Imaging-based prediction of histological clot composition from admission CT imaging
This study uses features derived from baseline CT and CTA scans to classify the clot either as red blood cell or fibrin rich. The algorithm uses a random forest classifier which combines imaging and shape features within the clot and its vicinity. This information can be very valuable to improve the emergency care that each patient receives.
Uta Hanning, Peter B Sporns, Marios N Psychogios, Astrid Jeibmann, Jens Minnerup, Mathias Gelderblom, Karolin Schulte, Jawed Nawabi, Hermann Krähling, Alex Brehm, Moritz Wildgruber, Helge Kniep
Background Thrombus composition has been shown to be a major determinant of recanalization success and occurrence of complications in mechanical thrombectomy. The most important parameters of thrombus behavior during interventional procedures are relative fractions of fibrin and red blood cells (RBCs). We hypothesized that quantitative information from admission non-contrast CT (NCCT) and CT angiography (CTA) can be used for machine learning based prediction of thrombus composition.
Methods The analysis included 112 patients with occlusion of the carotid-T or middle cerebral artery who underwent thrombectomy. Thrombi samples were histologically analyzed and fractions of fibrin and RBCs were determined. Thrombi were semi-automatically delineated in CTA scans and NCCT scans were registered to the same space. Two regions of interest (ROIs) were defined for each thrombus: small-diameter ROIs capture vessel walls and thrombi, large-diameter ROIs reflect peri-vascular tissue responses. 4844 quantitative image markers were extracted and evaluated for their ability to predict thrombus composition using random forest algorithms in a nested fivefold cross validation.
Results Test set receiver operating characteristic area under the curve was 0.83 (95% CI 0.80 to 0.87) for differentiating RBC-rich thrombi and 0.84 (95% CI 0.80 to 0.87) for differentiating fibrin-rich thrombi. At maximum Youden-Index, RBC-rich thrombi were identified at 77% sensitivity and 74% specificity; for fibrin-rich thrombi the classifier reached 81% sensitivity at 73% specificity.
Conclusions Machine learning based analysis of admission imaging allows for prediction of clot composition. Perspectively, such an approach could allow selection of clot-specific devices and retrieval procedures for personalized thrombectomy strategies.
Read the full paper here:
Hanning U, Sporns PB, Psychogios MN, et al. Imaging-based prediction of histological clot composition from admission CT imaging [published online ahead of print, 2021 Jan 22]. J Neurointerv Surg. 2021;neurintsurg-2020-016774. doi:10.1136/neurintsurg-2020-016774
Clot characteristics is an exciting area which is becoming better understood. It opens up a new valuable dimension to diagnosing patients in emergency care to determine which treatment would be best received. AI can play a big role in determining clot composition in the future.