OBJECTIVE:Regular imaging by conventional radiography to assess for joint damage is a cornerstone in the management of rheumatoid arthritis. Scoring systems to quantify such damage, such as the widely used Sharp/van der Heijde (SvdH) score, are limited by the requirement of time and experienced staff as well as intra- and interrater variability. To alleviate these problems, autoscoRA, a fully automated scoring system to assign SvdH scores to radiographs of the hands and feet was developed. METHODS:Using the hitherto largest data set of adult patients with rheumatoid arthritis, autoscoRA, a deep learning-based system, was trained to automatically perform joint extraction and scoring of joint space narrowing and bone erosion. RESULTS:The data set included 769 patients (155 of whom were in the test set) with 3,437 visits (707) and 12,144 radiographs (2,507). The model reached excellent agreement with a human scorer for joint space narrowing, erosion, and combined scores both on the joint level and for summed total SvdH scores (intraclass correlation 0.9). On a subset of data scored by a second human reader, the model outperformed the former in terms of agreement with the first human reader. In addition, autoscoRA demonstrated good agreement with a human reader for detecting longitudinal progression of joint damage across different SvdH score cutoffs defining the presence of progression (average agreement of 70%). CONCLUSION:Automated systems like autoscoRA could be used to facilitate scoring of radiographic joint damage in clinical trials, registries, and observational studies, and, eventually, routine clinical care.

Objectives It has recently become possible to assess lung vascular and parenchymal changes quantitatively in thoracic CT images using automated software tools. We investigated the vessel parameters of patients with SSc, quantified by CT imaging, and correlated them with interstitial lung disease (ILD) features. Methods SSc patients undergoing standard of care pulmonary function testing and CT evaluation were retrospectively evaluated. CT images were analysed for ILD patterns and total pulmonary vascular volume (PVV) extents with Imbio lung texture analysis. Vascular analysis (volumes, numbers and densities of vessels, separating arteries and veins) was performed with an in-house developed software. A threshold of 5% ILD extent was chosen to define the presence of ILD, and commonly used cut-offs of lung function were adopted. Results A total of 79 patients [52 women, 40 ILD, mean age 56.2 (s.d. 14.2) years, total ILD extent 9.5 (10.7)%, PVV/lung volume % 2.8%] were enrolled. Vascular parameters for total and separated PVV significantly correlated with functional parameters and ILD pattern extents. SSc-associated ILD (SSc-ILD) patients presented with an increased number and volume of arterial vessels, in particular those between 2 and 4 mm of diameter, and with a higher density of arteries and veins of <6 mm in diameter. Considering radiological and functional criteria concomitantly, as well as the descriptive trends from the longitudinal evaluations, the normalized PVVs, vessel numbers and densities increased progressively with the increase/worsening of ILD extent and functional impairment. Conclusion In SSc patients CT vessel parameters increase in parallel with ILD extent and functional impairment, and may represent a biomarker of SSc-ILD severity.

Cardiac digital twins (Cardiac Digital Twin (CDT)s) of human electrophysiology (Electrophysiology (EP)) are digital replicas of patient hearts derived from clinical data that match like-for-like all available clinical observations. Due to their inherent predictive potential, CDTs show high promise as a complementary modality aiding in clinical decision making and also in the cost-effective, safe and ethical testing of novel EP device therapies. However, current workflows for both the anatomical and functional twinning phases within CDT generation, referring to the inference of model anatomy and parameters from clinical data, are not sufficiently efficient, robust and accurate for advanced clinical and industrial applications. Our study addresses three primary limitations impeding the routine generation of high-fidelity CDTs by introducing; a comprehensive parameter vector encapsulating all factors relating to the ventricular EP; an abstract reference frame within the model allowing the unattended manipulation of model parameter fields; a novel fast-forward electrocardiogram (Electrocardiogram (ECG)) model for efficient and bio-physically-detailed simulation required for parameter inference. A novel workflow for the generation of CDTs is then introduced as an initial proof of concept. Anatomical twinning was performed within a reasonable time compatible with clinical workflows (<4h) for 12 subjects from clinically-attained magnetic resonance images. After assessment of the underlying fast forward ECG model against a gold standard bidomain ECG model, functional twinning of optimal parameters according to a clinically-attained 12 lead ECG was then performed using a forward Saltelli sampling approach for a single subject. The achieved results in terms of efficiency and fidelity demonstrate that our workflow is well-suited and viable for generating biophysically-detailed CDTs at scale.

