AcquisitionFocus: Joint Optimization of Acquisition Orientation and Cardiac Volume Reconstruction Using Deep Learning.

In cardiac cine imaging, acquiring high-quality data is challenging and time-consuming due to the artifacts generated by the heart's continuous movement. Volumetric, fully isotropic data acquisition with high temporal resolution is, to date, intractable due to MR physics constraints. To assess whole-heart movement under minimal acquisition time, we propose a deep learning model that reconstructs the volumetric shape of multiple cardiac chambers from a limited number of input slices while simultaneously optimizing the slice acquisition orientation for this task. We mimic the current clinical protocols for cardiac imaging and compare the shape reconstruction quality of standard clinical views and optimized views. In our experiments, we show that the jointly trained model achieves accurate high-resolution multi-chamber shape reconstruction with errors of <13 mm HD95 and Dice scores of >80%, indicating its effectiveness in both simulated cardiac cine MRI and clinical cardiac MRI with a wide range of pathological shape variations.

Development and validation of a machine learning model for prediction of type 2 diabetes in patients with mental illness.

BACKGROUND: Type 2 diabetes (T2D) is approximately twice as common among individuals with mental illness compared with the background population, but may be prevented by early intervention on lifestyle, diet, or pharmacologically. Such prevention relies on identification of those at elevated risk (prediction). The aim of this study was to develop and validate a machine learning model for prediction of T2D among patients with mental illness. METHODS: The study was based on routine clinical data from electronic health records from the psychiatric services of the Central Denmark Region. A total of 74,880 patients with 1.59 million psychiatric service contacts were included in the analyses. We created 1343 potential predictors from 51 source variables, covering patient-level information on demographics, diagnoses, pharmacological treatment, and laboratory results. T2D was operationalised as HbA1c ≥48 mmol/mol, fasting plasma glucose ≥7.0 mmol/mol, oral glucose tolerance test ≥11.1 mmol/mol or random plasma glucose ≥11.1 mmol/mol. Two machine learning models (XGBoost and regularised logistic regression) were trained to predict T2D based on 85% of the included contacts. The predictive performance of the best performing model was tested on the remaining 15% of the contacts. RESULTS: The XGBoost model detected patients at high risk 2.7 years before T2D, achieving an area under the receiver operating characteristic curve of 0.84. Of the 996 patients developing T2D in the test set, the model issued at least one positive prediction for 305 (31%). CONCLUSION: A machine learning model can accurately predict development of T2D among patients with mental illness based on routine clinical data from electronic health records. A decision support system based on such a model may inform measures to prevent development of T2D in this high-risk population.

Exploring the potential of high-resolution LC-MS in combination with ion mobility separation and surrogate minimal depth for enhanced almond origin authentication.

Almonds (Prunus dulcisMill.) are consumed worldwide and their geographical origin plays a crucial role in determining their market value. In the present study, a total of 250 almond reference samples from six countries (Australia, Spain, Iran, Italy, Morocco, and the USA) were non-polar extracted and analyzed by UPLC-ESI-IM-qToF-MS. Four harvest periods, more than 30 different varieties, including both sweet and bitter almonds, were considered in the method development. Principal component analysis showed that there are three groups of samples with similarities: Australia/USA, Spain/Italy and Iran/Morocco. For origin determination, a random forest achieved an accuracy of 88.8 %. Misclassifications occurred mainly between almonds from the USA and Australia, due to similar varieties and similar external influences such as climate conditions. Metabolites relevant for classification were selected using Surrogate Minimal Depth, with triacylglycerides containing oxidized, odd chained or short chained fatty acids and some phospholipids proven to be the most suitable marker substances. Our results show that focusing on the identified lipids (e. g., using a QqQ-MS instrument) is a promising approach to transfer the origin determination of almonds to routine analysis.

Variation of extrachromosomal circular DNA in cancer cell lines.

