Detection of acute rib fractures on CT images with convolutional neural networks: effect of location and type of fracture and reader's experience.
Minako AzumaHiroshi NakadaMizuki TakeiKeigo NakamuraShigehiko KatsuragawaNorihiro ShinkawaTamasa TeradaRie MasudaYouhei HattoriTakakazu IdeAya KimuraMei ShimomuraMasatsugu KawanoKengo MatsumuraTakayuki MeiriHidenobu OchiaiToshinori HiraiPublished in: Emergency radiology (2021)
The CNN specialized for the detection of acute rib fractures on CT images can improve the radiologists' diagnostic performance regardless of the type of fractures and reader's experience. Further studies are needed to clarify the usefulness of the CNN for the detection of acute rib fractures on CT images in actual clinical practice.
Keyphrases
- convolutional neural network
- deep learning
- liver failure
- respiratory failure
- image quality
- computed tomography
- dual energy
- loop mediated isothermal amplification
- contrast enhanced
- clinical practice
- drug induced
- aortic dissection
- real time pcr
- label free
- positron emission tomography
- magnetic resonance imaging
- palliative care
- optical coherence tomography
- machine learning
- mechanical ventilation
- case control