Segmentation of lung lobes and lesions in chest CT for the classification of COVID-19 severity.

To precisely determine the severity of COVID-19-related pneumonia, computed tomography (CT) is an imaging modality beneficial for patient monitoring and therapy planning. Thus, we aimed to develop a deep learning-based image segmentation model to automatically assess lung lesions related to COVID-19 infection and calculate the total severity score (TSS). The entire dataset consisted of 124 COVID-19 patients acquired from Chulabhorn Hospital, divided into 28 cases without lung lesions and 96 cases with lung lesions categorized severity by radiologists regarding TSS. The model used a 3D-UNet along with DenseNet and ResNet models that had already been trained to separate the lobes of the lungs and figure out the percentage of lung involvement due to COVID-19 infection. It also used the Dice similarity coefficient (DSC) to measure TSS. Our final model, consisting of 3D-UNet integrated with DenseNet169, achieved segmentation of lung lobes and lesions with the Dice similarity coefficients of 91.52% and 76.89%, respectively. The calculated TSS values were similar to those evaluated by radiologists, with an R2 of 0.842. The correlation between the ground-truth TSS and model prediction was greater than that of the radiologist, which was 0.890 and 0.709, respectively.

Efficacy of combination therapy of fluvoxamine and favipiravir vs favipiravir monotherapy to prevent severe COVID-19 among mild to moderate COVID-19 patients: Open-label randomized controlled trial (EFFaCo study).

OBJECTIVES: Fluvoxamine (FVX) is an antidepressant proposed to its immunomodulatory effects in preventing deterioration in mild and moderate COVID-19. METHODS: An open-label, 1:1 randomized controlled trial was assigned either combination therapy 50 mg twice daily of FVX for 10 days and favipiravir (FPV) or FPV alone to assess the efficacy in preventing disease progression in mild to moderate COVID-19 on the 5th day. RESULTS: In total, 134 patients with mild COVID-19 received FPV and 132 received FVX/FPV, 31 patients with moderate COVID-19 received FPV/dexamethasone (FPV/Dex), and 30 received FVX/FPV/Dex. The intention-to-treat (ITT) analysis showed no difference of no clinical deterioration on the 5th day in both mild COVID-19 (100% in FPV vs 97% in FVX/FPV) and moderate COVID-19 (83.9% in FPV/Dex vs 86.7% in FVX/FPV/Dex). However, there was a low rate of oxygen supplemental, hospitalization, or intensive care in both groups and zero death in all groups. No significant difference in oxygen supplemental, hospitalization, radiological, virological, or biochemical outcomes, and the immunomodulatory effect was observed between the group. CONCLUSION: The combined fluvoxamine treatment did not add benefit in preventing deterioration in patients with mild to moderate COVID-19 without the immunomodulatory effect observed, although it demonstrated low hospitalization rates, oxygen supplemental, intensive care needed, and zero mortality. TRIAL REGISTRATION: Thai clinical trials registry (TCTR) no. 20210615002.