Multiple Atlas construction from a heterogeneous brain MR image collection

Kernel-Based Generalized Median Computation for Consensus Learning

Computing a consensus object from a set of given objects is a core problem in machine learning and pattern recognition. One popular approach is to formulate it as an optimization problem using the generalized median. Previous methods like the Prototype and Distance-Preserving Embedding methods transform objects into a vector space, solve the generalized median problem in this space, and inversely transform back into the original space. Both of these methods have been successfully applied to a wide range of object domains, where the generalized median problem has inherent high computational complexity (typically NP-hard) and therefore approximate solutions are required. Previously, explicit embedding methods were used in the computation, which often do not reflect the spatial relationship between objects exactly. In this work we introduce a kernel-based generalized median framework that is applicable to both positive definite and indefinite kernels. This framework computes the relationship between objects and its generalized median in kernel space, without the need of an explicit embedding. We show that the spatial relationship between objects is more accurately represented in kernel space than in an explicit vector space using easy-to-compute kernels, and demonstrate superior performance of generalized median computation on datasets of three different domains. A software toolbox resulting from our work is made publicly available to encourage other researchers to explore the generalized median computation and applications.

Medical image segmentation with generative adversarial semi-supervised network

Recent medical image segmentation methods heavily rely on large-scale training data and high-quality annotations. However, these resources are hard to obtain due to the limitation of medical images and professional annotators. How to utilize limited annotations and maintain the performance is an essential yet challenging problem. In this paper, we try to tackle this problem in a self-learning manner by proposing a generative adversarial semi-supervised network. We use limited annotated images as main supervision signals, and the unlabeled images are manipulated as extra auxiliary information to improve the performance. More specifically, we modulate a segmentation network as a generator to produce pseudo labels for unlabeled images. To make the generator robust, we train an uncertainty discriminator with generative adversarial learning to determine the reliability of the pseudo labels. To further ensure dependability, we apply feature mapping loss to obtain statistic distribution consistency between the generated labels and the real labels. Then the verified pseudo labels are used to optimize the generator in a self-learning manner. We validate the effectiveness of the proposed method on right ventricle dataset, Sunnybrook dataset, STACOM, ISIC dataset, and Kaggle lung dataset. We obtain 0.8402-0.9121, 0.8103-0.9094, 0.9435-0.9724, 0.8635-0.886, and 0.9697-0.9885 dice coefficient with 1/8 to 1/2 proportion of densely annotated labels, respectively. The improvements are up to 28.6 points higher than the corresponding fully supervised baseline.

Rapid analysis of streaming platelet images by semi-unsupervised learning

We developed a fast and accurate deep learning approach employing a semi-unsupervised learning system (SULS) for capturing the real-time noisy, sparse, and ambiguous images of platelet activation. Outperforming several leading supervised learning methods when applied to segment various platelet morphologies, the SULS detects their complex boundaries at submicron resolutions and it massively decreases to only a few hours for segmenting streaming images of 45 million platelets that would have taken 40 years to annotate manually. For the first time, the fast dynamics of pseudopod formation and platelet morphological changes including membrane tethers and transient tethering to vessels are accurately captured.

[A brief history of artificial intelligence]

For more than a decade, we have witnessed an acceleration in the development and the adoption of artificial intelligence (AI) technologies. In medicine, it impacts clinical and fundamental research, hospital practices, medical examinations, hospital care or logistics. These in turn contribute to improvements in diagnostics and prognostics, and to improvements in personalised and targeted medicine, advanced observation and analysis technologies, or surgery and other assistance robots. Many challenges in AI and medicine, such as data digitalisation, medical data privacy, algorithm explicability, inclusive AI system development or their reproducibility, have to be tackled in order to build the confidence of medical practitioners in these technologies. This will be possible by mastering the key concepts via a brief history of artificial intelligence.

Not-so-supervised: A survey of semi-supervised, multi-instance, and transfer learning in medical image analysis

Machine learning (ML) algorithms have made a tremendous impact in the field of medical imaging. While medical imaging datasets have been growing in size, a challenge for supervised ML algorithms that is frequently mentioned is the lack of annotated data. As a result, various methods that can learn with less/other types of supervision, have been proposed. We give an overview of semi-supervised, multiple instance, and transfer learning in medical imaging, both in diagnosis or segmentation tasks. We also discuss connections between these learning scenarios, and opportunities for future research. A dataset with the details of the surveyed papers is available via https://figshare.com/articles/Database_of_surveyed_literature_in_Not-so-supervised_a_survey_of_semi-supervised_multi-instance_and_transfer_learning_in_medical_image_analysis_/7479416.

Consistent Spatial-Temporal Longitudinal Atlas Construction for Developing Infant Brains

Brain atlases are an essential component in understanding the dynamic cerebral development, especially for the early postnatal period. However, longitudinal atlases are rare for infants, and the existing ones are generally limited by their fuzzy appearance. Moreover, since longitudinal atlas construction is typically performed independently over time, the constructed atlases often fail to preserve temporal consistency. This problem is further aggravated for infant images since they typically have low spatial resolution and insufficient tissue contrast. In this paper, we propose a novel framework for consistent spatial-temporal construction of longitudinal atlases for developing infant brain MR images. Specifically, for preserving structural details, the atlas construction is performed in spatial-temporal wavelet domain simultaneously. This is achieved by a patch-based combination of results from each frequency subband. Compared with the existing infant longitudinal atlases, our experimental results indicate that our approach is able to produce longitudinal atlases with richer structural details and also better longitudinal consistency, thus leading to higher performance when used for spatial normalization of a group of infant brain images.

Sensor, signal, and imaging informatics: big data and smart health technologies

OBJECTIVES

This synopsis presents a selection for the IMIA (International Medical Informatics Association) Yearbook 2014 of excellent research in the broad field of Sensor, Signal, and Imaging Informatics published in the year 2013, with a focus on Big Data and Smart Health Technologies Methods: We performed a systematic initial selection and a double blind peer review process to find the best papers in this domain published in 2013, from the PubMed and Web of Science databases. A set of MeSH keywords provided by experts was used.

RESULTS

Big Data are collections of large and complex datasets which have the potential to capture the whole variability of a study population. More and more innovative sensors are emerging, allowing to enrich these big databases. However they become more and more challenging to process (i.e. capture, store, search, share, transfer, exploit) because traditional tools are not adapted anymore.

CONCLUSIONS

This review shows that it is necessary not only to develop new tools specifically designed for Big Data, but also to evaluate their performance on such large datasets.

Locally Weighted Multi-atlas Construction

In image-based medical research, atlases are widely used in many tasks, for example, spatial normalization and segmentation. If atlases are regarded as representative patterns for a population of images, then multiple atlases are required for a heterogeneous population. In conventional atlas construction methods, the "unit" of representative patterns is images. Every input image is associated with its most similar atlas. As the number of subjects increases, the heterogeneity increases accordingly, and a big number of atlases may be needed. In this paper, we explore using region-wise, instead of image-wise, patterns to represent a population. Different parts of an input image is fuzzily associated with different atlases according to voxel-level association weights. In this way, regional structure patterns from different atlases can be combined together. Based on this model, we design a variational framework for multi-atlas construction. In the application to two T1-weighted MRI data sets, the method shows promising performance, in comparison with a conventional unbiased atlas construction method.