An optimal deep learning framework for multi-type hemorrhagic lesions detection and quantification in head CT images for traumatic brain injury

Abstract

Traumatic Brain Injury (TBI) could lead to intracranial hemorrhage (ICH), which has now been identified as a major cause of death after trauma if it is not adequately diagnosed and properly treated within the first 24 hours. CT examination is widely preferred for urgent ICH diagnosis, which enables the fast identification and detection of ICH regions. However, the use of it requires the clinical interpretation by experts to identify the subtypes of ICH. Besides, it is unable to provide the details needed to conduct quantitative assessment, such as the volume and thickness of hemorrhagic lesions, which may have prognostic importance to the decision-making on emergency treatment. In this paper, an optimal deep learning framework is proposed to assist the quantitative assessment for ICH diagnosis and the accurate detection of different subtypes of ICH through head CT scan. Firstly, the format of raw input data is converted from 3D DICOM to NIfTI. Secondly, a pre-trained multi-class semantic segmentation model is applied to each slice of CT images, so as to obtain a precise 3D mask of the whole ICH region. Thirdly, a fine-tuned classification neural network is employed to extract the key features from the raw input data and identify the subtypes of ICH. Finally, a quantitative assessment algorithm is adopted to automatically measure both thickness and volume via the 3D shape mask combined with the output probabilities of the classification network. The results of our extensive experiments demonstrate the effectiveness of the proposed framework where the average accuracy of 96.21 percent is achieved for three types of hemorrhage. The capability of our optimal classification model to distinguish between different types of lesion plays a significant role in reducing the false-positive rate in the existing work. Furthermore, the results suggest that our automatic quantitative assessment algorithm is effective in providing clinically relevant quantification in terms of volume and thickness. It is more important than the qualitative assessment conducted through visual inspection to the decision-making on emergency surgical treatment.

Prediction of Intraparenchymal Hemorrhage Progression and Neurologic Outcome in Traumatic Brain Injury Patients Using Radiomics Score and Clinical Parameters

“…In contrast to spontaneous IPH, the multiplicity and lower imaging contrast due to close locations to bone and extra-axial hemorrhages make traumatic IPH lesions more difficult to segment automatically. Inconsistent performances were reported by recent studies, showing a wide range of Dice coefficient results for automatic traumatic IPH segmentation [ 44 , 45 , 46 ]; however, development in this field is rapid. By using a finely-tuned automatic segmentation tool for traumatic IPH, larger numbers of images can be processed timely for radiomics analysis in the near future.…”

Automated identification and quantification of traumatic brain injury from CT scans: Are we there yet?

“…The authors of Monteiro et al [ 28 ] relied on Deep Medic, [ 76 ] a 3D-CNN architecture, for the 3D-segmentation of IPH, EDH, edema, and IVH. Phaphuangwittayakul et al The authors in [ 29 ] developed a 3D-segmentation model and trained it with the Physio Net dataset to detect EDH, SDH, and IPH. Some modifications of U-net were also implemented in other studies that focused on voxel-wise hematoma segmentations.…”

The Added Value of Intraventricular Hemorrhage on the Radiomics Analysis for the Prediction of Hematoma Expansion of Spontaneous Intracerebral Hemorrhage

“…Even though radiomics analysis shows promising results for HE prediction, the segmentation of hematoma is required, which hinders its clinical application in the emergency room. Deep learning has been shown to provide a promising solution to achieve expert-level detection and segmentation of intracranial hemorrhage [ 37 , 38 , 39 , 40 , 41 ]. Precise differentiation of IVH and IPH is challenging, which requires judgement based on the knowledge of neuroanatomy and is usually performed manually by experienced neuroradiologists.…”