Using End-to-End imbalanced Temporal Deep Gaussian Process (iTDGP) to Predict Acute Ischemic Stroke Lesions

Abstract

As one of the leading causes of mortality and disability worldwide, Acute Ischemic Stroke (AIS) occurs when the blood supply to the brain is suddenly interrupted because of a blocked artery. Within seconds of AIS onset, the brain cells surrounding the blocked artery die. The automated and precise prediction of AIS lesions plays a vital role in the treatment planning and prevention of further injuries. Unfortunately, the current standard AIS assessment method, which thresholds the 3D measurement maps extracted from Computed Tomography Perfusion (CTP) images, is not accurate enough. Due to this fact, in this article, we propose the imbalanced Temporal Deep Gaussian Process (iTDGP), a probabilistic model that can improve AIS lesions prediction by using baseline CTP time series. Our proposed model can effectively extract temporal information from the CTP time series and map it to the class labels of the brain's voxels. In addition, by using batch training and voxel-level analysis iTDGP can learn from a few patients and it is robust against imbalanced classes. Moreover, our model incorporates a post-processor capable of improving prediction accuracy using spatial information. Our comprehensive experiments, on the ISLES 2018 and the University of Alberta Hospital (UAH) datasets (including 63 and 100 patients respectively), show that iTDGP performs better than state-of-the-art AIS lesion predictors, obtaining the (cross-validation) Dice score of 71.42% and 65.37% with a significant p<0.05, respectively.

Exploiting 4D CT Perfusion for segmenting infarcted areas in patients with suspected acute ischemic stroke

“…Using 2D images as output is less computationally expensive and less memory intensive than using 3D volumetric data as output [52]. Few studies have adopted 4D datasets in DNN models to detect ischemic stroke [5,30,31,33]. This has roots in the high computational complexity of 4D data and the lack of ground truth for the whole set.…”

“…TMAX is the time to maximum map; TTP represents the time to peak map, while MIP gives the map for the maximum intensity projection. Although PMs provide helpful information about ischemic brain tissue, extracting them from the 4D CTP scans limits the spatio-temporal information only to specific subsets of information [5]. Several methods [6,7] have used thresholding techniques to predict the ischemic areas from the PMs.…”

“…Nevertheless, relying on raw data (directly exploiting the temporal and spatial dimensions) is scarcely explored in the literature for AIS applications. To the best of our knowledge, few studies proposed DNN models with promising results, exploiting the temporal dimension to assess ischemic stroke lesions using CTP images [5,30,31,32,33]. Soltanpour et al [5] utilized 4D CTP images to create 2D matrices, in which each row is a voxel, and each column is a time point.…”

“…To the best of our knowledge, few studies proposed DNN models with promising results, exploiting the temporal dimension to assess ischemic stroke lesions using CTP images [5,30,31,32,33]. Soltanpour et al [5] utilized 4D CTP images to create 2D matrices, in which each row is a voxel, and each column is a time point. The 2D matrices are used as input for a model that shows encouraging results in differentiating healthy tissue from the ischemic core.…”

CT Perfusion is All we Need: 4D CNN Segmentation of Penumbra and Core in Patients With Suspected Acute Ischemic Stroke

“…MIP images are calculated as the maximum Hounsfield unit (HU) value over the time sequence of the CTP, providing a 3D volume from the 4D acquisition of CTP. Although PMs provide helpful information about ischemic brain tissue, extracting them from the 4D CTP scans limits the spatiotemporal information only to specific subsets of information [9].…”