.png){kind=icon}
返回
Avoiding Shortcut-Learning by Mutual Information Minimization in Deep Learning-Based Image Processing
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2023.3289397.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep learning models are increasingly being used in detecting patterns and correlations in medical imaging data such as magnetic resonance imaging. However, conventional methods are incapable of considering the real underlying causal relationships. In the presence of confounders, spurious correlations between data, imaging process, content, and output can occur that allow the network to learn shortcuts instead of the desired causal relationship. This effect is even more prominent in new environments or when using out-of-distribution data since the learning process is primarily focused on correlations and patterns within the data. Hence, wrong conclusions or false diagnoses can be obtained from such confounded models. In this paper, we propose a novel framework, denoted as Mutual Information Minimization Model (MIMM), that predicts the desired causal outcome while simultaneously reducing the influence of present spurious correlations. The input imaging data is encoded into a feature vector that is split into two components to predict the primary task and the presumed spuriously correlated factor separately. We hypothesize that learned mutual information between both feature vector components can be reduced to achieve independence, i.e., confounder-free task prediction. The proposed approach is investigated on five databases: two non-medical benchmark databases (Morpho-MNIST and Fashion-MNIST) to verify the hypothesis and three medical databases (German National Cohort, UK Biobank, and ADNI). The results show that our proposed framework serves as a solution to address the limitations of conventional deep learning models in medical image analysis. By explicitly considering and minimizing spurious correlations, it learns causal relationships which result in more accurate and reliable predictions. The novel contributions in this work are: 1) the separation of features into the prediction of the primary task and the spuriously correlated factor; 2) MIMM targets the preservation of invariance to counterfactuals, prevents shortcut learning, and enables confounder-free network training; and 3) the mutual information minimization addresses heterogeneous data cohorts as usually encountered in the medical domain.
Keyword:
Causality
deep learning
medical image analysis
mutual information
shortcut learning
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Clinically applicable deep learning for diagnosis and referral in retinal disease深度学习在视网膜疾病诊断和转诊中的临床应用.png)
NATURE MEDICINE
NATURE MEDICINEIF50
PREAI
分享收藏GIT1 promotes lung cancer cell metastasis through modulating Rac1/Cdc42 activity and is associated with poor prognosisOncotargetOAAI
OncotargetIF0
OAAI分享收藏A Review of Deep-Learning-Based Medical Image Segmentation Methods基于深度学习的医学图像分割方法综述SUSTAINABILITY
OAAI
SUSTAINABILITYIF3.3
OAAI分享收藏
查看更多内容