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

Source: [Uncertainty-Aware Segmentation Quality Prediction via Deep Learning Bayesian Modeling: Comprehensive Evaluation and Interpretation on Skin Cancer and Liver Segmentation](<https://www.sota2.com/research/paper/68fa7a671e209131cea82f8e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:19.997Z

Authors: Sikha O K, Meritxell Riera-Mar\\'in, Adrian Galdran, Javier Garc\\'ia Lopez, Julia Rodr\\'iguez-Comas, Gemma Piella, Miguel A. Gonz\\'alez Ballester

Published: 2025-08-02T18:30:32.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2508.01460>)

[PDF](<https://arxiv.org/pdf/2508.01460.pdf>)