Automatic segmentation of abdominal organs in CT scans plays an important role in clinical practice. However, most existing benchmarks and datasets only focus on segmentation accuracy, while the model efficiency and its accuracy on the testing cases from different medical centers have not been evaluated. To comprehensively benchmark abdominal organ segmentation methods, we organized the first Fast and Low GPU memory Abdominal oRgan sEgmentation (FLARE) challenge, where the segmentation methods were encouraged to achieve high accuracy on the testing cases from different medical centers, fast inference speed, and low GPU memory consumption, simultaneously. The winning method surpassed the existing state-of-the-art method, achieving a 19× faster inference speed and reducing the GPU memory consumption by 60% with comparable accuracy. We provide a summary of the top methods, make their code and Docker containers publicly available, and give practical suggestions on building accurate and efficient abdominal organ segmentation models. The FLARE challenge remains open for future submissions through a live platform for benchmarking further methodology developments at https://flare.grand-challenge.org/.

An important factor for the development of spinal degeneration, pain and the outcome of spinal surgery is known to be the balance of the spine. It must be analyzed in an upright, standing position to ensure physiological loading conditions and visualize load-dependent deformations. Despite the complex 3D shape of the spine, this analysis is currently performed using 2D radiographs, as all frequently used 3D imaging techniques require the patient to be scanned in a prone position. To overcome this limitation, we propose a deep neural network to reconstruct the 3D spinal pose in an upright standing position, loaded naturally. Specifically, we propose a novel neural network architecture, which takes orthogonal 2D radiographs and infers the spine’s 3D posture using vertebral shape priors. In this work, we define vertebral shape priors using an atlas and a spine shape prior, incorporating both into our proposed network architecture. We validate our architecture on digitally reconstructed radiographs, achieving a 3D reconstruction Dice of 0.95, indicating an almost perfect 2D-to-3D domain translation. Validating the reconstruction accuracy of a 3D standing spine on real data is infeasible due to the lack of a valid ground truth. Hence, we design a novel experiment for this purpose, using an orientation invariant distance metric, to evaluate our model’s ability to synthesize full-3D, upright, and patient-specific spine models. We compare the synthesized spine shapes from clinical upright standing radiographs to the same patient’s 3D spinal posture in the prone position from CT.

We propose a reinforcement learning (RL) based approach for anatomical landmark localization in medical images, where the agent can move in arbitrary directions with a variable step size. Using a continuous action space reduces the average number of steps required to locate a landmark by more than 30 times compared to localization using discrete actions. Our approach outperforms a state-of-the-art RL method based on a discrete action space and is inline with state-of-the-art supervised regression based methods. Furthermore, we extend our approach to a multi-agent setting, where we allow collaboration between agents to enable learning of the landmarks’ spatial configuration. The results of the multi-agent RL based approach show that the position of occluded landmarks can be successfully estimated based on the relative position predicted for the visible landmarks.

