Automatic hemorrhage segmentation on head CT scan for traumatic brain injury using 3D deep learning model

Inkeaw, Papangkorn; Angkurawaranon, Salita; Khumrin, Piyapong; Inmutto, Nakarin; Traisathit, Patrinee; Chaijaruwanich, Jeerayut; Angkurawaranon, Chaisiri; Chitapanarux, Imjai

doi:10.1016/j.compbiomed.2022.105530

Cited by 34 publications

(24 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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.…”

Section: Discussionmentioning

confidence: 93%

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

et al. 2022

View full text Add to dashboard Cite

(1) Background: Radiomics analysis of spontaneous intracerebral hemorrhages on computed tomography (CT) images has been proven effective in predicting hematoma expansion and poor neurologic outcome. In contrast, there is limited evidence on its predictive abilities for traumatic intraparenchymal hemorrhage (IPH). (2) Methods: A retrospective analysis of 107 traumatic IPH patients was conducted. Among them, 45 patients (42.1%) showed hemorrhagic progression of contusion (HPC) and 51 patients (47.7%) had poor neurological outcome. The IPH on the initial CT was manually segmented for radiomics analysis. After feature extraction, selection and repeatability evaluation, several machine learning algorithms were used to derive radiomics scores (R-scores) for the prediction of HPC and poor neurologic outcome. (3) Results: The AUCs for R-scores alone to predict HPC and poor neurologic outcome were 0.76 and 0.81, respectively. Clinical parameters were used to build comparison models. For HPC prediction, variables including age, multiple IPH, subdural hemorrhage, Injury Severity Score (ISS), international normalized ratio (INR) and IPH volume taken together yielded an AUC of 0.74, which was significantly (p = 0.022) increased to 0.83 after incorporation of the R-score in a combined model. For poor neurologic outcome prediction, clinical variables of age, Glasgow Coma Scale, ISS, INR and IPH volume showed high predictability with an AUC of 0.92, and further incorporation of the R-score did not improve the AUC. (4) Conclusion: The results suggest that radiomics analysis of IPH lesions on initial CT images has the potential to predict HPC and poor neurologic outcome in traumatic IPH patients. The clinical and R-score combined model further improves the performance of HPC prediction.

show abstract

Section: Discussionmentioning

confidence: 93%

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

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Inkeaw et al proposed a 3D convolutional neural network, which processes CT images with different resolutions through four parallel paths, and segments different types of bleeding lesions through the region-growing method. The median DICE coefficient of segmentation for each bleeding subtype was higher than 0.37 ( Inkeaw et al, 2022 ). Xu et al (2021) adopted the densely connected U-Net architecture to test on nearly 300 ICH images and achieved a DICE coefficient of 0.89.…”

Section: Introductionmentioning

confidence: 83%

A symmetric prior knowledge based deep learning model for intracerebral hemorrhage lesion segmentation

Nijiati¹,

Tuersun²,

Zhang³

et al. 2022

Front. Physiol.

View full text Add to dashboard Cite

Background: Accurate localization and classification of intracerebral hemorrhage (ICH) lesions are of great significance for the treatment and prognosis of patients with ICH. The purpose of this study is to develop a symmetric prior knowledge based deep learning model to segment ICH lesions in computed tomography (CT).Methods: A novel symmetric Transformer network (Sym-TransNet) is designed to segment ICH lesions in CT images. A cohort of 1,157 patients diagnosed with ICH is established to train (n = 857), validate (n = 100), and test (n = 200) the Sym-TransNet. A healthy cohort of 200 subjects is added, establishing a test set with balanced positive and negative cases (n = 400), to further evaluate the accuracy, sensitivity, and specificity of the diagnosis of ICH. The segmentation results are obtained after data pre-processing and Sym-TransNet. The DICE coefficient is used to evaluate the similarity between the segmentation results and the segmentation gold standard. Furthermore, some recent deep learning methods are reproduced to compare with Sym-TransNet, and statistical analysis is performed to prove the statistical significance of the proposed method. Ablation experiments are conducted to prove that each component in Sym-TransNet could effectively improve the DICE coefficient of ICH lesions.Results: For the segmentation of ICH lesions, the DICE coefficient of Sym-TransNet is 0.716 ± 0.031 in the test set which contains 200 CT images of ICH. The DICE coefficients of five subtypes of ICH, including intraparenchymal hemorrhage (IPH), intraventricular hemorrhage (IVH), extradural hemorrhage (EDH), subdural hemorrhage (SDH), and subarachnoid hemorrhage (SAH), are 0.784 ± 0.039, 0.680 ± 0.049, 0.359 ± 0.186, 0.534 ± 0.455, and 0.337 ± 0.044, respectively. Statistical results show that the proposed Sym-TransNet can significantly improve the DICE coefficient of ICH lesions in most cases. In addition, the accuracy, sensitivity, and specificity of Sym-TransNet in the diagnosis of ICH in 400 CT images are 91.25%, 98.50%, and 84.00%, respectively.Conclusion: Compared with recent mainstream deep learning methods, the proposed Sym-TransNet can segment and identify different types of lesions from CT images of ICH patients more effectively. Moreover, the Sym-TransNet can diagnose ICH more stably and efficiently, which has clinical application prospects.

