A pilot study of deep learning-based CT volumetry for traumatic hemothorax.
David DreizinBryan NixonJiazhen HuBenjamin AlbertChang YanGary YangHaomin ChenYuanyuan LiangNahye KimJean JeudyGuang LiElana B SmithMathias UnberathPublished in: Emergency radiology (2022)
Automated HTX volumetry had high method validity, yielded interpretable visual results, and had similar performance for the hemorrhage-related outcomes assessed compared to manual volumes and expert consensus grading. The results suggest promising avenues for automated HTX volumetry in research and clinical care.
Keyphrases
- deep learning
- machine learning
- artificial intelligence
- convolutional neural network
- high throughput
- healthcare
- spinal cord injury
- computed tomography
- palliative care
- image quality
- quality improvement
- contrast enhanced
- dual energy
- type diabetes
- pain management
- adipose tissue
- magnetic resonance imaging
- positron emission tomography
- affordable care act
- weight loss
- single cell