Statements (74)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:Data
|
| gptkbp:ai |
Utilized deep learning techniques.
|
| gptkbp:algorithm_development |
Facilitated algorithm development.
|
| gptkbp:analysis |
Used for data analysis in research.
Visualizations created for analysis. |
| gptkbp:annotations |
Expert annotations for training.
|
| gptkbp:available_at |
The Cancer Imaging Archive (TCIA).
|
| gptkbp:award |
Awards for top performers.
|
| gptkbp:challenge_community |
Fostered a community of researchers.
|
| gptkbp:challenge_duration |
Held over several months.
|
| gptkbp:challenge_feedback |
Feedback provided to participants.
|
| gptkbp:challenge_impact |
Impact on future challenges.
|
| gptkbp:challenge_outcome |
Improved algorithms for cancer detection.
|
| gptkbp:challenge_participants |
International participants.
|
| gptkbp:challenge_results |
Results presented at conferences.
|
| gptkbp:challenge_results_publication |
Results published in 2017.
|
| gptkbp:challenge_website |
https://camelyon16.grand-challenge.org/.
|
| gptkbp:challenges |
Image classification.
Outcomes influenced future research directions. |
| gptkbp:collaboration |
Collaboration between academia and industry.
|
| gptkbp:collaborations |
Promoted research collaboration.
|
| gptkbp:community_engagement |
Engaged the research community.
|
| gptkbp:contains |
H& E stained histopathology images.
|
| gptkbp:created_by |
gptkb:The_Camelyon_Challenge
|
| gptkbp:data_collaboration_opportunities |
Opportunities for collaboration.
|
| gptkbp:data_ethics |
Adheres to ethical standards.
|
| gptkbp:data_labeling |
Performed by pathologists.
|
| gptkbp:data_reusability |
Data is reusable for future research.
|
| gptkbp:data_size |
Large dataset.
|
| gptkbp:data_standardization |
Standardized data formats.
|
| gptkbp:data_type |
TIFF.
|
| gptkbp:data_usage |
Used in various research projects.
|
| gptkbp:description |
A dataset for the detection of metastases in lymph node sections.
|
| gptkbp:evaluates |
Area under the ROC curve (AUC).
|
| gptkbp:evaluation_phase |
Included a rigorous evaluation phase.
|
| gptkbp:field_of_study |
Computer vision.
|
| gptkbp:follow_up_challenge |
Camelyon17.
|
| gptkbp:funding |
Funded by various grants.
|
| gptkbp:goal |
Improve automated detection of cancer.
|
| gptkbp:goals |
Set goals for improving detection accuracy.
|
| gptkbp:has_artwork |
Over 4000 images.
|
| https://www.w3.org/2000/01/rdf-schema#label |
Camelyon16
|
| gptkbp:image_diversity |
Diverse set of images.
|
| gptkbp:image_format |
Microscopic images.
|
| gptkbp:image_labeling |
Labeled for cancer presence.
|
| gptkbp:image_processing |
Acquired from hospitals.
Involved advanced image processing techniques. |
| gptkbp:impact |
Influenced research in medical imaging.
Significant impact on cancer research. |
| gptkbp:innovation |
Encouraged innovation in detection methods.
|
| gptkbp:is_divided_into |
Training, validation, and test sets.
|
| gptkbp:participants |
Various research teams and institutions.
|
| gptkbp:product_quality |
High quality images.
|
| gptkbp:provides_information_on |
Addressed challenges in data collection.
Clinical data. Collaboration with medical institutions. Easily accessible for researchers. Integrated with other datasets. Open access for research purposes. Promoted data sharing among researchers. |
| gptkbp:publication |
Published in research papers.
Results published in scientific journals. |
| gptkbp:publication_year |
2016.
|
| gptkbp:related_to |
Pathology.
|
| gptkbp:research_output |
Led to significant research outcomes.
|
| gptkbp:resolution |
High resolution.
|
| gptkbp:results_sharing |
Results shared publicly.
|
| gptkbp:sponsored_by |
Various academic and industry partners.
|
| gptkbp:sponsorship |
Sponsored by various organizations.
|
| gptkbp:used_for |
Training machine learning models for cancer detection.
|
| gptkbp:wins |
Multiple submissions from participants.
|
| gptkbp:year |
gptkb:2016
|
| gptkbp:bfsParent |
gptkb:Na'vi
|
| gptkbp:bfsLayer |
5
|