Deep learning-based classification of erosion, synovitis and osteitis in hand MRI of patients with inflammatory arthritis.

OBJECTIVES: To train, test and validate the performance of a convolutional neural network (CNN)-based approach for the automated assessment of bone erosions, osteitis and synovitis in hand MRI of patients with inflammatory arthritis. METHODS: Hand MRIs (coronal T1-weighted, T2-weighted fat-suppressed, T1-weighted fat-suppressed contrast-enhanced) of rheumatoid arthritis (RA) and psoriatic arthritis (PsA) patients from the rheumatology department of the Erlangen University Hospital were assessed by two expert rheumatologists using the Outcome Measures in Rheumatology-validated RA MRI Scoring System and PsA MRI Scoring System scores and were used to train, validate and test CNNs to automatically score erosions, osteitis and synovitis. Scoring performance was compared with human annotations in terms of macro-area under the receiver operating characteristic curve (AUC) and balanced accuracy using fivefold cross-validation. Validation was performed on an independent dataset of MRIs from a second patient cohort. RESULTS: In total, 211 MRIs from 112 patients (14 906 region of interests (ROIs)) were included for training/internal validation using cross-validation and 220 MRIs from 75 patients (11 040 ROIs) for external validation of the networks. The networks achieved high mean (SD) macro-AUC of 92%±1% for erosions, 91%±2% for osteitis and 85%±2% for synovitis. Compared with human annotation, CNNs achieved a high mean Spearman correlation for erosions (90±2%), osteitis (78±8%) and synovitis (69±7%), which remained consistent in the validation dataset. CONCLUSIONS: We developed a CNN-based automated scoring system that allowed a rapid grading of erosions, osteitis and synovitis with good diagnostic accuracy and using less MRI sequences compared with conventional scoring. This CNN-based approach may help develop standardised cost-efficient and time-efficient assessments of hand MRIs for patients with arthritis.

Research priorities for global food security under extreme events.

Extreme events, such as those caused by climate change, economic or geopolitical shocks, and pest or disease epidemics, threaten global food security. The complexity of causation, as well as the myriad ways that an event, or a sequence of events, creates cascading and systemic impacts, poses significant challenges to food systems research and policy alike. To identify priority food security risks and research opportunities, we asked experts from a range of fields and geographies to describe key threats to global food security over the next two decades and to suggest key research questions and gaps on this topic. Here, we present a prioritization of threats to global food security from extreme events, as well as emerging research questions that highlight the conceptual and practical challenges that exist in designing, adopting, and governing resilient food systems. We hope that these findings help in directing research funding and resources toward food system transformations needed to help society tackle major food system risks and food insecurity under extreme events.

A deep image-to-image network organ segmentation algorithm for radiation treatment planning: principles and evaluation.

BACKGROUND: We describe and evaluate a deep network algorithm which automatically contours organs at risk in the thorax and pelvis on computed tomography (CT) images for radiation treatment planning. METHODS: The algorithm identifies the region of interest (ROI) automatically by detecting anatomical landmarks around the specific organs using a deep reinforcement learning technique. The segmentation is restricted to this ROI and performed by a deep image-to-image network (DI2IN) based on a convolutional encoder-decoder architecture combined with multi-level feature concatenation. The algorithm is commercially available in the medical products "syngo.via RT Image Suite VB50" and "AI-Rad Companion Organs RT VA20" (Siemens Healthineers). For evaluation, thoracic CT images of 237 patients and pelvic CT images of 102 patients were manually contoured following the Radiation Therapy Oncology Group (RTOG) guidelines and compared to the DI2IN results using metrics for volume, overlap and distance, e.g., Dice Similarity Coefficient (DSC) and Hausdorff Distance (HD95). The contours were also compared visually slice by slice. RESULTS: We observed high correlations between automatic and manual contours. The best results were obtained for the lungs (DSC 0.97, HD95 2.7 mm/2.9 mm for left/right lung), followed by heart (DSC 0.92, HD95 4.4 mm), bladder (DSC 0.88, HD95 6.7 mm) and rectum (DSC 0.79, HD95 10.8 mm). Visual inspection showed excellent agreements with some exceptions for heart and rectum. CONCLUSIONS: The DI2IN algorithm automatically generated contours for organs at risk close to those by a human expert, making the contouring step in radiation treatment planning simpler and faster. Few cases still required manual corrections, mainly for heart and rectum.

Deep Learning Based Centerline-Aggregated Aortic Hemodynamics: An Efficient Alternative to Numerical Modeling of Hemodynamics.

