Machine learning identifies stroke features between species

Exploring the potential of machine learning and magnetic resonance imaging in early stroke diagnosis: a bibliometric analysis (2004-2023)

Objective

To examine the focal areas of research in the early diagnosis of stroke through machine learning identification of magnetic resonance imaging characteristics from 2004 to 2023.

Methods

Data were gathered from the Science Citation Index-Expanded (SCI-E) within the Web of Science Core Collection (WoSCC). Utilizing CiteSpace 6.2.R6, a thorough analysis was conducted, encompassing publications, authors, cited authors, countries, institutions, cited journals, references, and keywords. This investigation covered the period from 2004 to 2023, with the data retrieval completed on December 1, 2023, in a single day.

Results

In total, 395 articles were incorporated into the analysis. Prior to 2015, the annual publication count was under 10, but a significant surge in publications was observed post-2015. Institutions and authors from the USA and China have established themselves as mature academic entities on a global scale, forging extensive collaborative networks with other institutions. High-impact journals in this field predominantly feature in top-tier publications, indicating a consensus in the medical community on the application of machine learning for early stroke diagnosis. "deep learning," "magnetic resonance imaging," and "stroke" emerged as the most attention-gathering keywords among researchers. The development in this field is marked by a coexisting pattern of interdisciplinary integration and refinement within major disciplinary branches.

Conclusion

The application of machine learning in the early prediction and personalized medical plans for stroke patients using neuroimaging characteristics offers significant value. The most notable research hotspots currently are the optimal selection of neural imaging markers and the most suitable machine learning algorithm models.

Research on prognostic risk assessment model for acute ischemic stroke based on imaging and multidimensional data

Accurately assessing the prognostic outcomes of patients with acute ischemic stroke and adjusting treatment plans in a timely manner for those with poor prognosis is crucial for intervening in modifiable risk factors. However, there is still controversy regarding the correlation between imaging-based predictions of complications in acute ischemic stroke. To address this, we developed a cross-modal attention module for integrating multidimensional data, including clinical information, imaging features, treatment plans, prognosis, and complications, to achieve complementary advantages. The fused features preserve magnetic resonance imaging (MRI) characteristics while supplementing clinical relevant information, providing a more comprehensive and informative basis for clinical diagnosis and treatment. The proposed framework based on multidimensional data for activity of daily living (ADL) scoring in patients with acute ischemic stroke demonstrates higher accuracy compared to other state-of-the-art network models, and ablation experiments confirm the effectiveness of each module in the framework.

Deep learning-based automated lesion segmentation on mouse stroke magnetic resonance images

Magnetic resonance imaging (MRI) is widely used for ischemic stroke lesion detection in mice. A challenge is that lesion segmentation often relies on manual tracing by trained experts, which is labor-intensive, time-consuming, and prone to inter- and intra-rater variability. Here, we present a fully automated ischemic stroke lesion segmentation method for mouse T2-weighted MRI data. As an end-to-end deep learning approach, the automated lesion segmentation requires very little preprocessing and works directly on the raw MRI scans. We randomly split a large dataset of 382 MRI scans into a subset (n = 293) to train the automated lesion segmentation and a subset (n = 89) to evaluate its performance. We compared Dice coefficients and accuracy of lesion volume against manual segmentation, as well as its performance on an independent dataset from an open repository with different imaging characteristics. The automated lesion segmentation produced segmentation masks with a smooth, compact, and realistic appearance that are in high agreement with manual segmentation. We report dice scores higher than the agreement between two human raters reported in previous studies, highlighting the ability to remove individual human bias and standardize the process across research studies and centers.

Cerebrovascular Gi Proteins Protect Against Brain Hypoperfusion and Collateral Failure in Cerebral Ischemia

Cerebral hypoperfusion and vascular dysfunction are closely related to common risk factors for ischemic stroke such as hypertension, dyslipidemia, diabetes, and smoking. The role of inhibitory G protein-dependent receptor (G_iPCR) signaling in regulating cerebrovascular functions remains largely elusive. We examined the importance of G_iPCR signaling in cerebral blood flow (CBF) and its stability after sudden interruption using various in vivo high-resolution magnetic resonance imaging techniques. To this end, we induced a functional knockout of G_iPCR signaling in the brain vasculature by injection of pertussis toxin (PTX). Our results show that PTX induced global brain hypoperfusion and microvascular collapse. When PTX-pretreated animals underwent transient unilateral occlusion of one common carotid artery, CBF was disrupted in the ipsilateral hemisphere resulting in the collapse of the cortically penetrating microvessels. In addition, pronounced stroke features in the affected brain regions appeared in both MRI and histological examination. Our findings suggest an impact of cerebrovascular G_iPCR signaling in the maintenance of CBF, which may be useful for novel pharmacotherapeutic approaches to prevent and treat cerebrovascular dysfunction and stroke.

