Multitask Weakly Supervised Generative Network for MR-US Registration.

Registering pre-operative modalities, such as magnetic resonance imaging or computed tomography, to ultrasound images is crucial for guiding clinicians during surgeries and biopsies. Recently, deep-learning approaches have been proposed to increase the speed and accuracy of this registration problem. However, all of these approaches need expensive supervision from the ultrasound domain. In this work, we propose a multitask generative framework that needs weak supervision only from the pre-operative imaging domain during training. To perform a deformable registration, the proposed framework translates a magnetic resonance image to the ultrasound domain while preserving the structural content. To demonstrate the efficacy of the proposed method, we tackle the registration problem of pre-operative 3D MR to transrectal ultrasonography images as necessary for targeted prostate biopsies. We use an in-house dataset of 600 patients, divided into 540 for training, 30 for validation, and the remaining for testing. An expert manually segmented the prostate in both modalities for validation and test sets to assess the performance of our framework. The proposed framework achieves a 3.58 mm target registration error on the expert-selected landmarks, 89.2% in the Dice score, and 1.81 mm 95th percentile Hausdorff distance on the prostate masks in the test set. Our experiments demonstrate that the proposed generative model successfully translates magnetic resonance images into the ultrasound domain. The translated image contains the structural content and fine details due to an ultrasound-specific two-path design of the generative model. The proposed framework enables training learning-based registration methods while only weak supervision from the pre-operative domain is available.

Metrics reloaded: recommendations for image analysis validation.

Increasing evidence shows that flaws in machine learning (ML) algorithm validation are an underestimated global problem. In biomedical image analysis, chosen performance metrics often do not reflect the domain interest, and thus fail to adequately measure scientific progress and hinder translation of ML techniques into practice. To overcome this, we created Metrics Reloaded, a comprehensive framework guiding researchers in the problem-aware selection of metrics. Developed by a large international consortium in a multistage Delphi process, it is based on the novel concept of a problem fingerprint-a structured representation of the given problem that captures all aspects that are relevant for metric selection, from the domain interest to the properties of the target structure(s), dataset and algorithm output. On the basis of the problem fingerprint, users are guided through the process of choosing and applying appropriate validation metrics while being made aware of potential pitfalls. Metrics Reloaded targets image analysis problems that can be interpreted as classification tasks at image, object or pixel level, namely image-level classification, object detection, semantic segmentation and instance segmentation tasks. To improve the user experience, we implemented the framework in the Metrics Reloaded online tool. Following the convergence of ML methodology across application domains, Metrics Reloaded fosters the convergence of validation methodology. Its applicability is demonstrated for various biomedical use cases.

Understanding metric-related pitfalls in image analysis validation.

Validation metrics are key for tracking scientific progress and bridging the current chasm between artificial intelligence research and its translation into practice. However, increasing evidence shows that, particularly in image analysis, metrics are often chosen inadequately. Although taking into account the individual strengths, weaknesses and limitations of validation metrics is a critical prerequisite to making educated choices, the relevant knowledge is currently scattered and poorly accessible to individual researchers. Based on a multistage Delphi process conducted by a multidisciplinary expert consortium as well as extensive community feedback, the present work provides a reliable and comprehensive common point of access to information on pitfalls related to validation metrics in image analysis. Although focused on biomedical image analysis, the addressed pitfalls generalize across application domains and are categorized according to a newly created, domain-agnostic taxonomy. The work serves to enhance global comprehension of a key topic in image analysis validation.

Understanding metric-related pitfalls in image analysis validation.

Validation metrics are key for the reliable tracking of scientific progress and for bridging the current chasm between artificial intelligence (AI) research and its translation into practice. However, increasing evidence shows that particularly in image analysis, metrics are often chosen inadequately in relation to the underlying research problem. This could be attributed to a lack of accessibility of metric-related knowledge: While taking into account the individual strengths, weaknesses, and limitations of validation metrics is a critical prerequisite to making educated choices, the relevant knowledge is currently scattered and poorly accessible to individual researchers. Based on a multi-stage Delphi process conducted by a multidisciplinary expert consortium as well as extensive community feedback, the present work provides the first reliable and comprehensive common point of access to information on pitfalls related to validation metrics in image analysis. Focusing on biomedical image analysis but with the potential of transfer to other fields, the addressed pitfalls generalize across application domains and are categorized according to a newly created, domain-agnostic taxonomy. To facilitate comprehension, illustrations and specific examples accompany each pitfall. As a structured body of information accessible to researchers of all levels of expertise, this work enhances global comprehension of a key topic in image analysis validation.

