Test Retest Reproducibility of Organ Volume Measurements in ADPKD Using 3D Multimodality Deep Learning.

RATIONALE AND OBJECTIVES: Following autosomal dominant polycystic kidney disease (ADPKD) progression by measuring organ volumes requires low measurement variability. The objective of this study is to reduce organ volume measurement variability on MRI of ADPKD patients by utilizing all pulse sequences to obtain multiple measurements which allows outlier analysis to find errors and averaging to reduce variability. MATERIALS AND METHODS: In order to make measurements on multiple pulse sequences practical, a 3D multi-modality multi-class segmentation model based on nnU-net was trained/validated using T1, T2, SSFP, DWI and CT from 413 subjects. Reproducibility was assessed with test-re-test methodology on ADPKD subjects (n = 19) scanned twice within a 3-week interval correcting outliers and averaging the measurements across all sequences. Absolute percent differences in organ volumes were compared to paired students t-test. RESULTS: Dice similarlity coefficient > 97%, Jaccard Index > 0.94, mean surface distance < 1 mm and mean Hausdorff Distance < 2 cm for all three organs and all five sequences were found on internal (n = 25), external (n = 37) and test-re-test reproducibility assessment (38 scans in 19 subjects). When averaging volumes measured from five MRI sequences, the model automatically segmented kidneys with test-re-test reproducibility (percent absolute difference between exam 1 and exam 2) of 1.3% which was better than all five expert observers. It reliably stratified ADPKD into Mayo Imaging Classification (area under the curve=100%) compared to radiologist. CONCLUSION: 3D deep learning measures organ volumes on five MRI sequences leveraging the power of outlier analysis and averaging to achieve 1.3% total kidney test-re-test reproducibility.

Effect of Averaging Measurements From Multiple MRI Pulse Sequences on Kidney Volume Reproducibility in Autosomal Dominant Polycystic Kidney Disease.

BACKGROUND: Total kidney volume (TKV) is an important biomarker for assessing kidney function, especially for autosomal dominant polycystic kidney disease (ADPKD). However, TKV measurements from a single MRI pulse sequence have limited reproducibility, ± ~5%, similar to ADPKD annual kidney growth rates. PURPOSE: To improve TKV measurement reproducibility on MRI by extending artificial intelligence algorithms to automatically segment kidneys on T1-weighted, T2-weighted, and steady state free precession (SSFP) sequences in axial and coronal planes and averaging measurements. STUDY TYPE: Retrospective training, prospective testing. SUBJECTS: Three hundred ninety-seven patients (356 with ADPKD, 41 without), 75% for training and 25% for validation, 40 ADPKD patients for testing and 17 ADPKD patients for assessing reproducibility. FIELD STRENGTH/SEQUENCE: T2-weighted single-shot fast spin echo (T2), SSFP, and T1-weighted 3D spoiled gradient echo (T1) at 1.5 and 3T. ASSESSMENT: 2D U-net segmentation algorithm was trained on images from all sequences. Five observers independently measured each kidney volume manually on axial T2 and using model-assisted segmentations on all sequences and image plane orientations for two MRI exams in two sessions separated by 1-3 weeks to assess reproducibility. Manual and model-assisted segmentation times were recorded. STATISTICAL TESTS: Bland-Altman, Schapiro-Wilk (normality assessment), Pearson's chi-squared (categorical variables); Dice similarity coefficient, interclass correlation coefficient, and concordance correlation coefficient for analyzing TKV reproducibility. P-value < 0.05 was considered statistically significant. RESULTS: In 17 ADPKD subjects, model-assisted segmentations of axial T2 images were significantly faster than manual segmentations (2:49 minute vs. 11:34 minute), with no significant absolute percent difference in TKV (5.9% vs. 5.3%, P = 0.88) between scans 1 and 2. Absolute percent differences between the two scans for model-assisted segmentations on other sequences were 5.5% (axial T1), 4.5% (axial SSFP), 4.1% (coronal SSFP), and 3.2% (coronal T2). Averaging measurements from all five model-assisted segmentations significantly reduced absolute percent difference to 2.5%, further improving to 2.1% after excluding an outlier. DATA CONCLUSION: Measuring TKV on multiple MRI pulse sequences in coronal and axial planes is practical with deep learning model-assisted segmentations and can improve TKV measurement reproducibility more than 2-fold in ADPKD. EVIDENCE LEVEL: 2 TECHNICAL EFFICACY: Stage 1.

