Dataset Information

Prediction of Malignant Acute Middle Cerebral Artery Infarction via Computed Tomography Radiomics.

ABSTRACT: Malignant middle cerebral artery infarction (mMCAi) is a serious complication of cerebral infarction usually associated with poor patient prognosis. In this retrospective study, we analyzed clinical information as well as non-contrast computed tomography (NCCT) and computed tomography angiography (CTA) data from patients with cerebral infarction in the middle cerebral artery (MCA) territory acquired within 24 h from symptoms onset. Then, we aimed to develop a model based on the radiomics signature to predict the development of mMCAi in cerebral infarction patients. Patients were divided randomly into training (n = 87) and validation (n = 39) sets. A total of 396 texture features were extracted from each NCCT image from the 126 patients. The least absolute shrinkage and selection operator regression analysis was used to reduce the feature dimension and construct an accurate radiomics signature based on the remaining texture features. Subsequently, we developed a model based on the radiomics signature and Alberta Stroke Program Early CT Score (ASPECTS) based on NCCT to predict mMCAi. Our prediction model showed a good predictive performance with an AUC of 0.917 [95% confidence interval (CI), 0.863-0.972] and 0.913 [95% CI, 0.795-1] in the training and validation sets, respectively. Additionally, the decision curve analysis (DCA) validated the clinical efficacy of the combined risk factors of radiomics signature and ASPECTS based on NCCT in the prediction of mMCAi development in patients with acute stroke across a wide range of threshold probabilities. Our research indicates that radiomics signature can be an instrumental tool to predict the risk of mMCAi.

SUBMITTER: Wen X

PROVIDER: S-EPMC7358521 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Prediction of Malignant Acute Middle Cerebral Artery Infarction via Computed Tomography Radiomics.

Wen Xuehua X Li Yumei Y He Xiaodong X Xu Yuyun Y Shu Zhenyu Z Hu Xingfei X Chen Junfa J Jiang Hongyang H Gong Xiangyang X

Frontiers in neuroscience 20200707

Malignant middle cerebral artery infarction (mMCAi) is a serious complication of cerebral infarction usually associated with poor patient prognosis. In this retrospective study, we analyzed clinical information as well as non-contrast computed tomography (NCCT) and computed tomography angiography (CTA) data from patients with cerebral infarction in the middle cerebral artery (MCA) territory acquired within 24 h from symptoms onset. Then, we aimed to develop a model based on the radiomics signatu ...[more]

PMID: 32733197

Similar Datasets

Project description:BackgroundEarly diagnosis is crucial to the treatment of breast cancer, but conventional imaging detection is challenging. Radiomics has the potential to improve early diagnostic efficacy in a noninvasive manner. This study examined whether integrating computed tomography (CT) radiomics information based on ultrasound (US) models can improve the efficacy of breast cancer prediction.MethodsWe retrospectively analyzed 420 patients with pathologically confirmed benign or malignant breast tumors. Clinical data and examination images were collected, and the population was divided into training (n=294) and validation (n=126) groups at a ratio of 7:3. The region of interest (ROI) was manually segmented along the tumor boundary using MaZda software, and the features of each ROI was extracted. After dimension reduction and screening, the best features were retained. Subsequently, random forest (RF), support vector machines, and K-nearest neighbor classifiers were used to establish prediction models in an US and combined-methods group.ResultsFinally, 8 of the 379 features were retained in the US group. Random forest was found to be the best model, and the area under the curve (AUC) of the training and validation groups was 0.90 [95% confidence interval (CI): 0.852-0.942] and 0.85 (95% CI: 0.775-0.930), respectively. Meanwhile, 12 of the 750 features were retained in the combined group. In this regard, random forest proved to be the best model, and the AUC of the training and validation group was 0.95 (95% CI: 0.918-0.981) and 0.92 (95% CI: 0.866-0.969), respectively. The calibration curve showed a good fit of the model. The decision curve showed that the clinical net benefit of the combined group was far greater than that of any single examination, and the prediction model of the combined group exhibited a degree of practical clinical value.ConclusionsThe combined model based on US and CT images has potential application value in the prognostic prediction of benign and malignant breast diseases.

