Journal article Open Access
Image Synthesis as a Pretext for Unsupervised Histopathological Diagnosis
Stepec, D.; Skocaj, D.
Anomaly detection in visual data refers to the problem of differentiating abnormal appearances from normal cases. Supervised approaches have been successfully applied to different domains, but require an abundance of labeled data. Due to the nature of how anomalies occur and their underlying generating processes, it is hard to characterize and label them. Recent advances in deep generative based models have sparked interest in applying such methods for unsupervised anomaly detection and have shown promising results in medical and industrial inspection domains. In this work we evaluate a crucial part of the unsupervised visual anomaly detection pipeline, that is needed for normal appearance modeling, as well as the ability to reconstruct closest looking normal and tumor samples. We adapt and evaluate different high-resolution state-of-the-art generative models from the face synthesis domain and demonstrate their superiority over currently used approaches on a challenging domain of digital pathology. Multifold improvement in image synthesis is demonstrated in terms of the quality and resolution of the generated images, validated also against the supervised model.
| Name | Size | |
|---|---|---|
|
MICCAI_paper_XLAB_stepec.pdf
md5:7352a72ea1ed6e59e62fa65554e028e4 |
28.5 MB | Download |
| All versions | This version | |
|---|---|---|
| Views | 66 | 66 |
| Downloads | 106 | 106 |
| Data volume | 3.0 GB | 3.0 GB |
| Unique views | 64 | 64 |
| Unique downloads | 102 | 102 |
- Publication date:
- November 24, 2020
- DOI:
-
- Keyword(s):
- Anomaly detection Unsupervised Deep-learning Generative adversarial networks Image synthesis Digital pathology
- Grants:
-
European Commission:
- iPC - individualizedPaediatricCure: Cloud-based virtual-patient models for precision paediatric oncology (826121)
- Meeting:
- 23rd International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2020)
- Related identifiers:
- New versions
- Communities:
- License (for files):
- Creative Commons Attribution 4.0 International