Remote Expert DVT Triaging of Novice-User Compression Sonography with AI-Guidance.

BACKGROUND: Compression ultrasonography of the leg is established for triaging proximal lower extremity deep vein thrombosis (DVT). AutoDVT, a machine-learning software, provides a tool for nonspecialists in acquiring compression sequences to be reviewed by an expert for patient triage. The purpose of this study was to test image acquisition and remote triaging in a clinical setting. METHODS: Patients with a suspected DVT were recruited at 2 centers in Germany and Greece. Enrolled patients underwent an artificial intelligence-guided two-point compression examination by a nonspecialist using a handheld ultrasound device prior to a standard scan. Images collected by the software were uploaded for blind review by 5 qualified physicians. All reviewers rated the quality of all sequences on the American College of Emergency Physicians (ACEP) image quality scale (score 1-5, ≥ 3 defined as adequate imaging quality) and for an ACEP score ≥3, chose "Compressible", "Incompressible", or "Other". Sensitivity and specificity were calculated for adequate quality scans with an assessment as "Compressible" or "Incompressible". We define this group as diagnostic quality. To simulate a triaging clinical algorithm, a post hoc analysis was performed merging the "incomplete", the "low quality", and the "Incompressible" into a high-risk group for proximal DVT. RESULTS: Seventy-three patients (average age 64.2 years, 44% females) were eligible for inclusion and scanned by 3 nonultrasound-qualified healthcare professionals. Three patients were excluded from further analysis due to incomplete scans. Sixty two of 70 (88.57%) of the completed scans were judged to be of adequate image quality with an average ACEP score of 3.35. Forty seven of 62 adequate AutoDVT scans were assessed as diagnostic quality, of which 8 were interpreted as positive for proximal DVT by the reviewers resulting in a sensitivity of 100% and specificity of 95.12%. When simulating a triaging algorithm, 34/73 (46.58%) of patients would be triaged as high risk and 8 would be confirmed as positive for proximal DVT (6 in the diagnostic and 2 in the low-quality cohort). Of 39/73 patients triaged as low risk, all were negative for proximal DVT in standard duplex; thus, this triaging algorithm could potentially save 53.42% of standard duplex scans. CONCLUSIONS: Machine learning software was able to aid nonexperts in acquiring valid ultrasound images of venous compressions and allowed remote triaging. This strategy allows faster diagnosis and treatment of high-risk patients and can spare the need for multiple unnecessary duplex scans, the vast majority being negative.

Prenatal diagnosis of hypoplastic left heart syndrome on ultrasound using artificial intelligence: How does performance compare to a current screening programme?

BACKGROUND: Artificial intelligence (AI) has the potential to improve prenatal detection of congenital heart disease. We analysed the performance of the current national screening programme in detecting hypoplastic left heart syndrome (HLHS) to compare with our own AI model. METHODS: Current screening programme performance was calculated from local and national sources. AI models were trained using four-chamber ultrasound views of the fetal heart, using a ResNet classifier. RESULTS: Estimated current fetal screening programme sensitivity and specificity for HLHS were 94.3% and 99.985%, respectively. Depending on calibration, AI models to detect HLHS were either highly sensitive (sensitivity 100%, specificity 94.0%) or highly specific (sensitivity 93.3%, specificity 100%). Our analysis suggests that our highly sensitive model would generate 45,134 screen positive results for a gain of 14 additional HLHS cases. Our highly specific model would be associated with two fewer detected HLHS cases, and 118 fewer false positives. CONCLUSION: If used independently, our AI model performance is slightly worse than the performance level of the current screening programme in detecting HLHS, and this performance is likely to deteriorate further when used prospectively. This demonstrates that collaboration between humans and AI will be key for effective future clinical use.

Fast fetal head compounding from multi-view 3D ultrasound.