Repurposing the mucolytic agent ambroxol for treatment of sub-acute and chronic ischaemic stroke

Ambroxol is a well-known mucolytic expectorant, which has gained much attention in amyotrophic lateral sclerosis, Parkinson's and Gaucher's disease. A specific focus has been placed on ambroxol's glucocerebrosidase-stimulating activity, on grounds that the point mutation of the gba1 gene, which codes for this enzyme, is a risk factor for developing Parkinson's disease. However, ambroxol has been attributed other characteristics, such as the potent inhibition of sodium channels, modification of calcium homeostasis, anti-inflammatory effects and modifications of oxygen radical scavengers. We hypothesized that ambroxol could have a direct impact on neuronal rescue if administered directly after ischaemic stroke induction. We longitudinally evaluated 53 rats using magnetic resonance imaging to examine stroke volume, oedema, white matter integrity, resting state functional MRI and behaviour for 1 month after ischemic stroke onset. For closer mechanistic insights, we evaluated tissue metabolomics of different brain regions in a subgroup of animals using ex vivo nuclear magnetic resonance spectroscopy. Ambroxol-treated animals presented reduced stroke volumes, reduced cytotoxic oedema, reduced white matter degeneration, reduced necrosis, improved behavioural outcomes and complex changes in functional brain connectivity. Nuclear magnetic resonance spectroscopy tissue metabolomic data at 24 h post-stroke proposes several metabolites that are capable of minimizing post-ischaemic damage and that presented prominent shifts during ambroxol treatment in comparison to controls. Taking everything together, we propose that ambroxol catalyzes recovery in energy metabolism, cellular homeostasis, membrane repair mechanisms and redox balance. One week of ambroxol administration following stroke onset reduced ischaemic stroke severity and improved functional outcome in the subacute phase followed by reduced necrosis in the chronic stroke phase.

The predictors of death within 1 year in acute ischemic stroke patients based on machine learning

OBJECTIVE

To explore the predictors of death in acute ischemic stroke (AIS) patients within 1 year based on machine learning (ML) algorithms.

METHODS

This study retrospectively analyzed the clinical data of patients hospitalized and diagnosed with AIS in the Second Affiliated Hospital of Xuzhou Medical University between August 2017 and July 2019. The patients were randomly divided into training and validation sets at a ratio of 7:3, and the clinical characteristic variables of the patients were screened using univariate and multivariate logistics regression. Six ML algorithms, including logistic regression (LR), gradient boosting machine (GBM), extreme gradient boosting (XGB), random forest (RF), decision tree (DT), and naive Bayes classifier (NBC), were applied to develop models to predict death in AIS patients within 1 year. During training, a 10-fold cross-validation approach was used to validate the training set internally, and the models were interpreted using important ranking and the SHapley Additive exPlanations (SHAP) principle. The validation set was used to externally validate the models. Ultimately, the highest-performing model was selected to build a web-based calculator.

RESULTS

Multivariate logistic regression analysis revealed that C-reactive protein (CRP), homocysteine (HCY) levels, stroke severity (SS), and the number of stroke lesions (NOS) were independent risk factors for death within 1 year in patients with AIS. The area under the curve value of the XGB model was 0.846, which was the highest among the six ML algorithms. Therefore, we built an ML network calculator (https://mlmedicine-de-stroke-de-stroke-m5pijk.streamlitapp.com/) based on XGB to predict death in AIS patients within 1 year.

CONCLUSIONS

The network calculator based on the XGB model developed in this study can help clinicians make more personalized and rational clinical decisions.

Deep Learning in Ischemic Stroke Imaging Analysis: A Comprehensive Review

Ischemic stroke is a cerebrovascular disease with a high morbidity and mortality rate, which poses a serious challenge to human health and life. Meanwhile, the management of ischemic stroke remains highly dependent on manual visual analysis of noncontrast computed tomography (CT) or magnetic resonance imaging (MRI). However, artifacts and noise of the equipment as well as the radiologist experience play a significant role on diagnostic accuracy. To overcome these defects, the number of computer-aided diagnostic (CAD) methods for ischemic stroke is increasing substantially during the past decade. Particularly, deep learning models with massive data learning capabilities are recognized as powerful auxiliary tools for the acute intervention and guiding prognosis of ischemic stroke. To select appropriate interventions, facilitate clinical practice, and improve the clinical outcomes of patients, this review firstly surveys the current state-of-the-art deep learning technology. Then, we summarized the major applications in acute ischemic stroke imaging, particularly in exploring the potential function of stroke diagnosis and multimodal prognostication. Finally, we sketched out the current problems and prospects.

