Decoding intra-tumoral spatial heterogeneity on radiological images using the Hilbert curve

Background Current intra-tumoral heterogeneous feature extraction in radiology is limited to the use of a single slice or the region of interest within a few context-associated slices, and the decoding of intra-tumoral spatial heterogeneity using whole tumor samples is rare. We aim to propose a mathematical model of space-filling curve-based spatial correspondence mapping to interpret intra-tumoral spatial locality and heterogeneity. Methods A Hilbert curve-based approach was employed to decode and visualize intra-tumoral spatial heterogeneity by expanding the tumor volume to a two-dimensional (2D) matrix in voxels while preserving the spatial locality of the neighboring voxels. The proposed method was validated using three-dimensional (3D) volumes constructed from lung nodules from the LIDC-IDRI dataset, regular axial plane images, and 3D blocks. Results Dimensionality reduction of the Hilbert volume with a single regular axial plane image showed a sparse and scattered pixel distribution on the corresponding 2D matrix. However, for 3D blocks and lung tumor inside the volume, the dimensionality reduction to the 2D matrix indicated regular and concentrated squares and rectangles. For classification into benign and malignant masses using lung nodules from the LIDC-IDRI dataset, the Inception-V4 indicated that the Hilbert matrix images improved accuracy (85.54% vs. 73.22%, p < 0.001) compared to the original CT images of the test dataset. Conclusions Our study indicates that Hilbert curve-based spatial correspondence mapping is promising for decoding intra-tumoral spatial heterogeneity of partial or whole tumor samples on radiological images. This spatial-locality-preserving approach for voxel expansion enables existing radiomics and convolution neural networks to filter structured and spatially correlated high-dimensional intra-tumoral heterogeneity.

Virtual brain grafting: Enabling whole brain parcellation in the presence of large lesions

Brain atlases and templates are at the heart of neuroimaging analyses, for which they facilitate multimodal registration, enable group comparisons and provide anatomical reference. However, as atlas-based approaches rely on correspondence mapping between images they perform poorly in the presence of structural pathology. Whilst several strategies exist to overcome this problem, their performance is often dependent on the type, size and homogeneity of any lesions present. We therefore propose a new solution, referred to as Virtual Brain Grafting (VBG), which is a fully-automated, open-source workflow to reliably parcellate MR images in the presence of a broad spectrum of focal brain pathologies, including large, bilateral, intra- and extra-axial, heterogeneous lesions with and without mass effect.The core of the VBG approach is the generation of a lesion-free T1-weighted input image which enables further image processing operations that would otherwise fail. Here we validated our solution based on Freesurfer recon-all parcellation in a group of 10 patients with heterogeneous gliomatous lesions, and a realistic synthetic cohort of glioma patients (n=100) derived from healthy control data and patient data.We demonstrate that VBG outperforms a non-VBG approach assessed qualitatively by expert neuroradiologists and Mann-Whitney U tests to compare corresponding parcellations (real patients U(6,6) = 33, z = 2.738, P < .010, synthetic patients U(48,48) = 2076, z = 7.336, P < .001). Results were also quantitatively evaluated by comparing mean dice scores from the synthetic patients using one-way ANOVA (unilateral VBG = 0.894, bilateral VBG = 0.903, and non-VBG = 0.617, P < .001). Additionally, we used linear regression to show the influence of lesion volume, lesion overlap with, and distance from the Freesurfer volumes of interest, on labelling accuracy.VBG may benefit the neuroimaging community by enabling automated state-of-the-art MRI analyses in clinical populations, for example by providing input data for automated solutions for fiber tractography or resting-state fMRI analyses that could also be used in the clinic. To fully maximize its availability, VBG is provided as open software under a Mozilla 2.0 license (https://github.com/KUL-Radneuron/KUL_VBG).Graphical abstract:(A) shows T1 images from two patients with gliomatous lesions. VBG is a lesion replacement/filling workflow with one approach for unilateral lesions (uVBG) and another for bilateral lesions (bVBG). (B) shows the recon-all approach selected, (C) & (D) show the output, tissue segmentations (C) and whole brain parcellations (D). If VBG is not used (non-VBG) recon-all may finish with some errors in the parcellations (left) or fail to generate a parcellation entirely (right). However, using either VBG method allows recon-all to complete where it had previously failed and also improves parcellation quality.

Automated Morphometric Analysis of the Femur on Large Anatomical Databases with Highly Accurate Correspondence Detection

For a variety of medical applications, detailed knowledge on the statistical distribution of morphometric characteristics among specific patient groups is required. We present a novel approach for performing automated morphometric measurements on the surface of anatomical bone samples obtained from CT segmentation. The system developed supports various types of measurements (distances, angles, radii) on several kinds of features (points, lines, planes or circles), which are performed automatically for every bone sample in a given data set. The desired features can be specified by the user in two ways, either by marking them on a standardized template that is mapped to all samples via a correspondence mapping, or by hierarchically building new features from existing features. The system was implemented and tested on a database containing about 1200 segmented femur. The quality of the automated matching was assessed through a study comparing the performance of the system with results obtained from manual labeling by medical experts. It was found that the deviation between the two methods was generally less than 2mm.

Sketch Based Image Deformation and Editing with Guaranteed Feature Correspondence

The establishment of a good correspondence mapping is a key issue in planar animations such as image morphing and deformation. In this paper, we present a novel mapping framework for animation of complex shapes. We firstly let the user extract the outlines of the interested object and target interested area from the input images and specify some optional feature lines, and then we generate a sparse delaunay triangulation mesh taking the outlines and the feature lines of the source shape as constraints. Then we copy the topology from the source shape to the target shape to construct a valid triangulation in the target shape. After that, each triangle of this triangular mesh is further segmented into a dense mesh patch. Each mesh patch is parameterized onto a unit circle domain. With such parametrization, we can easily construct a correspondence mapping between the source patches and the corresponding target patches. Our framework can work well for various applications such as shape deformation and morphing. Pleasing results generated by our framework show that the framework works well.