A Machine Learning Approach for Classifying Ischemic Stroke Onset Time From Imaging

Ho, K.C.; Speier, William; Zhang, Haoyue; Scalzo, Fabien; El‐Saden, Suzie; Arnold, Corey

doi:10.1109/tmi.2019.2901445

Cited by 90 publications

(70 citation statements)

References 49 publications

(50 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Another study evaluating various traditional ML models in predicting stroke onset time demonstrated that incorporation of DL features to the models improved AUC compared with the ground truth (ie, a DWI-FLAIR mismatch), with the optimal AUC of 0.765 incorporating logistic regression and DL features of MR imaging and MR perfusion (MRP) images. 50 Lee et al 51 used DWI-FLAIR mismatch to predict stroke onset time ,4.5 hours and found that traditional ML models were more sensitive than stroke neurologists (sensitivity ¼ 48.5% for stroke neurologists vs 75.8% for logistic regression; P ¼ .020; 72.7% for SVM, P ¼ .033; 75.8% for RF, P ¼ .013).…”

Section: Additional Factors In Treatment Selectionmentioning

confidence: 99%

Artificial Intelligence and Acute Stroke Imaging

Soun¹,

Chow

Nagamine

et al. 2020

AJNR Am J Neuroradiol

142

View full text Add to dashboard Cite

Artificial intelligence technology is a rapidly expanding field with many applications in acute stroke imaging, including ischemic and hemorrhage subtypes. Early identification of acute stroke is critical for initiating prompt intervention to reduce morbidity and mortality. Artificial intelligence can help with various aspects of the stroke treatment paradigm, including infarct or hemorrhage detection, segmentation, classification, large vessel occlusion detection, Alberta Stroke Program Early CT Score grading, and prognostication. In particular, emerging artificial intelligence techniques such as convolutional neural networks show promise in performing these imaging-based tasks efficiently and accurately. The purpose of this review is twofold: first, to describe AI methods and available public and commercial platforms in stroke imaging, and second, to summarize the literature of current artificial intelligence-driven applications for acute stroke triage, surveillance, and prediction. ABBREVIATIONS: AI ¼ artificial intelligence; ANN ¼ artificial neural network; AUC ¼ area under the curve; CNN ¼ convolutional neural network; DL ¼ deep learning; ICC ¼ intraclass correlation coefficient; ICH ¼ intracranial hemorrhage; LVO ¼ large vessel occlusion; ML ¼ machine learning; MRP ¼ MR perfusion; RF ¼ random forest; SVM ¼ support vector machine S troke is the second leading cause of death worldwide with an annual mortality of about 5.5 million. 1,2 In the United States, nearly 800,000 people have a stroke annually, and the economic burden of stroke is estimated at $34 billion per year. 3 Morbidity is high, with more than half of patients with stroke left chronically disabled. 2 Neuroimaging is an important tool for the detection, characterization, and prognostication of acute strokes, including ischemic and hemorrhagic subtypes. Artificial intelligence (AI) technology is a rapidly burgeoning field, providing a promising avenue for fast and efficient imaging analysis. 4 AI applications for imaging of acute cerebrovascular disease have been implemented, including tools for triage, quantification, surveillance, and prediction. This review aims to summarize the current landscape of AIdriven applications for acute cerebrovascular disease assessment focusing primarily on deep learning (DL) methods. OVERVIEW OF AI Although AI, machine learning (ML), and DL are used interchangeably, these in fact represent subdisciplines. Specifically, DL is a subset of ML, and ML is a subset of AI (Fig 1). Broadly, AI uses computers to perform tasks that typically require human knowledge. ML, a subset of AI, uses statistical approaches to enable machines to optimize outcome prediction as they are exposed to data and train computers for pattern recognition, a task generally requiring human intelligence. 5 ML offers several potential advantages over visual inspection by human experts, including objective and quantitative evaluation, the ability to detect subtle voxel-level patterns, speed, and large-scale implementation. Feature selection, classifi...

show abstract

Section: Additional Factors In Treatment Selectionmentioning

confidence: 99%

Artificial Intelligence and Acute Stroke Imaging

Soun¹,

Chow

Nagamine

et al. 2020

AJNR Am J Neuroradiol

142

View full text Add to dashboard Cite

show abstract

“…Instead of predicting the future, one can also use ML to go back in time and estimate the date at which the disease started. For instance, Ho et al [12] distinguished patients with time-sincestroke lower or higher than 4.5 hours from diffusion, perfusion and FLAIR MRI.…”

