TissueWand, a rapid histopathology annotation tool [Elektronisk resurs]
-
Lindvall, Martin (författare)
-
Sanner, Alexander (författare)
-
Petré, Fredrik (författare)
-
Skoglund, Karin, 1980- (författare)
-
Treanor, Darren, 1974- (författare)
-
Lundström, Claes, 1973- (författare)
-
Löwgren, Jonas, 1964- (författare)
-
Linköpings universitet Institutionen för teknik och naturvetenskap (utgivare)
-
Linköpings universitet Tekniska fakulteten (utgivare)
-
Linköpings universitet Centrum för medicinsk bildvetenskap och visualisering, CMIV (utgivare)
-
Linköpings universitet Institutionen för biomedicinska och kliniska vetenskaper (utgivare)
-
Linköpings universitet Medicinska fakulteten (utgivare)
-
Region Östergötland Diagnostikcentrum (utgivare)
- Publicerad: Medknow Publications, 2020
- Engelska.
-
Ingår i: Journal of Pathology Informatics. - 2229-5089. ; 11:27
-
Läs hela texten
-
Läs hela texten
-
Läs hela texten
- Relaterad länk:
-
http://www.liu.se (Värdpublikation)
Sammanfattning
Ämnesord
Stäng
- 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.
Ämnesord
- Humanities and the Arts (hsv)
- Arts (hsv)
- Design (hsv)
- Humaniora och konst (hsv)
- Konst (hsv)
- Design (hsv)
- Natural Sciences (hsv)
- Computer and Information Sciences (hsv)
- Human Computer Interaction (hsv)
- Naturvetenskap (hsv)
- Data- och informationsvetenskap (hsv)
- Människa-datorinteraktion (interaktionsdesign) (hsv)
Genre
- government publication (marcgt)
Indexterm och SAB-rubrik
- Annotation
- digital pathology
- usability
- user interface design
- machine learning
Inställningar
Hjälp
Ingår i annan publikation. Gå till titeln
Journal of Pathology Informatics