nnUNet for Automatic Kidney and Cyst Segmentation in Autosomal Dominant Polycystic Kidney Disease.

BACKGROUND: Autosomal Dominant Polycystic Kidney Disease (ADPKD) is a genetic disorder that causes uncontrolled kidney cyst growth, leading to kidney volume enlargement and renal function loss over time. Total kidney volume (TKV) and cyst burdens have been used as prognostic imaging biomarkers for ADPKD. OBJECTIVE: This study aimed to evaluate nnUNet for automatic kidney and cyst segmentation in T2-weighted (T2W) MRI images of ADPKD patients. METHODS: 756 kidney images were retrieved from 95 patients in the Consortium for Radiologic Imaging Studies of Polycystic Kidney Disease (CRISP) cohort (95 patients × 2 kidneys × 4 follow-up scans). The nnUNet model was trained, validated, and tested on 604, 76, and 76 images, respectively. In contrast, all images of each patient were exclusively assigned to either the training, validation, or test sets to minimize evaluation bias. The kidney and cyst regions defined using a semi-automatic method were employed as ground truth. The model performance was assessed using the Dice Similarity Coefficient (DSC), the intersection over union (IoU) score, and the Hausdorff distance (HD). RESULTS: The test DSC values were 0.96±0.01 (mean±SD) and 0.90±0.05 for kidney and cysts, respectively. Similarly, the IoU scores were 0.91± 0.09 and 0.81±0.06, and the HD values were 12.49±8.71 mm and 12.04±10.41 mm, respectively, for kidney and cyst segmentation. CONCLUSION: The nnUNet model is a reliable tool to automatically determine kidney and cyst volumes in T2W MRI images for ADPKD prognosis and therapy monitoring.

Deep learning-based automated kidney and cyst segmentation of autosomal dominant polycystic kidney disease using single vs. multi-institutional data.

PURPOSE: This study aimed to investigate if a deep learning model trained with a single institution's data has comparable accuracy to that trained with multi-institutional data for segmenting kidney and cyst regions in magnetic resonance (MR) images of patients affected by autosomal dominant polycystic kidney disease (ADPKD). METHODS: We used TensorFlow with a Keras custom UNet on 2D slices of 756 MRI images of kidneys with ADPKD obtained from four institutions in the Consortium for Radiologic Imaging Studies of Polycystic Kidney Disease (CRISP) study. The ground truth was determined via a manual plus global thresholding method. Five models were trained with 80 % of all institutional data (n = 604) and each institutional data (n = 232, 172, 148, or 52), respectively, and validated with 10 % and tested on an unseen 10 % of the data. The model's performance was evaluated using the Dice Similarity Coefficient (DSC). RESULTS: The DSCs by the model trained with all institutional data ranged from 0.92 to 0.95 for kidney image segmentation, only 1-2 % higher than those by the models trained with single institutional data (0.90-0.93).In cyst segmentation, however, the DSCs by the model trained with all institutional data ranged from 0.83 to 0.89, which were 2-20 % higher than those by the models trained with single institutional data (0.66-0.86). CONCLUSION: The UNet performance, when trained with a single institutional dataset, exhibited similar accuracy to the model trained on a multi-institutional dataset. Segmentation accuracy increases with models trained on larger sample sizes, especially in more complex cyst segmentation.

Mucociliary clearance augmenting drugs block SARS-CoV-2 replication in human airway epithelial cells.

The coronavirus disease (COVID-19) pandemic, caused by SARS-CoV-2 coronavirus, is devastatingly impacting human health. A prominent component of COVID-19 is the infection and destruction of the ciliated respiratory cells, which perpetuates dissemination and disrupts protective mucociliary transport (MCT) function, an innate defense of the respiratory tract. Thus, drugs that augment MCT could improve the barrier function of the airway epithelium and reduce viral replication and, ultimately, COVID-19 outcomes. We tested five agents known to increase MCT through distinct mechanisms for activity against SARS-CoV-2 infection using a model of human respiratory epithelial cells terminally differentiated in an air/liquid interphase. Three of the five mucoactive compounds tested showed significant inhibitory activity against SARS-CoV-2 replication. An archetype mucoactive agent, ARINA-1, blocked viral replication and therefore epithelial cell injury; thus, it was further studied using biochemical, genetic, and biophysical methods to ascertain the mechanism of action via the improvement of MCT. ARINA-1 antiviral activity was dependent on enhancing the MCT cellular response, since terminal differentiation, intact ciliary expression, and motion were required for ARINA-1-mediated anti-SARS-CoV2 protection. Ultimately, we showed that the improvement of cilia movement was caused by ARINA-1-mediated regulation of the redox state of the intracellular environment, which benefited MCT. Our study indicates that intact MCT reduces SARS-CoV-2 infection, and its pharmacologic activation may be effective as an anti-COVID-19 treatment.

Perfusion Change of Hepatocellular Carcinoma During Atezolizumab plus Bevacizumab Treatment: A Pilot Study.

PURPOSE: To investigate whether the early perfusion change in hepatocellular carcinoma (HCC) predicts the long-term therapeutic response to atezolizumab plus bevacizumab. METHODS: We retrospectively selected 19 subjects (median age: 62 years, 4 females, and 15 males) having advanced HCC and treated with atezolizumab alone (n = 3) or in combination with bevacizumab (n = 16). The 4-phased CT or MRI imaging was performed for each subject before and at 9 ± 2 and 21 ± 5 weeks after therapy initiation. The tumor-to-liver signal ratio in the arterial phase was used to estimate the tumor perfusion. The change in tumor perfusion from the baseline to the 1st follow-up exam was correlated with the tumor response evaluated using mRECIST at the 2nd follow-up exam. The difference between favorably responding and non-responding groups was statistically analyzed using one-way ANOVA. RESULTS: The mean tumor long axis in the baseline image was 59 ± 47 mm. The HCC perfusion changes were -26 ± 18% for complete (or partial) response (CR/PR, n = 8), -24 ± 12% for stable disease (SD, n = 8), and 9 ± 13% for progressive disease (PD, n = 3). The HCC perfusion change of the CR/PR groups was significantly lower than that of the PD group (p = 0.0040). The HCC perfusion changes between the SD and PD groups were also significantly different (p = 0.0135). The sensitivity and specificity of the early perfusion change to predict the long-term progression of the disease were 100 and 94%, respectively. CONCLUSION: The early change in HCC perfusion may predict the long-term therapeutic response to atezolizumab plus bevacizumab, promoting personalized treatment for HCC patients.