show abstract

“…Our semi-automated method adds to the growing literature of potential applications for machine learning methods in radiological interpretation and triage, and removes some of this intra- and inter-rater variability. Many computer-assisted methods for delineation of blood volume have previously focused on segmentation of haemorrhages within non-subarachnoid space [39,56–59]. However, application of these methods to aSAH has been noted to be challenging [40,57], and accordingly Dice scores for segmentations of subarachnoid blood have been consistently lower than for other haemorrhage subtypes [37,53,60,61], and convolutional networks used to automatically segment intracranial haemorrhage that includes subarachnoid blood have only achieved low-to-moderate Dice scores [62,63].…”

Section: Discussionmentioning

confidence: 99%

“…While previous machine learning methods have been used to detect and classify intracranial haemorrhages [36,37], by providing saliency maps highlighting probable regions where blood is distributed [38], these methods do not produce segmentations from which precise blood volumes can be obtained. Quantitative volumetric segmentations have typically been applied to haemorrhagic lesions from traumatic brain injuries, with focus on subdural haematoma, extradural haematoma, and intraparenchymal haemorrhage [39][40][41][42][43]. Less work has attempted the automated segmentation of subarachnoid blood [37], and to our knowledge this work represents the first use of machine learning techniques to segment blood from CT head scans in aneurysmal SAH patients.…”

Section: Interpretation and Contextmentioning

confidence: 99%

Predicting vasospasm risk using first presentation aneurysmal subarachnoid haemorrhage volume: a semi-automated CT image segmentation analysis in ITK-SNAP

Street

Pandit

Toma

2023

Preprint

View full text Add to dashboard Cite

PurposeCerebral vasospasm following aneurysmal subarachnoid haemorrhage (aSAH) is a significant complication associated with poor neurological outcomes. We present a novel, semi-automated pipeline in ITK-SNAP to segment subarachnoid blood volume from initial CT head (CTH) scans and use this to predict future radiological vasospasm.Methods42 patients were admitted between February 2020 and December 2021 to our tertiary neurosciences centre, and whose initial referral CTH scan was used for this retrospective cohort study. Blood load was segmented using a semi-automated random forest classifier and active contour evolution implemented in the open-source medical imaging analysis software ITK-SNAP. Clinical data were extracted from electronic healthcare records in order to fit models aimed at predicting radiological vasospasm risk.ResultsSemi-automated segmentations demonstrated excellent agreement with manual, expert-derived volumes (mean Dice coefficient=0.92). Total normalised blood volume, extracted from CTH images at first presentation, was significantly associated with greater odds of later radiological vasospasm, increasing by approximately 7% for each additional cm3of blood (OR=1.069, 95% CI: 1.021-1.120; p<.005). Greater blood volume was also significantly associated with vasospasm of a higher Lindegaard ratio, of longer duration, and a greater number of discrete episodes. Total blood volume predicted radiological vasospasm with a greater accuracy as compared to the modified Fisher scale (AUC= 0.86 vs 0.70), and was of independent predictive value.ConclusionSemi-automated methods provide a plausible pipeline for the segmentation of blood from CT head images in aSAH, and total blood volume is a robust, extendable predictor of radiological vasospasm, outperforming the modified Fisher scale. Greater subarachnoid blood volume significantly increases the odds of subsequent vasospasm, its time course and its severity.

show abstract

Automatic hemorrhage segmentation on head CT scan for traumatic brain injury using 3D deep learning model

Cited by 34 publications

References 16 publications

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

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

A symmetric prior knowledge based deep learning model for intracerebral hemorrhage lesion segmentation

Predicting vasospasm risk using first presentation aneurysmal subarachnoid haemorrhage volume: a semi-automated CT image segmentation analysis in ITK-SNAP

Contact Info

Product

Resources

About