Chromatin jets define the properties of cohesin-driven in vivo loop extrusion.

Complex genomes show intricate organization in three-dimensional (3D) nuclear space. Current models posit that cohesin extrudes loops to form self-interacting domains delimited by the DNA binding protein CTCF. Here, we describe and quantitatively characterize cohesin-propelled, jet-like chromatin contacts as landmarks of loop extrusion in quiescent mammalian lymphocytes. Experimental observations and polymer simulations indicate that narrow origins of loop extrusion favor jet formation. Unless constrained by CTCF, jets propagate symmetrically for 1-2 Mb, providing an estimate for the range of in vivo loop extrusion. Asymmetric CTCF binding deflects the angle of jet propagation as experimental evidence that cohesin-mediated loop extrusion can switch from bi- to unidirectional and is controlled independently in both directions. These data offer new insights into the physiological behavior of in vivo cohesin-mediated loop extrusion and further our understanding of the principles that underlie genome organization.

Virtual reality-empowered deep-learning analysis of brain cells.

Automated detection of specific cells in three-dimensional datasets such as whole-brain light-sheet image stacks is challenging. Here, we present DELiVR, a virtual reality-trained deep-learning pipeline for detecting c-Fos+ cells as markers for neuronal activity in cleared mouse brains. Virtual reality annotation substantially accelerated training data generation, enabling DELiVR to outperform state-of-the-art cell-segmenting approaches. Our pipeline is available in a user-friendly Docker container that runs with a standalone Fiji plugin. DELiVR features a comprehensive toolkit for data visualization and can be customized to other cell types of interest, as we did here for microglia somata, using Fiji for dataset-specific training. We applied DELiVR to investigate cancer-related brain activity, unveiling an activation pattern that distinguishes weight-stable cancer from cancers associated with weight loss. Overall, DELiVR is a robust deep-learning tool that does not require advanced coding skills to analyze whole-brain imaging data in health and disease.

Genetic and functional insights into the fractal structure of the heart.

The inner surfaces of the human heart are covered by a complex network of muscular strands that is thought to be a remnant of embryonic development1,2. The function of these trabeculae in adults and their genetic architecture are unknown. Here we performed a genome-wide association study to investigate image-derived phenotypes of trabeculae using the fractal analysis of trabecular morphology in 18,096 participants of the UK Biobank. We identified 16 significant loci that contain genes associated with haemodynamic phenotypes and regulation of cytoskeletal arborization3,4. Using biomechanical simulations and observational data from human participants, we demonstrate that trabecular morphology is an important determinant of cardiac performance. Through genetic association studies with cardiac disease phenotypes and Mendelian randomization, we find a causal relationship between trabecular morphology and risk of cardiovascular disease. These findings suggest a previously unknown role for myocardial trabeculae in the function of the adult heart, identify conserved pathways that regulate structural complexity and reveal the influence of the myocardial trabeculae on susceptibility to cardiovascular disease.

How AI May Transform Musculoskeletal Imaging.

While musculoskeletal imaging volumes are increasing, there is a relative shortage of subspecialized musculoskeletal radiologists to interpret the studies. Will artificial intelligence (AI) be the solution? For AI to be the solution, the wide implementation of AI-supported data acquisition methods in clinical practice requires establishing trusted and reliable results. This implementation will demand close collaboration between core AI researchers and clinical radiologists. Upon successful clinical implementation, a wide variety of AI-based tools can improve the musculoskeletal radiologist's workflow by triaging imaging examinations, helping with image interpretation, and decreasing the reporting time. Additional AI applications may also be helpful for business, education, and research purposes if successfully integrated into the daily practice of musculoskeletal radiology. The question is not whether AI will replace radiologists, but rather how musculoskeletal radiologists can take advantage of AI to enhance their expert capabilities.

Predictive uncertainty in deep learning-based MR image reconstruction using deep ensembles: Evaluation on the fastMRI data set.

