Perfusion estimation from dynamic non-contrast computed tomography using self-supervised learning and a physics-inspired U-net transformer architecture.

Purpose: Pulmonary perfusion imaging is a key lung health indicator with clinical utility as a diagnostic and treatment planning tool. However, current nuclear medicine modalities face challenges like low spatial resolution and long acquisition times which limit clinical utility to non-emergency settings and often placing extra financial burden on the patient. This study introduces a novel deep learning approach to predict perfusion imaging from non-contrast inhale and exhale computed tomography scans (IE-CT).

From risk factors to disease situations: A socio-spatial analysis of COVID-19 experiences in Lima, Peru.

The goal of this qualitative research study, part of an interdisciplinary project, was to understand the overlapping geographical distribution of COVID-19 and tuberculosis burden in Lima. Using an ethnographic approach, we applied the concept of disease situations to explore how inhabitants' social and spatial situatedness affected their capacity to respond to the pandemic. Our results show that for some populations in Lima, the risk to develop COVID-19 did not emerge suddenly; it could be traced back to situations of living under subsistence models, relying on unstable sources of income, facing food insecurity, depending on certain mechanisms of social protection, residing in precarious living environments and lacking access to quality health care.