The diagnostic value of ultrasound images may be limited by the presence of artefacts, notably acoustic shadows, lack of contrast and localised signal dropout. Some of these artefacts are dependent on probe orientation and scan technique, with each image giving a distinct, partial view of the imaged anatomy. In this work, we propose a novel method to fuse the partially imaged fetal head anatomy, acquired from numerous views, into a single coherent 3D volume of the full anatomy. Firstly, a stream of freehand 3D US images is acquired using a single probe, capturing as many different views of the head as possible. The imaged anatomy at each time-point is then independently aligned to a canonical pose using a recurrent spatial transformer network, making our approach robust to fast fetal and probe motion. Secondly, images are fused by averaging only the most consistent and salient features from all images, producing a more detailed compounding, while minimising artefacts. We evaluated our method quantitatively and qualitatively, using image quality metrics and expert ratings, yielding state of the art performance in terms of image quality and robustness to misalignments. Being online, fast and fully automated, our method shows promise for clinical use and deployment as a real-time tool in the fetal screening clinic, where it may enable unparallelled insight into the shape and structure of the face, skull and brain.

Video-Based Activity Recognition for Automated Motor Assessment of Parkinson's Disease.

Over the last decade, video-enabled mobile devices have become ubiquitous, while advances in markerless pose estimation allow an individual's body position to be tracked accurately and efficiently across the frames of a video. Previous work by this and other groups has shown that pose-extracted kinematic features can be used to reliably measure motor impairment in Parkinson's disease (PD). This presents the prospect of developing an asynchronous and scalable, video-based assessment of motor dysfunction. Crucial to this endeavour is the ability to automatically recognise the class of an action being performed, without which manual labelling is required. Representing the evolution of body joint locations as a spatio-temporal graph, we implement a deep-learning model for video and frame-level classification of activities performed according to part 3 of the Movement Disorder Society Unified PD Rating Scale (MDS-UPDRS). We train and validate this system using a dataset of n = 7310 video clips, recorded at 5 independent sites. This approach reaches human-level performance in detecting and classifying periods of activity within monocular video clips. Our framework could support clinical workflows and patient care at scale through applications such as quality monitoring of clinical data collection, automated labelling of video streams, or a module within a remote self-assessment system.

Placenta segmentation in ultrasound imaging: Addressing sources of uncertainty and limited field-of-view.

Automatic segmentation of the placenta in fetal ultrasound (US) is challenging due to the (i) high diversity of placenta appearance, (ii) the restricted quality in US resulting in highly variable reference annotations, and (iii) the limited field-of-view of US prohibiting whole placenta assessment at late gestation. In this work, we address these three challenges with a multi-task learning approach that combines the classification of placental location (e.g., anterior, posterior) and semantic placenta segmentation in a single convolutional neural network. Through the classification task the model can learn from larger and more diverse datasets while improving the accuracy of the segmentation task in particular in limited training set conditions. With this approach we investigate the variability in annotations from multiple raters and show that our automatic segmentations (Dice of 0.86 for anterior and 0.83 for posterior placentas) achieve human-level performance as compared to intra- and inter-observer variability. Lastly, our approach can deliver whole placenta segmentation using a multi-view US acquisition pipeline consisting of three stages: multi-probe image acquisition, image fusion and image segmentation. This results in high quality segmentation of larger structures such as the placenta in US with reduced image artifacts which are beyond the field-of-view of single probes.

CortexODE: Learning Cortical Surface Reconstruction by Neural ODEs.

We present CortexODE, a deep learning framework for cortical surface reconstruction. CortexODE leverages neural ordinary differential equations (ODEs) to deform an input surface into a target shape by learning a diffeomorphic flow. The trajectories of the points on the surface are modeled as ODEs, where the derivatives of their coordinates are parameterized via a learnable Lipschitz-continuous deformation network. This provides theoretical guarantees for the prevention of self-intersections. CortexODE can be integrated to an automatic learning-based pipeline, which reconstructs cortical surfaces efficiently in less than 5 seconds. The pipeline utilizes a 3D U-Net to predict a white matter segmentation from brain Magnetic Resonance Imaging (MRI) scans, and further generates a signed distance function that represents an initial surface. Fast topology correction is introduced to guarantee homeomorphism to a sphere. Following the isosurface extraction step, two CortexODE models are trained to deform the initial surface to white matter and pial surfaces respectively. The proposed pipeline is evaluated on large-scale neuroimage datasets in various age groups including neonates (25-45 weeks), young adults (22-36 years) and elderly subjects (55-90 years). Our experiments demonstrate that the CortexODE-based pipeline can achieve less than 0.2mm average geometric error while being orders of magnitude faster compared to conventional processing pipelines.

ParaDime: A Framework for Parametric Dimensionality Reduction.