Finite element (FE) biomechanical studies for adolescent idiopathic scoliosis (AIS) treatments will greatly benefit from utilizing true-scale, patient-specific anatomy that accurately characterizes all tissue properties. This study presents a method to automatically generate patient-specific, FE meshes containing volumetric soft tissues, such as ligaments and cartilage, that are inconspicuous in computed tomography (CT) imaging of AIS patients. Convolutional neural network (CNN) derived vertebrae segmentations, obtained from CT scans, provide a foundation for subsequent elastic deformations of ligamentoskeletal, computer-aided designed (CAD) surface meshes, to ascertain patient-specific anatomy, including soft tissue structures. Patient-specific, ligamentoskeletal meshes are then tetrahedralized for use in FE studies. Dice similarity coefficients of 90% and submillimeter Hausdorff distances demonstrate vertebrae and intervertebral disc fitting accuracy of the automatic methodology. In severe AIS cases, when CNN segmentations fail due to overfitting, a semi-automatic step augments the automatic method. The generated FE meshes can provide the basis for biomechanical simulations seeking to correct AIS through bracing, minimally invasive operations, or patient-specific, surgical procedures, like posterior spinal fusion.

In landmark localization, due to ambiguities in defining their exact position, landmark annotations may suffer from large observer variabilities, which result in uncertain annotations. To model the annotation ambiguities of the training dataset, we propose to learn anisotropic Gaussian parameters modeling the shape of the target heatmap during optimization. Furthermore, our method models the prediction uncertainty of individual samples by fitting anisotropic Gaussian functions to the predicted heatmaps during inference. Besides state-of-the-art results, our experiments on datasets of hand radiographs and lateral cephalograms also show that Gaussian functions are correlated with both localization accuracy and observer variability. As a final experiment, we show the importance of integrating the uncertainty into decision making by measuring the influence of the predicted location uncertainty on the classification of anatomical abnormalities in lateral cephalograms.

Even though many semantic segmentation methods exist that are able to perform well on many medical datasets, often, they are not designed for direct use in clinical practice. The two main concerns are generalization to unseen data with a different visual appearance, e.g., images acquired using a different scanner, and efficiency in terms of computation time and required Graphics Processing Unit (GPU) memory. In this work, we employ a multi-organ segmentation model based on the SpatialConfiguration-Net (SCN), which integrates prior knowledge of the spatial configuration among the labelled organs to resolve spurious responses in the network outputs. Furthermore, we modified the architecture of the segmentation model to reduce its memory footprint as much as possible without drastically impacting the quality of the predictions. Lastly, we implemented a minimal inference script for which we optimized both, execution time and required GPU memory.

Vertebral labelling and segmentation are two fundamental tasks in an automated spine processing pipeline. Reliable and accurate processing of spine images is expected to benefit clinical decision-support systems for diagnosis, surgery planning, and population-based analysis on spine and bone health. However, designing automated algorithms for spine processing is challenging predominantly due to considerable variations in anatomy and acquisition protocols and due to a severe shortage of publicly available data. Addressing these limitations, the Large Scale Vertebrae Segmentation Challenge (VerSe) was organised in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2019 and 2020, with a call for algorithms towards labelling and segmentation of vertebrae. Two datasets containing a total of 374 multi-detector CT scans from 355 patients were prepared and 4505 vertebrae have individually been annotated at voxel-level by a human-machine hybrid algorithm (https://osf.io/nqjyw/, https://osf.io/t98fz/). A total of 25 algorithms were benchmarked on these datasets. In this work, we present the the results of this evaluation and further investigate the performance-variation at vertebra-level, scan-level, and at different fields-of-view. We also evaluate the generalisability of the approaches to an implicit domain shift in data by evaluating the top performing algorithms of one challenge iteration on data from the other iteration. The principal takeaway from VerSe: the performance of an algorithm in labelling and segmenting a spine scan hinges on its ability to correctly identify vertebrae in cases of rare anatomical variations. The content and code concerning VerSe can be accessed at: https://github.com/anjany/verse.

