RESUMO
Pulmonary fibrosis is a devastating chronic lung disease that causes irreparable lung tissue scarring and damage, resulting in progressive loss in lung capacity and has no known cure. A critical step in the treatment and management of pulmonary fibrosis is the assessment of lung function decline, with computed tomography (CT) imaging being a particularly effective method for determining the extent of lung damage caused by pulmonary fibrosis. Motivated by this, we introduce Fibrosis-Net, a deep convolutional neural network design tailored for the prediction of pulmonary fibrosis progression from chest CT images. More specifically, machine-driven design exploration was leveraged to determine a strong architectural design for CT lung analysis, upon which we build a customized network design tailored for predicting forced vital capacity (FVC) based on a patient's CT scan, initial spirometry measurement, and clinical metadata. Finally, we leverage an explainability-driven performance validation strategy to study the decision-making behavior of Fibrosis-Net as to verify that predictions are based on relevant visual indicators in CT images. Experiments using a patient cohort from the OSIC Pulmonary Fibrosis Progression Challenge showed that the proposed Fibrosis-Net is able to achieve a significantly higher modified Laplace Log Likelihood score than the winning solutions on the challenge. Furthermore, explainability-driven performance validation demonstrated that the proposed Fibrosis-Net exhibits correct decision-making behavior by leveraging clinically-relevant visual indicators in CT images when making predictions on pulmonary fibrosis progress. Fibrosis-Net is able to achieve a significantly higher modified Laplace Log Likelihood score than the winning solutions on the OSIC Pulmonary Fibrosis Progression Challenge, and has been shown to exhibit correct decision-making behavior when making predictions. Fibrosis-Net is available to the general public in an open-source and open access manner as part of the OpenMedAI initiative. While Fibrosis-Net is not yet a production-ready clinical assessment solution, we hope that its release will encourage researchers, clinicians, and citizen data scientists alike to leverage and build upon it.
RESUMO
BACKGROUND: Epinephrine injection represents the standard of care for anaphylaxis treatment. It is most effective if delivered intramuscularly, whereas inadvertent intraosseous injection may be harmful. The needle length in current pediatric epinephrine autoinjectors (EAIs) is 12.7 mm; however, the ideal needle length for infants and toddlers weighing less than 15 kg is unknown. OBJECTIVE: To determine the skin-to-bone distance (STBD) and skin-to-muscle distance (STMD) at baseline and after simulated EAI application in infants and toddlers (weighing 7.5-15 kg). METHODS: Study participants recruited from 2 North American allergy clinics underwent baseline and compression (10-lb pressure) ultrasonography of the anterolateral thigh with a modified ultrasound transducer mimicking the footprint and maximum pressure application of an EAI device. Ultrasound images, with clinical data masked, were analyzed offline for STBD and STMD in short-axis approach. RESULTS: Of 53 infants (mean age, 18.9 months; 54.7% male; 81.1% white; mean weight, 11.0 kg), 51 had adequate images for short-axis STBD measurements. In these infants, the mean (SD) baseline STBD was 22.4 (3.8 mm), and the mean (SD) STMD was 7.9 (1.7) mm. With 10-lb compression, the mean (SD) STBD was 13.3 (2.1) mm, and the mean (SD) STMD was 6.3 (1.2) mm. An EAI with a needle length of 12.7 mm applying 10-lb pressure could strike the bone in 43.1% of infants and toddlers in this cohort. CONCLUSION: Our data suggest that the optimal EAI needle length for infants and toddlers weighing 7.5 to 15 kg should be shorter than the needle length in currently available pediatric EAIs to avoid accidental intraosseous injections.