Deep Learning Automation of Kidney, Liver, and Spleen Segmentation for Organ Volume Measurements in Autosomal Dominant Polycystic Kidney Disease.

Organ volume measurements are a key metric for managing ADPKD (the most common inherited renal disease). However, measuring organ volumes is tedious and involves manually contouring organ outlines on multiple cross-sectional MRI or CT images. The automation of kidney contouring using deep learning has been proposed, as it has small errors compared to manual contouring. Here, a deployed open-source deep learning ADPKD kidney segmentation pipeline is extended to also measure liver and spleen volumes, which are also important. This 2D U-net deep learning approach was developed with radiologist labeled T2-weighted images from 215 ADPKD subjects (70% training = 151, 30% validation = 64). Additional ADPKD subjects were utilized for prospective (n = 30) and external (n = 30) validations for a total of 275 subjects. Image cropping previously optimized for kidneys was included in training but removed for the validation and inference to accommodate the liver which is closer to the image border. An effective algorithm was developed to adjudicate overlap voxels that are labeled as more than one organ. Left kidney, right kidney, liver and spleen labels had average errors of 3%, 7%, 3%, and 1%, respectively, on external validation and 5%, 6%, 5%, and 1% on prospective validation. Dice scores also showed that the deep learning model was close to the radiologist contouring, measuring 0.98, 0.96, 0.97 and 0.96 on external validation and 0.96, 0.96, 0.96 and 0.95 on prospective validation for left kidney, right kidney, liver and spleen, respectively. The time required for manual correction of deep learning segmentation errors was only 19:17 min compared to 33:04 min for manual segmentations, a 42% time saving (p = 0.004). Standard deviation of model assisted segmentations was reduced to 7, 5, 11, 5 mL for right kidney, left kidney, liver and spleen respectively from 14, 10, 55 and 14 mL for manual segmentations. Thus, deep learning reduces the radiologist time required to perform multiorgan segmentations in ADPKD and reduces measurement variability.

Pulmonary Embolism in Hospitalized Patients with COVID-19: A Multicenter Study.

Background Pulmonary embolism (PE) commonly complicates SARS-CoV-2 infection, but incidence and mortality reported in single-center studies, along with risk factors, vary. Purpose To determine the incidence of PE in patients with COVID-19 and its associations with clinical and laboratory parameters. Materials and Methods In this HIPAA-compliant study, electronic medical records were searched retrospectively for demographic, clinical, and laboratory data and outcomes among patients with COVID-19 admitted at four hospitals from March through June 2020. PE found at CT pulmonary angiography and perfusion scintigraphy was correlated with clinical and laboratory parameters. The d-dimer level was used to predict PE, and the obtained threshold was externally validated among 85 hospitalized patients with COVID-19 at a fifth hospital. The association between right-sided heart strain and embolic burden was evaluated in patients with PE undergoing echocardiography. Results A total of 413 patients with COVID-19 (mean age, 60 years ± 16 [standard deviation]; age range, 20-98 years; 230 men) were evaluated. PE was diagnosed in 102 (25%; 95% CI: 21, 29) of 413 hospitalized patients with COVID-19 who underwent CT pulmonary angiography or perfusion scintigraphy. PE was observed in 21 (29%; 95% CI: 19, 41) of 73 patients in the intensive care unit (ICU) versus 81 (24%; 95% CI: 20, 29) of 340 patients who were not in the ICU (P = .37). PE was associated with male sex (odds ratio [OR], 1.74; 95% CI: 1.1, 2.8; P = .02); smoking (OR, 1.86; 95% CI: 1.0, 3.4; P = .04); and increased d-dimer (P < .001), lactate dehydrogenase (P < .001), ferritin (P = .001), and interleukin-6 (P = .02) levels. Mortality in hospitalized patients was similar between patients with PE and those without PE (14% [13 of 102]; 95% CI: 8, 22] vs 13% [40 of 311]; 95% CI: 9, 17; P = .98), suggesting that diagnosis and treatment of PE were not associated with excess mortality. The d-dimer levels greater than 1600 ng/mL [8.761 nmol/L] helped predict PE with 100% sensitivity and 62% specificity in an external validation cohort. Embolic burden was higher in patients with right-sided heart strain among the patients with PE undergoing echocardiography (P = .03). Conclusion Pulmonary embolism (PE) incidence was 25% in patients hospitalized with COVID-19 suspected of having PE. A d-dimer level greater than 1600 ng/mL [8.761 nmol/L] was sensitive for identification of patients who needed CT pulmonary angiography. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Ketai in this issue.

