Faster Deep Ensemble Averaging for Quantification of DNA Damage from Comet Assay Images With Uncertainty Estimates
This work addresses the need for faster and more rigorous uncertainty estimation in DNA damage quantification for neurodegenerative disease research, representing an incremental improvement over existing methods.
The authors tackled the problem of quantifying DNA damage from comet assay images by developing a deep learning approach that speeds up uncertainty estimation and improves hyper-parameter optimization, achieving an R² of 0.84 with confidence intervals for predictions.
Several neurodegenerative diseases involve the accumulation of cellular DNA damage. Comet assays are a popular way of estimating the extent of DNA damage. Current literature on the use of deep learning to quantify DNA damage presents an empirical approach to hyper-parameter optimization and does not include uncertainty estimates. Deep ensemble averaging is a standard approach to estimating uncertainty but it requires several iterations of network training, which makes it time-consuming. Here we present an approach to quantify the extent of DNA damage that combines deep learning with a rigorous and comprehensive method to optimize the hyper-parameters with the help of statistical tests. We also use an architecture that allows for a faster computation of deep ensemble averaging and performs statistical tests applicable to networks using transfer learning. We applied our approach to a comet assay dataset with more than 1300 images and achieved an $R^2$ of 0.84, where the output included the confidence interval for each prediction. The proposed architecture is an improvement over the current approaches since it speeds up the uncertainty estimation by 30X while being statistically more rigorous.