PURPOSE: To estimate pixel-wise predictive uncertainty for deep learning-based MR image reconstruction and to examine the impact of domain shifts and architecture robustness. METHODS: Uncertainty prediction could provide a measure for robustness of deep learning (DL)-based MR image reconstruction from undersampled data. DL methods bear the risk of inducing reconstruction errors like in-painting of unrealistic structures or missing pathologies. These errors may be obscured by visual realism of DL reconstruction and thus remain undiscovered. Furthermore, most methods are task-agnostic and not well calibrated to domain shifts. We propose a strategy that estimates aleatoric (data) and epistemic (model) uncertainty, which entails training a deep ensemble (epistemic) with nonnegative log-likelihood (aleatoric) loss in addition to the conventional applied losses terms. The proposed procedure can be paired with any DL reconstruction, enabling investigations of their predictive uncertainties on a pixel level. Five different architectures were investigated on the fastMRI database. The impact on the examined uncertainty of in-distributional and out-of-distributional data with changes to undersampling pattern, imaging contrast, imaging orientation, anatomy, and pathology were explored. RESULTS: Predictive uncertainty could be captured and showed good correlation to normalized mean squared error. Uncertainty was primarily focused along the aliased anatomies and on hyperintense and hypointense regions. The proposed uncertainty measure was able to detect disease prevalence shifts. Distinct predictive uncertainty patterns were observed for changing network architectures. CONCLUSION: The proposed approach enables aleatoric and epistemic uncertainty prediction for DL-based MR reconstruction with an interpretable examination on a pixel level.

Deep learning for autosegmentation for radiotherapy treatment planning: State-of-the-art and novel perspectives.

The rapid development of artificial intelligence (AI) has gained importance, with many tools already entering our daily lives. The medical field of radiation oncology is also subject to this development, with AI entering all steps of the patient journey. In this review article, we summarize contemporary AI techniques and explore the clinical applications of AI-based automated segmentation models in radiotherapy planning, focusing on delineation of organs at risk (OARs), the gross tumor volume (GTV), and the clinical target volume (CTV). Emphasizing the need for precise and individualized plans, we review various commercial and freeware segmentation tools and also state-of-the-art approaches. Through our own findings and based on the literature, we demonstrate improved efficiency and consistency as well as time savings in different clinical scenarios. Despite challenges in clinical implementation such as domain shifts, the potential benefits for personalized treatment planning are substantial. The integration of mathematical tumor growth models and AI-based tumor detection further enhances the possibilities for refining target volumes. As advancements continue, the prospect of one-stop-shop segmentation and radiotherapy planning represents an exciting frontier in radiotherapy, potentially enabling fast treatment with enhanced precision and individualization.

Retinal small vessel pathology is associated with disease burden in multiple sclerosis.

BACKGROUND: Alterations of the superficial retinal vasculature are commonly observed in multiple sclerosis (MS) and can be visualized through optical coherence tomography angiography (OCTA). OBJECTIVES: This study aimed to examine changes in the retinal vasculature during MS and to integrate findings into current concepts of the underlying pathology. METHODS: In this cross-sectional study, including 259 relapsing-remitting MS patients and 78 healthy controls, we analyzed OCTAs using deep-learning-based segmentation algorithm tools. RESULTS: We identified a loss of small-sized vessels (diameter < 10 µm) in the superficial vascular complex in all MS eyes, irrespective of their optic neuritis (ON) history. This alteration was associated with MS disease burden and appears independent of retinal ganglion cell loss. In contrast, an observed reduction of medium-sized vessels (diameter 10-20 µm) was specific to eyes with a history of ON and was closely linked to ganglion cell atrophy. CONCLUSION: These findings suggest distinct atrophy patterns in retinal vessels in patients with MS. Further studies are necessary to investigate retinal vessel alterations and their underlying pathology in MS.

Recommender-based bone tumour classification with radiographs-a link to the past.

