Your browser doesn't support javascript.
loading
Interpretable artificial intelligence in radiology and radiation oncology.
Cui, Sunan; Traverso, Alberto; Niraula, Dipesh; Zou, Jiaren; Luo, Yi; Owen, Dawn; El Naqa, Issam; Wei, Lise.
Affiliation
  • Cui S; Department of Radiation Oncology, University of Washington, Seattle, WA, United States.
  • Traverso A; Department of Radiotherapy, Maastro Clinic, Maastricht, Netherlands.
  • Niraula D; Department of Machine Learning, Moffitt Cancer Center, FL, United States.
  • Zou J; Department of Radiation Oncology, University of Michigan, Ann Arbor, MI, United States.
  • Luo Y; Department of Machine Learning, Moffitt Cancer Center, FL, United States.
  • Owen D; Department of Radiation Oncology, Mayo Clinic, Rochester, MN, United States.
  • El Naqa I; Department of Machine Learning, Moffitt Cancer Center, FL, United States.
  • Wei L; Department of Radiation Oncology, University of Michigan, Ann Arbor, MI, United States.
Br J Radiol ; 96(1150): 20230142, 2023 Oct.
Article in En | MEDLINE | ID: mdl-37493248
Artificial intelligence has been introduced to clinical practice, especially radiology and radiation oncology, from image segmentation, diagnosis, treatment planning and prognosis. It is not only crucial to have an accurate artificial intelligence model, but also to understand the internal logic and gain the trust of the experts. This review is intended to provide some insights into core concepts of the interpretability, the state-of-the-art methods for understanding the machine learning models, the evaluation of these methods, identifying some challenges and limits of them, and gives some examples of medical applications.
Subject(s)

Full text: 1 Collection: 01-internacional Database: MEDLINE Main subject: Radiology / Radiation Oncology Limits: Humans Language: En Journal: Br J Radiol Year: 2023 Document type: Article Affiliation country: United States Country of publication: United kingdom

Full text: 1 Collection: 01-internacional Database: MEDLINE Main subject: Radiology / Radiation Oncology Limits: Humans Language: En Journal: Br J Radiol Year: 2023 Document type: Article Affiliation country: United States Country of publication: United kingdom