Prescribing in Type 2 Diabetes Patients With and Without Cardiovascular Disease History: A Descriptive Analysis in the UK CPRD.

PURPOSE: Some classes of glucose-lowering medications, including sodium-glucose co-transporter 2 inhibitors (SGLT2is) and glucagon-like peptide 1-receptor agonists (GLP1-RAs) have cardio-protective benefit, but it is unclear whether this influences prescribing in the United Kingdom (UK). This study aims to describe class-level prescribing in adults with type 2 diabetes mellitus (T2DM) by cardiovascular disease (CVD) history using the Clinical Practice Research Datalink (CPRD). METHODS: Four cross-sections of people with T2DM aged 18-90 and registered with their general practice for >1 year on 1st January 2017 (n = 166,012), 1st January 2018 (n = 155,290), 1st January 2019 (n = 152,602) and 31st December 2019 (n = 143,373) were identified. Age-standardised proportions for class use through time were calculated separately in those with and without CVD history and by total number of medications prescribed (one, two, three, four+). An analysis by UK country was also performed. FINDINGS: Around 31% of patients had CVD history at each cross-section. Metformin was the most common treatment (>70% of those with and without CVD had prescriptions across all treatment lines). Overall use of SGLT2is and GLP1-RAs was low, with slightly less use in patients with CVD (SGLT2i: 9.8% and 13.8% in those with and without CVD respectively; GLP1-RA: 4.3% and 4.9%, December 2019). Use of SGLT2is as part of dual therapy was low but rose throughout the study. In January 2017, estimated use was 8.0% (95% CI 6.9-9.1%) and 8.9% (8.6-9.3%) in those with and without CVD. By December 2019 this reached 18.3% (17.0-19.5%) and 21.2% (20.6-21.7%) for those with and without CVD respectively. SGLT2i use as triple therapy increased: 22.7% (21.0-24.4%) and 25.9% (25.2-26.6%) in January 2017 to 41.3% (39.5-43.0%) and 45.5% (44.7-46.3%) in December 2019. GLP1-RA use also increased, but observed usage remained lower than SGLT2 inhibitors. Insulin use remained stable throughout, with higher use observed in those with CVD (16% vs 9.7% Dec 2019). Time trends in England, Wales, Scotland and Northern Ireland were similar, although class prevalence varied. IMPLICATIONS: Although use of SGLT2is and GLP1-RAs has increased, overall usage remains low with slightly lower use in those with CVD history, suggesting there is opportunity to optimise use of these medicines in T2DM patients to manage CVD risk. Insulin use was substantially more prevalent in those with CVD despite no evidence of CVD benefit. Further investigation of factors influencing this finding may highlight strategies to improve patient access to the most appropriate treatments, including those with evidence of cardiovascular benefit.

Long-Term Cost-Effectiveness Analyses of Empagliflozin Versus Oral Semaglutide, in Addition to Metformin, for the Treatment of Type 2 Diabetes in the UK.

INTRODUCTION: International guidelines recommend treatment with a sodium-glucose cotransporter-2 (SGLT-2) inhibitor or glucagon-like peptide-1 (GLP-1) receptor agonist for treatment intensification in type 2 diabetes mellitus (T2DM) patients with progression on metformin. In the randomised, controlled, Peptide Innovation for Early Diabetes Treatment (PIONEER) 2 trial, the SGLT-2 inhibitor empagliflozin was compared with the GLP-1 receptor agonist oral semaglutide, in addition to metformin. The aim of the current study was to assess the long-term cost-effectiveness of empagliflozin 25 mg versus oral semaglutide 14 mg, in addition to metformin, for T2DM patients in the UK. METHODS: Analyses were conducted from the UK healthcare payer perspective, using the IQVIA Core Diabetes model, with a time horizon of 50 years. Patients received either empagliflozin or oral semaglutide, in addition to metformin, until Hba1c threshold of 7.5% (58 mmol/mol) was exceeded, following which treatment intensification with insulin glargine in addition to empagliflozin or oral semaglutide plus metformin was assumed. Baseline cohort characteristics and 52-week treatment effects were derived from the PIONEER 2 trial. Treatment effects of empagliflozin and GLP-1 receptor agonists on hospitalisation for heart failure (hHF) were based on the Empagliflozin Comparative Effectiveness and Safety (EMPRISE) real-world study. Utilities, treatment costs and costs of diabetes-related complications were obtained from published sources. RESULTS: Direct costs for empagliflozin plus metformin were considerably lower than those for oral semaglutide plus metformin (by more than GBP 6000). Compared with oral semaglutide plus metformin, empagliflozin plus metformin was a cost-effective treatment for T2DM patients in all scenarios tested. Probabilistic sensitivity analysis showed cost-effectiveness in > 95% of the iterations using a threshold of 20,000 GBP/QALY. CONCLUSION: Empagliflozin 25 mg is a cost-effective treatment option versus oral semaglutide 14 mg, when used in addition to metformin, for the treatment of T2DM patients in the UK.