The presence of oncogene carrying eccDNAs is strongly associated with carcinogenesis and poor patient survival. Tumour biopsies and in vitro cancer cell lines are frequently utilized as models to investigate the role of eccDNA in cancer. However, eccDNAs are often lost during the in vitro growth of cancer cell lines, questioning the reproducibility of studies utilizing cancer cell line models. Here, we conducted a comprehensive analysis of eccDNA variability in seven cancer cell lines (MCA3D, PDV, HaCa4, CarC, MIA-PaCa-2, AsPC-1, and PC-3). We compared the content of unique eccDNAs between triplicates of each cell line and found that the number of unique eccDNA is specific to each cell line, while the eccDNA sequence content varied greatly among triplicates (∼ 0-1% eccDNA coordinate commonality). In the PC-3 cell line, we found that the large eccDNA (ecDNA) with MYC is present in high-copy number in an NCI cell line isolate but not present in ATCC isolates. Together, these results reveal that the sequence content of eccDNA is highly variable in cancer cell lines. This highlights the importance of testing cancer cell lines before use, and to enrich for subclones in cell lines with the desired eccDNA to get relatively pure population for studying the role of eccDNA in cancer.

Combined endoscopic and laparoscopic surgery (CELS) for early colon cancer in high-risk patients.

BACKGROUND: Local excision of early colon cancers could be an option in selected patients with high risk of complications and no sign of lymph node metastasis (LNM). The primary aim was to assess feasibility in high-risk patients with early colon cancer treated with Combined Endoscopic and Laparoscopic Surgery (CELS). METHODS: A non-randomized prospective feasibility study including 25 patients with Performance Status score ≥ 1 and/or American Society of Anesthesiologists score ≥ 3, and clinical Union of International Cancer Control stage-1 colon cancer suitable for CELS resection. The primary outcome was failure of CELS resection, defined as either: Incomplete resection (R1/R2), local recurrence within 3 months, complication related to CELS within 30 days (Clavien-Dindo grade ≥ 3), death within 30 days or death within 90 days due to complications to surgery. RESULTS: Fifteen patients with clinical T1 (cT1) and ten with clinical T2 (cT2) colon cancer and without suspicion of metastases were included. Failure occurred in two patients due to incomplete resections. Histopathological examination classified seven patients as having pT1, nine as pT2, six as pT3 adenocarcinomas, and three as non-invasive tumors. In three patients, the surgical strategy was changed intraoperatively to conventional colectomy due to tumor location or size. Median length of stay was 1 day. Seven patients had completion colectomy performed due to histological high-risk factors. None had LNM. CONCLUSIONS: In selected patients, CELS resection was feasible, and could spare some patients large bowel resection.

Lexical stability of psychiatric clinical notes from electronic health records over a decade.

OBJECTIVE: Natural language processing (NLP) methods hold promise for improving clinical prediction by utilising information otherwise hidden in the clinical notes of electronic health records. However, clinical practice - as well as the systems and databases in which clinical notes are recorded and stored - change over time. As a consequence, the content of clinical notes may also change over time, which could degrade the performance of prediction models. Despite its importance, the stability of clinical notes over time has rarely been tested. METHODS: The lexical stability of clinical notes from the Psychiatric Services of the Central Denmark Region in the period from January 1, 2011, to November 22, 2021 (a total of 14,811,551 clinical notes describing 129,570 patients) was assessed by quantifying sentence length, readability, syntactic complexity and clinical content. Changepoint detection models were used to estimate potential changes in these metrics. RESULTS: We find lexical stability of the clinical notes over time, with minor deviations during the COVID-19 pandemic. Out of 2988 data points, 17 possible changepoints (corresponding to 0.6%) were detected. The majority of these were related to the discontinuation of a specific note type. CONCLUSION: We find lexical and syntactic stability of clinical notes from psychiatric services over time, which bodes well for the use of NLP for predictive modelling in clinical psychiatry.

Methods for the purification and detection of single nucleotide KRAS mutations on extrachromosomal circular DNA in human plasma.

