Better Diffusion Segmentation in Acute Ischemic Stroke Through Automatic Tree Learning Anomaly Segmentation

Abstract

Stroke is the second most common cause of death worldwide, responsible for 6.24 million deaths in 2015 (about 11% of all deaths). Three out of four stroke survivors suffer long term disability, as many cannot return to their prior employment or live independently. Eighty-seven percent of strokes are ischemic. As an increasing volume of ischemic brain tissue proceeds to permanent infarction in the hours following the onset, immediate treatment is pivotal to increase the likelihood of good clinical outcome for the patient. Triaging stroke patients for active therapy requires assessment of the volume of salvageable and irreversible damaged tissue, respectively. With Magnetic Resonance Imaging (MRI), diffusion-weighted imaging is commonly used to assess the extent of permanently damaged tissue, the core lesion. To speed up and standardize decision-making in acute stroke management we present a fully automated algorithm, ATLAS, for delineating the core lesion. We compare performance to widely used threshold based methodology, as well as a recently proposed state-of-the-art algorithm: COMBAT Stroke. ATLAS is a machine learning algorithm trained to match the lesion delineation by human experts. The algorithm utilizes decision trees along with spatial pre- and post-regularization to outline the lesion. As input data the algorithm takes images from 108 patients with acute anterior circulation stroke from the I-Know multicenter study. We divided the data into training and test data using leave-one-out cross validation to assess performance in independent patients. Performance was quantified by the Dice index. The median Dice coefficient of ATLAS algorithm was 0.6122, which was significantly higher than COMBAT Stroke, with a median Dice coefficient of 0.5636 (p < 0.0001) and the best possible performing methods based on thresholding of the diffusion weighted images (median Dice coefficient: 0.3951) or the apparent diffusion coefficient (median Dice coefficeint: 0.2839). Furthermore, the volume of the ATLAS segmentation was compared to the volume of the expert segmentation, yielding a standard deviation of the residuals of 10.25 ml compared to 17.53 ml for COMBAT Stroke. Since accurate quantification of the volume of permanently damaged tissue is essential in acute stroke patients, ATLAS may contribute to more optimal patient triaging for active or supportive therapy.

Keywords: computer learning; decision trees; diffusion MRI; diffusion lesion; segmentation; stroke.

Figure 1

The algorithm for calculating the mirror correced images. First an affine transformation, sending the left hemisphere to the right hemisphere and vise versa, is calculated by coregitering the b₀-image to the image you get by flipping it along the sagittal plane. The DWI (or ADC) image is then flipped using this transformation. The flipped image is smoothed using an 3-dimensional Gaussian isotropic kernel. The mirror corrected image is then made voxel for voxel by subtracting the current voxel value in the DWI (or ADC) image by the most critical (highest for DWI, lowest for ADC) value of the transformed and smoothed image in a small neighborhood around the current voxel.

Figure 2

The full ATLAS algorithm with examples of intermediate results. Panel (A) shows the input variables (the DWI and the ADC images). Panel (B) shows the preprocessed variables, that is the original two variable, and the mirror corrected versions of the original two variables. Panel (C) illustrated the voxelvise output of the decision tree. Panel (D) shows the postprocessing of first smoothing the output, and then thresholding. Finally panel (E) shows the ATLAS segmentation (blue outline) overlaying the original DWI image along with the expert drawn segmentation (red outline).

Figure 3

The predicted volumes of the lesions segmented by the ATLAS algorithm and by the Combat stroke method compared to the volume segmented by the expert outlining.

Figure 4

A boxplot of the Dice coefficients for the ATLAS segmentation, the Combat stroke segmentation and the best possible solely threshold based segmentation by DWI and by ADC.