# Sparse Bayesian Networks: Efficient Uncertainty Quantification in Medical Image Analysis

arXiv: https://arxiv.org/abs/2406.06946 · HTML: https://mlsanity.com/paper/2406.06946/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 33 references that are in the map.
- First posted on arXiv 11 Jun 2024.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases](https://mlsanity.com/paper/1705.02315/) (2017)
- [MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification](https://mlsanity.com/paper/2110.14795/) (2021)
- [Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1902.03368/) (2019)
- [Learning Structured Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1608.03665/) (2016)
- [Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks](https://mlsanity.com/paper/2102.00554/) (2021)
- [Rigging the Lottery: Making All Tickets Winners](https://mlsanity.com/paper/1911.11134/) (2019)
- [Variational Dropout and the Local Reparameterization Trick](https://mlsanity.com/paper/1506.02557/) (2015)
- [Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users](https://mlsanity.com/paper/2007.06823/) (2020)
- [Dynamic Network Surgery for Efficient DNNs](https://mlsanity.com/paper/1608.04493/) (2016)
- [Efficient Exploration through Bayesian Deep Q-Networks](https://mlsanity.com/paper/1802.04412/) (2018)
- [The Relevance of Bayesian Layer Positioning to Model Uncertainty in Deep Bayesian Active Learning](https://mlsanity.com/paper/1811.12535/) (2018)
- [Efficient Computation Reduction in Bayesian Neural Networks Through Feature Decomposition and Memorization](https://mlsanity.com/paper/2005.03857/) (2020)
- [Pre-Defined Sparse Neural Networks with Hardware Acceleration](https://mlsanity.com/paper/1812.01164/) (2018)
- [Bayesian Neural Networks at Scale: A Performance Analysis and Pruning Study](https://mlsanity.com/paper/2005.11619/) (2020)

## Built on by (most cited first, 8 of 8)

- [Uncertainty Quantification for Machine Learning in Healthcare: A Survey](https://mlsanity.com/paper/2505.02874/) (2025)
- [Towards Clinical Practice in CT-Based Pulmonary Disease Screening: An Efficient and Reliable Framework](https://mlsanity.com/paper/2412.01525/) (2024)
- [Towards Reliable Medical LLMs: Benchmarking and Enhancing Confidence Estimation of Large Language Models in Medical Consultation](https://mlsanity.com/paper/2601.15645/) (2026)
- [DGRNet: Disagreement-Guided Refinement for Uncertainty-Aware Brain Tumor Segmentation](https://mlsanity.com/paper/2603.21086/) (2026)
- [AMO-ENE: Attention-based Multi-Omics Fusion Model for Outcome Prediction in Extra Nodal Extension and HPV-associated Oropharyngeal Cancer](https://mlsanity.com/paper/2604.09280/) (2026)
- [Specificity- and Calibration-Aware Breast Ultrasound Segmentation via Entropy-Guided Boundary Supervision](https://mlsanity.com/paper/2606.22308/) (2026)
- [Entropy-Regularized Probabilistic Gates for Sparse Model Discovery in Scarce-Data Federated Learning](https://mlsanity.com/paper/2607.00275/) (2026)
- [Parameter-Efficient pretrained-CT-to-MRI Transfer for Rectal Cancer Segmentation: Performance-Calibration Trade-offs](https://mlsanity.com/paper/2608.27178/) (2026)

## Abstract (arXiv)

Efficiently quantifying predictive uncertainty in medical images remains a challenge. While Bayesian neural networks (BNN) offer predictive uncertainty, they require substantial computational resources to train. Although Bayesian approximations such as ensembles have shown promise, they still suffer from high training and inference costs. Existing approaches mainly address the costs of BNN inference post-training, with little focus on improving training efficiency and reducing parameter complexity. This study introduces a training procedure for a sparse (partial) Bayesian network. Our method selectively assigns a subset of parameters as Bayesian by assessing their deterministic saliency through gradient sensitivity analysis. The resulting network combines deterministic and Bayesian parameters, exploiting the advantages of both representations to achieve high task-specific performance and minimize predictive uncertainty. Demonstrated on multi-label ChestMNIST for classification and ISIC, LIDC-IDRI for segmentation, our approach achieves competitive performance and predictive uncertainty estimation by reducing Bayesian parameters by over 95%, significantly reducing computational expenses compared to fully Bayesian and ensemble methods.