BACKGROUNDS: Despite recent advances, many cancers are still detected too late for curative treatment. There is, therefore, a need for the development of new diagnostic methods and biomarkers. One approach may arise from the detection of extrachromosomal circular DNA (eccDNA), which is part of cell-free DNA in human plasma. AIMS: First, we assessed and compared two methods for the purification of eccDNA from plasma. Second, we tested for an easy diagnostic application of eccDNA liquid biopsy-based assays. MATERIALS & METHODS: For the comparison we tested a solid-phase silica purification method and a phenol/chloroform method with salt precipitation. For the diagnostic application of eccDNA we developed and tested a qPCR primer-based SNP detection system, for the detection of two well-established cancer-causing KRAS mutations (G12V and G12R) on circular DNA. This investigation was supported by purifying, sequencing, and analysing clinical plasma samples for eccDNAs containing KRAS mutant alleles in 0.5 mL plasma from 16 pancreatic ductal adenocarcinoma patients and 19 healthy controls. RESULTS: In our method comparison we observed, that following exonuclease treatment a lower eccDNA yield was found for the phenol/chloroform method (15.7%-26.7%) compared with the solid-phase purification approach (47.8%-65.9%). For the diagnostic application of eccDNA tests, the sensitivity of the tested qPCR assay only reached ~10-3 in a background of 105 wild type (wt) KRAS circular entities, which was not improved by general amplification or primer-based inhibition of wt KRAS amplification. Furthermore, we did not detect eccDNA containing KRAS in any of the clinical samples. DISCUSSION: A potential explanation for our inability to detect any KRAS mutations in the clinical samples may be related to the general low abundance of eccDNA in plasma. CONCLUSION: Taken together our results provide a benchmark for eccDNA purification methods while raising the question of what is required for the optimal fast and sensitive detection of SNP mutations on eccDNA with greater sensitivity than primer-based qPCR detection.

Anatomy-guided domain adaptation for 3D in-bed human pose estimation.

3D human pose estimation is a key component of clinical monitoring systems. The clinical applicability of deep pose estimation models, however, is limited by their poor generalization under domain shifts along with their need for sufficient labeled training data. As a remedy, we present a novel domain adaptation method, adapting a model from a labeled source to a shifted unlabeled target domain. Our method comprises two complementary adaptation strategies based on prior knowledge about human anatomy. First, we guide the learning process in the target domain by constraining predictions to the space of anatomically plausible poses. To this end, we embed the prior knowledge into an anatomical loss function that penalizes asymmetric limb lengths, implausible bone lengths, and implausible joint angles. Second, we propose to filter pseudo labels for self-training according to their anatomical plausibility and incorporate the concept into the Mean Teacher paradigm. We unify both strategies in a point cloud-based framework applicable to unsupervised and source-free domain adaptation. Evaluation is performed for in-bed pose estimation under two adaptation scenarios, using the public SLP dataset and a newly created dataset. Our method consistently outperforms various state-of-the-art domain adaptation methods, surpasses the baseline model by 31%/66%, and reduces the domain gap by 65%/82%. Source code is available at https://github.com/multimodallearning/da-3dhpe-anatomy.

Neoadjuvant intratumoral influenza vaccine treatment in patients with proficient mismatch repair colorectal cancer leads to increased tumor infiltration of CD8+ T cells and upregulation of PD-L1: a phase 1/2 clinical trial.

BACKGROUND: In colorectal cancer, the effects of immune checkpoint inhibitors are mostly limited to patients with deficient mismatch repair tumors, characterized by a high grade infiltration of CD8+T cells. Interventions aimed at increasing intratumoral CD8+T-cell infiltration in proficient mismatch repair tumors are lacking. METHODS: We conducted a proof of concept phase 1/2 clinical trial, where patients with non-metastasizing sigmoid or rectal cancer, scheduled for curative intended surgery, were treated with an endoscopic intratumorally administered neoadjuvant influenza vaccine. Blood and tumor samples were collected before the injection and at the time of surgery. The primary outcome was safety of the intervention. Evaluation of pathological tumor regression grade, immunohistochemistry, flow cytometry of blood, tissue bulk transcriptional analyses, and spatial protein profiling of tumor regions were all secondary outcomes. RESULTS: A total of 10 patients were included in the trial. Median patient age was 70 years (range 54-78), with 30% women. All patients had proficient mismatch repair Union of International Cancer Control stage I-III tumors. No endoscopic safety events occurred, with all patients undergoing curative surgery as scheduled (median 9 days after intervention). Increased CD8+T-cell tumor infiltration was evident after vaccination (median 73 vs 315 cells/mm2, p<0.05), along with significant downregulation of messenger RNA gene expression related to neutrophils and upregulation of transcripts encoding cytotoxic functions. Spatial protein analysis showed significant local upregulation of programmed death-ligand 1 (PD-L1) (adjusted p value<0.05) and downregulation of FOXP3 (adjusted p value<0.05). CONCLUSIONS: Neoadjuvant intratumoral influenza vaccine treatment in this cohort was demonstrated to be safe and feasible, and to induce CD8+T-cell infiltration and upregulation of PD-L1 proficient mismatch repair sigmoid and rectal tumors. Definitive conclusions regarding safety and efficacy can only be made in larger cohorts. TRIAL REGISTRATION NUMBER: NCT04591379.

