4D ACTIVE CUT: AN INTERACTIVE TOOL FOR PATHOLOGICAL ANATOMY MODELING

Acute cognitive impairment after traumatic brain injury predicts the occurrence of brain atrophy patterns similar to those observed in Alzheimer's disease

Traumatic brain injuries (TBIs) are often followed by persistent structural brain alterations and by cognitive sequalae, including memory deficits, reduced neural processing speed, impaired social function, and decision-making difficulties. Although mild TBI (mTBI) is a risk factor for Alzheimer's disease (AD), the extent to which these conditions share patterns of macroscale neurodegeneration has not been quantified. Comparing such patterns can not only reveal how the neurodegenerative trajectories of TBI and AD are similar, but may also identify brain atrophy features which can be leveraged to prognosticate AD risk after TBI. The primary aim of this study is to systematically map how TBI affects white matter (WM) and gray matter (GM) properties in AD-analogous patterns. Our findings identify substantial similarities in the regional macroscale neurodegeneration patterns associated with mTBI and AD. In cerebral GM, such similarities are most extensive in brain areas involved in memory and executive function, such as the temporal poles and orbitofrontal cortices, respectively. Our results indicate that the spatial pattern of cerebral WM degradation observed in AD is broadly similar to the pattern of diffuse axonal injury observed in TBI, which frequently affects WM structures like the fornix, corpus callosum, and corona radiata. Using machine learning, we find that the severity of AD-like brain changes observed during the chronic stage of mTBI can be accurately prognosticated based on acute assessments of post-traumatic mild cognitive impairment. These findings suggest that acute post-traumatic cognitive impairment predicts the magnitude of AD-like brain atrophy, which is itself associated with AD risk.

Semixup: In- and Out-of-Manifold Regularization for Deep Semi-Supervised Knee Osteoarthritis Severity Grading From Plain Radiographs

Knee osteoarthritis (OA) is one of the highest disability factors in the world. This musculoskeletal disorder is assessed from clinical symptoms, and typically confirmed via radiographic assessment. This visual assessment done by a radiologist requires experience, and suffers from moderate to high inter-observer variability. The recent literature has shown that deep learning methods can reliably perform the OA severity assessment according to the gold standard Kellgren-Lawrence (KL) grading system. However, these methods require large amounts of labeled data, which are costly to obtain. In this study, we propose the Semixup algorithm, a semi-supervised learning (SSL) approach to leverage unlabeled data. Semixup relies on consistency regularization using in- and out-of-manifold samples, together with interpolated consistency. On an independent test set, our method significantly outperformed other state-of-the-art SSL methods in most cases. Finally, when compared to a well-tuned fully supervised baseline that yielded a balanced accuracy (BA) of 70.9 ± 0.8% on the test set, Semixup had comparable performance - BA of 71 ± 0.8% ( p=0.368 ) while requiring 6 times less labeled data. These results show that our proposed SSL method allows building fully automatic OA severity assessment tools with datasets that are available outside research settings.

Semi Supervised Learning with Deep Embedded Clustering for Image Classification and Segmentation

Deep neural networks usually require large labeled datasets to construct accurate models; however, in many real-world scenarios, such as medical image segmentation, labelling data is a time-consuming and costly human (expert) intelligent task. Semi-supervised methods leverage this issue by making use of a small labeled dataset and a larger set of unlabeled data. In this article, we present a flexible framework for semi-supervised learning that combines the power of supervised methods that learn feature representations using state-of-the-art deep convolutional neural networks with the deep embedded clustering algorithm that assigns data points to clusters based on their probability distributions and feature representations learned by the networks. Our proposed semi-supervised learning algorithm based on deep embedded clustering (SSLDEC) learns feature representations via iterations by alternatively using labeled and unlabeled data points and computing target distributions from predictions. During this iterative procedure the algorithm uses labeled samples to keep the model consistent and tuned with labeling, as it simultaneously learns to improve feature representation and predictions. SSLDEC requires few hyper-parameters and thus does not need large labeled validation sets, which addresses one of the main limitations of many semi-supervised learning algorithms. It is also flexible and can be used with many state-of-the-art deep neural network configurations for image classification and segmentation tasks. To this end, we implemented and tested our approach on benchmark image classification tasks as well as in a challenging medical image segmentation scenario. In benchmark classification tasks, SSLDEC outperformed several state-of-the-art semi-supervised learning methods, achieving 0.46% error on MNIST with 1000 labeled points, and 4.43% error on SVHN with 500 labeled points. In the iso-intense infant brain MRI tissue segmentation task, we implemented SSLDEC on a 3D densely connected fully convolutional neural network where we achieved significant improvement over supervised-only training as well as a semi-supervised method based on pseudo-labelling. Our results show that SSLDEC can be effectively used to reduce the need for costly expert annotations, enhancing applications such as automatic medical image segmentation.

