System and method for inferring thickness of class of objects of interest in two-dimensional medical image using deep neural network

Methods and systems are provided for inferring the thickness and volume of one or more classes of objects of interest in a two-dimensional (2D) medical image using a deep neural network. In an exemplary embodiment, a thickness of a class of objects of interest may be inferred by acquiring a 2D medical image; extracting features from the 2D medical image; mapping the feature to a segmentation mask of the object class of interest using a first convolutional neural network (CNN); mapping the feature to a thickness mask of the object class of interest using a second CNN, wherein the thickness mask indicates a thickness of the object class of interest at each of a plurality of pixels of the 2D medical image; and determining a volume of the class of objects of interest based on the thickness mask and the segmentation mask. 本发明提供了用于使用深度神经网络来推断二维(2D)医学图像中的一个或多个感兴趣的对象类的厚度和体积的方法和系统。在示例性实施方案中，可通过以下方式来推断感兴趣的对象类的厚度：获取2D医学图像；从该2D医学图像中提取特征；使用第一卷积神经网络(CNN)来将该特征映射到感兴趣的对象类的分割掩模；使用第二CNN来将该特征映射到该感兴趣的对象类的厚度掩模，其中该厚度掩模指示该感兴趣的对象类在该2