Robust and Realtime Large Deformation Ultrasound Registration Using End-to-End Differentiable Displacement Optimisation.

Image registration for temporal ultrasound sequences can be very beneficial for image-guided diagnostics and interventions. Cooperative human-machine systems that enable seamless assistance for both inexperienced and expert users during ultrasound examinations rely on robust, realtime motion estimation. Yet rapid and irregular motion patterns, varying image contrast and domain shifts in imaging devices pose a severe challenge to conventional realtime registration approaches. While learning-based registration networks have the promise of abstracting relevant features and delivering very fast inference times, they come at the potential risk of limited generalisation and robustness for unseen data; in particular, when trained with limited supervision. In this work, we demonstrate that these issues can be overcome by using end-to-end differentiable displacement optimisation. Our method involves a trainable feature backbone, a correlation layer that evaluates a large range of displacement options simultaneously and a differentiable regularisation module that ensures smooth and plausible deformation. In extensive experiments on public and private ultrasound datasets with very sparse ground truth annotation the method showed better generalisation abilities and overall accuracy than a VoxelMorph network with the same feature backbone, while being two times faster at inference.

CrossMoDA 2021 challenge: Benchmark of cross-modality domain adaptation techniques for vestibular schwannoma and cochlea segmentation.

Domain Adaptation (DA) has recently been of strong interest in the medical imaging community. While a large variety of DA techniques have been proposed for image segmentation, most of these techniques have been validated either on private datasets or on small publicly available datasets. Moreover, these datasets mostly addressed single-class problems. To tackle these limitations, the Cross-Modality Domain Adaptation (crossMoDA) challenge was organised in conjunction with the 24th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2021). CrossMoDA is the first large and multi-class benchmark for unsupervised cross-modality Domain Adaptation. The goal of the challenge is to segment two key brain structures involved in the follow-up and treatment planning of vestibular schwannoma (VS): the VS and the cochleas. Currently, the diagnosis and surveillance in patients with VS are commonly performed using contrast-enhanced T1 (ceT1) MR imaging. However, there is growing interest in using non-contrast imaging sequences such as high-resolution T2 (hrT2) imaging. For this reason, we established an unsupervised cross-modality segmentation benchmark. The training dataset provides annotated ceT1 scans (N=105) and unpaired non-annotated hrT2 scans (N=105). The aim was to automatically perform unilateral VS and bilateral cochlea segmentation on hrT2 scans as provided in the testing set (N=137). This problem is particularly challenging given the large intensity distribution gap across the modalities and the small volume of the structures. A total of 55 teams from 16 countries submitted predictions to the validation leaderboard. Among them, 16 teams from 9 different countries submitted their algorithm for the evaluation phase. The level of performance reached by the top-performing teams is strikingly high (best median Dice score - VS: 88.4%; Cochleas: 85.7%) and close to full supervision (median Dice score - VS: 92.5%; Cochleas: 87.7%). All top-performing methods made use of an image-to-image translation approach to transform the source-domain images into pseudo-target-domain images. A segmentation network was then trained using these generated images and the manual annotations provided for the source image.

Learn2Reg: Comprehensive Multi-Task Medical Image Registration Challenge, Dataset and Evaluation in the Era of Deep Learning.