: Localization and segmentation of vertebral bodies from spine CT volumes are crucial for pathological diagnosis, surgical planning, and postoperative assessment. However, fully automatic analysis of spine CT volumes is difficult due to the anatomical variation of pathologies, noise caused by screws and implants, and the large range of different field-of-views. We propose a fully automatic coarse to fine approach for vertebrae localization and segmentation based on fully convolutional CNNs. In a three-step approach, at first, a U-Net localizes the rough position of the spine. Then, the SpatialConfiguration-Net performs vertebrae localization and identification using heatmap regression. Finally, a U-Net performs binary segmentation of each identified vertebrae in a high resolution, before merging the individual predictions into the resulting multi-label vertebrae segmentation. The evaluation shows top performance of our approach, ranking first place and winning the MICCAI 2019 Large Scale Vertebrae Segmentation Challenge (VerSe 2019).

In landmark localization, due to ambiguities in defining their exact position, landmark annotations may suffer from both large inter- and intra-observer variabilites, which result in uncertain annotations. Therefore, predicting a single coordinate for a landmark is not sufficient for modeling the distribution of possible landmark locations. We propose to learn the Gaussian covariances of target heatmaps, such that covariances for pointed heatmaps correspond to more certain landmarks and covariances for flat heatmaps to more uncertain or ambiguous landmarks. By fitting Gaussian functions to the predicted heatmaps, our method is able to obtain landmark location distributions, which model location uncertainties. We show on a dataset of left hand radiographs and on a dataset of lateral cephalograms that the predicted uncertainties correlate with the landmark error, as well as inter-observer variabilities.

The treatment of degenerative spinal disorders requires an understanding of the individual spinal anatomy and curvature in 3D. An upright spinal pose (i.e. standing) under natural weight bearing is crucial for such bio-mechanical analysis. 3D volumetric imaging modalities (e.g. CT and MRI) are performed in patients lying down. On the other hand, radiographs are captured in an upright pose, but result in 2D projections. This work aims to integrate the two realms, i.e. it combines the upright spinal curvature from radiographs with the 3D vertebral shape from CT imaging for synthesizing an upright 3D model of spine, loaded naturally. Specifically, we propose a novel neural network architecture working vertebra-wise, termed TransVert, which takes orthogonal 2D radiographs and infers the spine’s 3D posture. We validate our architecture on digitally reconstructed radiographs, achieving a 3D reconstruction Dice of 95.52% , indicating an almost perfect 2D-to-3D domain translation. Deploying our model on clinical radiographs, we successfully synthesise full-3D, upright, patient-specific spine models for the first time .

Additionally to the extensive use in clinical medicine, biological age (BA) in legal medicine is used to assess unknown chronological age (CA) in applications where identification documents are not available. Automatic methods for age estimation proposed in the literature are predicting point estimates, which can be misleading without the quantification of predictive uncertainty. In our multi-factorial age estimation method from MRI data, we used the Variational Inference approach to estimate the uncertainty of a Bayesian CNN model. Distinguishing model uncertainty from data uncertainty, we interpreted data uncertainty as biological variation, i.e. the range of possible CA of subjects having the same BA.

This work is a technical report concerning the Large Scale Vertebrae Segmentation Challenge (VerSe) organised in conjunction with the MICCAI 2019. The challenge set-up consisting of two tasks, vertebrae labelling and vertebrae segmentation, is detailed. A total of 160 multidetector CT scans closely resembling a typical spine-centreed clinical setting were prepared and annotated at voxel-level by a human-machine hybrid algorithm. Both the annotation protocol and the algorithm that aided the medical experts in this annotation process are presented. More importantly, eleven fully automated algorithms of the participating teams were submitted to be benchmarked on the VerSe data. This work presents a detailed performance analysis of these algorithms with the best performing algorithm achieving a vertebrae identification rate of 95% and a Dice coefficient of 90%. VerSe'19 is an open-call challenge and its image data along with the annotations and evaluation tools will continue to be publicly accessible through its online portal.

