels, and the most effective number of input slices was determined. RESULTS: The Dice coefficient was 0.918 at the pixel level, and there were no false positives at the slice level using U-Net++ with 9 input slices. CONCLUSION: The proposed system based on U-Net++ with multi-slice input provided highly accurate myocardial region extraction and reduced the effects of extracardiac activity in myocardial SPECT images.
Asunto(s)
Aprendizaje Profundo , Redes Neurales de la Computación , Perfusión , Tomografía Computarizada de Emisión de Fotón ÚnicoRESUMEN
OBJECTIVE: Myocardial perfusion imaging (MPI) with single-photon emission computed tomography (SPECT) is confounded by the extracardiac artefacts cause by hepatobiliary clearance of the radiotracers. Various techniques have been evaluated to lessen those artefacts. In this study, we endeavoured to determine the effect of carbonated water in reducing such infracardiac artefact so to improve MPI image quality, sensitivity and specificity. METHODS: A total of 1000 patients were prospectively enrolled and randomised into two equal groups as A and B. Group A were given 250 ml of carbonated beverages and Group B were given 250 ml plain water immediately after radiotracer injection. Images were evaluated qualitatively and quantitatively for the interfering extracardiac artefacts. RESULTS: The qualitative analysis favoured carbonated water in reducing the interfering intestinal activity during rest as well as stress (p = 0.005 and p < 0.001, respectively). Quantitative calculation showed significant improvement of myocardium to extracardiac ratio with carbonated water ingestion in rest (p = 0.031) and vasodilator stress studies (p = 0.004). However, for exercise stress studies quantitative evaluation were not statistically different between the two protocols (p = 0.855). CONCLUSION: Carbonated water ingestion is an easy and effective way to enhance SPECT image quality by mitigating extracardiac artefacts.