Your browser doesn't support javascript.
loading
Enhancing Annotation Efficiency with Machine Learning: Automated Partitioning of a Lung Ultrasound Dataset by View.
VanBerlo, Bennett; Smith, Delaney; Tschirhart, Jared; VanBerlo, Blake; Wu, Derek; Ford, Alex; McCauley, Joseph; Wu, Benjamin; Chaudhary, Rushil; Dave, Chintan; Ho, Jordan; Deglint, Jason; Li, Brian; Arntfield, Robert.
Afiliación
  • VanBerlo B; Faculty of Engineering, University of Western Ontario, London, ON N6A 5C1, Canada.
  • Smith D; Faculty of Mathematics, University of Waterloo, Waterloo, ON N2L 3G1, Canada.
  • Tschirhart J; Schulich School of Medicine and Dentistry, Western University, London, ON N6A 5C1, Canada.
  • VanBerlo B; Faculty of Mathematics, University of Waterloo, Waterloo, ON N2L 3G1, Canada.
  • Wu D; Department of Medicine, Western University, London, ON N6A 5C1, Canada.
  • Ford A; Lawson Health Research Institute, London, ON N6C 2R5, Canada.
  • McCauley J; Faculty of Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada.
  • Wu B; Lawson Health Research Institute, London, ON N6C 2R5, Canada.
  • Chaudhary R; Department of Medicine, Western University, London, ON N6A 5C1, Canada.
  • Dave C; Division of Critical Care Medicine, Western University, London, ON N6A 5C1, Canada.
  • Ho J; Department of Family Medicine, Western University, London, ON N6A 5C1, Canada.
  • Deglint J; Faculty of Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada.
  • Li B; Faculty of Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada.
  • Arntfield R; Division of Critical Care Medicine, Western University, London, ON N6A 5C1, Canada.
Diagnostics (Basel) ; 12(10)2022 Sep 28.
Article en En | MEDLINE | ID: mdl-36292042
BACKGROUND: Annotating large medical imaging datasets is an arduous and expensive task, especially when the datasets in question are not organized according to deep learning goals. Here, we propose a method that exploits the hierarchical organization of annotating tasks to optimize efficiency. METHODS: We trained a machine learning model to accurately distinguish between one of two classes of lung ultrasound (LUS) views using 2908 clips from a larger dataset. Partitioning the remaining dataset by view would reduce downstream labelling efforts by enabling annotators to focus on annotating pathological features specific to each view. RESULTS: In a sample view-specific annotation task, we found that automatically partitioning a 780-clip dataset by view saved 42 min of manual annotation time and resulted in 55±6 additional relevant labels per hour. CONCLUSIONS: Automatic partitioning of a LUS dataset by view significantly increases annotator efficiency, resulting in higher throughput relevant to the annotating task at hand. The strategy described in this work can be applied to other hierarchical annotation schemes.
Palabras clave
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: Diagnostics (Basel) Año: 2022 Tipo del documento: Article País de afiliación: Canadá Pais de publicación: Suiza
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: Diagnostics (Basel) Año: 2022 Tipo del documento: Article País de afiliación: Canadá Pais de publicación: Suiza