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.

Investigating the impact of class-dependent label noise in medical image classification.

Label noise is inevitable in medical image databases developed for deep learning due to the inter-observer variability caused by the different levels of expertise of the experts annotating the images, and, in some cases, the automated methods that generate labels from medical reports. It is known that incorrect annotations or label noise can degrade the actual performance of supervised deep learning models and can bias the model's evaluation. Existing literature show that noise in one class has minimal impact on the model's performance for another class in natural image classification problems where different target classes have a relatively distinct shape and share minimal visual cues for knowledge transfer among the classes. However, it is not clear how class-dependent label noise affects the model's performance when operating on medical images, for which different output classes can be difficult to distinguish even for experts, and there is a high possibility of knowledge transfer across classes during the training period. We hypothesize that for medical image classification tasks where the different classes share a very similar shape with differences only in texture, the noisy label for one class might affect the performance across other classes, unlike the case when the target classes have different shapes and are visually distinct. In this paper, we study this hypothesis using two publicly available datasets: a 2D organ classification dataset with target organ classes being visually distinct, and a histopathology image classification dataset where the target classes look very similar visually. Our results show that the label noise in one class has a much higher impact on the model's performance on other classes for the histopathology dataset compared to the organ dataset.

Challenges of deep learning methods for COVID-19 detection using public datasets.

Since the COVID-19 pandemic, several research studies have proposed Deep Learning (DL)-based automated COVID-19 detection, reporting high cross-validation accuracy when classifying COVID-19 patients from normal or other common Pneumonia. Although the reported outcomes are very high in most cases, these results were obtained without an independent test set from a separate data source(s). DL models are likely to overfit training data distribution when independent test sets are not utilized or are prone to learn dataset-specific artifacts rather than the actual disease characteristics and underlying pathology. This study aims to assess the promise of such DL methods and datasets by investigating the key challenges and issues by examining the compositions of the available public image datasets and designing different experimental setups. A convolutional neural network-based network, called CVR-Net (COVID-19 Recognition Network), has been proposed for conducting comprehensive experiments to validate our hypothesis. The presented end-to-end CVR-Net is a multi-scale-multi-encoder ensemble model that aggregates the outputs from two different encoders and their different scales to convey the final prediction probability. Three different classification tasks, such as 2-, 3-, 4-classes, are designed where the train-test datasets are from the single, multiple, and independent sources. The obtained binary classification accuracy is 99.8% for a single train-test data source, where the accuracies fall to 98.4% and 88.7% when multiple and independent train-test data sources are utilized. Similar outcomes are noticed in multi-class categorization tasks for single, multiple, and independent data sources, highlighting the challenges in developing DL models with the existing public datasets without an independent test set from a separate dataset. Such a result concludes a requirement for a better-designed dataset for developing DL tools applicable in actual clinical settings. The dataset should have an independent test set; for a single machine or hospital source, have a more balanced set of images for all the prediction classes; and have a balanced dataset from several hospitals and demography. Our source codes and model are publicly available for the research community for further improvements.

Machine-Learning-Assisted Analysis of Colorimetric Assays on Paper Analytical Devices.

Paper-based analytical devices (PADs) employing colorimetric detection and smartphone images have gained wider acceptance in a variety of measurement applications. PADs are primarily meant to be used in field settings where assay and imaging conditions greatly vary, resulting in less accurate results. Recently, machine-learning (ML)-assisted models have been used in image analysis. We evaluated a combination of four ML models-logistic regression, support vector machine (SVM), random forest, and artificial neural network (ANN)-as well as three image color spaces, RGB, HSV, and LAB, for their ability to accurately predict analyte concentrations. We used images of PADs taken at varying lighting conditions, with different cameras and users for food color and enzyme inhibition assays to create training and test datasets. The prediction accuracy was higher for food color than enzyme inhibition assays in most of the ML models and color space combinations. All models better predicted coarse-level classifications than fine-grained concentration classes. ML models using the sample color along with a reference color increased the models' ability to predict the result in which the reference color may have partially factored out the variation in ambient assay and imaging conditions. The best concentration class prediction accuracy obtained for food color was 0.966 when using the ANN model and LAB color space. The accuracy for enzyme inhibition assay was 0.908 when using the SVM model and LAB color space. Appropriate models and color space combinations can be useful to analyze large numbers of samples on PADs as a powerful low-cost quick field-testing tool.