Machine learning based analysis of stroke lesions on mouse tissue sections

An unbiased, automated and reliable method for analysis of brain lesions in tissue after ischemic stroke is missing. Manual infarct volumetry or by threshold-based semi-automated approaches is laborious, and biased to human error or biased by many false -positive and -negative data, respectively. Thereby, we developed a novel machine learning, atlas-based method for fully automated stroke analysis in mouse brain slices stained with 2% Triphenyltetrazolium-chloride (2% TTC), named "StrokeAnalyst", which runs on a user-friendly graphical interface. StrokeAnalyst registers subject images on a common spatial domain (a novel mouse TTC- brain atlas of 80 average mathematical images), calculates pixel-based, tissue-intensity statistics (z-scores), applies outlier-detection and machine learning (Random-Forest) models to increase accuracy of lesion detection, and produces volumetry data and detailed neuroanatomical information per lesion. We validated StrokeAnalyst in two separate experimental sets using the filament stroke model. StrokeAnalyst detects stroke lesions in a rater-independent and reproducible way, correctly detects hemispheric volumes even in presence of post-stroke edema and significantly minimizes false-positive errors compared to threshold-based approaches (false-positive rate 1.2-2.3%, p < 0.05). It can process scanner-acquired, and even smartphone-captured or pdf-retrieved images. Overall, StrokeAnalyst surpasses all previous TTC-volumetry approaches and increases quality, reproducibility and reliability of stroke detection in relevant preclinical models.

A Presurgical Unfavorable Prediction Scale of Endovascular Treatment for Acute Ischemic Stroke

Objective

To develop a prognostic prediction model of endovascular treatment (EVT) for acute ischemic stroke (AIS) induced by large-vessel occlusion (LVO), this study applied machine learning classification model light gradient boosting machine (LightGBM) to construct a unique prediction model.

Methods

A total of 973 patients were enrolled, primary outcome was assessed with modified Rankin scale (mRS) at 90 days, and favorable outcome was defined using mRS 0–2 scores. Besides, LightGBM algorithm and logistic regression (LR) were used to construct a prediction model. Then, a prediction scale was further established and verified by both internal data and other external data.

Results

A total of 20 presurgical variables were analyzed using LR and LightGBM. The results of LightGBM algorithm indicated that the accuracy and precision of the prediction model were 73.77 and 73.16%, respectively. The area under the curve (AUC) was 0.824. Furthermore, the top 5 variables suggesting unfavorable outcomes were namely admitting blood glucose levels, age, onset to EVT time, onset to hospital time, and National Institutes of Health Stroke Scale (NIHSS) scores (importance = 130.9, 102.6, 96.5, 89.5 and 84.4, respectively). According to AUC, we established the key cutoff points and constructed prediction scale based on their respective weightings. Then, the established prediction scale was verified in raw and external data and the sensitivity was 80.4 and 83.5%, respectively. Finally, scores &gt;3 demonstrated better accuracy in predicting unfavorable outcomes.

Conclusion

Presurgical prediction scale is feasible and accurate in identifying unfavorable outcomes of AIS after EVT.

Gene clusters based on OLIG2 and CD276 could distinguish molecular profiling in glioblastoma

Background

The molecular profiling of glioblastoma (GBM) based on transcriptomic analysis could provide precise treatment and prognosis. However, current subtyping (classic, mesenchymal, neural, proneural) is time-consuming and cost-intensive hindering its clinical application. A simple and efficient method for classification was imperative.

Methods

In this study, to simplify GBM subtyping more efficiently, we applied a random forest algorithm to conduct 26 genes as a cluster featured with hub genes, OLIG2 and CD276. Functional enrichment analysis and Protein–protein interaction were performed using the genes in this gene cluster. The classification efficiency of the gene cluster was validated by WGCNA and LASSO algorithms, and tested in GSE84010 and Gravandeel’s GBM datasets.

Results

The gene cluster (n = 26) could distinguish mesenchymal and proneural excellently (AUC = 0.92), which could be validated by multiple algorithms (WGCNA, LASSO) and datasets (GSE84010 and Gravandeel’s GBM dataset). The gene cluster could be functionally enriched in DNA elements and T cell associated pathways. Additionally, five genes in the signature could predict the prognosis well (p = 0.0051 for training cohort, p = 0.065 for test cohort).

Conclusions

Our study proved the accuracy and efficiency of random forest classifier for GBM subtyping, which could provide a convenient and efficient method for subtyping Proneural and Mesenchymal GBM.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12967-021-03083-y.