Accuracy of automated segmentation and volumetry of acute intracerebral hemorrhage following minimally invasive surgery using a patch-based convolutional neural network in a small dataset

Abstract

Purpose: In cases of acute intracerebral hemorrhage (ICH) volume estimation is of prognostic and therapeutic value following minimally invasive surgery (MIS). The ABC/2 method is widely used, but suffers from inaccuracies and is time consuming. Supervised machine learning using convolutional neural networks (CNN), trained on large datasets, is suitable for segmentation tasks in medical imaging. Our objective was to develop a CNN based machine learning model for the segmentation of ICH and of the drain and volumetry of ICH following MIS of acute supratentorial ICH on a relatively small dataset.

Methods: Ninety two scans were assigned to training (n = 29 scans), validation (n = 4 scans) and testing (n = 59 scans) datasets. The mean age (SD) was 70 (± 13.56) years. Male patients were 36. A hierarchical, patch-based CNN for segmentation of ICH and drain was trained. Volume of ICH was calculated from the segmentation mask.

Results: The best performing model achieved a Dice similarity coefficient of 0.86 and 0.91 for the ICH and drain respectively. Automated ICH volumetry yielded high agreement with ground truth (Intraclass correlation coefficient = 0.94 [95% CI: 0.91, 0.97]). Average difference in the ICH volume was 1.33 mL.

Conclusion: Using a relatively small dataset, originating from different CT-scanners and with heterogeneous voxel dimensions, we applied a patch-based CNN framework and successfully developed a machine learning model, which accurately segments the intracerebral hemorrhage (ICH) and the drains. This provides automated and accurate volumetry of the bleeding in acute ICH treated with minimally invasive surgery.

Keywords: Automated volumetry; Convolutional neural network; Intracerebral hemorrhage; Machine learning; Minimally invasive surgery.

Fig. 1

a: Dice and surface dice coefficients in all model variations in validation dataset. b: Similarity and overlap metrics of the final model variation in all datasets

Fig. 2

CT images of a test patient. a & d axial, b & e coronal and c & f sagittal reformats of the CT scan with GT (top row) and predicted masks (bottom row) of ICH (red) and the drain (green)

Fig. 3

a: Concordance plot of GT and predicted ICH volumes in all patients in the CNN dataset. Regression line (blue) and 95% confidence interval of predicted values. b: Bland–Altman plot of GT and predicted ICH volumes in all patients. Regression line (blue) and 95% confidence interval of differences