While deep convolutional neural networks (CNN) have been successfully applied for 2D image analysis, it is still challenging to apply them to 3D anisotropic volumes, especially when the within-slice resolution is much higher than the between-slice resolution and when the amount of 3D volumes is relatively small. On one hand, direct learning of CNN with 3D convolution kernels suffers from the lack of data and likely ends up with poor generalization; insufficient GPU memory limits the model size or representational power. On the other hand, applying 2D CNN with generalizable features to 2D slices ignores between-slice information. Coupling 2D network with LSTM to further handle the between-slice information is not optimal due to the difficulty in LSTM learning. To overcome the above challenges, we propose a 3D Anisotropic Hybrid Network (AH-Net) that transfers convolutional features learned from 2D images to 3D anisotropic volumes. Such a transfer inherits the desired strong generalization capability for withinslice information while naturally exploiting between-slice information for more effective modelling. The focal loss is further utilized for more effective end-to-end learning. We experiment with the proposed 3D AH-Net on two different medical image analysis tasks, namely lesion detection from a Digital Breast Tomosynthesis volume, and liver and liver tumor segmentation from a Computed Tomography volume and obtain the state-of-the-art results.

Abstract. Automatic localization of multiple anatomical structures in medical images provides important semantic information with potential benefits to diverse clinical applications. Aiming at organ-specific attenuation correction in PET/MR imaging, we propose an efficient approach for estimating location and size of multiple anatomical structures in MR scans. Our contribution is three-fold: (1) we apply supervised regression techniques to the problem of anatomy detection and localization in whole-body MR, (2) we adapt random ferns to produce multidimensional regression output and compare them with random regression forests, and (3) introduce the use of 3D LBP descriptors in multi-channel MR Dixon sequences. The localization accuracy achieved with both fern-and forest-based approaches is evaluated by direct comparison with state of the art atlas-based registration, on ground-truth data from 33 patients. Our results demonstrate improved anatomy localization accuracy with higher efficiency and robustness.

Deep learning methods typically require vast amounts of training data to reach their full potential. While some publicly available datasets exists, domain specific data always needs to be collected and manually labeled, an expensive, time consuming and error prone process. Training with synthetic data is therefore very lucrative, as dataset creation and labeling comes for free. We propose a novel method for creating purely synthetic training data for object detection. We leverage a large dataset of 3D background models and densely render them using full domain randomization. This yields background images with realistic shapes and texture on top of which we render the objects of interest. During training, the data generation process follows a curriculum strategy guaranteeing that all foreground models are presented to the network equally under all possible poses and conditions with increasing complexity. As a result, we entirely control the underlying statistics and we create optimal training samples at every stage of training. Using a set of 64 retail objects, we demonstrate that our simple approach enables the training of detectors that outperform models trained with real data on a challenging evaluation dataset.

No abstract

BackgroundPlaque imaging based on magnetic resonance imaging (MRI) represents a new modality for risk assessment in atherosclerosis. It allows classification of carotid plaques in high-risk and low-risk lesion types (I-VIII). Type 2 diabetes mellitus (DM 2) represents a known risk factor for atherosclerosis, but its specific influence on plaque vulnerability is not fully understood. This study investigates whether MRI-plaque imaging can reveal differences in carotid plaque features of diabetic patients compared to nondiabetics.Methods191 patients with moderate to high-grade carotid artery stenosis were enrolled after written informed consent was obtained. Each patient underwent MRI-plaque imaging using a 1.5-T scanner with phased-array carotid coils. The carotid plaques were classified as lesion types I-VIII according to the MRI-modified AHA criteria. For 36 patients histology data was available.ResultsEleven patients were excluded because of insufficient MR-image quality. DM 2 was diagnosed in 51 patients (28.3%). Concordance between histology and MRI-classification was 91.7% (33/36) and showed a Cohen's kappa value of 0.81 with a 95% CI of 0.98-1.15. MRI-defined high-risk lesion types were overrepresented in diabetic patients (n = 29; 56.8%). Multiple logistic regression analysis revealed association between DM 2 and MRI-defined high-risk lesion types (OR 2.59; 95% CI [1.15-5.81]), independent of the degree of stenosis.ConclusionDM 2 seems to represent a predictor for the development of vulnerable carotid plaques irrespective of the degree of stenosis and other risk factors. MRI-plaque imaging represents a new tool for risk stratification of diabetic patients.See Commentary: http://www.biomedcentral.com/1741-7015/8/78/abstract

No abstract

Deformable guide-wire tracking in fluoroscopic sequences is a challenging task due to the low signal to noise ratio of the images and the apparent complex motion of the object of interest. Common tracking methods are based on data terms that do not differentiate well between medical tools and anatomic background such as ribs and vertebrae. A data term learned directly from fluoroscopic sequences would be more adapted to the image characteristics and could help to improve tracking. In this work, our contribution is to learn the relationship between features extracted from the original image and the tracking error. By randomly deforming a guide-wire model around its ground truth position in one single reference frame, we explore the space spanned by these features. Therefore, a guide-wire motion distribution model is learned to reduce the intrisic dimensionality of this feature space. Random deformations and the corresponding features can be then automatically generated. In a regression approach, the function mapping this space to the tracking error is learned. The resulting data term is integrated into a tracking framework based on a second-order MAP-MRF formulation which is optimized by QPBO moves yielding high-quality tracking results. Experiments conducted on two fluoroscopic sequences show that our approach is a promising alternative for deformable tracking of guide-wires.

No abstract