Related Experiment Video
Updated: May 30, 2026
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
Published on: September 25, 2019
Predicting final extent of ischemic infarction using artificial neural network analysis of multi-parametric MRI in
Hassan Bagher-Ebadian1, Kourosh Jafari-Khouzani, Panayiotis D Mitsias
1Department of Neurology, Henry Ford Hospital, Detroit, Michigan, United States of America. ebadian@neurnis.neuro.hfh.edu
Abstract:
In hemispheric ischemic stroke, the final size of the ischemic lesion is the most important correlate of clinical functional outcome. Using a set of acute-phase MR images (Diffusion-weighted--DWI, T(1)-weighted--T1WI, T(2)-weighted--T2WI, and proton density weighted--PDWI) for inputs, and the chronic T2WI at 3 months as an outcome measure, an Artificial Neural Network (ANN) was trained to predict the 3-month outcome in the form of a voxel-by-voxel forecast of the chronic T2WI. The ANN was trained and tested using 12 subjects (with 83 slices and 140218 voxels) using a leave-one-out cross-validation method with calculation of the Area Under the Receiver Operator Characteristic Curve (AUROC) for training, testing and optimization of the ANN. After training and optimization, the ANN produced maps of predicted outcome that were well correlated (r = 0.80, p<0.0001) with the T2WI at 3 months for all 12 patients. This result implies that the trained ANN can provide an estimate of 3-month ischemic lesion on T2WI in a stable and accurate manner (AUROC = 0.89).
Insights
Artificial Neural Networks accurately predict chronic ischemic stroke lesion size using acute MRI scans. This AI approach aids in forecasting long-term outcomes for stroke patients.
Area of Science:
- Neuroimaging
- Artificial Intelligence
- Stroke Medicine
Background:
- Ischemic stroke lesion size is a key predictor of patient functional outcomes.
- Accurate prediction of long-term lesion size is crucial for stroke management.
Purpose of the Study:
- To develop and validate an Artificial Neural Network (ANN) for predicting chronic ischemic stroke lesion size.
- To forecast the 3-month T2-weighted imaging (T2WI) lesion outcome using acute-phase MRI data.
Main Methods:
- Utilized acute MRI sequences (DWI, T1WI, T2WI, PDWI) as input for an ANN.
- Trained and tested the ANN on 12 subjects using leave-one-out cross-validation.
- Evaluated prediction accuracy using the Area Under the Receiver Operator Characteristic Curve (AUROC).
Main Results:
- The ANN achieved a strong correlation (r=0.80, p<0.0001) between predicted and actual 3-month T2WI lesion size.
- The model demonstrated stable and accurate prediction capabilities with an AUROC of 0.89.
- Voxel-by-voxel forecasts of chronic T2WI were generated.
Conclusions:
- Trained ANNs can reliably estimate 3-month ischemic lesion size on T2WI.
- This AI-driven approach offers a promising tool for predicting stroke outcomes.
- The method provides a stable and accurate forecast of chronic lesion development.