Evaluation and comparison of accurate automated spinal curvature estimation algorithms with spinal anterior-posterior X-Ray images: The AASCE2019 challenge.

Scoliosis is a common medical condition, which occurs most often during the growth spurt just before puberty. Untreated Scoliosis may cause long-term sequelae. Therefore, accurate automated quantitative estimation of spinal curvature is an important task for the clinical evaluation and treatment planning of Scoliosis. A couple of attempts have been made for automated Cobb angle estimation on single-view x-rays. It is very challenging to achieve a highly accurate automated estimation of Cobb angles because it is difficult to utilize x-rays efficiently. With the idea of developing methods for accurate automated spinal curvature estimation, AASCE2019 challenge provides spinal anterior-posterior x-ray images with manual labels for training and testing the participating methods. We review eight top-ranked methods from 12 teams. Experimental results show that overall the best performing method achieved a symmetric mean absolute percentage (SMAPE) of 21.71%. Limitations and possible future directions are also described in the paper. We hope the dataset in AASCE2019 and this paper could provide insights into quantitative measurement of the spine.

COVID-19 control strategies and intervention effects in resource limited settings: A modeling study.

INTRODUCTION: Many countries with weaker health systems are struggling to put together a coherent strategy against the COVID-19 epidemic. We explored COVID-19 control strategies that could offer the greatest benefit in resource limited settings. METHODS: Using an age-structured SEIR model, we explored the effects of COVID-19 control interventions-a lockdown, physical distancing measures, and active case finding (testing and isolation, contact tracing and quarantine)-implemented individually and in combination to control a hypothetical COVID-19 epidemic in Kathmandu (population 2.6 million), Nepal. RESULTS: A month-long lockdown will delay peak demand for hospital beds by 36 days, as compared to a base scenario of no intervention (peak demand at 108 days (IQR 97-119); a 2 month long lockdown will delay it by 74 days, without any difference in annual mortality, or healthcare demand volume. Year-long physical distancing measures will reduce peak demand to 36% (IQR 23%-46%) and annual morality to 67% (IQR 48%-77%) of base scenario. Following a month long lockdown with ongoing physical distancing measures and an active case finding intervention that detects 5% of the daily infection burden could reduce projected morality and peak demand by more than 99%. CONCLUSION: Limited resource settings are best served by a combination of early and aggressive case finding with ongoing physical distancing measures to control the COVID-19 epidemic. A lockdown may be helpful until combination interventions can be put in place but is unlikely to reduce annual mortality or healthcare demand.

3-D Reconstruction in Canonical Co-Ordinate Space From Arbitrarily Oriented 2-D Images.

Limited capture range, and the requirement to provide high quality initialization for optimization-based 2-D/3-D image registration methods, can significantly degrade the performance of 3-D image reconstruction and motion compensation pipelines. Challenging clinical imaging scenarios, which contain significant subject motion, such as fetal in-utero imaging, complicate the 3-D image and volume reconstruction process. In this paper, we present a learning-based image registration method capable of predicting 3-D rigid transformations of arbitrarily oriented 2-D image slices, with respect to a learned canonical atlas co-ordinate system. Only image slice intensity information is used to perform registration and canonical alignment, no spatial transform initialization is required. To find image transformations, we utilize a convolutional neural network architecture to learn the regression function capable of mapping 2-D image slices to a 3-D canonical atlas space. We extensively evaluate the effectiveness of our approach quantitatively on simulated magnetic resonance imaging (MRI), fetal brain imagery with synthetic motion and further demonstrate qualitative results on real fetal MRI data where our method is integrated into a full reconstruction and motion compensation pipeline. Our learning based registration achieves an average spatial prediction error of 7 mm on simulated data and produces qualitatively improved reconstructions for heavily moving fetuses with gestational ages of approximately 20 weeks. Our model provides a general and computationally efficient solution to the 2-D/3-D registration initialization problem and is suitable for real-time scenarios.

Fast Multiple Landmark Localisation Using a Patch-based Iterative Network.