OBJECTIVES: To develop an algorithm to link undiagnosed patients to previous patient histories based on radiographs, and simultaneous classification of multiple bone tumours to enable early and specific diagnosis. MATERIALS AND METHODS: For this retrospective study, data from 2000 to 2021 were curated from our database by two orthopaedic surgeons, a radiologist and a data scientist. Patients with complete clinical and pre-therapy radiographic data were eligible. To ensure feasibility, the ten most frequent primary tumour entities, confirmed histologically or by tumour board decision, were included. We implemented a ResNet and transformer model to establish baseline results. Our method extracts image features using deep learning and then clusters the k most similar images to the target image using a hash-based nearest-neighbour recommender approach that performs simultaneous classification by majority voting. The results were evaluated with precision-at-k, accuracy, precision and recall. Discrete parameters were described by incidence and percentage ratios. For continuous parameters, based on a normality test, respective statistical measures were calculated. RESULTS: Included were data from 809 patients (1792 radiographs; mean age 33.73 ± 18.65, range 3-89 years; 443 men), with Osteochondroma (28.31%) and Ewing sarcoma (1.11%) as the most and least common entities, respectively. The dataset was split into training (80%) and test subsets (20%). For k = 3, our model achieved the highest mean accuracy, precision and recall (92.86%, 92.86% and 34.08%), significantly outperforming state-of-the-art models (54.10%, 55.57%, 19.85% and 62.80%, 61.33%, 23.05%). CONCLUSION: Our novel approach surpasses current models in tumour classification and links to past patient data, leveraging expert insights. CLINICAL RELEVANCE STATEMENT: The proposed algorithm could serve as a vital support tool for clinicians and general practitioners with limited experience in bone tumour classification by identifying similar cases and classifying bone tumour entities. KEY POINTS: • Addressed accurate bone tumour classification using radiographic features. • Model achieved 92.86%, 92.86% and 34.08% mean accuracy, precision and recall, respectively, significantly surpassing state-of-the-art models. • Enhanced diagnosis by integrating prior expert patient assessments.

Development of neonatal brain functional centrality and alterations associated with preterm birth.

Formation of the functional connectome in early life underpins future learning and behavior. However, our understanding of how the functional organization of brain regions into interconnected hubs (centrality) matures in the early postnatal period is limited, especially in response to factors associated with adverse neurodevelopmental outcomes such as preterm birth. We characterized voxel-wise functional centrality (weighted degree) in 366 neonates from the Developing Human Connectome Project. We tested the hypothesis that functional centrality matures with age at scan in term-born babies and is disrupted by preterm birth. Finally, we asked whether neonatal functional centrality predicts general neurodevelopmental outcomes at 18 months. We report an age-related increase in functional centrality predominantly within visual regions and a decrease within the motor and auditory regions in term-born infants. Preterm-born infants scanned at term equivalent age had higher functional centrality predominantly within visual regions and lower measures in motor regions. Functional centrality was not related to outcome at 18 months old. Thus, preterm birth appears to affect functional centrality in regions undergoing substantial development during the perinatal period. Our work raises the question of whether these alterations are adaptive or disruptive and whether they predict neurodevelopmental characteristics that are more subtle or emerge later in life.

Transformer models in biomedicine.

Deep neural networks (DNN) have fundamentally revolutionized the artificial intelligence (AI) field. The transformer model is a type of DNN that was originally used for the natural language processing tasks and has since gained more and more attention for processing various kinds of sequential data, including biological sequences and structured electronic health records. Along with this development, transformer-based models such as BioBERT, MedBERT, and MassGenie have been trained and deployed by researchers to answer various scientific questions originating in the biomedical domain. In this paper, we review the development and application of transformer models for analyzing various biomedical-related datasets such as biomedical textual data, protein sequences, medical structured-longitudinal data, and biomedical images as well as graphs. Also, we look at explainable AI strategies that help to comprehend the predictions of transformer-based models. Finally, we discuss the limitations and challenges of current models, and point out emerging novel research directions.

Single-heartbeat cardiac cine imaging via jointly regularized nonrigid motion-corrected reconstruction.