ParaDime is a framework for parametric dimensionality reduction (DR). In parametric DR, neural networks are trained to embed high-dimensional data items in a low-dimensional space while minimizing an objective function. ParaDime builds on the idea that the objective functions of several modern DR techniques result from transformed inter-item relationships. It provides a common interface for specifying these relations and transformations and for defining how they are used within the losses that govern the training process. Through this interface, ParaDime unifies parametric versions of DR techniques such as metric MDS, t-SNE, and UMAP. It allows users to fully customize all aspects of the DR process. We show how this ease of customization makes ParaDime suitable for experimenting with interesting techniques such as hybrid classification/embedding models and supervised DR. This way, ParaDime opens up new possibilities for visualizing high-dimensional data.

MOOD 2020: A Public Benchmark for Out-of-Distribution Detection and Localization on Medical Images.

Detecting Out-of-Distribution (OoD) data is one of the greatest challenges in safe and robust deployment of machine learning algorithms in medicine. When the algorithms encounter cases that deviate from the distribution of the training data, they often produce incorrect and over-confident predictions. OoD detection algorithms aim to catch erroneous predictions in advance by analysing the data distribution and detecting potential instances of failure. Moreover, flagging OoD cases may support human readers in identifying incidental findings. Due to the increased interest in OoD algorithms, benchmarks for different domains have recently been established. In the medical imaging domain, for which reliable predictions are often essential, an open benchmark has been missing. We introduce the Medical-Out-Of-Distribution-Analysis-Challenge (MOOD) as an open, fair, and unbiased benchmark for OoD methods in the medical imaging domain. The analysis of the submitted algorithms shows that performance has a strong positive correlation with the perceived difficulty, and that all algorithms show a high variance for different anomalies, making it yet hard to recommend them for clinical practice. We also see a strong correlation between challenge ranking and performance on a simple toy test set, indicating that this might be a valuable addition as a proxy dataset during anomaly detection algorithm development.

Video Summarization Through Reinforcement Learning With a 3D Spatio-Temporal U-Net.

Intelligent video summarization algorithms allow to quickly convey the most relevant information in videos through the identification of the most essential and explanatory content while removing redundant video frames. In this paper, we introduce the 3DST-UNet-RL framework for video summarization. A 3D spatio-temporal U-Net is used to efficiently encode spatio-temporal information of the input videos for downstream reinforcement learning (RL). An RL agent learns from spatio-temporal latent scores and predicts actions for keeping or rejecting a video frame in a video summary. We investigate if real/inflated 3D spatio-temporal CNN features are better suited to learn representations from videos than commonly used 2D image features. Our framework can operate in both, a fully unsupervised mode and a supervised training mode. We analyse the impact of prescribed summary lengths and show experimental evidence for the effectiveness of 3DST-UNet-RL on two commonly used general video summarization benchmarks. We also applied our method on a medical video summarization task. The proposed video summarization method has the potential to save storage costs of ultrasound screening videos as well as to increase efficiency when browsing patient video data during retrospective analysis or audit without loosing essential information.

PRETUS: A plug-in based platform for real-time ultrasound imaging research.

We present PRETUS - a Plugin-based Real Time UltraSound software platform for live ultrasound image analysis and operator support. The software is lightweight; functionality is brought in via independent plug-ins that can be arranged in sequence. The software allows to capture the real-time stream of ultrasound images from virtually any ultrasound machine, applies computational methods and visualizes the results on-the-fly. Plug-ins can run concurrently without blocking each other. They can be implemented in C++ and Python. A graphical user interface can be implemented for each plug-in, and presented to the user in a compact way. The software is free and open source, and allows for rapid prototyping and testing of real-time ultrasound imaging methods in a manufacturer-agnostic fashion. The software is provided with input, output and processing plug-ins, as well as with tutorials to illustrate how to develop new plug-ins for PRETUS.

Exploring a new paradigm for the fetal anomaly ultrasound scan: Artificial intelligence in real time.

OBJECTIVE: Advances in artificial intelligence (AI) have demonstrated potential to improve medical diagnosis. We piloted the end-to-end automation of the mid-trimester screening ultrasound scan using AI-enabled tools. METHODS: A prospective method comparison study was conducted. Participants had both standard and AI-assisted US scans performed. The AI tools automated image acquisition, biometric measurement, and report production. A feedback survey captured the sonographers' perceptions of scanning. RESULTS: Twenty-three subjects were studied. The average time saving per scan was 7.62 min (34.7%) with the AI-assisted method (p < 0.0001). There was no difference in reporting time. There were no clinically significant differences in biometric measurements between the two methods. The AI tools saved a satisfactory view in 93% of the cases (four core views only), and 73% for the full 13 views, compared to 98% for both using the manual scan. Survey responses suggest that the AI tools helped sonographers to concentrate on image interpretation by removing disruptive tasks. CONCLUSION: Separating freehand scanning from image capture and measurement resulted in a faster scan and altered workflow. Removing repetitive tasks may allow more attention to be directed identifying fetal malformation. Further work is required to improve the image plane detection algorithm for use in real time.