TopoAngler: Interactive Topology-Based Extraction of Fishes

We present TopoAngler, a visualization framework that enables an interactive user-guided segmentation of fishes contained in a micro-CT scan. The inherent noise in the CT scan coupled with the often disconnected (and sometimes broken) skeletal structure of fishes makes an automatic segmentation of the volume impractical. To overcome this, our framework combines techniques from computational topology with an interactive visual interface, enabling the human-in-the-Ioop to effectively extract fishes from the volume. In the first step, the join tree of the input is used to create a hierarchical segmentation of the volume. Through the use of linked views, the visual interface then allows users to interactively explore this hierarchy, and gather parts of individual fishes into a coherent sub-volume, thus reconstructing entire fishes. Our framework was primarily developed for its application to CT scans of fishes, generated as part of the ScanAllFish project, through close collaboration with their lead scientist. However, we expect it to also be applicable in other biological applications where a single dataset contains multiple specimen; a common routine that is now widely followed in laboratories to increase throughput of expensive CT scanners.

Multi-modal Registration Improves Group Discrimination in Pediatric Traumatic Brain Injury

Traumatic brain injury (TBI) can disrupt the white matter (WM) integrity in the brain, leading to functional and cognitive disruptions that may persist for years. There is considerable heterogeneity within the patient group, which complicates group analyses. Here we present improvements to a tract identification workflow, automated multi-atlas tract extraction (autoMATE), evaluating the effects of improved registration. Use of study-specific template improved group classification accuracy over the standard workflow. The addition of a multi-modal registration that includes information from diffusion weighted imaging (DWI), T₁-weighted, and Fluid-Attenuated Inversion Recovery (FLAIR) further improved classification accuracy. We also examined whether particular tracts contribute more to group classification than others. Parts of the corpus callosum contributed most, and there were unexpected asymmetries between bilateral tracts.

Slic-Seg: A minimally interactive segmentation of the placenta from sparse and motion-corrupted fetal MRI in multiple views

Segmentation of the placenta from fetal MRI is challenging due to sparse acquisition, inter-slice motion, and the widely varying position and shape of the placenta between pregnant women. We propose a minimally interactive framework that combines multiple volumes acquired in different views to obtain accurate segmentation of the placenta. In the first phase, a minimally interactive slice-by-slice propagation method called Slic-Seg is used to obtain an initial segmentation from a single motion-corrupted sparse volume image. It combines high-level features, online Random Forests and Conditional Random Fields, and only needs user interactions in a single slice. In the second phase, to take advantage of the complementary resolution in multiple volumes acquired in different views, we further propose a probability-based 4D Graph Cuts method to refine the initial segmentations using inter-slice and inter-image consistency. We used our minimally interactive framework to examine the placentas of 16 mid-gestation patients from MRI acquired in axial and sagittal views respectively. The results show the proposed method has 1) a good performance even in cases where sparse scribbles provided by the user lead to poor results with the competitive propagation approaches; 2) a good interactivity with low intra- and inter-operator variability; 3) higher accuracy than state-of-the-art interactive segmentation methods; and 4) an improved accuracy due to the co-segmentation based refinement, which outperforms single volume or intensity-based Graph Cuts.

Modeling 4D Pathological Changes by Leveraging Normative Models

With the increasing use of efficient multimodal 3D imaging, clinicians are able to access longitudinal imaging to stage pathological diseases, to monitor the efficacy of therapeutic interventions, or to assess and quantify rehabilitation efforts. Analysis of such four-dimensional (4D) image data presenting pathologies, including disappearing and newly appearing lesions, represents a significant challenge due to the presence of complex spatio-temporal changes. Image analysis methods for such 4D image data have to include not only a concept for joint segmentation of 3D datasets to account for inherent correlations of subject-specific repeated scans but also a mechanism to account for large deformations and the destruction and formation of lesions (e.g., edema, bleeding) due to underlying physiological processes associated with damage, intervention, and recovery. In this paper, we propose a novel framework that provides a joint segmentation-registration framework to tackle the inherent problem of image registration in the presence of objects not present in all images of the time series. Our methodology models 4D changes in pathological anatomy across time and and also provides an explicit mapping of a healthy normative template to a subject's image data with pathologies. Since atlas-moderated segmentation methods cannot explain appearance and locality pathological structures that are not represented in the template atlas, the new framework provides different options for initialization via a supervised learning approach, iterative semisupervised active learning, and also transfer learning, which results in a fully automatic 4D segmentation method. We demonstrate the effectiveness of our novel approach with synthetic experiments and a 4D multimodal MRI dataset of severe traumatic brain injury (TBI), including validation via comparison to expert segmentations. However, the proposed methodology is generic in regard to different clinical applications requiring quantitative analysis of 4D imaging representing spatio-temporal changes of pathologies.

Interactive Whole-Heart Segmentation in Congenital Heart Disease

We present an interactive algorithm to segment the heart chambers and epicardial surfaces, including the great vessel walls, in pediatric cardiac MRI of congenital heart disease. Accurate whole-heart segmentation is necessary to create patient-specific 3D heart models for surgical planning in the presence of complex heart defects. Anatomical variability due to congenital defects precludes fully automatic atlas-based segmentation. Our interactive segmentation method exploits expert segmentations of a small set of short-axis slice regions to automatically delineate the remaining volume using patch-based segmentation. We also investigate the potential of active learning to automatically solicit user input in areas where segmentation error is likely to be high. Validation is performed on four subjects with double outlet right ventricle, a severe congenital heart defect. We show that strategies asking the user to manually segment regions of interest within short-axis slices yield higher accuracy with less user input than those querying entire short-axis slices.