Stroke Lesion Outcome Prediction Based on MRI Imaging Combined With Clinical Information

Abstract

In developed countries, the second leading cause of death is stroke, which has the ischemic stroke as the most common type. The preferred diagnosis procedure involves the acquisition of multi-modal Magnetic Resonance Imaging. Besides detecting and locating the stroke lesion, Magnetic Resonance Imaging captures blood flow dynamics that guides the physician in evaluating the risks and benefits of the reperfusion procedure. However, the decision process is an intricate task due to the variability of lesion size, shape, and location, as well as the complexity of the underlying cerebral hemodynamic process. Therefore, an automatic method that predicts the stroke lesion outcome, at a 3-month follow-up, would provide an important support to the physicians' decision process. In this work, we propose an automatic deep learning-based method for stroke lesion outcome prediction. Our main contribution resides in the combination of multi-modal Magnetic Resonance Imaging maps with non-imaging clinical meta-data: the thrombolysis in cerebral infarction scale, which categorizes the success of recanalization, achieved through mechanical thrombectomy. In our proposal, this clinical information is considered at two levels. First, at a population level by embedding the clinical information in a custom loss function used during training of our deep learning architecture. Second, at a patient-level through an extra input channel of the neural network used at testing time for a given patient case. By merging imaging with non-imaging clinical information, we aim to obtain a model aware of the principal and collateral blood flow dynamics for cases where there is no perfusion beyond the point of occlusion and for cases where the perfusion is complete after the occlusion point.

Use of Deep Learning to Predict Final Ischemic Stroke Lesions From Initial Magnetic Resonance Imaging

“…Some initial studies have shown that machine learning can be used to predict stroke lesions. [9][10][11][12][13] Convolutional neural networks are a subtype of machine learning that does not require humans to define relevant features but instead learns them from data in a training set.…”

Integrating uncertainty in deep neural networks for MRI based stroke analysis

“…Besides clinical and patient data, medical experts rely on multi-modal Computed Tomography (CT) and Magnetic Resonance (MR) imaging for diagnoses and treatment decisions (Baird & Warach, 1998;Chilla, et al, 2015). To both support physicians in their diagnosis and accelerate treatment decision-making, methods for automatic image analysis are increasingly integrated into acute stroke care (Feng, et al, 2018;Pinto, et al, 2018). Deep Convolutional Neural Networks (CNNs) are state-of-the-art to recognize pathological features such as ischemic stroke lesions on brain images (Bernal, et al, 2019;Havaei, et al, 2017).…”

Brain SegNet: 3D local refinement network for brain lesion segmentation

“…al. combined CNN features and a SVM classifier to automatically predict genotypes from brain MRIs [3]. An end-to-end learning allows features learning and classifier training to work collaboratively, resulting in a more meaningful and stronger deep representation that leads to state-of-the-art performance on brain tumor segmentation [1,2,[4][5][6][7] and stroke lesion segmentation [8][9][10][11][12].…”