Corpus ID: 44166582

Producing radiologist-quality reports for interpretable artificial intelligence

@article{Gale2018ProducingRR,
  title={Producing radiologist-quality reports for interpretable artificial intelligence},
  author={William Gale and L. Oakden-Rayner and G. Carneiro and A. Bradley and L. Palmer},
  journal={ArXiv},
  year={2018},
  volume={abs/1806.00340}
}
Current approaches to explaining the decisions of deep learning systems for medical tasks have focused on visualising the elements that have contributed to each decision. [...] Key Method We propose a model-agnostic interpretability method that involves training a simple recurrent neural network model to produce descriptive sentences to clarify the decision of deep learning classifiers. We test our method on the task of detecting hip fractures from frontal pelvic x-rays.Expand
20 Citations
Multitask and Multimodal Neural Network Model for Interpretable Analysis of X-ray Images
  • 1
  • Highly Influenced
Baselines for Chest X-Ray Report Generation
  • 8
  • PDF
Clinically Accurate Chest X-Ray Report Generation
  • 42
  • PDF
Chest X-ray Report Generation through Fine-Grained Label Learning
  • 1
  • PDF
Machine learning in radiology
  • P. Brotchie
  • Medicine
  • Journal of medical imaging and radiation oncology
  • 2019
  • 1
...
1
2
...

References

SHOWING 1-10 OF 20 REFERENCES
TieNet: Text-Image Embedding Network for Common Thorax Disease Classification and Reporting in Chest X-Rays
  • 159
  • PDF
Detecting hip fractures with radiologist-level performance using deep neural networks
  • 59
  • PDF
Dermatologist-level classification of skin cancer with deep neural networks
  • 4,483
  • PDF
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
  • 2,360
  • PDF
SmoothGrad: removing noise by adding noise
  • 580
  • Highly Influential
  • PDF
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
  • 5,840
  • PDF
Dropout: a simple way to prevent neural networks from overfitting
  • 21,834
  • PDF
How to Construct Deep Recurrent Neural Networks
  • 669
  • PDF
Learning From Explanations Using Sentiment and Advice in RL
  • 51
  • PDF
...
1
2
...