Image registration is a fundamental medical image analysis task, and a wide variety of approaches have been proposed. However, only a few studies have comprehensively compared medical image registration approaches on a wide range of clinically relevant tasks. This limits the development of registration methods, the adoption of research advances into practice, and a fair benchmark across competing approaches. The Learn2Reg challenge addresses these limitations by providing a multi-task medical image registration data set for comprehensive characterisation of deformable registration algorithms. A continuous evaluation will be possible at https://learn2reg.grand-challenge.org. Learn2Reg covers a wide range of anatomies (brain, abdomen, and thorax), modalities (ultrasound, CT, MR), availability of annotations, as well as intra- and inter-patient registration evaluation. We established an easily accessible framework for training and validation of 3D registration methods, which enabled the compilation of results of over 65 individual method submissions from more than 20 unique teams. We used a complementary set of metrics, including robustness, accuracy, plausibility, and runtime, enabling unique insight into the current state-of-the-art of medical image registration. This paper describes datasets, tasks, evaluation methods and results of the challenge, as well as results of further analysis of transferability to new datasets, the importance of label supervision, and resulting bias. While no single approach worked best across all tasks, many methodological aspects could be identified that push the performance of medical image registration to new state-of-the-art performance. Furthermore, we demystified the common belief that conventional registration methods have to be much slower than deep-learning-based methods.

Acute effects on glucose tolerance by neprilysin inhibition in patients with type 2 diabetes.

AIMS: Sacubitril/valsartan is a neprilysin-inhibitor/angiotensin II receptor blocker used for the treatment of heart failure. Recently, a post-hoc analysis of a 3-year randomized controlled trial showed improved glycaemic control with sacubitril/valsartan in patients with heart failure and type 2 diabetes. We previously reported that sacubitril/valsartan combined with a dipeptidyl peptidase-4 inhibitor increases active glucagon-like peptide-1 (GLP-1) in healthy individuals. We now hypothesized that administration of sacubitril/valsartan with or without a dipeptidyl peptidase-4 inhibitor would lower postprandial glucose concentrations (primary outcome) in patients with type 2 diabetes via increased active GLP-1. METHODS: We performed a crossover trial in 12 patients with obesity and type 2 diabetes. A mixed meal was ingested following five respective interventions: (a) a single dose of sacubitril/valsartan; (b) sitagliptin; (c) sacubitril/valsartan + sitagliptin; (d) control (no treatment); and (e) valsartan alone. Glucose, gut and pancreatic hormone responses were measured. RESULTS: Postprandial plasma glucose increased by 57% (incremental area under the curve 0-240 min) (p = .0003) and increased peak plasma glucose by 1.7 mM (95% CI: 0.6-2.9) (p = .003) after sacubitril/valsartan compared with control, whereas postprandial glucose levels did not change significantly after sacubitril/valsartan + sitagliptin. Glucagon, GLP-1 and C-peptide concentrations increased after sacubitril/valsartan, but insulin and glucose-dependent insulinotropic polypeptide did not change. CONCLUSIONS: The glucose-lowering effects of long-term sacubitril/valsartan treatment reported in patients with heart failure and type 2 diabetes may not depend on changes in entero-pancreatic hormones. Neprilysin inhibition results in hyperglucagonaemia and this may explain the worsen glucose tolerance observed in this study. CLINICALTRIALS: gov (NCT03893526).

Stability of diagnostic coding of psychiatric outpatient visits across the transition from the second to the third version of the Danish National Patient Registry.

OBJECTIVE: In Denmark, data on hospital contacts are reported to the Danish National Patient Registry (DNPR). The ICD-10 main diagnoses from the DNPR are often used as proxies for mental disorders in psychiatric research. With the transition from the second version of the DNPR (DNPR2) to the third (DNPR3) in February-March 2019, the way main diagnoses are coded in relation to outpatient treatment changed substantially. Specifically, in the DNPR2, each outpatient treatment course was labelled with only one main diagnosis. In the DNPR3, however, each visit during an outpatient treatment course is labelled with a main diagnosis. We assessed whether this change led to a break in the diagnostic time-series represented by the DNPR, which would pose a threat to the research relying on this source. METHODS: All main diagnoses from outpatients attending the Psychiatric Services of the Central Denmark Region from 2013 to 2021 (n = 100,501 unique patients) were included in the analyses. The stability of the DNPR diagnostic time-series at the ICD-10 subchapter level was examined by comparing means across the transition from the DNPR2 to the DNPR3. RESULTS: While the proportion of psychiatric outpatients with diagnoses from some ICD-10 subchapters changed statistically significantly from the DNPR2 to the DNPR3, the changes were small in absolute terms (e.g., +0.6% for F2-psychotic disorders and +0.6% for F3-mood disorders). CONCLUSION: The change from the DNPR2 to the DNPR3 is unlikely to pose a substantial threat to the validity of most psychiatric research at the diagnostic subchapter level.

