A dynamic uncertainty-aware ensemble model: Application to lung cancer segmentation in digital pathology
Article
Salvi, Massimo, Mogetta, Alessandro, Raghavendra, U., Gudigar, Anjan, Acharya, U. Rajendra and Molinari, Filippo. 2024. "A dynamic uncertainty-aware ensemble model: Application to lung cancer segmentation in digital pathology." Applied Soft Computing. 165. https://doi.org/10.1016/j.asoc.2024.112081
| Article Title | A dynamic uncertainty-aware ensemble model: Application to lung cancer segmentation in digital pathology |
|---|---|
| ERA Journal ID | 17759 |
| Article Category | Article |
| Authors | Salvi, Massimo, Mogetta, Alessandro, Raghavendra, U., Gudigar, Anjan, Acharya, U. Rajendra and Molinari, Filippo |
| Journal Title | Applied Soft Computing |
| Journal Citation | 165 |
| Article Number | 112081 |
| Number of Pages | 12 |
| Year | 2024 |
| Publisher | Elsevier |
| Place of Publication | Netherlands |
| ISSN | 1568-4946 |
| 1872-9681 | |
| Digital Object Identifier (DOI) | https://doi.org/10.1016/j.asoc.2024.112081 |
| Web Address (URL) | https://www.sciencedirect.com/science/article/pii/S156849462400855X |
| Abstract | Ensemble models have emerged as a powerful technique for improving robustness in medical image segmentation. However, traditional ensembles suffer from limitations such as under-confidence and over-reliance on poor performing models. In this work, we introduce an Adaptive Uncertainty-based Ensemble (AUE) model for tumor segmentation in histopathological slides. Our approach leverages uncertainty estimates from Monte Carlo dropout during testing to dynamically select the optimal pair of models for each whole slide image. The AUE model combines predictions from the two most reliable models (K-Net, ResNeSt, Segformer, Twins), identified through uncertainty quantification, to enhance segmentation performance. We validate the AUE model on the ACDC@LungHP challenge dataset, systematically comparing it against state-of-the-art approaches. Results demonstrate that our uncertainty-guided ensemble achieves a mean Dice score of 0.8653 and outperforms traditional ensemble techniques and top-ranked methods from the challenge by over 3 %. Our adaptive ensemble approach provides accurate and reliable lung tumor delineation in histopathology images by managing model uncertainty. |
| Keywords | Deep learning; Ensemble model; Lung cancer; Monte Carlo dropout; Uncertainty |
| Contains Sensitive Content | Does not contain sensitive content |
| ANZSRC Field of Research 2020 | 420311. Health systems |
| Byline Affiliations | Polytechnic University of Turin, Italy |
| Manipal Academy of Higher Education, India | |
| School of Mathematics, Physics and Computing | |
| Centre for Health Research |
Permalink -
https://research.usq.edu.au/item/z9q2v/a-dynamic-uncertainty-aware-ensemble-model-application-to-lung-cancer-segmentation-in-digital-pathology
Download files
34
total views14
total downloads5
views this month3
downloads this month