Image-based patient-specific modelling of hemodynamics are gaining increased popularity as a diagnosis and outcome prediction solution for a variety of cardiovascular diseases. While their potential to improve diagnostic capabilities and thereby clinical outcome is widely recognized, these methods require considerable computational resources since they are mostly based on conventional numerical methods such as computational fluid dynamics (CFD). As an alternative to the numerical methods, we propose a machine learning (ML) based approach to calculate patient-specific hemodynamic parameters. Compared to CFD based methods, our approach holds the benefit of being able to calculate a patient-specific hemodynamic outcome instantly with little need for computational power. In this proof-of-concept study, we present a deep artificial neural network (ANN) capable of computing hemodynamics for patients with aortic coarctation in a centerline aggregated (i.e., locally averaged) form. Considering the complex relation between vessels shape and hemodynamics on the one hand and the limited availability of suitable clinical data on the other, a sufficient accuracy of the ANN may however not be achieved with available data only. Another key aspect of this study is therefore the successful augmentation of available clinical data. Using a statistical shape model, additional training data was generated which substantially increased the ANN's accuracy, showcasing the ability of ML based methods to perform in-silico modelling tasks previously requiring resource intensive CFD simulations.

Child Abuse and Neglect and the Burden of the COVID-19 Pandemic on Families: A Series of Cases Consulted at the German Medical Child Protection Hotline.

Increased stress and decreased resources during a lockdown and social distancing can augment the risk for child abuse and neglect during the COVID-19 pandemic.Health practitioners should continue to be prepared for potentially rising numbers of cases of child abuse and neglect.Child protection services and mental health care should be considered essential and be available for adults and children at all times.

[Reporting "Reasonable Suspicion" of Child Abuse - A Survey among Physicians and Psychotherapists in Germany]. / "Gewichtige Anhaltspunkte" bei Verdacht auf Kindesmisshandlung ­ eine Befragung in Deutschland tätiger Ärzte und Psychotherapeuten.

BACKGROUND: There is evidence that health care professionals are uncertain about the legal framework when suspicion of child abuse or neglect is raised. This could result in inconsistent handling of such cases, putting children at risk in further danger. The present study was intended to provide an empirical basis for examining the knowledge of the legal framework among health care professionals. METHODS: A survey of child and youth physicians, child surgeons, child and adolescent psychiatrists as well as psychotherapists working in Germany was carried out to obtain information on the general conditions. RESULTS: In all occupational groups, a majority of respondents feel insecure about the application of the legal framework on particular cases. Only a minority can correctly reflect the legal regulations of the Federal Child Protection Act ("Bundeskinderschutzgesetz"). Experience with child abuse cases doubled the odds to correctly understanding legal frameworks. Having attended training courses showed no impact. CONCLUSION: There is little knowledge of the legal framework in child protection. There is a need to improve training and provide low-threshold counselling services, especially for professionals with little experience in child protection cases.

[Legal Aspects of Child Protection]. / Rechtliche Aspekte im Kinderschutz.

Legal Aspects of Child Protection Several legal codes (e. g. family, social and criminal law) are of importance in child protection cases in Germany. The intention of legal codes differs between family law (relations between family members), social law (support for families) and criminal law (penal aspects). Mental health professionals have to know the prevailing legal norms concerning child-welfare. Collaborative work between medicine and youth welfare and child protection services (CPS) requires a weighing of data protection issues and the risk for the child. German child protection law provides a stepped model for health care professionals to inform CPS. This includes a careful weighing of the risk for child abuse and own competences to provide support. Medical personnel should be aware of several further legislative regulations concerning child protection issues.

Noninvasive hemodynamic assessment, treatment outcome prediction and follow-up of aortic coarctation from MR imaging.