Project description:BackgroundMalignant middle cerebral artery infarction is a potentially life-threatening disease. Decompressive hemicraniectomy constitutes an evidence-based treatment practice, especially in patients under 60 years of age; however, recommendations with respect to postoperative management and particularly duration of postoperative sedation lack standardization.ObjectiveThis survey study aimed to analyze the current situation of patients with malignant middle cerebral artery infarction following hemicraniectomy in the neurointensive care setting.Material and methodsFrom 20 September 2021 to 31 October 2021, 43 members of the initiative of German neurointensive trial engagement (IGNITE) network were invited to participate in a standardized anonymous online survey. Descriptive data analysis was performed.ResultsOut of 43 centers 29 (67.4%) participated in the survey, including 24 university hospitals. Of the hospitals 21 have their own neurological intensive care unit. While 23.1% favored a standardized approach regarding postoperative sedation, the majority utilized individual criteria (e.g., intracranial pressure increase, weaning parameters, complications) to assess the need and duration. The timing of targeted extubation varied widely between hospitals (≤ 24 h 19.2%, ≤ 3 days in 30.8%, ≤ 5 days in 19.2%, > 5 days in 15.4%). Early tracheotomy (≤ 7 days) is performed in 19.2% and 80.8% of the centers aim for tracheotomy within 14 days. Hyperosmolar treatment is used on a regular basis in 53.9% and 22 centers (84.6%) agreed to participate in a clinical trial addressing the duration of postoperative sedation and ventilation.ConclusionThe results of this nationwide survey among neurointensive care units in Germany reflect a remarkable heterogeneity in the treatment practices of patients with malignant middle cerebral artery infarction undergoing hemicraniectomy, especially with respect to the duration of postoperative sedation and ventilation. A randomized trial in this matter seems warranted.

Project description:A disrupted blood-brain barrier (BBB) with extravasation of macromolecules plays a critical role in the development of malignant middle cerebral artery infarction (MMI). Proteinuria is considered a marker of generalized endothelial dysfunction, including BBB disruption. This study aimed to clarify whether proteinuria identified in the acute stage of stroke is associated with MMI development. Patients with infarctions involving the middle cerebral artery territory were reviewed. Urine samples collected within 8 hours after stroke were analyzed using urine dipsticks. Patients were divided into proteinuria (urine dipstick reading of 1 + to 4+) and nonproteinuria groups. MMI was present if either signs of uncal herniation or a progressive conscious disturbance were recorded along with a midline shift > 5 mm identified on follow-up computed tomography (CT). Among the 1261 patients identified between January 2010 and June 2019, 138 were eligible for final analyses. Patients in the MMI group had lower Alberta Stroke Program Early CT Scores (ASPECTS), higher National Institutes of Health Stroke Scale scores, and a greater proportion of proteinuria than those in the non-MMI group. Four multivariate logistic regression models were used to clarify the role of proteinuria in MMI development. In model 1, proteinuria was significantly associated with MMI after adjusting for age, sex, dyslipidemia and ASPECTS (OR = 2.987, 95% CI = 1.329-6.716, P = .0081). The risk of developing MMI in patients with proteinuria remained significant in model 2 (OR = 3.066, 95% CI = 1.349-6.968, P = .0075) after adjusting for estimated glomerular filtrate rate (eGFR) < 60ml/min/1.73 m2 in addition to variables in model 1. In model 3, proteinuria was still significantly associated with MMI after adjusting for age, sex, dyslipidemia, ASPECTS, hypertension, diabetes, and atrial fibrillation (OR = 2.521, 95% CI = 1.075-5.912, P = .0335). In model 4, the risk of developing MMI in patients with proteinuria remained significant (OR = 2.579, 95% CI = 1.094-6.079, P = .0304) after adjusting for eGFR < 60ml/min/1.73 m2 in addition to variables in model 3. Proteinuria is independently associated with MMI development. Proteinuria may be a clinically accessible predictor of MMI development.

