Mitigating Unknown Bias in Deep Learning-based Assessment of CT Images DeepTechnome

S Langer, O Taubmann, F Denzinger, A Maier… - BVM Workshop, 2023 - Springer
Reliably detecting diseases using relevant biological information is crucial for real-world
applicability of deep learning techniques in medical imaging. We debias deep learning
models during training against unknown bias–without preprocessing/filtering the input
beforehand or assuming specific knowledge about its distribution or precise nature in the
dataset. Control regions are used as surrogates that carry information regarding the bias;
subsequently, the classifier model extracts features, and biased intermediate features are …

DeepTechnome: Mitigating Unknown Bias in Deep Learning Based Assessment of CT Images

S Langer, O Taubmann, F Denzinger, A Maier… - arXiv preprint arXiv …, 2022 - arxiv.org
Reliably detecting diseases using relevant biological information is crucial for real-world
applicability of deep learning techniques in medical imaging. We debias deep learning
models during training against unknown bias-without preprocessing/filtering the input
beforehand or assuming specific knowledge about its distribution or precise nature in the
dataset. We use control regions as surrogates that carry information regarding the bias,
employ the classifier model to extract features, and suppress biased intermediate features …
Showing the best results for this search. See all results