Automated deep-neural-network surveillance of cranial images for acute neurologic events

By Joseph J. Titano, Marcus A. Badgeley, J. Schefflein, M. Pain, Andres Su, Michael Cai, N. Swinburne, John R. Zech, Jun S. Kim, J. Bederson and 6 more. 2018

397 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Deep learning predicts hip fracture using confounding patient and healthcare variables (2018, background): “Class imbalance can be partly mitigated by data augmentation strategies.(8,12,28,29,33) Islam et al.”
AI in Medical Imaging Informatics: Current Challenges and Future Directions (2020, neutral): “Applications include screening for acute neurologic events [114], diabetic retinopathy [115], and melanoma [116].”
Making the Most of Text Semantics to Improve Biomedical Vision-Language Processing (2022, background): “[71] Joseph J Titano, Marcus Badgeley, Javin Schefflein, Margaret Pain, Andres Su, Michael Cai, Nathaniel Swinburne, John Zech, Jun Kim, Joshua Bederson, et al.”
Role of Artificial Intelligence Applications in Real-Life Clinical Practice: Systematic Review (2020, background): “Other potential sources of bias included a small sample size [62,70,72], a short study period [62], and a lack of detailed information regarding RCTs and follow-ups [57,66].”
Key challenges for delivering clinical impact with artificial intelligence (2019, background): “…of diminutive adenomas and hyperplastic polyps [59]; a simulated prospective, double-blind RCT of an algorithm to detect acute neurologic events [60]; and an unmasked RCT of a system to provide automated interpretation of cardiotocographs in labour that found no improvement in clinical outcomes…”
Assessing the (Un)Trustworthiness of Saliency Maps for Localizing Abnormalities in Medical Imaging (2020, background): “A likely future application of CNNs in the clinical setting is to help clinicians flag particular images that need further review [52].”
On the Intrinsic Privacy of Stochastic Gradient Descent (2019, background): “These attacks raise privacy concerns about the deployment of models in sensitive applications such as healthcare [49].”
The Role of Massively Multi-Task and Weak Supervision in Software 2.0 (2019, background): “…across domains, feature sets, and execution environments—for example, by training image classifiers with weak supervision over accompanying text [21, 39], or by using slower or more expensive feature sets with the mother model before transferring to more servable feature sets for deployment.”