Fully Automated Segmentation Algorithm for Perihematomal Edema Volumetry After Spontaneous Intracerebral Hemorrhage

Abstract

Background and Purpose— Perihematomal edema (PHE) is a promising surrogate marker of secondary brain injury in patients with spontaneous intracerebral hemorrhage, but it can be challenging to accurately and rapidly quantify. The aims of this study are to derive and internally validate a fully automated segmentation algorithm for volumetric analysis of PHE. Methods— Inpatient computed tomography scans of 400 consecutive adults with spontaneous, supratentorial intracerebral hemorrhage enrolled in the Intracerebral Hemorrhage Outcomes Project (2009–2018) were separated into training (n=360) and test (n=40) datasets. A fully automated segmentation algorithm was derived from manual segmentations in the training dataset using convolutional neural networks, and its performance was compared with that of manual and semiautomated segmentation methods in the test dataset. Results— The mean volumetric dice similarity coefficients for the fully automated segmentation algorithm were 0.838±0.294 and 0.843±0.293 with manual and semiautomated segmentation methods as reference standards, respectively. PHE volumes derived from the fully automated versus manual (r=0.959; P <0.0001), fully automated versus semiautomated (r=0.960; P <0.0001), and semiautomated versus manual (r=0.961; P <0.0001) segmentation methods had strong between-group correlations. The fully automated segmentation algorithm (mean 18.0±1.8 seconds/scan) quantified PHE volumes at a significantly faster rate than both of the manual (mean 316.4±168.8 seconds/scan; P <0.0001) and semiautomated (mean 480.5±295.3 seconds/scan; P <0.0001) segmentation methods. Conclusions— The fully automated segmentation algorithm accurately quantified PHE volumes from computed tomography scans of supratentorial intracerebral hemorrhage patients with high fidelity and greater efficiency compared with manual and semiautomated segmentation methods. External validation of fully automated segmentation for assessment of PHE is warranted.

Efficiency of a deep learning-based artificial intelligence diagnostic system in spontaneous intracerebral hemorrhage volume measurement

“…Several different deep learning models have been developed for ICH automated quantification. Research has supported that the volume of ICH segmented by deep learning models, which is faster than manual CTP, yields similar results to CTP; [ 18 , 19 , 28 – 30 ]this is consistent with our present results.…”

Cytokine-Laden Extracellular Vesicles Predict Patient Prognosis after Cerebrovascular Accident

“…Edema, particularly perihematomal edema, is dynamic and rather variable over the 2 weeks following ICH onset [68]. Edema can also be challenging to image [69,70]; for these reasons, we chose only to use hemorrhage volume at the earliest available time point in our data and evaluations. However, the relationships between this ICH sequela and biofluid EV cytokine changes would surely be a valuable future study, as the temporal impacts on inflammation may hold clues about the pathophysiology of stroke and also potentially targetable areas of intervention.…”

Molecular, Pathological, Clinical, and Therapeutic Aspects of Perihematomal Edema in Different Stages of Intracerebral Hemorrhage

“…The PHE on CT images can be delineated by highlighting the hematoma and the edge of the hypodense area surrounding the hematoma on axial slices using the software's region of interest (ROI, cm 2 ) module with the semiautomated edge detection tool or manually [108][109][110][111][112]. Similarly, the volume of PHE on CT images can also be calculated manually or with some semiautomatic/automatic computer-based methods [113].…”