The non-ELR CXC chemokine encoded by human cytomegalovirus UL146 genotype 5 contains a C-terminal ß-hairpin and induces neutrophil migration as a selective CXCR2 agonist.

Human cytomegalovirus (HCMV) is a major pathogen in immunocompromised patients. The UL146 gene exists as 14 diverse genotypes among clinical isolates, which encode 14 different CXC chemokines. One genotype (vCXCL1GT1) is a known agonist for CXCR1 and CXCR2, while two others (vCXCL1GT5 and vCXCL1GT6) lack the ELR motif considered crucial for CXCR1 and CXCR2 binding, thus suggesting another receptor targeting profile. To determine the receptor target for vCXCL1GT5, the chemokine was probed in a G protein signaling assay on all 18 classical human chemokine receptors, where CXCR2 was the only receptor being activated. In addition, vCXCL1GT5 recruited ß-arrestin in a BRET-based assay and induced migration in a chemotaxis assay through CXCR2, but not CXCR1. In contrast, vCXCL1GT1 stimulated G protein signaling, recruited ß-arrestin and induced migration through both CXCR1 and CXCR2. Both vCXCL1GT1 and vCXCL1GT5 induced equally potent and efficacious migration of neutrophils, and ELR vCXCL1GT4 and non-ELR vCXCL1GT6 activated only CXCR2. In contrast to most human chemokines, the 14 UL146 genotypes have remarkably long C-termini. Comparative modeling using Rosetta showed that each genotype could adopt the classic chemokine core structure, and predicted that the extended C-terminal tail of several genotypes (including vCXCL1GT1, vCXCL1GT4, vCXCL1GT5, and vCXCL1GT6) forms a novel ß-hairpin not found in human chemokines. Secondary NMR shift and TALOS+ analysis of vCXCL1GT1 supported the existence of two stable ß-strands. C-terminal deletion of vCXCL1GT1 resulted in a non-functional protein and in a shift to solvent exposure for tryptophan residues likely due to destabilization of the chemokine fold. The results demonstrate that non-ELR chemokines can activate CXCR2 and suggest that the UL146 chemokines have unique C-terminal structures that stabilize the chemokine fold. Increased knowledge of the structure and interaction partners of the chemokine variants encoded by UL146 is key to understanding why circulating HCMV strains sustain 14 stable genotypes.

First episode of uncomplicated diverticulitis does not increase the risk of colorectal cancer.

INTRODUCTION: Danish guidelines recommend colonoscopy after a case of acute diverticulitis to exclude colorectal cancer (CRC), but evidence in support this practice is limited. A series of studies has reported a low incidence of CRC in patients after they presented with acute diverticulitis, especially in uncomplicated cases. The purpose of this study was to investigate the incidence of CRC after acute diverticulitis detected during colonoscopy. METHODS: All patients seen between January 2010 and November 2017 with a first episode of acute diverticulitis and a subsequent computed tomography and colonoscopy were included. RESULTS: A total of 332 patients were included in the study. The incidence of CRC after a case of uncomplicated acute diverticulitis was 0.8%. The incidence of malignancy was 2.8% in the group of patients with complicated diverticulitis. CONCLUSIONS: This study showed a low risk of CRC after a case of acute diverticulitis and no cases of CRC in patients with uncomplicated diverticulitis without clinical symptoms of CRC. This indicates that revising guidelines in regards to follow-up after diverticulitis may be warranted. FUNDING: none. TRIAL REGISTRATION: not relevant.

Circulating Concentrations of C-Type Natriuretic Peptides Increase with Sacubitril/Valsartan Treatment in Healthy Young Men.

