ArticleNature communications2024
Improving deep neural network generalization and robustness to background bias via layer-wise relevance propagation optimization.
Article in Nature communications, 2024. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 11 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
11 citing papers in PubMed.
- Report Supervision.Medical image analysis · 2026Article
- Large-Scale Multi-Cancer Detection by Learning Segmentation from Reports.Research square · 2026Article
- Beyond transparency: why Traditional Chinese Medicine (TCM) need explainable artificial intelligence (XAI).Chinese medicine · 2026Review
- Machine learning, whole genome sequencing, and Mendelian randomization support a role of CRP on COVID-19 severity.Molecular medicine (Cambridge, Mass.) · 2026Article
- Enhancing Chest X-ray Diagnosis with a Multimodal Deep Learning Network by Integrating Clinical History to Refine Attention.Journal of imaging informatics in medicine · 2025Article
- Detecting and Mitigating the Clever Hans Effect in Medical Imaging: A Scoping Review.Journal of imaging informatics in medicine · 2025Article
- Machine learning is changing osteoporosis detection: an integrative review.Osteoporosis international : a journal established as result of cooperation between the European Foundation for Osteoporosis and the National Osteoporosis Foundation of the USA · 2025Review
- Safeguarding large language models: a survey.Artificial intelligence review · 2025Article
- Unmasking the Clever Hans effect in AI models: shortcut learning, spurious correlations, and the path toward robust intelligence.Frontiers in artificial intelligence · 2025Review
- Deep learning-based classification of anti-personnel mines and sub-gram metal content in mineralized soil (DL-MMD).Scientific reports · 2024Article
- Improving deep neural network generalization and robustness to background bias via layer-wise relevance propagation optimization.Nature communications · 2024Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
3 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Features in images' backgrounds can spuriously correlate with the images' classes, representing background bias. They can influence the classifier's decisions, causing shortcut learning (Clever Hans effect). The phenomenon generates deep neural networks (DNNs) that perform well on standard evaluation datasets but generalize poorly to real-world data. Layer-wise Relevance Propagation (LRP) explains DNNs' decisions. Here, we show that the optimization of LRP heatmaps can minimize the background bias influence on deep classifiers, hindering shortcut learning. By not increasing run-time computational cost, the approach is light and fast. Furthermore, it applies to virtually any classification architecture. After injecting synthetic bias in images' backgrounds, we compared our approach (dubbed ISNet) to eight state-of-the-art DNNs, quantitatively demonstrating its superior robustness to background bias. Mixed datasets are common for COVID-19 and tuberculosis classification with chest X-rays, fostering background bias. By focusing on the lungs, the ISNet reduced shortcut learning. Thus, its generalization performance on external (out-of-distribution) test databases significantly surpassed all implemented benchmark models.
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.