Section: Predicting Evolutionmentioning

confidence: 99%

“…Computer-aided diagnosis has moved from the discrimination between a single disease and controls to differential diagnosis [4*-8]. In addition to diagnosis, models for predicting the subsequent evolution of patients have been developed [9][10][11][12][13]. Most of the initial work focused on neuroimaging as the data source, because it is inherently digital and databases are easy to access.…”

Section: Introductionmentioning

confidence: 99%

Machine learning for classification and prediction of brain diseases: recent advances and upcoming challenges

Burgos

Colliot

2020

Current Opinion in Neurology

View full text Add to dashboard Cite

Purpose of review. Machine learning (ML) is an artificial intelligence technique that allows computers to perform a task without being explicitly programmed. ML can be used to assist diagnosis and prognosis of brain disorders. While the earliest papers date from more than ten years ago, research increases at a very fast pace. Recent findings. Recent works using ML for diagnosis have moved from classification of a given disease versus controls to differential diagnosis. Intense research has been devoted to the prediction of the future patient state. While a lot of earlier works focused on neuroimaging as data source, the current trend is on the integration of multimodal. In terms of targeted diseases, dementia remains dominant, but approaches have been developed for a wide variety of neurological and psychiatric diseases. Summary. ML is extremely promising for assisting diagnosis and prognosis in brain disorders. Nevertheless, we argue that key challenges remain to be addressed by the community for bringing these tools in clinical routine: good practices regarding validation and reproducible research need to be more widely adopted; extensive generalization studies are required; interpretable models are needed to overcome the limitations of black-box approaches.

show abstract

“…These are mostly based on deep learning yet also include texture analysis using radiomics 50 or fractal analysis. 51 In brief, deep learning has been successfully applied to several fields using convolutional neural networks: scoring knee osteoarthritis on radiographs, 52 improving detection of wrist fractures on radiographs, 53 detecting breast cancer on mammograms, 44 augmenting the ability of radiologists to detect cancer on screening mammograms without increased reading times, 54 classifying breast masses on ultrasound, 55,56 prioritizing the worklist of radiologists for suspected intracranial bleeding on CT, 57 detecting and possibly sub-classifying intracranial bleeding on CT, 58 identifying critical findings on head CT with somewhat limited sensitivity for stroke, 59 predicting ischemic stroke onset time on MR imaging, 60 classifying six common liver tumor entities, 61 triaging chest radiographs for urgent findings, 62 pulmonary nodule detection on chest radiographs, 63 and predicting 2-year survival in patients with non-small cell lung cancer based on standard-of-care CT images of the chest. 64…”

Section: Impact Of the Bionic Radiologistmentioning

confidence: 99%

The Bionic Radiologist: avoiding blurry pictures and providing greater insights

Dewey

Wilkens

2019

npj Digit. Med.

View full text Add to dashboard Cite

Radiology images and reports have long been digitalized. However, the potential of the more than 3.6 billion radiology examinations performed annually worldwide has largely gone unused in the effort to digitally transform health care. The Bionic Radiologist is a concept that combines humanity and digitalization for better health care integration of radiology. At a practical level, this concept will achieve critical goals: (1) testing decisions being made scientifically on the basis of disease probabilities and patient preferences; (2) image analysis done consistently at any time and at any site; and (3) treatment suggestions that are closely linked to imaging results and are seamlessly integrated with other information. The Bionic Radiologist will thus help avoiding missed care opportunities, will provide continuous learning in the work process, and will also allow more time for radiologists’ primary roles: interacting with patients and referring physicians. To achieve that potential, one has to cope with many implementation barriers at both the individual and institutional levels. These include: reluctance to delegate decision making, a possible decrease in image interpretation knowledge and the perception that patient safety and trust are at stake. To facilitate implementation of the Bionic Radiologist the following will be helpful: uncertainty quantifications for suggestions, shared decision making, changes in organizational culture and leadership style, maintained expertise through continuous learning systems for training, and role development of the involved experts. With the support of the Bionic Radiologist , disparities are reduced and the delivery of care is provided in a humane and personalized fashion.

show abstract

A Machine Learning Approach for Classifying Ischemic Stroke Onset Time From Imaging

Cited by 90 publications

References 49 publications

Artificial Intelligence and Acute Stroke Imaging

Artificial Intelligence and Acute Stroke Imaging

Machine learning for classification and prediction of brain diseases: recent advances and upcoming challenges

The Bionic Radiologist: avoiding blurry pictures and providing greater insights

Contact Info

Product

Resources

About