Loss of the interleukin-6 receptor causes immunodeficiency, atopy, and abnormal inflammatory responses.

IL-6 excess is central to the pathogenesis of multiple inflammatory conditions and is targeted in clinical practice by immunotherapy that blocks the IL-6 receptor encoded by IL6R We describe two patients with homozygous mutations in IL6R who presented with recurrent infections, abnormal acute-phase responses, elevated IgE, eczema, and eosinophilia. This study identifies a novel primary immunodeficiency, clarifying the contribution of IL-6 to the phenotype of patients with mutations in IL6ST, STAT3, and ZNF341, genes encoding different components of the IL-6 signaling pathway, and alerts us to the potential toxicity of drugs targeting the IL-6R.

Novel homozygous mutations in the EVC and EVC2 genes in two consanguineous families segregating autosomal recessive Ellis-van Creveld syndrome.

Ellis-van Creveld syndrome (EVC) is a rare developmental disorder characterized by short limbs, short ribs, postaxial polydactyly, dysplastic nails, teeth, oral and cardiac abnormalities. It is caused by biallelic mutations in the EVC or EVC2 gene, separated by 2.6 kb of genomic sequence on chromosome 4p16. In the present study, we have investigated two consanguineous families of Pakistani origin, segregating EVC in autosomal recessive manner. Linkage in the families was established to chromosome 4p16. Subsequently, sequence analysis identified a novel nonsense mutation (p.Trp234*) in exon 8 of the EVC2 gene and 15 bp duplication in exon 14 of the EVC gene in the two families. This further expands the mutations in the EVC or EVC2 genes resulting in the EVC syndrome.

Mutations in TBC1D24, a gene associated with epilepsy, also cause nonsyndromic deafness DFNB86.

Inherited deafness is clinically and genetically heterogeneous. We recently mapped DFNB86, a locus associated with nonsyndromic deafness, to chromosome 16p. In this study, whole-exome sequencing was performed with genomic DNA from affected individuals from three large consanguineous families in which markers linked to DFNB86 segregate with profound deafness. Analyses of these data revealed homozygous mutation c.208G>T (p.Asp70Tyr) or c.878G>C (p.Arg293Pro) in TBC1D24 as the underlying cause of deafness in the three families. Sanger sequence analysis of TBC1D24 in an additional large family in which deafness segregates with DFNB86 identified the c.208G>T (p.Asp70Tyr) substitution. These mutations affect TBC1D24 amino acid residues that are conserved in orthologs ranging from fruit fly to human. Neither variant was observed in databases of single-nucleotide variants or in 634 chromosomes from ethnically matched control subjects. TBC1D24 in the mouse inner ear was immunolocalized predominantly to spiral ganglion neurons, indicating that DFNB86 deafness might be an auditory neuropathy spectrum disorder. Previously, six recessive mutations in TBC1D24 were reported to cause seizures (hearing loss was not reported) ranging in severity from epilepsy with otherwise normal development to epileptic encephalopathy resulting in childhood death. Two of our four families in which deafness segregates with mutant alleles of TBC1D24 were available for neurological examination. Cosegregation of epilepsy and deafness was not observed in these two families. Although the causal relationship between genotype and phenotype is not presently understood, our findings, combined with published data, indicate that recessive alleles of TBC1D24 can cause either epilepsy or nonsyndromic deafness.