Related Experiment Video
Updated: Jun 17, 2025
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
Deep learning models for separate segmentations of intracerebral and intraventricular hemorrhage on head CT and
Yifan Li1, Ruijie Zhang2,3,4, Ying Li5
1School of Medical Technology, School of Medical Imaging, and Tianjin Key Laboratory of Functional Imaging, Tianjin Medical University, Tianjin, China.
Insights
A new deep learning model, REUnet, accurately segments intracerebral hemorrhage (ICH) and intraventricular hemorrhage (IVH). It also provides reliable quality assessment for IVH segmentation, aiding clinical decisions for spontaneous ICH patients.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Neurology
Background:
- Accurate volume measurement of intracerebral hemorrhage (ICH) and intraventricular hemorrhage (IVH) is crucial for treating spontaneous ICH.
- Existing ICH and IVH segmentation tools lack external validation and quality assessment.
Purpose of the Study:
- Develop a robust deep learning model for ICH and IVH segmentation with external validation.
- Provide a method for assessing the quality of IVH segmentation.
Main Methods:
- A Residual Encoding Unet (REUnet) model was developed and trained on 977 CT images.
- The model was externally validated on 375 CT images and compared to six other deep learning models.
- Prototype Segmentation (ProtoSeg), Test Time Dropout (TTD), and Test Time Augmentation (TTA) were used for segmentation quality assessment.
Main Results:
- REUnet demonstrated superior performance in ICH and IVH segmentation compared to other models, with high Dice scores.
- REUnet-generated volumes showed strong concordance with manual segmentations (0.944-0.987).
- ProtoSeg effectively assessed IVH segmentation quality, correlating well with Dice scores and identifying low-quality results.
Conclusions:
- REUnet is a promising tool for accurate, automated ICH and IVH segmentation.
- The model facilitates therapeutic decision-making for spontaneous ICH patients.
- Effective IVH segmentation quality assessment is now feasible in clinical practice.
Background:
The volume measurement of intracerebral hemorrhage (ICH) and intraventricular hemorrhage (IVH) provides critical information for precise treatment of patients with spontaneous ICH but remains a big challenge, especially for IVH segmentation. However, the previously proposed ICH and IVH segmentation tools lack external validation and segmentation quality assessment.
Purpose:
This study aimed to develop a robust deep learning model for the segmentation of ICH and IVH with external validation, and to provide quality assessment for IVH segmentation.
Methods:
In this study, a Residual Encoding Unet (REUnet) for the segmentation of ICH and IVH was developed using a dataset composed of 977 CT images (all contained ICH, and 338 contained IVH; a five-fold cross-validation procedure was adopted for training and internal validation), and externally tested using an independent dataset consisting of 375 CT images (all contained ICH, and 105 contained IVH). The performance of REUnet was compared with six other advanced deep learning models. Subsequently, three approaches, including Prototype Segmentation (ProtoSeg), Test Time Dropout (TTD), and Test Time Augmentation (TTA), were employed to derive segmentation quality scores in the absence of ground truth to provide a way to assess the segmentation quality in real practice.
Results:
For ICH segmentation, the median (lower-quantile-upper quantile) of Dice scores obtained from REUnet were 0.932 (0.898-0.953) for internal validation and 0.888 (0.859-0.916) for external test, both of which were better than those of other models while comparable to that of nnUnet3D in external test. For IVH segmentation, the Dice scores obtained from REUnet were 0.826 (0.757-0.868) for internal validation and 0.777 (0.693-0.827) for external tests, which were better than those of all other models. The concordance correlation coefficients between the volumes estimated from the REUnet-generated segmentations and those from the manual segmentations for both ICH and IVH ranged from 0.944 to 0.987. For IVH segmentation quality assessment, the segmentation quality score derived from ProtoSeg was correlated with the Dice Score (Spearman r = 0.752 for the external test) and performed better than those from TTD (Spearman r = 0.718) and TTA (Spearman r = 0.260) in the external test. By setting a threshold to the segmentation quality score, we were able to identify low-quality IVH segmentation results by ProtoSeg.
Conclusions:
The proposed REUnet offers a promising tool for accurate and automated segmentation of ICH and IVH, and for effective IVH segmentation quality assessment, and thus exhibits the potential to facilitate therapeutic decision-making for patients with spontaneous ICH in clinical practice.
