Automated deep-neural-network surveillance of cranial images for acute neurologic events.
Joseph J TitanoMarcus BadgeleyJavin ScheffleinMargaret PainAndres SuMichael CaiNathaniel C SwinburneJohn ZechJun KimJoshua BedersonJ MoccoBurton DrayerJoseph LehárSamuel ChoAnthony CostaEric K OermannPublished in: Nature medicine (2018)
Rapid diagnosis and treatment of acute neurological illnesses such as stroke, hemorrhage, and hydrocephalus are critical to achieving positive outcomes and preserving neurologic function-'time is brain'1-5. Although these disorders are often recognizable by their symptoms, the critical means of their diagnosis is rapid imaging6-10. Computer-aided surveillance of acute neurologic events in cranial imaging has the potential to triage radiology workflow, thus decreasing time to treatment and improving outcomes. Substantial clinical work has focused on computer-assisted diagnosis (CAD), whereas technical work in volumetric image analysis has focused primarily on segmentation. 3D convolutional neural networks (3D-CNNs) have primarily been used for supervised classification on 3D modeling and light detection and ranging (LiDAR) data11-15. Here, we demonstrate a 3D-CNN architecture that performs weakly supervised classification to screen head CT images for acute neurologic events. Features were automatically learned from a clinical radiology dataset comprising 37,236 head CTs and were annotated with a semisupervised natural-language processing (NLP) framework16. We demonstrate the effectiveness of our approach to triage radiology workflow and accelerate the time to diagnosis from minutes to seconds through a randomized, double-blinded, prospective trial in a simulated clinical environment.
Keyphrases
- convolutional neural network
- deep learning
- artificial intelligence
- liver failure
- machine learning
- respiratory failure
- emergency department
- drug induced
- aortic dissection
- public health
- neural network
- loop mediated isothermal amplification
- big data
- high resolution
- electronic health record
- randomized controlled trial
- high throughput
- computed tomography
- systematic review
- clinical trial
- coronary artery disease
- depressive symptoms
- multiple sclerosis
- extracorporeal membrane oxygenation
- optical coherence tomography
- metabolic syndrome
- autism spectrum disorder
- blood brain barrier
- intensive care unit
- study protocol
- photodynamic therapy
- physical activity
- mass spectrometry
- adipose tissue
- cerebral ischemia
- resting state
- functional connectivity
- image quality
- contrast enhanced
- smoking cessation
- acute respiratory distress syndrome
- glycemic control