We propose a new Patch-based Iterative Network (PIN) for fast and accurate landmark localisation in 3D medical volumes. PIN utilises a Convolutional Neural Network (CNN) to learn the spatial relationship between an image patch and anatomical landmark positions. During inference, patches are repeatedly passed to the CNN until the estimated landmark position converges to the true landmark location. PIN is computationally efficient since the inference stage only selectively samples a small number of patches in an iterative fashion rather than a dense sampling at every location in the volume. Our approach adopts a multitask learning framework that combines regression and classification to improve localisation accuracy. We extend PIN to localise multiple landmarks by using principal component analysis, which models the global anatomical relationships between landmarks. We have evaluated PIN using 72 3D ultrasound images from fetal screening examinations. PIN achieves quantitatively an average landmark localisation error of 5.59mm and a runtime of 0.44s to predict 10 landmarks per volume. Qualitatively, anatomical 2D standard scan planes derived from the predicted landmark locations are visually similar to the clinical ground truth.

Simulating Longitudinal Brain MRIs with Known Volume Changes and Realistic Variations in Image Intensity.

This paper presents a simulator tool that can simulate large databases of visually realistic longitudinal MRIs with known volume changes. The simulator is based on a previously proposed biophysical model of brain deformation due to atrophy in AD. In this work, we propose a novel way of reproducing realistic intensity variation in longitudinal brain MRIs, which is inspired by an approach used for the generation of synthetic cardiac sequence images. This approach combines a deformation field obtained from the biophysical model with a deformation field obtained by a non-rigid registration of two images. The combined deformation field is then used to simulate a new image with specified atrophy from the first image, but with the intensity characteristics of the second image. This allows to generate the realistic variations present in real longitudinal time-series of images, such as the independence of noise between two acquisitions and the potential presence of variable acquisition artifacts. Various options available in the simulator software are briefly explained in this paper. In addition, the software is released as an open-source repository. The availability of the software allows researchers to produce tailored databases of images with ground truth volume changes; we believe this will help developing more robust brain morphometry tools. Additionally, we believe that the scientific community can also use the software to further experiment with the proposed model, and add more complex models of brain deformation and atrophy generation.

A biophysical model of brain deformation to simulate and analyze longitudinal MRIs of patients with Alzheimer's disease.

We propose a framework for developing a comprehensive biophysical model that could predict and simulate realistic longitudinal MRIs of patients with Alzheimer's disease (AD). The framework includes three major building blocks: i) atrophy generation, ii) brain deformation, and iii) realistic MRI generation. Within this framework, this paper focuses on a detailed implementation of the brain deformation block with a carefully designed biomechanics-based tissue loss model. For a given baseline brain MRI, the model yields a deformation field imposing the desired atrophy at each voxel of the brain parenchyma while allowing the CSF to expand as required to globally compensate for the locally prescribed volume loss. Our approach is inspired by biomechanical principles and involves a system of equations similar to Stokes equations in fluid mechanics but with the presence of a non-zero mass source term. We use this model to simulate longitudinal MRIs by prescribing complex patterns of atrophy. We present experiments that provide an insight into the role of different biomechanical parameters in the model. The model allows simulating images with exactly the same tissue atrophy but with different underlying deformation fields in the image. We explore the influence of different spatial distributions of atrophy on the image appearance and on the measurements of atrophy reported by various global and local atrophy estimation algorithms. We also present a pipeline that allows evaluating atrophy estimation algorithms by simulating longitudinal MRIs from large number of real subject MRIs with complex subject-specific atrophy patterns. The proposed framework could help understand the implications of different model assumptions, regularization choices, and spatial priors for the detection and measurement of brain atrophy from longitudinal brain MRIs.

A biophysical model of shape changes due to atrophy in the brain with Alzheimer's disease.

This paper proposes a model of brain deformation triggered by atrophy in Alzheimer's Disease (AD). We introduce a macroscopic biophysical model assuming that the density of the brain remains constant, hence its volume shrinks when neurons die in AD. The deformation in the brain parenchyma minimizes the elastic strain energy with the prescribed local volume loss. The cerebrospinal fluid (CSF) is modelled differently to allow for fluid readjustments occuring at a much faster time-scale. PDEs describing the model is discretized in staggered grid and solved using Finite Difference Method. We illustrate the power of the model by showing different deformation patterns obtained for the same global atrophy but prescribed in gray matter (GM) or white matter (WM) on a generic atlas MRI, and with a realistic AD simulation on a subject MRI. This well-grounded forward model opens a way to study different hypotheses about the distribution of brain atrophy, and to study its impact on the observed changes in MR images.