Automatic lesion analysis for increased efficiency in outcome prediction of traumatic brain injury

TL;DR

This paper demonstrates that automated extraction of lesion features from CT scans using deep learning can predict traumatic brain injury outcomes as effectively or better than traditional qualitative scoring methods, aiding prognosis.

Contribution

It introduces a deep learning-based method for automatic lesion segmentation in CT scans and shows its effectiveness in TBI outcome prediction, surpassing traditional scoring systems.

Findings

Automated CT features match or outperform Marshall score in outcome prediction.

Lesion volumes and statistics improve prognostic models.

Frontal extra-axial lesions are key indicators of poor outcome.

Abstract

The accurate prognosis for traumatic brain injury (TBI) patients is difficult yet essential to inform therapy, patient management, and long-term after-care. Patient characteristics such as age, motor and pupil responsiveness, hypoxia and hypotension, and radiological findings on computed tomography (CT), have been identified as important variables for TBI outcome prediction. CT is the acute imaging modality of choice in clinical practice because of its acquisition speed and widespread availability. However, this modality is mainly used for qualitative and semi-quantitative assessment, such as the Marshall scoring system, which is prone to subjectivity and human errors. This work explores the predictive power of imaging biomarkers extracted from routinely-acquired hospital admission CT scans using a state-of-the-art, deep learning TBI lesion segmentation method. We use lesion volumes and corresponding lesion statistics as inputs for an extended TBI outcome prediction model. We compare the predictive power of our proposed features to the Marshall score, independently and when paired with classic TBI biomarkers. We find that automatically extracted quantitative CT features perform similarly or better than the Marshall score in predicting unfavourable TBI outcomes. Leveraging automatic atlas alignment, we also identify frontal extra-axial lesions as important indicators of poor outcome. Our work may contribute to a better understanding of TBI, and provides new insights into how automated neuroimaging analysis can be used to improve prognostication after TBI.