January 20, 2021

Image-based Quality Assessment of Middle Cerebral Artery Occlusion using SIFT Descriptor and Support Vector Machine

Background and Purpose: Quality assessment of middle cerebral artery occlusion (MCAO) is of vital importance to a wide range of animal studies of stroke such as reperfusion therapy. However, a non-invasive and objective assessment method is still lacking. Herein, we propose an image feature-based protocol to assess the quality of the procedure. Methods: We performed permanent MCAO to a total of 161 Sprague-Dawley rats. Micro positron emission tomography (PET) images were acquired both before and after the MCAO procedure. Triphenyl tetrazolium chloride (TTC) staining was also conducted as a ground truth to ensure the MCAO quality. After preprocessing of the PET images, a combination of 3D scale invariant feature transform (SIFT) and support vector machine (SVM) was applied to extract features and train a classifier that can assess the quality of the MCAO procedure. Results: 106 rats and 212 images were used as training data to construct the classification model. The SVM classifier achieved over 98% accuracy in cross validation. 10 rats with TTC results served as validation data as the staining showed clear infarction in the ipsilateral brain. Their images were tested by the classifier and all of them were categorized into the correct group. Finally, the remaining 45 rats from a separate experiment were treated as independent test data. The prediction accuracy for their 90 images reached the level of 91%. An online interface was constructed for users to upload their scans and obtain the assessment results. Conclusion: This image-based protocol provides a convenient, quantitative and non-invasive tool to assess the quality of the MCAO procedure.

 bioRxiv Subject Collection: Neuroscience

 Read More

Leave a Reply

%d bloggers like this: