Code: github.com/nielsvyncke/patch-based-querying
Motivation: Volume electron microscopy (vEM) has emerged as an essential sensing technique in biomedical research, allowing the three-dimensional imaging of biological cells and tissues at nanometer resolution. The ability to generate extensive datasets has reached the limitations of downstream analysis processes, which depend significantly on the intervention of human experts for preprocessing and annotation.
Results: This work proposes an efficient and reliable patch-based retrieval framework based on self-supervised learning of local image descriptors to locate self-similar structures in vEM datasets. Given a few manual annotations of a given cellular structure, our method can retrieve similar structures across the EM volume. Our framework is interactive, allowing the human expert to refine the search queries and retrieve relevant image patches quickly and using little labeled data. Experiments on real-world vEM images of biological tissues show the capacity of our framework to identify relevant cellular structures and significantly speed up the labeling process.
References
[1] N. Vyncke, N. Nadisic, Y. Saeys, and A. Pižurica. Patch-based Querying Identifies Structures of Interest in Electron Microscopy Data. Oxford Bioinformatics, 2025. (in submission)
[2] N. Žižakić and A. Pižurica, “Efficient local image descriptors learned with autoencoders,” IEEE ACCESS, vol. 10, pp. 221–235, 2022.
[3] N. Žižakić, I. Ito, and A. Pižurica, “Learning local image descriptors with autoencoders,” in Image Processing and Communications : Techniques, Algorithms and Applications, Bydgoszcz, Poland, 2019, vol. 1062, pp. 214–221.