PURPOSE: Coarctation of the aorta (CoA) is a congenital heart disease characterized by an abnormal narrowing of the proximal descending aorta. Severity of this pathology is quantified by the blood pressure drop (△P) across the stenotic coarctation lesion. In order to evaluate the physiological significance of the preoperative coarctation and to assess the postoperative results, the hemodynamic analysis is routinely performed by measuring the △P across the coarctation site via invasive cardiac catheterization. The focus of this work is to present an alternative, noninvasive measurement of blood pressure drop △P through the introduction of a fast, image-based workflow for personalized computational modeling of the CoA hemodynamics. METHODS: The authors propose an end-to-end system comprised of shape and computational models, their personalization setup using MR imaging, and a fast, noninvasive method based on computational fluid dynamics (CFD) to estimate the pre- and postoperative hemodynamics for coarctation patients. A virtual treatment method is investigated to assess the predictive power of our approach. RESULTS: Automatic thoracic aorta segmentation was applied on a population of 212 3D MR volumes, with mean symmetric point-to-mesh error of 3.00 ± 1.58 mm and average computation time of 8 s. Through quantitative evaluation of 6 CoA patients, good agreement between computed blood pressure drop and catheter measurements is shown: average differences are 2.38 ± 0.82 mm Hg (pre-), 1.10 ± 0.63 mm Hg (postoperative), and 4.99 ± 3.00 mm Hg (virtual stenting), respectively. CONCLUSIONS: The complete workflow is realized in a fast, mostly-automated system that is integrable in the clinical setting. To the best of our knowledge, this is the first time that three different settings (preoperative--severity assessment, poststenting--follow-up, and virtual stenting--treatment outcome prediction) of CoA are investigated on multiple subjects. We believe that in future-given wider clinical validation-our noninvasive in-silico method could replace invasive pressure catheterization for CoA.

6DoF catheter detection, application to intracardiac echocardiography.

Hybrid imaging systems, consisting of fluoroscopy and echocardiography, are increasingly selected for intra-operative support of minimally invasive cardiac interventions. Intracardiac echocardiograpy (ICE) is an emerging modality with the promise of removing sedation or general anesthesia associated with transesophageal echocardiography (TEE). We introduce a novel 6 degrees of freedom (DoF) pose estimation approach for catheters (equipped with radiopaque ball markers) in single X-Ray fluoroscopy projection and investigate the method's application to a prototype ICE catheter. Machine learning based catheter detection is implemented in a Bayesian hypothesis fusion framework, followed by refinement of ball marker locations through template matching. Marker correspondence and 3D pose estimation are solved through iterative optimization. The method registers the ICE volume to the C-arm coordinate system. Experiments are performed on synthetic and porcine in-vivo data. Target registration error (TRE), defined in the echo cone, is the basis of our preliminary evaluation. The method reached 8.06 ± 7.2 mm TRE on 703 cases. Potential uses of our hybrid system include structural heart disease interventions and electrophysiologycal mapping or catheter ablation procedures.

2D/3D registration of TEE probe from two non-orthogonal C-arm directions.

2D/3D registration is a well known technique in medical imaging for combining pre-operative volume data with live fluoroscopy. A common issue of this type of algorithms is that out-of-plane parameters are hard to determine. One solution to overcome this issue is the use of X-ray images from two angulations. However, performing in-plane transformation in one image destroys the registration in the other image, particularly if the angulations are smaller than 90 degrees apart. Our main contribution is the automation of a novel registration approach. It handles translation and rotation of a volume in a way that in-plane parameters are kept invariant and independent of the angle offset between both projections in a double-oblique setting. Our approach yields more robust and partially faster registration results, compared to conventional methods, especially in case of object movement. It was successfully tested on clinical data for fusion of transesophageal ultrasound and X-ray.

Pose-independent surface matching for intra-operative soft-tissue marker-less registration.

One of the main challenges in computer-assisted soft tissue surgery is the registration of multi-modal patient-specific data for enhancing the surgeon's navigation capabilities by observing beyond exposed tissue surfaces. A new approach to marker-less guidance involves capturing the intra-operative patient anatomy with a range image device and doing a shape-based registration. However, as the target organ is only partially visible, typically does not provide salient features and underlies severe non-rigid deformations, surface matching in this context is extremely challenging. Furthermore, the intra-operatively acquired surface data may be subject to severe systematic errors and noise. To address these issues, we propose a new approach to establishing surface correspondences, which can be used to initialize fine surface matching algorithms in the context of intra-operative shape-based registration. Our method does not require any prior knowledge on the relative poses of the input surfaces to each other, does not rely on the detection of prominent surface features, is robust to noise and can be used for overlapping surfaces. It takes into account (1) similarity of feature descriptors, (2) compatibility of multiple correspondence pairs, as well as (3) the spatial configuration of the entire correspondence set. We evaluate the algorithm on time-of-flight (ToF) data from porcine livers in a respiratory liver motion simulator. In all our experiments the alignment computed from the established surface correspondences yields a registration error below 1cm and is thus well suited for initializing fine surface matching algorithms for intra-operative soft-tissue registration.

Real-time ultrasound transducer localization in fluoroscopy images by transfer learning from synthetic training data.

