An unobtrusive quality supervision approach for medical image annotation
This addresses the issue of annotator variability in medical imaging for robust disease recognition, though it is incremental as it builds on existing generative methods.
The paper tackled the problem of unreliable medical image annotation by developing an unobtrusive quality supervision system using synthetic cell images, finding that users could not detect 52.12% of images generated by diffusion models, proving feasibility for replacement without notice.
Image annotation is one essential prior step to enable data-driven algorithms. In medical imaging, having large and reliably annotated data sets is crucial to recognize various diseases robustly. However, annotator performance varies immensely, thus impacts model training. Therefore, often multiple annotators should be employed, which is however expensive and resource-intensive. Hence, it is desirable that users should annotate unseen data and have an automated system to unobtrusively rate their performance during this process. We examine such a system based on whole slide images (WSIs) showing lung fluid cells. We evaluate two methods the generation of synthetic individual cell images: conditional Generative Adversarial Networks and Diffusion Models (DM). For qualitative and quantitative evaluation, we conduct a user study to highlight the suitability of generated cells. Users could not detect 52.12% of generated images by DM proofing the feasibility to replace the original cells with synthetic cells without being noticed.