The aim of the current study was to develop a novel approach for 2D breath-hold cardiac cine imaging from a single heartbeat, by combining cardiac motion-corrected reconstructions and nonrigidly aligned patch-based regularization. Conventional cardiac cine imaging is obtained via motion-resolved reconstructions of data acquired over multiple heartbeats. Here, we achieve single-heartbeat cine imaging by incorporating nonrigid cardiac motion correction into the reconstruction of each cardiac phase, in conjunction with a motion-aligned patch-based regularization. The proposed Motion-Corrected CINE (MC-CINE) incorporates all acquired data into the reconstruction of each (motion-corrected) cardiac phase, resulting in a better posed problem than motion-resolved approaches. MC-CINE was compared with iterative sensitivity encoding (itSENSE) and Extra-Dimensional Golden Angle Radial Sparse Parallel (XD-GRASP) in 14 healthy subjects in terms of image sharpness, reader scoring (range: 1-5) and reader ranking (range: 1-9) of image quality, and single-slice left ventricular assessment. MC-CINE was significantly superior to both itSENSE and XD-GRASP using 20 heartbeats, two heartbeats, and one heartbeat. Iterative SENSE, XD-GRASP, and MC-CINE achieved a sharpness of 74%, 74%, and 82% using 20 heartbeats, and 53%, 66%, and 82% with one heartbeat, respectively. The corresponding results for reader scoring were 4.0, 4.7, and 4.9 with 20 heartbeats, and 1.1, 3.0, and 3.9 with one heartbeat. The corresponding results for reader ranking were 5.3, 7.3, and 8.6 with 20 heartbeats, and 1.0, 3.2, and 5.4 with one heartbeat. MC-CINE using a single heartbeat presented nonsignificant differences in image quality to itSENSE with 20 heartbeats. MC-CINE and XD-GRASP at one heartbeat both presented a nonsignificant negative bias of less than 2% in ejection fraction relative to the reference itSENSE. It was concluded that the proposed MC-CINE significantly improves image quality relative to itSENSE and XD-GRASP, enabling 2D cine from a single heartbeat.

Cortical morphology at birth reflects spatiotemporal patterns of gene expression in the fetal human brain.

Interruption to gestation through preterm birth can significantly impact cortical development and have long-lasting adverse effects on neurodevelopmental outcome. We compared cortical morphology captured by high-resolution, multimodal magnetic resonance imaging (MRI) in n = 292 healthy newborn infants (mean age at birth = 39.9 weeks) with regional patterns of gene expression in the fetal cortex across gestation (n = 156 samples from 16 brains, aged 12 to 37 postconceptional weeks [pcw]). We tested the hypothesis that noninvasive measures of cortical structure at birth mirror areal differences in cortical gene expression across gestation, and in a cohort of n = 64 preterm infants (mean age at birth = 32.0 weeks), we tested whether cortical alterations observed after preterm birth were associated with altered gene expression in specific developmental cell populations. Neonatal cortical structure was aligned to differential patterns of cell-specific gene expression in the fetal cortex. Principal component analysis (PCA) of 6 measures of cortical morphology and microstructure showed that cortical regions were ordered along a principal axis, with primary cortex clearly separated from heteromodal cortex. This axis was correlated with estimated tissue maturity, indexed by differential expression of genes expressed by progenitor cells and neurons, and engaged in stem cell differentiation, neuron migration, and forebrain development. Preterm birth was associated with altered regional MRI metrics and patterns of differential gene expression in glial cell populations. The spatial patterning of gene expression in the developing cortex was thus mirrored by regional variation in cortical morphology and microstructure at term, and this was disrupted by preterm birth. This work provides a framework to link molecular mechanisms to noninvasive measures of cortical development in early life and highlights novel pathways to injury in neonatal populations at increased risk of neurodevelopmental disorder.

SAM-X: sorting algorithm for musculoskeletal x-ray radiography.