Non-invasive diagnosis of deep vein thrombosis from ultrasound imaging with machine learning.

Deep vein thrombosis (DVT) is a blood clot most commonly found in the leg, which can lead to fatal pulmonary embolism (PE). Compression ultrasound of the legs is the diagnostic gold standard, leading to a definitive diagnosis. However, many patients with possible symptoms are not found to have a DVT, resulting in long referral waiting times for patients and a large clinical burden for specialists. Thus, diagnosis at the point of care by non-specialists is desired. We collect images in a pre-clinical study and investigate a deep learning approach for the automatic interpretation of compression ultrasound images. Our method provides guidance for free-hand ultrasound and aids non-specialists in detecting DVT. We train a deep learning algorithm on ultrasound videos from 255 volunteers and evaluate on a sample size of 53 prospectively enrolled patients from an NHS DVT diagnostic clinic and 30 prospectively enrolled patients from a German DVT clinic. Algorithmic DVT diagnosis performance results in a sensitivity within a 95% CI range of (0.82, 0.94), specificity of (0.70, 0.82), a positive predictive value of (0.65, 0.89), and a negative predictive value of (0.99, 1.00) when compared to the clinical gold standard. To assess the potential benefits of this technology in healthcare we evaluate the entire clinical DVT decision algorithm and provide cost analysis when integrating our approach into diagnostic pathways for DVT. Our approach is estimated to generate a positive net monetary benefit at costs up to £72 to £175 per software-supported examination, assuming a willingness to pay of £20,000/QALY.

A survey on active learning and human-in-the-loop deep learning for medical image analysis.

Fully automatic deep learning has become the state-of-the-art technique for many tasks including image acquisition, analysis and interpretation, and for the extraction of clinically useful information for computer-aided detection, diagnosis, treatment planning, intervention and therapy. However, the unique challenges posed by medical image analysis suggest that retaining a human end-user in any deep learning enabled system will be beneficial. In this review we investigate the role that humans might play in the development and deployment of deep learning enabled diagnostic applications and focus on techniques that will retain a significant input from a human end user. Human-in-the-Loop computing is an area that we see as increasingly important in future research due to the safety-critical nature of working in the medical domain. We evaluate four key areas that we consider vital for deep learning in the clinical practice: (1) Active Learning to choose the best data to annotate for optimal model performance; (2) Interaction with model outputs - using iterative feedback to steer models to optima for a given prediction and offering meaningful ways to interpret and respond to predictions; (3) Practical considerations - developing full scale applications and the key considerations that need to be made before deployment; (4) Future Prospective and Unanswered Questions - knowledge gaps and related research fields that will benefit human-in-the-loop computing as they evolve. We offer our opinions on the most promising directions of research and how various aspects of each area might be unified towards common goals.

Federated deep learning for detecting COVID-19 lung abnormalities in CT: a privacy-preserving multinational validation study.

Data privacy mechanisms are essential for rapidly scaling medical training databases to capture the heterogeneity of patient data distributions toward robust and generalizable machine learning systems. In the current COVID-19 pandemic, a major focus of artificial intelligence (AI) is interpreting chest CT, which can be readily used in the assessment and management of the disease. This paper demonstrates the feasibility of a federated learning method for detecting COVID-19 related CT abnormalities with external validation on patients from a multinational study. We recruited 132 patients from seven multinational different centers, with three internal hospitals from Hong Kong for training and testing, and four external, independent datasets from Mainland China and Germany, for validating model generalizability. We also conducted case studies on longitudinal scans for automated estimation of lesion burden for hospitalized COVID-19 patients. We explore the federated learning algorithms to develop a privacy-preserving AI model for COVID-19 medical image diagnosis with good generalization capability on unseen multinational datasets. Federated learning could provide an effective mechanism during pandemics to rapidly develop clinically useful AI across institutions and countries overcoming the burden of central aggregation of large amounts of sensitive data.