|
TissueWand, a rapid histopathology annotation tool
Martin Lindvall1, Alexander Sanner2, Fredrik Petré2, Karin Lindman3, Darren Treanor4, Claes Lundström1, Jonas Löwgren5
1 Sectra AB, Research Department; Center for Medical Image Science and Visualization, Linköping University, Linköping; Department of Science and Technology (ITN), Linköping University, Norrköping, Sweden
2 Sectra AB, Research Department, Linköping, Sweden
3 Department of Clinical Pathology, Region Östergötland; Department of Biomedical and Clinical Sciences, Linköping University, Linköping, Sweden
4 Center for Medical Image Science and Visualization, Linköping University, Linköping, Sweden; Department of Cellular Pathology, Leeds Teaching Hospitals NHS Trust; University of Leeds, Leeds, UK
5 Department of Science and Technology (ITN), Linköping University, Norrköping, Sweden
Correspondence Address:
Mr. Martin Lindvall
Sectra AB, 58330 Linköping
Sweden
 Source of Support: None, Conflict of Interest: None  | Check |
DOI: 10.4103/jpi.jpi_5_20
|
|
Background: Recent advancements in machine learning (ML) bring great possibilities for the development of tools to assist with diagnostic tasks within histopathology. However, these approaches typically require a large amount of ground truth training data in the form of image annotations made by human experts. As such annotation work is a very time-consuming task, there is a great need for tools that can assist in this process, saving time while not sacrificing annotation quality. Methods: In an iterative design process, we developed TissueWand – an interactive tool designed for efficient annotation of gigapixel-sized histopathological images, not being constrained to a predefined annotation task. Results: Several findings regarding appropriate interaction concepts were made, where a key design component was semi-automation based on rapid interaction feedback in a local region. In a user study, the resulting tool was shown to cause substantial speed-up compared to manual work while maintaining quality. Conclusions: The TissueWand tool shows promise to replace manual methods for early stages of dataset curation where no task-specific ML model yet exists to aid the effort.
|