BACKGROUND: C-type natriuretic peptide (CNP) is a cardioprotective peptide with high affinity for the ectoenzyme neutral endopeptidase (neprilysin). We aimed to determine whether angiotensin receptor-neprilysin inhibitor treatment acutely affects circulating concentrations of bioactive CNP and its molecular amino-terminal precursor (NT-proCNP). METHODS: We included 9 and 10 healthy young men in 2 randomized crossover trials with sacubitril/valsartan vs control (Trial 1) and sacubitril/valsartan and sitagliptin vs sitagliptin (Trial 2). The participants were randomized to a single dose of sacubitril/valsartan (194/206 mg) or control at the first visit 30 min prior to a standardized meal intake. We obtained blood samples at 12 time points over 5 h and measured plasma concentrations of NT-proCNP in both trials and CNP in Trial 2. RESULTS: NT-proCNP concentrations increased 3.5 h after sacubitril/valsartan treatment, and at 4.5 h concentrations were 42% and 65% higher compared with control in Trial 1 and Trial 2, respectively. The total area under the curve (tAUC)15-270 min was 22% higher (P = 0.007) in Trial 1 and 17% higher with treatment (P = 0.017) in Trial 2. Concentrations of bioactive CNP followed a similar temporal pattern with an increase of 93% at 4.5 h and a 31% higher tAUC15-270 min compared with control (P = 0.001) in Trial 2. CONCLUSIONS: Sacubitril/valsartan augments circulating concentrations of both bioactive CNP and NT-proCNP in healthy young men. The increase in bioactive CNP is most likely caused by de novo synthesis and secretion rather than diminished breakdown through neprilysin inhibition.ClinicalTrials.gov registration number NCT03717688.

Learning a Metric for Multimodal Medical Image Registration without Supervision Based on Cycle Constraints.

Deep learning based medical image registration remains very difficult and often fails to improve over its classical counterparts where comprehensive supervision is not available, in particular for large transformations-including rigid alignment. The use of unsupervised, metric-based registration networks has become popular, but so far no universally applicable similarity metric is available for multimodal medical registration, requiring a trade-off between local contrast-invariant edge features or more global statistical metrics. In this work, we aim to improve over the use of handcrafted metric-based losses. We propose to use synthetic three-way (triangular) cycles that for each pair of images comprise two multimodal transformations to be estimated and one known synthetic monomodal transform. Additionally, we present a robust method for estimating large rigid transformations that is differentiable in end-to-end learning. By minimising the cycle discrepancy and adapting the synthetic transformation to be close to the real geometric difference of the image pairs during training, we successfully tackle intra-patient abdominal CT-MRI registration and reach performance on par with state-of-the-art metric-supervision and classic methods. Cyclic constraints enable the learning of cross-modality features that excel at accurate anatomical alignment of abdominal CT and MRI scans.

A generalizable speech emotion recognition model reveals depression and remission.

OBJECTIVE: Affective disorders are associated with atypical voice patterns; however, automated voice analyses suffer from small sample sizes and untested generalizability on external data. We investigated a generalizable approach to aid clinical evaluation of depression and remission from voice using transfer learning: We train machine learning models on easily accessible non-clinical datasets and test them on novel clinical data in a different language. METHODS: A Mixture of Experts machine learning model was trained to infer happy/sad emotional state using three publicly available emotional speech corpora in German and US English. We examined the model's predictive ability to classify the presence of depression on Danish speaking healthy controls (N = 42), patients with first-episode major depressive disorder (MDD) (N = 40), and the subset of the same patients who entered remission (N = 25) based on recorded clinical interviews. The model was evaluated on raw, de-noised, and speaker-diarized data. RESULTS: The model showed separation between healthy controls and depressed patients at the first visit, obtaining an AUC of 0.71. Further, speech from patients in remission was indistinguishable from that of the control group. Model predictions were stable throughout the interview, suggesting that 20-30 s of speech might be enough to accurately screen a patient. Background noise (but not speaker diarization) heavily impacted predictions. CONCLUSION: A generalizable speech emotion recognition model can effectively reveal changes in speaker depressive states before and after remission in patients with MDD. Data collection settings and data cleaning are crucial when considering automated voice analysis for clinical purposes.