Deep Learning System Boosts Radiologist Detection of Intracranial Hemorrhage

Warman, Roshan; Warman, Anmol; Warman, Pranav; Degnan, Andrew J.; Blickman, Johan G.; Chowdhary, Varun; Dash, Dev; Sangal, Rohit B.; Vadhan, Jason D; Bueso, Tulio; Windisch, T.; Neves, Gabriel

doi:10.7759/cureus.30264

Cited by 3 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2,4,5 Over the past decade, deep learning (DL) algorithms have revolutionized the diagnosis and management of acute stroke, from detecting and classifying stroke types to assessing patient therapeutic eligibility. 6,7 While there are many instances of work using DL strategies to automatically identify and characterize occlusions on CTA, there has been comparably less effort in adopting similar strategies for DSA. [8][9][10][11][12] Previous work has attempted to predict reperfusion grading or classify the occlusion as M1 or M2 based on DSA.…”

Section: Introductionmentioning

confidence: 99%

A deep learning method to identify and localize large‐vessel occlusions from cerebral digital subtraction angiography

Warman,

Warman

et al. 2024

Journal of Neuroimaging

Self Cite

View full text Add to dashboard Cite

Background and purposeAn essential step during endovascular thrombectomy is identifying the occluded arterial vessel on a cerebral digital subtraction angiogram (DSA). We developed an algorithm that can detect and localize the position of occlusions in cerebral DSA.MethodsWe retrospectively collected cerebral DSAs from a single institution between 2018 and 2020 from 188 patients, 86 of whom suffered occlusions of the M1 and proximal M2 segments. We trained an ensemble of deep‐learning models on fewer than 60 large‐vessel occlusion (LVO)‐positive patients. We evaluated the model on an independent test set and evaluated the truth of its predicted localizations using Intersection over Union and expert review.ResultsOn an independent test set of 166 cerebral DSA frames with an LVO prevalence of 0.19, the model achieved a specificity of 0.95 (95% confidence interval [CI]: 0.90, 0.99), a precision of 0.7450 (95% CI: 0.64, 0.88), and a sensitivity of 0.76 (95% CI: 0.66, 0.91). The model correctly localized the LVO in at least one frame in 13 of the 14 LVO‐positive patients in the test set. The model achieved a precision of 0.67 (95% CI: 0.52, 0.79), recall of 0.69 (95% CI: 0.46, 0.81), and a mean average precision of 0.75 (95% CI: 0.56, 0.91).ConclusionThis work demonstrates that a deep learning strategy using a limited dataset can generate effective representations used to identify LVOs. Generating an expanded and more complete dataset of LVOs with obstructed LVOs is likely the best way to improve the model's ability to localize LVOs.

show abstract

Section: Introductionmentioning

confidence: 99%

A deep learning method to identify and localize large‐vessel occlusions from cerebral digital subtraction angiography

Warman,

Warman

et al. 2024

Journal of Neuroimaging

Self Cite

View full text Add to dashboard Cite

show abstract

AI assisted reader evaluation in acute CT head interpretation (AI-REACT): protocol for a multireader multicase study

Fu,

Novak,

Robert

et al. 2024

BMJ Open

View full text Add to dashboard Cite

IntroductionA non-contrast CT head scan (NCCTH) is the most common cross-sectional imaging investigation requested in the emergency department. Advances in computer vision have led to development of several artificial intelligence (AI) tools to detect abnormalities on NCCTH. These tools are intended to provide clinical decision support for clinicians, rather than stand-alone diagnostic devices. However, validation studies mostly compare AI performance against radiologists, and there is relative paucity of evidence on the impact of AI assistance on other healthcare staff who review NCCTH in their daily clinical practice.Methods and analysisA retrospective data set of 150 NCCTH will be compiled, to include 60 control cases and 90 cases with intracranial haemorrhage, hypodensities suggestive of infarct, midline shift, mass effect or skull fracture. The intracranial haemorrhage cases will be subclassified into extradural, subdural, subarachnoid, intraparenchymal and intraventricular. 30 readers will be recruited across four National Health Service (NHS) trusts including 10 general radiologists, 15 emergency medicine clinicians and 5 CT radiographers of varying experience. Readers will interpret each scan first without, then with, the assistance of the qER EU 2.0 AI tool, with an intervening 2-week washout period. Using a panel of neuroradiologists as ground truth, the stand-alone performance of qER will be assessed, and its impact on the readers’ performance will be analysed as change in accuracy (area under the curve), median review time per scan and self-reported diagnostic confidence. Subgroup analyses will be performed by reader professional group, reader seniority, pathological finding, and neuroradiologist-rated difficulty.Ethics and disseminationThe study has been approved by the UK Healthcare Research Authority (IRAS 310995, approved 13 December 2022). The use of anonymised retrospective NCCTH has been authorised by Oxford University Hospitals. The results will be presented at relevant conferences and published in a peer-reviewed journal.Trial registration numberNCT06018545.

show abstract

Using an artificial intelligence software improves emergency medicine physician intracranial haemorrhage detection to radiologist levels

Warman,

Warman

et al. 2024

Emerg Med J

View full text Add to dashboard Cite

BackgroundTools to increase the turnaround speed and accuracy of imaging reports could positively influence ED logistics. The Caire ICH is an artificial intelligence (AI) software developed for ED physicians to recognise intracranial haemorrhages (ICHs) on non-contrast enhanced cranial CT scans to manage the clinical care of these patients in a timelier fashion.MethodsA dataset of 532 non-contrast cranial CT scans was reviewed by five board-certified emergency physicians (EPs) with an average of 14.8 years of practice experience. The scans were labelled in random order for the presence or absence of an ICH. If an ICH was detected, the reader further labelled all subtypes present (ie, epidural, subdural, subarachnoid, intraparenchymal and/or intraventricular haemorrhage). After a washout period, the five EPs reviewed again the scans individually with the assistance of Caire ICH. The mean accuracy of the EP readings with AI assistance was compared with the mean accuracy of three general radiologists reading the films individually. The final diagnosis (ie, ground truth) was adjudicated by a consensus of the radiologists after their individual readings.ResultsMean EP reader accuracy significantly increased by 6.20% (95% CI for the difference 5.10%–7.29%; p=0.0092) when using Caire ICH to detect an ICH. Mean accuracy of the EP cohort in detecting an ICH using Caire ICH was found to be more accurate than the radiologist cohort prior to discussion; this difference, however, was not statistically significant.ConclusionThe Caire ICH software significantly improved the accuracy and sensitivity of detecting an ICH by the EP to a level comparable to general radiologists. Further prospective research with larger numbers will be needed to understand the impact of Caire ICH on ED logistics and patient outcomes.

show abstract

Deep Learning System Boosts Radiologist Detection of Intracranial Hemorrhage

Cited by 3 publications

References 22 publications

A deep learning method to identify and localize large‐vessel occlusions from cerebral digital subtraction angiography

A deep learning method to identify and localize large‐vessel occlusions from cerebral digital subtraction angiography

AI assisted reader evaluation in acute CT head interpretation (AI-REACT): protocol for a multireader multicase study

Using an artificial intelligence software improves emergency medicine physician intracranial haemorrhage detection to radiologist levels

Contact Info

Product

Resources

About