Improving Ischemic Stroke Care With MRI and Deep Learning Artificial Intelligence

Yu, Yannan; Heit, Jeremy J; Zaharchuk, Greg

doi:10.1097/rmr.0000000000000290

Cited by 14 publications

(9 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Accurate and complete evaluation of infarction is the basis of determining the individualized treatment strategy for AIS. Among them, neuroimaging data-based treatment may push into a new era of AIS prognosis (17,18). Based on our previous ndings on tiro ban, we re-evaluated the response of tiro ban treatment according to imaging features.…”

Section: Discussionmentioning

confidence: 99%

Subtyping treatment response of tirofiban in acute ischemic stroke based on neuroimaging features

Han

Ding

et al. 2023

Preprint

View full text Add to dashboard Cite

Our previous trial demonstrated that tirofiban was effective and safe in acute ischemic stroke (AIS) patients who were not undergoing early recanalization treatments. We aimed to further evaluate the structural MRI characteristics and their clinical significance to better predict and guide tirofiban treatment. In this post hoc analysis of imaging features, the location of infarcts (anterior circulation stroke [ACS] vs posterior circulation stroke [PCS]), degree of cerebral artery stenosis (≤ 69% vs ≥ 70% or occlusion), total infarct volume and ASPECTS score were used to predict the treatment response of tirofiban, defined as a proportion of excellent functional outcome (modified Rankin Scale (mRS) score of 0–1) and favorable functional outcome (mRS score of 0–2) at 90 days. Patients with ACS were more likely to achieve excellent functional outcome (p = 0.004) and favorable functional outcome (p = 0.008) when treated with tirofiban. However, there were no significant differences between the two groups for patients with PCS. For patients due to severe stenosis (≥ 70% or occlusion), there were significant differences between the two groups (p = 0.002 for mRS 0–1; p = 0.011 for mRS 0–2). Meanwhile, we found that tirofiban treatment improved clinical outcome only in patients with ASPECTS (8–10) (p = 0.016). In addition, we found that the effect of tirofiban treatment was independent of total infarct volume. The neuroimaging data supported that patients with ACS and severe stenosis were recommended for the application of tirofiban, and better treatment response could be predicted independent of total infarct volume.

show abstract

Section: Discussionmentioning

confidence: 99%

Subtyping treatment response of tirofiban in acute ischemic stroke based on neuroimaging features

Han

Ding

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Making an accurate and complete evaluation of infarction is the basis for determining the individualized treatment strategy for AIS patients. Among them, neuroimaging data‐based analysis may lead to a new era of good prognosis for AIS patients 16,17 . Based on our previous findings on tirofiban, we re‐evaluated the treatment response of tirofiban according to neuroimaging features.…”

Section: Discussionmentioning

confidence: 99%

Subtyping treatment response of tirofiban in acute ischemic stroke based on neuroimaging features

Han,

Man,

Ding

et al. 2023

Clinical Translational Sci

View full text Add to dashboard Cite

In a previously published clinical trial, we demonstrated that tirofiban was effective and safe in acute ischemic stroke (AIS) patients who did not undergo early recanalization treatments. We aimed to evaluate neuroimaging characteristics and their clinical significance to guide tirofiban treatment. In this post hoc analysis, location of infarcts (anterior circulation stroke [ACS] vs posterior circulation stroke [PCS]), degree of cerebral artery stenosis (≤ 69% vs ≥ 70% or occlusion), total infarct volume and ASPECTS were used to predict the treatment effects of tirofiban, defined as the proportions of excellent and favorable functional outcome (modified Rankin Scale (mRS) score of 0‐1, 0‐2) at 90 days. ACS patients were more likely to achieve excellent (OR, 2.08; 95% CI, 1.25 to 3.45; p = 0.004) and favorable functional outcome (OR, 2.28; 95% CI, 1.24 to 4.22; p = 0.008) when treated with tirofiban. However, there was no significant difference in PCS patients between tirofiban and control group. For patients due to severe stenosis (≥ 70% or occlusion), tirofiban treatment improved the proportions of good outcome (OR, 2.84; 95% CI, 1.44 to 5.60, p = 0.002 for mRS 0‐1; OR, 2.42; 95% CI, 1.22 to 4.77, p = 0.011 for mRS 0‐2). Meanwhile, we found that tirofiban improved outcome in patients with ASPECTS (8‐10), and was independent of total infarct volume. These findings supported the hypothesis that patients with ACS and severe stenosis may be recommended for the treatment with tirofiban, which could be predicted independent of total infarct volume.

show abstract

“…The data extracted from radiomicroscopy, when combined with other clinical data and correlated with outcome, can create accurate, robust, and evidence-based clinical decision support systems (CDSS) [ 62 , 119 ]. The rationale for radiomics is that quantitative variables based on individual voxels are more sensitive to various clinical endpoints than the qualitative radiologic, histopathologic, and clinical data routinely used in clinical practice [ 120 , 121 , 122 , 123 , 124 ]. An extension of radiomics is radiogenomics, which aims to correlate imaging data with some known genetic predictors of response to therapy and metastatic spread, with potential prognostic utility [ 92 , 125 ].…”

Section: Radiomicsmentioning

confidence: 99%

Advanced Magnetic Resonance Imaging (MRI) Techniques: Technical Principles and Applications in Nanomedicine

Bruno

Granata

Bellisari

et al. 2022

Cancers

View full text Add to dashboard Cite

In the last decades, nanotechnology has been used in a wide range of biomedical applications, both diagnostic and therapeutic. In this scenario, imaging techniques represent a fundamental tool to obtain information about the properties of nanoconstructs and their interactions with the biological environment in preclinical and clinical settings. This paper reviews the state of the art of the application of magnetic resonance imaging in the field of nanomedicine, as well as the use of nanoparticles as diagnostic and therapeutic tools, especially in cancer, including the characteristics that hinder the use of nanoparticles in clinical practice.

show abstract

Improving Ischemic Stroke Care With MRI and Deep Learning Artificial Intelligence

Cited by 14 publications

References 61 publications

Subtyping treatment response of tirofiban in acute ischemic stroke based on neuroimaging features

Subtyping treatment response of tirofiban in acute ischemic stroke based on neuroimaging features

Subtyping treatment response of tirofiban in acute ischemic stroke based on neuroimaging features

Advanced Magnetic Resonance Imaging (MRI) Techniques: Technical Principles and Applications in Nanomedicine

Contact Info

Product

Resources

About