OBJECTIVE: To develop a two-phased deep learning sorting algorithm for post-X-ray image acquisition in order to facilitate large musculoskeletal image datasets according to their anatomical entity. METHODS: In total, 42,608 unstructured and pseudonymized radiographs were retrieved from the PACS of a musculoskeletal tumor center. In phase 1, imaging data were sorted into 1000 clusters by a self-supervised model. A human-in-the-loop radiologist assigned weak, semantic labels to all clusters and clusters with the same label were merged. Three hundred thirty-two non-musculoskeletal clusters were discarded. In phase 2, the initial model was modified by "injecting" the identified labels into the self-supervised model to train a classifier. To provide statistical significance, data split and cross-validation were applied. The hold-out test set consisted of 50% external data. To gain insight into the model's predictions, Grad-CAMs were calculated. RESULTS: The self-supervised clustering resulted in a high normalized mutual information of 0.930. The expert radiologist identified 28 musculoskeletal clusters. The modified model achieved a classification accuracy of 96.2% and 96.6% for validation and hold-out test data for predicting the top class, respectively. When considering the top two predicted class labels, an accuracy of 99.7% and 99.6% was accomplished. Grad-CAMs as well as final cluster results underlined the robustness of the proposed method by showing that it focused on similar image regions a human would have considered for categorizing images. CONCLUSION: For efficient dataset building, we propose an accurate deep learning sorting algorithm for classifying radiographs according to their anatomical entity in the assessment of musculoskeletal diseases. KEY POINTS: • Classification of large radiograph datasets according to their anatomical entity. • Paramount importance of structuring vast amounts of retrospective data for modern deep learning applications. • Optimization of the radiological workflow and increase in efficiency as well as decrease of time-consuming tasks for radiologists through deep learning.

Physics-Driven Deep Learning for Computational Magnetic Resonance Imaging: Combining physics and machine learning for improved medical imaging.

Physics-driven deep learning methods have emerged as a powerful tool for computational magnetic resonance imaging (MRI) problems, pushing reconstruction performance to new limits. This article provides an overview of the recent developments in incorporating physics information into learning-based MRI reconstruction. We consider inverse problems with both linear and non-linear forward models for computational MRI, and review the classical approaches for solving these. We then focus on physics-driven deep learning approaches, covering physics-driven loss functions, plug-and-play methods, generative models, and unrolled networks. We highlight domain-specific challenges such as real- and complex-valued building blocks of neural networks, and translational applications in MRI with linear and non-linear forward models. Finally, we discuss common issues and open challenges, and draw connections to the importance of physics-driven learning when combined with other downstream tasks in the medical imaging pipeline.

Prediction of complications and surgery duration in primary TKA with high accuracy using machine learning with arthroplasty-specific data.

PURPOSE: The number of primary total knee arthroplasties (TKA) is expected to rise constantly. For patients and healthcare providers, the early identification of risk factors therefore becomes increasingly fundamental in the context of precision medicine. Others have already investigated the detection of risk factors by conducting literature reviews and applying conventional statistical methods. Since the prediction of events has been moderately accurate, a more comprehensive approach is needed. Machine learning (ML) algorithms have had ample success in many disciplines. However, these methods have not yet had a significant impact in orthopaedic research. The selection of a data source as well as the inclusion of relevant parameters is of utmost importance in this context. In this study, a standardized approach for ML in TKA to predict complications during surgery and an irregular surgery duration using data from two German arthroplasty-specific registries was evaluated. METHODS: The dataset is based on two initiatives of the German Society for Orthopaedics and Orthopaedic Surgery. A problem statement and initial parameters were defined. After screening, cleaning and preparation of these datasets, 864 cases of primary TKA (2016-2019) were gathered. The XGBoost algorithm was chosen and applied with a hyperparameter search, a cross validation and a loss weighting to cope with class imbalance. For final evaluation, several metrics (accuracy, sensitivity, specificity, AUC) were calculated. RESULTS: An accuracy of 92.0%, sensitivity of 34.8%, specificity of 95.8%, and AUC of 78.0% were achieved for predicting complications in primary TKA and 93.4%, 74.0%, 96.3%, and 91.6% for predicting irregular surgery duration, respectively. While traditional statistics (correlation coefficient) could not find any relevant correlation between any two parameters, the feature importance revealed several non-linear outcomes. CONCLUSION: In this study, a feasible ML model to predict outcomes of primary TKA with very promising results was built. Complex correlations between parameters were detected, which could not be recognized by conventional statistical analysis. Arthroplasty-specific data were identified as relevant by the ML model and should be included in future clinical applications. Furthermore, an interdisciplinary interpretation as well as evaluation of the results by a data scientist and an orthopaedic surgeon are of paramount importance. LEVEL OF EVIDENCE: Level IV.