In many medical image analysis applications, often only a limited amount of training data is available, which makes training of convolutional neural networks (CNNs) challenging. In this work on anatomical landmark localization, we propose a CNN architecture that learns to split the localization task into two simpler sub-problems, reducing the need for large training datasets. Our fully convolutional SpatialConfiguration-Net (SCN) dedicates one component to locally accurate but ambiguous candidate predictions, while the other component improves robustness to ambiguities by incorporating the spatial configuration of landmarks. In our experimental evaluation, we show that the proposed SCN outperforms related methods in terms of landmark localization error on size-limited datasets.

This study aimed to investigate whether quantitative lung vessel morphology determined by a new fully automated algorithm is associated with functional indices in idiopathic pulmonary fibrosis (IPF).

Highly relevant for both clinical and legal medicine applications, the established radiological methods for estimating unknown age in children and adolescents are based on visual examination of bone ossification in X-ray images of the hand. Our group has initiated the development of fully automatic age estimation methods from 3D MRI scans of the hand, in order to simultaneously overcome the problems of the radiological methods including (1) exposure to ionizing radiation, (2) necessity to define new, MRI specific staging systems, and (3) subjective influence of the examiner. The present work provides a theoretical background for understanding the nonlinear regression problem of biological age estimation and chronological age approximation. Based on this theoretical background, we comprehensively evaluate machine learning methods (random forests, deep convolutional neural networks) with different simplifications of the image information used as an input for learning. Trained on a large dataset of 328 MR images, we compare the performance of the different input strategies and demonstrate unprecedented results. For estimating biological age, we obtain a mean absolute error of 0.37 +/- 0.51 years for the age range of the subjects <= 18 years, i.e. where bone ossification has not yet saturated. Finally, we validate our findings by adapting our best performing method to 2D images and applying it to a publicly available dataset of X-ray images, showing that we are in line with the state-of-the-art automatic methods for this task. (C) 2019 The Authors. Published by Elsevier B.V.

Landmark localization is a widely used task required in medical image analysis and computer vision applications. Formulated in a heatmap regression framework, we have recently proposed a CNN architecture that learns on its own to split the localization task into two simpler sub-problems, dedicating one component to locally accurate but ambiguous predictions, while the other component improves robustness by incorporating the spatial configuration of landmarks to remove ambiguities. We learn this simplification in our SpatialConfiguration-Net (SCN) by multiplying the heatmap predictions of its two components and by training the network in and end-to-end manner, thus achieving regularization similar to e.g. a hand-crafted Markov Random Field model. While we have previously shown localization results solely on data from 2D and 3D medical imaging modalities, in this work our aim is to study the generalization capabilities of our SpatialConfiguration-Net to computer vision problems. Therefore, we evaluate our performance both in terms of accuracy and robustness on a facial alignment task, where we improve upon the state-of-the-art methods, as well as on a human body pose estimation task, where we demonstrate results in line with the recent state-of-the-art.

Despite some design limitations, CNNs have been largely adopted by the computer vision community due to their efficacy and versatility. Introduced by Sabour et al. to circumvent some limitations of CNNs, capsules replace scalars with vectors to encode appearance feature representation, allowing better preservation of spatial relationships between whole objects and its parts. They also introduced the dynamic routing mechanism, which allows to weight the contributions of parts to a whole object differently at each inference step. Recently, Hinton et al. have proposed to solely encode pose information to model such part-whole relationships. Additionally, they used a matrix instead of a vector encoding in the capsules framework. In this work, we introduce several improvements to the capsules framework, allowing it to be applied for multi-label semantic segmentation. More specifically, we combine pose and appearance information encoded as matrices into a new type of capsule, i.e. Matwo-Caps. Additionally, we propose a novel routing mechanism, i.e. Dual Routing, which effectively combines these two kinds of information. We evaluate our resulting Matwo-CapsNet on the JSRT chest X-ray dataset by comparing it to SegCaps, a capsule based network for binary segmentation, as well as to other CNN based state-of-the-art segmentation methods, where we show that our Matwo-CapsNet achieves competitive results, while requiring only a fraction of the parameters of other previously proposed methods.