A Segmentation Method Based on PDNet for Chest X-rays with Targets in Different Positions and Directions

To assess the impact of the relative displacement between machines and subjects, the machine angle and the fine-tuning of the subject posture on the segmentation accuracy of chest X-rays, this paper proposes a Position and Direction Network (PDNet) for chest X-rays with different angles and positions that provides more comprehensive information for cardiac image diagnosis and guided surgery. The implementation of PDnet was as follows: First, the extended database image was sent to a traditional segmentation network for training to prove that the network does not have linear invariant characteristics. Then, we evaluated the performance of the mask in the middle layers of the network and added a weight mask that identifies the position and direction of the object in the middle layer, thus improving the accuracy of segmenting targets at different positions and angles. Finally, the active-shape model (ASM) was used to postprocess the network segmentation results, allowing the model to be effectively applied to 2014 × 2014 or higher definition chest X-rays. The experimental comparison of LinkNet, ResNet, U-Net, and DeepLap networks before and after the improvement shows that its segmentation accuracy (MIoU) are 5%, 6%, 20%, and 13% better. Their differences of losses are 11.24%, 21.96%, 18.53%, and 13.43% and F-scores also show the improved networks are more stable.

Diffusion capacity abnormalities for carbon monoxide in patients with COVID-19 at 3-month follow-up.

OBJECTIVE: To evaluate pulmonary function and clinical symptoms in coronavirus disease 2019 (COVID-19) survivors within 3 months after hospital discharge, and to identify risk factors associated with impaired lung function. METHODS AND MATERIAL: COVID-19 patients were prospectively followed-up with pulmonary function tests and clinical characteristics for 3 months following discharge from a hospital in Wuhan, China between January and February 2020. RESULTS: 647 patients were included. 87 (13%) patients presented with weakness, 63 (10%) with palpitations and 56 (9%) with dyspnoea. The prevalence of each of the three symptoms were markedly higher in severe patients than nonsevere patients (19% versus 10% for weakness, p=0.003; 14% versus 7% for palpitations, p=0.007; 12% versus 7% for dyspnoea, p=0.014). Results of multivariable regression showed increased odds of ongoing symptoms among severe patients (OR 1.7, 95% CI 1.1-2.6; p=0.026) or patients with longer hospital stays (OR 1.03, 95% CI 1.00-1.05; p=0.041). Pulmonary function test results were available for 81 patients, including 41 nonsevere and 40 severe patients. In this subgroup, 44 (54%) patients manifested abnormal diffusing capacity of the lung for carbon monoxide (D LCO) (68% severe versus 42% nonsevere patients, p=0.019). Chest computed tomography (CT) total severity score >10.5 (OR 10.4, 95% CI 2.5-44.1; p=0.001) on admission and acute respiratory distress syndrome (ARDS) (OR 4.6, 95% CI 1.4-15.5; p=0.014) were significantly associated with impaired D LCO. Pulmonary interstitial damage may be associated with abnormal D LCO. CONCLUSION: Pulmonary function, particularly D LCO, declined in COVID-19 survivors. This decrease was associated with total severity score of chest CT >10.5 and ARDS occurrence. Pulmonary interstitial damage might contribute to the imparied D LCO.

Awareness and Prophylaxis of Venous Thromboembolism in Patients with COVID-19: A National Cross-Sectional Survey in Epidemic Era.

AIM: Patients with acute infectious diseases are at an increased risk of venous thromboembolism (VTE). Clinicians should be aware of the VTE risk in patients with COVID-19, many of whom present with severe coagulation disorders. METHOD: We used an online platform to conduct a cross-sectional questionnaire survey among doctors in mainland China in March 2020. The questionnaire was designed to figure out the clinician's current awareness of VTE prevention and detection rates, as well as the current status of VTE prophylaxis in patients with COVID-19. RESULTS: We collected 1,636 replies, of which 1,579 were valid. Among these, 991 (63%) clinicians were involved directly in frontline treatment. Most of the clinicians (1,492, or 94%) thought it was necessary to assess the VTE risk in patients with COVID-19. However, only 234 (24%) clinicians performed appropriate assessment during the COVID-19 outbreak. For patients with mild/moderate COVID-19, 752 (76%) clinicians would prescribe exercise and water to prevent VTE. For patients with severe COVID-19, 448 (45%) clinicians would prescribe mechanical devices if the patient had a high bleeding risk, and 648 (65%) clinicians would choose LMWH as prophylaxis if the patient had a low bleeding risk. The VTE detection rate was not that high in both mild/moderate and severe patients. CONCLUSION: Although most clinicians recommended prescribing VTE prophylaxis to patients with COVID-19, the practice still needs to be improved. A real-world registry to investigate the true incidence of VTE, and the effect of prescribing appropriate prophylaxis for patients with COVID-19, is necessary in the future.