Project description:AbstractDisrupted blood-brain barrier (BBB) in patients with ischemic stroke plays a critical role in malignant middle cerebral artery infarction (MMI) development.Cerebral white matter changes (WMC), particularly in the deep subcortical area or in severe one, may be also underlain by disrupted BBB. It is unclear whether the presence of WMC with potential premorbid disruption of BBB makes patients susceptible to MMI. Therefore, this study aimed to clarify any putative relationship between the MMI and WMC in terms of their severity and locations.In this case-control study, patients with infarction in the middle cerebral artery territory were retrospectively reviewed. Brain magnetic resonance images were analyzed according to Fazekas scale, and identified WMC were divided into periventricular WMC (PV-WMC) and deep subcortical WMC (deep-WMC). Patients were scored as having WMC, PV-WMC, deep-WMC, severe PV-WMC, and severe deep-WMC according to the severity and locations. Patients were defined as having MMI if either a progressive conscious disturbance or signs of uncal herniation was recorded in combination with a midline shift >5 mm identified on the follow-up computed tomography.Among 297 patients admitted between July 2009 and February 2015, 92 patients were eligible for final analysis. Compared to patients without MMI, patients with MMI had a higher score of National Institutes of Health Stroke Scale, a larger infarct volume, and an increasingly greater proportion of severe PV-WMC, deep-WMC, and severe deep-WMC, respectively. After adjustment for sex, age, infarct volume, and history of hypertension, severe deep-WMC (odds ratio [OR] = 6.362, 95% confidence interval [CI] = 1.444-28.023, P = .0144) and severe PV-WMC (odds ratio = 5.608, 95% confidence interval = 1.107-28.399, P = .0372) were significantly associated with MMI development.MMI and WMC are significantly associated such that MMI development is more likely when PV-WMC or deep-WMC is more severe. We hypothesize that Fazekas scale-defined severe deep-WMC and PV-WMC may be considered as clinically approachable predictors of MMI development. These findings support that the WMC with potential premorbid disrupted BBB may make patients susceptible to MMI, and further prospective study should be conducted to clarify this hypothesis.

Project description:Introduction Decompressive hemicraniectomy (DCE) is routinely performed for intracranial pressure control after malignant middle cerebral artery (MCA) infarction. Decompressed patients are at risk of traumatic brain injury and the syndrome of the trephined until cranioplasty. Cranioplasty after DCE is itself associated with high complication rates. Single-stage surgical strategies may eliminate the need for follow-up surgery while allowing for safe brain expansion and protection from environmental factors. Research question Assess the volume needed for safe expansion of the brain to enable single-stage surgery. Materials and methods We performed a retrospective radiological and volumetric analysis of all patients that had DCE in our clinic between January 2009 and December 2018 and met inclusion criteria. We investigated prognostic parameters in perioperative imaging and assessed clinical outcome. Results Of 86 patients with DCE, 44 fulfilled the inclusion criteria. Median brain swelling was 75.35 mL (8.7–151.2 mL). Median bone flap volume was 113.3 mL (73.34–146.1 mL). Median brain swelling was 1.62 mm below the previous outer rim of the skull (5.3 mm to –2.19 mm). In 79.6% of the patients, the volume of removed bone alone was equivalent to or larger than the additional intracranial volume needed for brain swelling. Discussion and conclusion The space provided by removal of the bone alone was sufficient to match the expansion of the injured brain after malignant MCA infarction in the vast majority of our patients A subgaleal space-expanding flap with a minimal offset can provide protection from trauma and atmospheric pressure without compromising brain expansion. Highlights • Volume augmentation of the swollen brain is smaller than the volume of removed bone in 79.6% of cases.• An additional Volume of about 50 mL would have provided adequate space for the swollen brain in all cases.• Maximum modeled brain swelling outside of the previous skull limit is 2.19 mm.

Dataset Information

Prediction of Malignant Acute Middle Cerebral Artery Infarction via Computed Tomography Radiomics.

Publications

Prediction of Malignant Acute Middle Cerebral Artery Infarction via Computed Tomography Radiomics.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets