# Uncertain but Useful: Leveraging CNN Training Variability into Data Augmentation

arXiv: https://arxiv.org/abs/2509.05238 · HTML: https://mlsanity.com/paper/2509.05238/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 28 references that are in the map.
- First posted on arXiv 5 Sep 2025.

## Builds on (most cited first, 6 of 6)

- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [FastSurfer -- A fast and accurate deep learning based neuroimaging pipeline](https://mlsanity.com/paper/1910.03866/) (2019)
- [FastSurferVINN: Building Resolution-Independence into Deep Learning Segmentation Methods -- A Solution for HighRes Brain MRI](https://mlsanity.com/paper/2112.09654/) (2021)
- [Numerical Uncertainty of Convolutional Neural Networks Inference for Structural Brain MRI Analysis](https://mlsanity.com/paper/2308.01939/) (2023)
- [Accurate simulation of operating system updates in neuroimaging using Monte-Carlo arithmetic](https://mlsanity.com/paper/2108.03129/) (2021)
- [Data Augmentation Through Monte Carlo Arithmetic Leads to More Generalizable Classification in Connectomics](https://mlsanity.com/paper/2109.09649/) (2021)

## Abstract (arXiv)

Deep learning (DL) has transformed neuroimaging by delivering state-of-the-art performance with reduced computation times. Yet, the numerical uncertainty inherent to DL training remains largely underexplored despite its potential to significantly impact the reliability of model outcomes. We show that training the FastSurfer segmentation model introduces substantial numerical uncertainty that exceeds its non-DL counterpart (FreeSurfer 7.3.2) in cortical regions, potentially impacting downstream clinical results. We also characterize this training-time uncertainty using random seed perturbations and demonstrate that seed-induced variability is structurally comparable to numerical variability. We then show that seed variability can be leveraged as a data augmentation technique through ensembling to improve downstream brain age regression performance. These findings position numerical uncertainty during DL training as a substantive factor in neuroimaging reliability, with measurable consequences for downstream tasks, and demonstrate that it can simultaneously be harnessed as a data augmentation technique.