xOpat: eXplainable Open Pathology Analysis Tool
| Authors | |
|---|---|
| Year of publication | 2023 |
| Type | Article in Periodical |
| Magazine / Source | COMPUTER GRAPHICS FORUM |
| MU Faculty or unit | |
| Citation | |
| web | https://diglib.eg.org/handle/10.1111/cgf14812 |
| Doi | http://dx.doi.org/10.1111/cgf.14812 |
| Keywords | Medical Imaging; Scientific Visualization; Open Pathology; Toolkit; artificial intelligence; Visual Analysis; AI explainability; GPU Rendering; |
| Description | Histopathology research quickly evolves thanks to advances in whole slide imaging (WSI) and artificial intelligence (AI). However, existing WSI viewers are tailored either for clinical or research environments, but none suits both. This hinders the adoption of new methods and communication between the researchers and clinicians. The paper presents xOpat, an open-source, browser- based WSI viewer that addresses these problems. xOpat supports various data sources, such as tissue images, pathologists’ annotations, or additional data produced by AI models. Furthermore, it provides efficient rendering of multiple data layers, their visual representations, and tools for annotating and presenting findings. Thanks to its modular, protocol-agnostic, and extensible architecture, xOpat can be easily integrated into different environments and thus helps to bridge the gap between research and clinical practice. To demonstrate the utility of xOpat, we present three case studies, one conducted with a developer of AI algorithms for image segmentation and two with a research pathologist. |
| Related projects: |