Deep learning and radiomics: the utility of Google TensorFlow™ Inception in classifying clear cell renal cell carcinoma and oncocytoma on multiphasic CT.
Heidi J CoyKevin HsiehWillie WuMahesh B NagarajanJonathan R YoungMichael L DouekMatthew S BrownFabien ScalzoSteven S RamanPublished in: Abdominal radiology (New York) (2020)
The best classification result was obtained in the EX phase among the thirteen classification methods tested. Our proof of concept study is the first step towards understanding the utility of machine learning in the differentiation of ccRCC from ONC on routine CT images. We hope this could lead to future investigation into the development of a multivariate machine learning model which may augment our ability to accurately predict renal lesion histology on imaging.
Keyphrases
- deep learning
- machine learning
- contrast enhanced
- artificial intelligence
- image quality
- dual energy
- convolutional neural network
- computed tomography
- big data
- magnetic resonance imaging
- high resolution
- positron emission tomography
- clinical practice
- magnetic resonance
- current status
- lymph node metastasis
- squamous cell carcinoma
- photodynamic therapy
- fluorescence imaging
- optical coherence tomography
- pet ct