Combining unsupervised and supervised learning for predicting the final stroke lesion

@article{Pinto2020CombiningUA,
  title={Combining unsupervised and supervised learning for predicting the final stroke lesion},
  author={Adriano Pinto and S{\'e}rgio Pereira and Raphael Meier and Roland Wiest and Victor Alves and Mauricio Reyes and Carlos A. Silva},
  journal={Medical image analysis},
  year={2020},
  volume={69},
  pages={
          101888
        }
}
View on PubMed
arxiv.org
8 Citations
Highly Influential Citations
1
Background Citations
1
Methods Citations
2

8 Citations

Prediction of Tissue Damage Using a User-Independent Machine Learning Algorithm vs. Tmax Threshold Maps

Test the accuracy of a fully automated stroke tissue estimation algorithm (FASTER) to predict final lesion volumes in an independent dataset in patients with acute stroke and found the decision forest algorithm overestimated the final infarct volume in patients without reperfusion.

Deep Learning in Ischemic Stroke Imaging Analysis: A Comprehensive Review

The current state-of-the-art deep learning technology in acute ischemic stroke imaging is surveyed, particularly in exploring the potential function of stroke diagnosis and multimodal prognostication.

Performance of Machine Learning for Tissue Outcome Prediction in Acute Ischemic Stroke: A Systematic Review and Meta-Analysis

Machine learning (ML) has been proposed for lesion segmentation in acute ischemic stroke (AIS). This study aimed to provide a systematic review and meta-analysis of the overall performance of current…

Radiomics, machine learning, and artificial intelligence—what the neuroradiologist needs to know

Deep radiomics uses CNNs to directly extract features and obviate the need for predefined features and common limitations and pitfalls in AI-based research in neuroradiology are limited sample sizes, selection bias, as well as overfitting and underfitting.

Deep learning for neurodegenerative disorder (2016 to 2022): A systematic review

Artificial Intelligence in Acute Ischemic Stroke

Intracerebral Haemorrhage Growth Prediction Based on Displacement Vector Field and Clinical Metadata

Title : " Deciphering astrocyte polarization in perinatal white matter injury and its role in disease pathogenesis

References

SHOWING 1-10 OF 69 REFERENCES

Enhancing clinical MRI Perfusion maps with data-driven maps of complementary nature for lesion outcome prediction

The ability of the proposed approach to improve prediction of tissue at risk before therapy, as compared to only using the standard clinical perfusion maps, is demonstrated, suggesting on the potential benefits of the data-driven raw perfusion data modelling approach.

Fully automated stroke tissue estimation using random forest classifiers (FASTER)

  • R. McKinleyL. Häni R. Wiest
  • Medicine, Biology
    Journal of cerebral blood flow and metabolism : official journal of the International Society of Cerebral Blood Flow and Metabolism
  • 2017
It is concluded that prediction of tissue damage in the event of either persistent occlusion or immediate and complete recanalization, from spatial features derived from MRI, provides a substantial improvement beyond predefined thresholds.

Towards automatic MRI volumetry for treatment selection in acute ischemic stroke patients

This work proposes a novel, more elaborate image analysis approach that is based on supervised classification methods to automatically segment and predict the extent of the tissue compartments of interest (healthy, infarct, penumbra regions).

MRI based diffusion and perfusion predictive model to estimate stroke evolution.

Regional Prediction of Tissue Fate in Acute Ischemic Stroke

A quantitative predictive model of tissue fate that combines regional imaging features available after onset that combines cuboids randomly sampled during the learning process is presented, showing the superiority of the regional model vs. a single-voxel-based approach.

Prediction of Tissue Outcome and Assessment of Treatment Effect in Acute Ischemic Stroke Using Deep Learning

A predictive model capable of automatically identifying and combining acute imaging features to accurately predict final lesion volume and seems to be able to differentiate outcomes based on treatment strategy with the volume of final infarct being significantly different.

ISLES 2015 ‐ A public evaluation benchmark for ischemic stroke lesion segmentation from multispectral MRI

Prediction of final infarct volume from native CT perfusion and treatment parameters using deep learning

ISLES 2016 and 2017-Benchmarking Ischemic Stroke Lesion Outcome Prediction Based on Multispectral MRI

The Ischemic Stroke Lesion Segmentation challenge, which has ran now consecutively for 3 years, aims to address the problem of comparability by providing a uniformly pre-processed data set and allowing new approaches to be compared directly via the online evaluation system.

Enhancing interpretability of automatically extracted machine learning features: application to a RBM‐Random Forest system on brain lesion segmentation

...