Loading BioAtlas...
Loading BioAtlas...
将生物大模型、对接计算引擎与组学管线并排横向对比。按获取方式、硬件开销及细分领域灵活筛选，在一分钟内得出客观可辩护的技术选型方案。
| 技术参数指标 | ＋ 添加工具 | |||
|---|---|---|---|---|
| Category | Research Imaging & Microscopy | Research Imaging & Structural Analysis | Research Imaging & Structural Analysis | — |
| Subcategory | Digital Pathology & Whole-Slide Analysis | Conventional or Statistical Baselines | Cell Segmentation | — |
| Company | University of Edinburgh | Research / method authors | Van Valen Lab | — |
| Access mode | Open Source | Confirm distribution and exact release | Research code or publication | — |
| Licence conditions | GPL-3.0 | NOT_INDEPENDENTLY_AUDITED | Check code and model weights separately | — |
| Compute requirements | Standard desktop / workstation (multi-core CPU, optional GPU for deep learning) | Version and data dependent | Check selected checkpoint and runtime; no GPU catalog recommendation | — |
| Biological application | Oncology biomarker quantification, spatial histology analysis, and clinical trials | 未明确记录 | 未明确记录 | — |
| Research workflow | Whole-slide image -> cell segmentation -> phenotyping -> spatial biomarker scoring | 未明确记录 | 未明确记录 | — |
| Evidence level | Peer-reviewed research (Scientific Reports 2017) with thousands of citations | OFFICIAL_DOCUMENTATION | Peer-reviewed primary method | — |
| Commercial eligibility | Permissive open source release | NOT_INDEPENDENTLY_AUDITED | Unknown, requires audit | — |
| Price | Free Open Source | Verify access and licence | Check selected model licence | — |
| Availability ⓘ | Available for Windows, macOS, and Linux | Method paper or official documentation | Public research method/code | — |
| Features | High-performance whole-slide image viewing and annotation across gigapixel files, Machine learning tissue classification (tumor vs stroma vs necrosis), Integration with StarDist and Cellpose for deep learning cell and nuclear segmentation, Extensive scripting API in Groovy and Python for automated cohort analysis | CellProfiler scientific method, Microscopy images and configured classical image-analysis modules, Segmented objects and quantitative image features | Automated cell instance segmentation using detector and Segment Anything models for supported microscopy., Individual cell instance masks | — |
| Entry type | Open Source Software | Classical/statistical scientific method | Research AI model / method | — |
| AI role | Deep Learning Image Segmentation | NON_AI_CLASSICAL | Published biomedical AI method | — |
| Input data | 未明确记录 | Microscopy images and configured classical image-analysis modules | Microscopy images; chosen checkpoint and pixel size | — |
| Output data | 未明确记录 | Segmented objects and quantitative image features | Individual cell instance masks | — |
| Validation | 未明确记录 | Published method scope; no independent BioAtlas execution or benchmark | Requires independent dataset-specific evaluation | — |
| Type | Digital pathology bioimage analysis platform | 未明确记录 | 未明确记录 | — |
| Intended use | 未明确记录 | 未明确记录 | 未明确记录 | — |
| Compatibility | 未明确记录 | 未明确记录 | 未明确记录 | — |
| Manufacturer | University of Edinburgh (Bankhead Lab) | 未明确记录 | 未明确记录 | — |
| Integration evidence | https://qupath.github.io | 未明确记录 | 未明确记录 | — |
| Laboratory handoff | Correlates histological features with genomic data and patient survival curves | 未明确记录 | 未明确记录 | — |