The fusion of image data from trans-esophageal echography (TEE) and X-ray fluoroscopy is attracting increasing interest in minimally-invasive treatment of structural heart disease. In order to calculate the needed transformation between both imaging systems, we employ a discriminative learning (DL) based approach to localize the TEE transducer in X-ray images. The successful application of DL methods is strongly dependent on the available training data, which entails three challenges: (1) the transducer can move with six degrees of freedom meaning it requires a large number of images to represent its appearance, (2) manual labeling is time consuming, and (3) manual labeling has inherent errors. This paper proposes to generate the required training data automatically from a single volumetric image of the transducer. In order to adapt this system to real X-ray data, we use unlabeled fluoroscopy images to estimate differences in feature space density and correct covariate shift by instance weighting. Two approaches for instance weighting, probabilistic classification and Kullback-Leibler importance estimation (KLIEP), are evaluated for different stages of the proposed DL pipeline. An analysis on more than 1900 images reveals that our approach reduces detection failures from 7.3% in cross validation on the test set to zero and improves the localization error from 1.5 to 0.8mm. Due to the automatic generation of training data, the proposed system is highly flexible and can be adapted to any medical device with minimal efforts.

Fast and robust 3D vertebra segmentation using statistical shape models.

We propose a top-down fully automatic 3D vertebra segmentation algorithm using global shape-related as well as local appearance-related prior information. The former is brought into the system by a global statistical shape model built from annotated training data, i.e., annotated CT volumes. The latter is handled by a machine learning-based component, i.e., a boundary detector, providing a strong discriminative model for vertebra surface appearance by making use of local context-encoding features. This boundary detector, which is essentially a probabilistic boosting-tree classifier, is also learnt from annotated training data. Contextual information is taken into account by representing vertebra surface candidate voxels with high-dimensional vectors of 3D steerable features derived from the observed volume intensities. Our system does not only consider the body of the individual vertebrae but also the spinal processes. Before segmentation, the image parts depicting individual vertebrae are spatially normalized with respect to their bounding box information in terms of translation, orientation, and scale leading to more accurate results. We evaluate segmentation accuracy on 7 CT volumes each depicting 22 vertebrae. The results indicate a symmetric point-to-mesh surface error of 1.37 ± 0.37 mm, which matches the current state-of-the-art.

Validation of Fourier decomposition MRI with dynamic contrast-enhanced MRI using visual and automated scoring of pulmonary perfusion in young cystic fibrosis patients.

PURPOSE: To validate Fourier decomposition (FD) magnetic resonance (MR) imaging in cystic fibrosis (CF) patients with dynamic contrast-enhanced (DCE) MR imaging. MATERIALS AND METHODS: Thirty-four CF patients (median age 4.08 years; range 0.16-30) were examined on a 1.5-T MR imager. For FD MR imaging, sets of lung images were acquired using an untriggered two-dimensional balanced steady-state free precession sequence. Perfusion-weighted images were obtained after correction of the breathing displacement and Fourier analysis of the cardiac frequency from the time-resolved data sets. DCE data sets were acquired with a three-dimensional gradient echo sequence. The FD and DCE images were visually assessed for perfusion defects by two readers independently (R1, R2) using a field based scoring system (0-12). Software was used for perfusion impairment evaluation (R3) of segmented lung images using an automated threshold. Both imaging and evaluation methods were compared for agreement and tested for concordance between FD and DCE imaging. RESULTS: Good or acceptable intra-reader agreement was found between FD and DCE for visual and automated scoring: R1 upper and lower limits of agreement (ULA, LLA): 2.72, -2.5; R2: ULA, LLA: ± 2.5; R3: ULA: 1.5, LLA: -2. A high concordance was found between visual and automated scoring (FD: 70-80%, DCE: 73-84%). CONCLUSIONS: FD MR imaging provides equivalent diagnostic information to DCE MR imaging in CF patients. Automated assessment of regional perfusion defects using FD and DCE MR imaging is comparable to visual scoring but allows for percentage-based analysis.

Learning without labeling: domain adaptation for ultrasound transducer localization.

The fusion of image data from trans-esophageal echography (TEE) and X-ray fluoroscopy is attracting increasing interest in minimally-invasive treatment of structural heart disease. In order to calculate the needed transform between both imaging systems, we employ a discriminative learning based approach to localize the TEE transducer in X-ray images. Instead of time-consuming manual labeling, we generate the required training data automatically from a single volumetric image of the transducer. In order to adapt this system to real X-ray data, we use unlabeled fluoroscopy images to estimate differences in feature space density and correct covariate shift by instance weighting. An evaluation on more than 1900 images reveals that our approach reduces detection failures by 95% compared to cross validation on the test set and improves the localization error from 1.5 to 0.8 mm. Due to the automatic generation of training data, the proposed system is highly flexible and can be adapted to any medical device with minimal efforts.