Automatic body part identification in real-world clinical dermatological images using machine learning.

BACKGROUND: Dermatological conditions are prevalent across all population sub-groups. The affected body part is of importance to their diagnosis, therapy, and research. The automatic identification of body parts in dermatological clinical pictures could therefore improve clinical care by providing additional information for clinical decision-making algorithms, discovering hard-to-treat areas, and research by identifying new patterns of disease. PATIENTS AND METHODS: In this study, we used 6,219 labelled dermatological images from our clinical database, which were used to train and validate a convolutional neural network. As a use case, qualitative heatmaps for the body part distribution in common dermatological conditions was generated using this system. RESULTS: The algorithm reached a mean balanced accuracy of 89% (range 74.8%-96.5%). Non-melanoma skin cancer photos were mostly of the face and torso, while hotspots of eczema and psoriasis image distribution included the torso, legs, and hands. CONCLUSIONS: The accuracy of this system is comparable to the best to-date published algorithms for image classification challenges, suggesting this algorithm could boost diagnosis, therapy, and research of dermatological conditions.

Predicting age and clinical risk from the neonatal connectome.

The development of perinatal brain connectivity underpins motor, cognitive and behavioural abilities in later life. Diffusion MRI allows the characterisation of subtle inter-individual differences in structural brain connectivity. Individual brain connectivity maps (connectomes) are by nature high in dimensionality and complex to interpret. Machine learning methods are a powerful tool to uncover properties of the connectome which are not readily visible and can give us clues as to how and why individual developmental trajectories differ. In this manuscript we used Deep Neural Networks and Random Forests to predict demographic and neurodevelopmental characteristics from neonatal structural connectomes in a large sample of babies (n = 524) from the developing Human Connectome Project. We achieved an accurate prediction of post menstrual age (PMA) at scan in term-born infants (mean absolute error (MAE) = 0.72 weeks, r = 0.83 and p < 0.001). We also achieved good accuracy when predicting gestational age at birth in a cohort of term and preterm babies scanned at term equivalent age (MAE = 2.21 weeks, r = 0.82, p < 0.001). We subsequently used sensitivity analysis to obtain feature relevance from our prediction models, with the most important connections for prediction of PMA and GA found to predominantly involve frontal and temporal regions, thalami, and basal ganglia. From our models of PMA at scan for infants born at term, we computed a brain maturation index (predicted age minus actual age) of individual preterm neonates and found a significant correlation between this index and motor outcome at 18 months corrected age. Our results demonstrate the applicability of machine learning techniques in analyses of the neonatal connectome and suggest that a neural substrate of brain maturation with implications for future neurodevelopment is detectable at term equivalent age from the neonatal connectome.

Effects of gestational age at birth on perinatal structural brain development in healthy term-born babies.

Infants born in early term (37-38 weeks gestation) experience slower neurodevelopment than those born at full term (40-41 weeks gestation). While this could be due to higher perinatal morbidity, gestational age at birth may also have a direct effect on the brain. Here we characterise brain volume and white matter correlates of gestational age at birth in healthy term-born neonates and their relationship to later neurodevelopmental outcome using T2 and diffusion weighted MRI acquired in the neonatal period from a cohort (n = 454) of healthy babies born at term age (>37 weeks gestation) and scanned between 1 and 41 days after birth. Images were analysed using tensor-based morphometry and tract-based spatial statistics. Neurodevelopment was assessed at age 18 months using the Bayley Scales of Infant and Toddler Development, Third Edition (Bayley-III). Infants born earlier had higher relative ventricular volume and lower relative brain volume in the deep grey matter, cerebellum and brainstem. Earlier birth was also associated with lower fractional anisotropy, higher mean, axial, and radial diffusivity in major white matter tracts. Gestational age at birth was positively associated with all Bayley-III subscales at age 18 months. Regression models predicting outcome from gestational age at birth were significantly improved after adding neuroimaging features associated with gestational age at birth. This work adds to the body of evidence of the impact of early term birth and highlights the importance of considering the effect of gestational age at birth in future neuroimaging studies including term-born babies.

