# Uncertainty-Aware Segmentation Quality Prediction via Deep Learning Bayesian Modeling: Comprehensive Evaluation and Interpretation on Skin Cancer and Liver Segmentation

arXiv: https://arxiv.org/abs/2508.01460 · HTML: https://mlsanity.com/paper/2508.01460/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 2 Aug 2025.

## Builds on (most cited first, 22 of 22)

- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2105.05537/) (2021)
- [A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges](https://mlsanity.com/paper/2011.06225/) (2020)
- [Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1902.03368/) (2019)
- [The Liver Tumor Segmentation Benchmark (LiTS)](https://mlsanity.com/paper/1901.04056/) (2019)
- [Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysis](https://mlsanity.com/paper/2111.14791/) (2021)
- [Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks](https://mlsanity.com/paper/1807.07356/) (2018)
- [Learning Confidence for Out-of-Distribution Detection in Neural Networks](https://mlsanity.com/paper/1802.04865/) (2018)
- [Multiplicative Normalizing Flows for Variational Bayesian Neural Networks](https://mlsanity.com/paper/1703.01961/) (2017)
- [Learning Active Learning from Data](https://mlsanity.com/paper/1703.03365/) (2017)
- [Abdominal multi-organ segmentation with organ-attention networks and statistical fusion](https://mlsanity.com/paper/1804.08414/) (2018)
- [Leveraging Uncertainty Estimates for Predicting Segmentation Quality](https://mlsanity.com/paper/1807.00502/) (2018)
- [Accurate Uncertainty Estimation and Decomposition in Ensemble Learning](https://mlsanity.com/paper/1911.04061/) (2019)
- [Bayesian QuickNAT: Model Uncertainty in Deep Whole-Brain Segmentation for Structure-wise Quality Control](https://mlsanity.com/paper/1811.09800/) (2018)
- [Reverse Classification Accuracy: Predicting Segmentation Performance in the Absence of Ground Truth](https://mlsanity.com/paper/1702.03407/) (2017)
- [ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation](https://mlsanity.com/paper/2401.08501/) (2024)
- [Estimating Uncertainty in Neural Networks for Cardiac MRI Segmentation: A Benchmark Study](https://mlsanity.com/paper/2012.15772/) (2020)
- [Uncertainty Estimation via Stochastic Batch Normalization](https://mlsanity.com/paper/1802.04893/) (2018)
- [Novel structural-scale uncertainty measures and error retention curves: application to multiple sclerosis](https://mlsanity.com/paper/2211.04825/) (2022)

## Built on by (most cited first, 2 of 2)

- [When Experts Disagree: Characterizing Annotator Variability for Vessel Segmentation in DSA Images](https://mlsanity.com/paper/2508.10797/) (2025)
- [Implicit Fuzzification via Bounded Noise Injection for Robust Medical Image Segmentation](https://mlsanity.com/paper/2606.04427/) (2026)

## Abstract (arXiv)

Image segmentation is a critical step in computational biomedical image analysis, typically evaluated using metrics like the Dice coefficient during training and validation. However, in clinical settings without manual annotations, assessing segmentation quality becomes challenging, and models lacking reliability indicators face adoption barriers. To address this gap, we propose a novel framework for predicting segmentation quality without requiring ground truth annotations during test time. Our approach introduces two complementary frameworks: one leveraging predicted segmentation and uncertainty maps, and another integrating the original input image, uncertainty maps, and predicted segmentation maps. We present Bayesian adaptations of two benchmark segmentation models-SwinUNet and Feature Pyramid Network with ResNet50-using Monte Carlo Dropout, Ensemble, and Test Time Augmentation to quantify uncertainty. We evaluate four uncertainty estimates: confidence map, entropy, mutual information, and expected pairwise Kullback-Leibler divergence on 2D skin lesion and 3D liver segmentation datasets, analyzing their correlation with segmentation quality metrics. Our framework achieves an R2 score of 93.25 and Pearson correlation of 96.58 on the HAM10000 dataset, outperforming previous segmentation quality assessment methods. For 3D liver segmentation, Test Time Augmentation with entropy achieves an R2 score of 85.03 and a Pearson correlation of 65.02, demonstrating cross-modality robustness. Additionally, we propose an aggregation strategy that combines multiple uncertainty estimates into a single score per image, offering a more robust and comprehensive assessment of segmentation quality. Finally, we use Grad-CAM and UMAP-based embedding analysis to interpret the model's behavior and reliability, highlighting the impact of uncertainty integration.