PSGR: Pixel-wise Sparse Graph Reasoning for COVID-19 Pneumonia Segmentation in CT Images (preprint)

Automated and accurate segmentation of the infected regions in computed tomography (CT) images is critical for the prediction of the pathological stage and treatment response of COVID-19. Several deep convolutional neural networks (DCNNs) have been designed for this task, whose performance, however, tends to be suppressed by their limited local receptive fields and insufficient global reasoning ability. In this paper, we propose a pixel-wise sparse graph reasoning (PSGR) module and insert it into a segmentation network to enhance the modeling of long-range dependencies for COVID-19 infected region segmentation in CT images. In the PSGR module, a graph is first constructed by projecting each pixel on a node based on the features produced by the segmentation backbone, and then converted into a sparsely-connected graph by keeping only K strongest connections to each uncertain pixel. The long-range information reasoning is performed on the sparsely-connected graph to generate enhanced features. The advantages of this module are two-fold: (1) the pixel-wise mapping strategy not only avoids imprecise pixel-to-node projections but also preserves the inherent information of each pixel for global reasoning; and (2) the sparsely-connected graph construction results in effective information retrieval and reduction of the noise propagation. The proposed solution has been evaluated against four widely-used segmentation models on three public datasets. The results show that the segmentation model equipped with our PSGR module can effectively segment COVID-19 infected regions in CT images, outperforming all other competing models.

Family automated voice reorientation (FAVoR) intervention for mechanically ventilated patients in the intensive care unit: Study protocol for a randomized controlled trial.

Delirium in the intensive care unit (ICU) affects up to 80% of critically ill, mechanically ventilated (MV) adults. Delirium is associated with substantial negative outcomes, including increased hospital complications and long-term effects on cognition and health status in ICU survivors. The purpose of this randomized controlled trial is to test the effectiveness of a Family Automated Voice Reorientation (FAVoR) intervention on delirium among critically ill MV patients. The FAVoR intervention uses scripted audio messages, which are recorded by the patient's family and played at hourly intervals during daytime hours. This ongoing orientation to the ICU environment through recorded messages in a voice familiar to the patient may enable the patient to more accurately interpret the environment and thus reduce risk of delirium. The study's primary aim is to test the effect of the FAVoR intervention on delirium in critically ill MV adults in the ICU. The secondary aims are to explore: (1) if the effect of FAVoR on delirium is mediated by sleep, (2) if selected biobehavioral factors moderate the effects of FAVoR on delirium, and (3) the effects of FAVoR on short-term and long-term outcomes, including cognition and health status. Subjects (n = 178) are randomly assigned to the intervention or control group within 48 h of initial ICU admission and intubation. The intervention group receives FAVoR over a 5-day period, while the control group receives usual care. Delirium-free days, sleep and activity, cognition, patient-reported health status and sleep quality, and data regarding iatrogenic/environmental and biobehavioral factors are collected.