Related Experiment Video
Updated: Mar 6, 2026
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
PItcHPERFeCT: Primary Intracranial Hemorrhage Probability Estimation using Random Forests on CT
John Muschelli1, Elizabeth M Sweeney1, Natalie L Ullman2
1Department of Biostatistics, Bloomberg School of Public Health, Johns Hopkins University, Baltimore, MD, USA.
Insights
This study developed an automated method for segmenting intracerebral hemorrhage (ICH) on CT scans using a random forest algorithm. The automated approach achieved high accuracy, comparable to manual segmentation, offering a faster and more consistent alternative for stroke assessment.
Area of Science:
- Medical imaging analysis
- Neurology
- Artificial intelligence in healthcare
Background:
- Intracerebral hemorrhage (ICH) is a severe type of stroke, often assessed using CT scans.
- Manual segmentation of ICH on CT scans is the gold standard but is time-consuming and prone to variability.
- Automated segmentation methods are needed to improve efficiency and consistency in ICH volume estimation.
Purpose of the Study:
- To develop and validate a fully automated segmentation approach for intracerebral hemorrhage (ICH) using CT scans.
- To compare the performance of a random forest algorithm against other machine learning models for ICH segmentation.
- To provide an accessible tool for automated ICH segmentation.
Main Methods:
- Utilized 112 baseline CT scans from the MISTIE trial patients.
- Developed four models: logistic regression, LASSO-penalized logistic regression, generalized additive model (GAM), and random forest classifier.
- Validated models using Dice Similarity Index (DSI) and volume correlation against expert manual segmentations.
Main Results:
- The random forest model achieved the highest median Dice Similarity Index (DSI) of 0.899, outperforming logistic, LASSO, and GAM models.
- Correlation between manual and random forest predicted hemorrhage volumes was high (0.93).
- The automated random forest approach demonstrated accurate and reliable ICH segmentation across diverse imaging centers.
Conclusions:
- A fully automated random forest segmentation approach provides accurate and efficient assessment of intracerebral hemorrhage.
- This method offers a viable alternative to manual segmentation, reducing time and inter-reader variability.
- An R package and Shiny application are available for implementing and testing the proposed ICH segmentation approach.
Introduction:
Intracerebral hemorrhage (ICH), where a blood vessel ruptures into areas of the brain, accounts for approximately 10-15% of all strokes. X-ray computed tomography (CT) scanning is largely used to assess the location and volume of these hemorrhages. Manual segmentation of the CT scan using planimetry by an expert reader is the gold standard for volume estimation, but is time-consuming and has within- and across-reader variability. We propose a fully automated segmentation approach using a random forest algorithm with features extracted from X-ray computed tomography (CT) scans.
Methods:
The Minimally Invasive Surgery plus rt-PA in ICH Evacuation (MISTIE) trial was a multi-site Phase II clinical trial that tested the safety of hemorrhage removal using recombinant-tissue plasminogen activator (rt-PA). For this analysis, we use 112 baseline CT scans from patients enrolled in the MISTE trial, one CT scan per patient. ICH was manually segmented on these CT scans by expert readers. We derived a set of imaging predictors from each scan. Using 10 randomly-selected scans, we used a first-pass voxel selection procedure based on quantiles of a set of predictors and then built 4 models estimating the voxel-level probability of ICH. The models used were: 1) logistic regression, 2) logistic regression with a penalty on the model parameters using LASSO, 3) a generalized additive model (GAM) and 4) a random forest classifier. The remaining 102 scans were used for model validation.For each validation scan, the model predicted the probability of ICH at each voxel. These voxel-level probabilities were then thresholded to produce binary segmentations of the hemorrhage. These masks were compared to the manual segmentations using the Dice Similarity Index (DSI) and the correlation of hemorrhage volume of between the two segmentations. We tested equality of median DSI using the Kruskal-Wallis test across the 4 models. We tested equality of the median DSI from sets of 2 models using a Wilcoxon signed-rank test.
Results:
All results presented are for the 102 scans in the validation set. The median DSI for each model was: 0.89 (logistic), 0.885 (LASSO), 0.88 (GAM), and 0.899 (random forest). Using the random forest results in a slightly higher median DSI compared to the other models. After Bonferroni correction, the hypothesis of equality of median DSI was rejected only when comparing the random forest DSI to the DSI from the logistic (p < 0.001), LASSO (p < 0.001), or GAM (p < 0.001) models. In practical terms the difference between the random forest and the logistic regression is quite small. The correlation (95% CI) between the volume from manual segmentation and the predicted volume was 0.93 (0.9,0.95) for the random forest model. These results indicate that random forest approach can achieve accurate segmentation of ICH in a population of patients from a variety of imaging centers. We provide an R package (https://github.com/muschellij2/ichseg) and a Shiny R application online (http://johnmuschelli.com/ich_segment_all.html) for implementing and testing the proposed approach.
