FISHing in Uncertainty: Synthetic Contrastive Learning for Genetic Aberration Detection
This work addresses challenges in cancer diagnosis by improving accuracy and reducing manual effort, though it appears incremental as it builds on existing contrastive learning and synthetic data techniques for a specific domain.
The paper tackles the problem of detecting genetic aberrations in cancer diagnosis using FISH images by introducing a method that uses synthetic images to eliminate manual annotations and a joint contrastive-classification objective, achieving 96.7% classification accuracy in the most certain cases.
Detecting genetic aberrations is crucial in cancer diagnosis, typically through fluorescence in situ hybridization (FISH). However, existing FISH image classification methods face challenges due to signal variability, the need for costly manual annotations and fail to adequately address the intrinsic uncertainty. We introduce a novel approach that leverages synthetic images to eliminate the requirement for manual annotations and utilizes a joint contrastive and classification objective for training to account for inter-class variation effectively. We demonstrate the superior generalization capabilities and uncertainty calibration of our method, which is trained on synthetic data, by testing it on a manually annotated dataset of real-world FISH images. Our model offers superior calibration in terms of classification accuracy and uncertainty quantification with a classification accuracy of 96.7% among the 50% most certain cases. The presented end-to-end method reduces the demands on personnel and time and improves the diagnostic workflow due to its accuracy and adaptability. All code and data is publicly accessible at: https://github.com/SimonBon/FISHing