Automatic quantification of subcutaneous and visceral adipose tissue from whole-body magnetic resonance images suitable for large cohort studies.

PURPOSE: To develop an automated method with which to distinguish metabolically different adipose tissues in a large number of subjects using whole-body magnetic resonance imaging (MRI) datasets for improving the understanding of chronic disease risk predictions associated with distinct adipose tissue compartments. MATERIALS AND METHODS: In all, 314 participants were scanned using a 1.5T MRI-scanner with a 2-point Dixon whole-body sequence. Image segmentation was automated using standard image processing techniques and knowledge-based methods. Abdominal adipose tissue was separated into subcutaneous adipose tissue (SAT) and visceral adipose tissue (VAT) by statistical shape models. Bone marrow was removed to provide a more accurate measurement of adipose tissue. To assess segmentation accuracy, ground-truth segmentations in 52 images were performed manually by one operator. Due to the high effort of manual delineation, manual segmentation was limited to seven slices per volume. RESULTS: Volumetric differences were 3.30 ± 2.97% and 6.22 ± 5.28% for SAT and VAT, respectively. The systematic error shows an overestimation of 4.22 ± 7.01% for VAT and 0.37 ± 4.45% for SAT. Coefficients-of-variation from repeated measurements were: 3.50 ± 2.93% for VAT and 0.35 ± 0.26% for SAT. The approach of removing bone marrow worked well in most body regions. Only occasionally the method failed for knees and/or shinbone, which resulted in an overestimation of SAT by 3.14 ± 1.45%. CONCLUSION: We developed a fully automatic process to assess SAT and VAT in whole-body MRI data. The method can support epidemiological studies investigating the relationship between excess body fat and chronic diseases.

Multiplicative Jacobian Energy Decomposition method for fast porous visco-hyperelastic soft tissue model.

Simulating soft tissues in real time is a significant challenge since a compromise between biomechanical accuracy and computational efficiency must be found. In this paper, we propose a new discretization method, the Multiplicative Jacobian Energy Decomposition (MJED) which is an alternative to the classical Galerkin FEM (Finite Element Method) formulation. This method for discretizing non-linear hyperelastic materials on linear tetrahedral meshes leads to faster stiffness matrix assembly for a large variety of isotropic and anisotropic materials. We show that our new approach, implemented within an implicit time integration scheme, can lead to fast and realistic liver deformations including hyperelasticity, porosity and viscosity.

Fast porous visco-hyperelastic soft tissue model for surgery simulation: application to liver surgery.

Understanding and modeling liver biomechanics represents a significant challenge due to its complex nature. In this paper, we tackle this issue in the context of real-time surgery simulation where a compromise between biomechanical accuracy and computational efficiency must be found. We describe a realistic liver model including hyperelasticity, porosity and viscosity that is implemented within an implicit time integration scheme. To optimize its computation, we introduce the Multiplicative Jacobian Energy Decomposition (MJED) method for discretizing hyperelastic materials on linear tetrahedral meshes which leads to faster matrix assembly than the standard Finite Element Method. Visco-hyperelasticity is modeled by Prony series while the mechanical effect of liver perfusion is represented with a linear Darcy law. Dynamic mechanical analysis has been performed on 60 porcine liver samples in order to identify some viscoelastic parameters. Finally, we show that liver deformation can be simulated in real-time on a coarse mesh and study the relative effects of the hyperelastic, viscous and porous components on the liver biomechanics.

Statistical shape models for 3D medical image segmentation: a review.

Statistical shape models (SSMs) have by now been firmly established as a robust tool for segmentation of medical images. While 2D models have been in use since the early 1990 s, wide-spread utilization of three-dimensional models appeared only in recent years, primarily made possible by breakthroughs in automatic detection of shape correspondences. In this article, we review the techniques required to create and employ these 3D SSMs. While we concentrate on landmark-based shape representations and thoroughly examine the most popular variants of Active Shape and Active Appearance models, we also describe several alternative approaches to statistical shape modeling. Structured into the topics of shape representation, model construction, shape correspondence, local appearance models and search algorithms, we present an overview of the current state of the art in the field. We conclude with a survey of applications in the medical field and a discussion of future developments.