Biomarker computation using deep-learning often relies on a two-step process, where the deep learning algorithm segments the region of interest and then the biomarker is measured. We propose an alternative paradigm, where the biomarker is estimated directly using a regression network. We showcase this image-to- biomarker paradigm using two biomarkers: the estimation of bone mineral…
Introduction: The Agatston score is a well-established metric of cardiovascular disease related to clinical outcomes. It is computed from CT scans by a) measuring the volume and intensity of the atherosclerotic plaques and b) aggregating such information in an index. Objective: To generate a convolutional neural network that inputs a non-contrast chest CT scan and…
Can we generate a single multi-structure segmentation network from partially annotated datasets? In this conference paper Sierra’s researchers in conjunction with Brigham and Women’s Hospital answer such question, showing that a) it is equivalent to use a single unet and b) that adding convolutions on the skip connections further improve segmentation results. The full article…
Given a biomarker regression network, what is the effect of training with different cost functions? In this conference publications, Sierra’s researcher investigate the influence of training with L1, L2, L1 in logarithmic scale or L2 in logarithmic scale for the problem of Agatston score regression from CT volumetric images center at the heart. There is…
Can artificial intelligence regression networks locate the regions of interest from whom they are obtaining their value? In this conference article, Sierra’s researchers explore such question. From Computer Tomography axial slices obtained at the level of the transversal aorta, and the areas of their pectoralis muscle and subcutaneous fat, we have been able to perform…