Data · dataset · 2024
CPIA Dataset_Part05: A Comprehensive Pathological Image Analysis Dataset for Self-supervised Learning Pre-training
Listed in ScienceDB
Pathological image analysis is a crucial field in computer-aided diagnosis.
Description
Transfer learning using models initialized on natural images has improved the downstream pathological performance. However, the lack of sophisticated domain-specific pathological initialization hinders their potential.
Self-supervised learning (SSL) enables pre-training without sample-level labels, overcoming the challenge of expensive annotations. Thus, this field calls for a comprehensive dataset, similar to the ImageNet in computer vision. This paper presents a large-scale comprehensive pathological image analysis (CPIA) dataset for SSL pre-training.
Read the rest (2 more)
The CPIA dataset contains 148,962,579 images, covering over 48 organs/tissues and approximately 100 kinds of diseases, which includes two main data types: whole slide images (WSIs) and characteristic regions of interest (ROIs). And we establish a multi-scale pathological data processing workflow, combined with the diagnosis habits of senior pathologists. The CPIA dataset facilitates a comprehensive pathological understanding and enables pattern discovery explorations.
Additionally, to launch the CPIA dataset, several state-of-the-art (SOTA) baselines of SSL pre-training and downstream evaluation are specially conducted. This is the Part05 of CPIA dataset, including the CPIA-Mini and partial CPIA dataset. The related code and information are available at github.com/zhanglab2021/CPIA_Dataset.
Links
Where it is published
- DOI doi.org/10.57760/sciencedb.14727 ↗
DOI / persistent id · from scidb cn
Catalogue records · 1
- OAI-PMH record scidb.cn/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.57760%2… ↗
metadata API · from scidb cn
Topics
- From keywords
- Earth & Environmental Science · Engineering · Humanities · Life Sciences · Social Science
- Inferred from text
- Image 75% · Veterinary sciences 70%
Provenance · 1 source records, 12 field assertions
| Source | Key | Last seen | Raw |
|---|---|---|---|
| ScienceDB | 10.57760/sciencedb.14727 | 7 d ago | JSON v1 |
| Field | Assertion | Extractor | Evidence |
|---|---|---|---|
| access_level | source · scidb cn | connector:scidb_cn@1.0.0 | |
| concepts[field].anzsrc:group:3009 | enrichment · scidb cn | taxonomy-embedding@1.0.0 | title+keywords+description (70%) |
| concepts[field].local:field:earth-environmental | mapping · scidb cn | connector:scidb_cn@1.0.0 | |
| concepts[field].local:field:engineering | mapping · scidb cn | connector:scidb_cn@1.0.0 | |
| concepts[field].local:field:humanities | mapping · scidb cn | connector:scidb_cn@1.0.0 | |
| concepts[field].local:field:life-sciences | mapping · scidb cn | connector:scidb_cn@1.0.0 | |
| concepts[field].local:field:social-science | mapping · scidb cn | connector:scidb_cn@1.0.0 | |
| concepts[modality].local:modality:image | enrichment · scidb cn | keyword-concept-rules@1.0.0 | title+description (75%) |
| description | source · scidb cn | connector:scidb_cn@1.0.0 | /metadata/dc/description |
| license | source · scidb cn | connector:scidb_cn@1.0.0 | /metadata/dc/rights |
| publication_date | source · scidb cn | connector:scidb_cn@1.0.0 | |
| title | source · scidb cn | connector:scidb_cn@1.0.0 | /metadata/dc/title |