Your browser doesn't support javascript.
loading
RootPainter3D: Interactive-machine-learning enables rapid and accurate contouring for radiotherapy.
Smith, Abraham George; Petersen, Jens; Terrones-Campos, Cynthia; Berthelsen, Anne Kiil; Forbes, Nora Jarrett; Darkner, Sune; Specht, Lena; Vogelius, Ivan Richter.
Afiliação
  • Smith AG; Department of Computer Science, University of Copenhagen, Copenhagen, Denmark.
  • Petersen J; Department of Oncology, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark.
  • Terrones-Campos C; Department of Computer Science, University of Copenhagen, Copenhagen, Denmark.
  • Berthelsen AK; Department of Oncology, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark.
  • Forbes NJ; Department of Oncology, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark.
  • Darkner S; Department of Infectious Diseases, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark.
  • Specht L; Department of Oncology, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark.
  • Vogelius IR; Department of Clinical Physiology, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark.
Med Phys ; 49(1): 461-473, 2022 Jan.
Article em En | MEDLINE | ID: mdl-34783028
PURPOSE: Organ-at-risk contouring is still a bottleneck in radiotherapy, with many deep learning methods falling short of promised results when evaluated on clinical data. We investigate the accuracy and time-savings resulting from the use of an interactive-machine-learning method for an organ-at-risk contouring task. METHODS: We implement an open-source interactive-machine-learning software application that facilitates corrective-annotation for deep-learning generated contours on X-ray CT images. A trained-physician contoured 933 hearts using our software by delineating the first image, starting model training, and then correcting the model predictions for all subsequent images. These corrections were added into the training data, which was used for continuously training the assisting model. From the 933 hearts, the same physician also contoured the first 10 and last 10 in Eclipse (Varian) to enable comparison in terms of accuracy and duration. RESULTS: We find strong agreement with manual delineations, with a dice score of 0.95. The annotations created using corrective-annotation also take less time to create as more images are annotated, resulting in substantial time savings compared to manual methods. After 923 images had been delineated, hearts took 2 min and 2 s to delineate on average, which includes time to evaluate the initial model prediction and assign the needed corrections, compared to 7 min and 1 s when delineating manually. CONCLUSIONS: Our experiment demonstrates that interactive-machine-learning with corrective-annotation provides a fast and accessible way for non computer-scientists to train deep-learning models to segment their own structures of interest as part of routine clinical workflows.
Assuntos
Palavras-chave

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Aprendizado Profundo Tipo de estudo: Guideline / Prognostic_studies Idioma: En Ano de publicação: 2022 Tipo de documento: Article

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Aprendizado Profundo Tipo de estudo: Guideline / Prognostic_studies Idioma: En Ano de publicação: 2022 Tipo de documento: Article