Applications of machine learning for imaging-driven diagnosis of musculoskeletal malignancies-a scoping review.

Musculoskeletal malignancies are a rare type of cancer. Consequently, sufficient imaging data for machine learning (ML) applications is difficult to obtain. The main purpose of this review was to investigate whether ML is already having an impact on imaging-driven diagnosis of musculoskeletal malignancies and what the respective reasons for this might be. A scoping review was conducted by a radiologist, an orthopaedic surgeon and a data scientist to identify suitable articles based on the PRISMA statement. Studies meeting the following criteria were included: primary malignant musculoskeletal tumours, machine/deep learning application, imaging data or data retrieved from images, human/preclinical, English language and original research. Initially, 480 articles were found and 38 met the eligibility criteria. Several continuous and discrete parameters related to publication, patient distribution, tumour specificities, ML methods, data and metrics were extracted from the final articles. For the synthesis, diagnosis-oriented studies were further examined by retrieving the number of patients and labels and metric scores. No significant correlations between metrics and mean number of samples were found. Several studies presented that ML could support imaging-driven diagnosis of musculoskeletal malignancies in distinct cases. However, data quality and quantity must be increased to achieve clinically relevant results. Compared to the experience of an expert radiologist, the studies used small datasets and mostly included only one type of data. Key to critical advancement of ML models for rare diseases such as musculoskeletal malignancies is a systematic, structured data collection and the establishment of (inter)national networks to obtain substantial datasets in the future. KEY POINTS: • Machine learning does not yet significantly impact imaging-driven diagnosis for musculoskeletal malignancies compared to other disciplines such as lung, breast or CNS cancer. • Research in the area of musculoskeletal tumour imaging and machine learning is still very limited. • Machine learning in musculoskeletal tumour imaging is impeded by insufficient availability of data and rarity of the disease.

Precision measurement of cardiac structure and function in cardiovascular magnetic resonance using machine learning.

BACKGROUND: Measurement of cardiac structure and function from images (e.g. volumes, mass and derived parameters such as left ventricular (LV) ejection fraction [LVEF]) guides care for millions. This is best assessed using cardiovascular magnetic resonance (CMR), but image analysis is currently performed by individual clinicians, which introduces error. We sought to develop a machine learning algorithm for volumetric analysis of CMR images with demonstrably better precision than human analysis. METHODS: A fully automated machine learning algorithm was trained on 1923 scans (10 scanner models, 13 institutions, 9 clinical conditions, 60,000 contours) and used to segment the LV blood volume and myocardium. Performance was quantified by measuring precision on an independent multi-site validation dataset with multiple pathologies with n = 109 patients, scanned twice. This dataset was augmented with a further 1277 patients scanned as part of routine clinical care to allow qualitative assessment of generalization ability by identifying mis-segmentations. Machine learning algorithm ('machine') performance was compared to three clinicians ('human') and a commercial tool (cvi42, Circle Cardiovascular Imaging). FINDINGS: Machine analysis was quicker (20 s per patient) than human (13 min). Overall machine mis-segmentation rate was 1 in 479 images for the combined dataset, occurring mostly in rare pathologies not encountered in training. Without correcting these mis-segmentations, machine analysis had superior precision to three clinicians (e.g. scan-rescan coefficients of variation of human vs machine: LVEF 6.0% vs 4.2%, LV mass 4.8% vs. 3.6%; both P < 0.05), translating to a 46% reduction in required trial sample size using an LVEF endpoint. CONCLUSION: We present a fully automated algorithm for measuring LV structure and global systolic function that betters human performance for speed and precision.