Citation

BibTex format

@article{Zhou:2024:10.1016/j.compbiomed.2024.108990,
author = {Zhou, X and Wang, X and Ma, H and Zhang, J and Wang, X and Bai, X and Zhang, L and Long, J and Chen, J and Le, H and He, W and Zhao, S and Xia, J and Yang, G},
doi = {10.1016/j.compbiomed.2024.108990},
journal = {Comput Biol Med},
title = {Customized T-time inner sampling network with uncertainty-aware data augmentation strategy for multi-annotated lesion segmentation.},
url = {http://dx.doi.org/10.1016/j.compbiomed.2024.108990},
volume = {180},
year = {2024}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Segmentation in medical images is inherently ambiguous. It is crucial to capture the uncertainty in lesion segmentations to assist cancer diagnosis and further interventions. Recent works have made great progress in generating multiple plausible segmentation results as diversified references to account for the uncertainty in lesion segmentations. However, the efficiency of existing models is limited, and the uncertainty information lying in multi-annotated datasets remains to be fully utilized. In this study, we propose a series of methods to corporately deal with the above limitation and leverage the abundant information in multi-annotated datasets: (1) Customized T-time Inner Sampling Network to promote the modeling flexibility and efficiently generate samples matching the ground-truth distribution of a number of annotators; (2) Uncertainty Degree defined for quantitatively measuring the uncertainty of each sample and the imbalance of the whole multi-annotated dataset from a brand new perspective; (3) Uncertainty-aware Data Augmentation Strategy to help probabilistic models adaptively fit samples with different ranges of uncertainty. We have evaluated each of them on both the publicly available lung nodule dataset and our in-house Liver Tumor dataset. Results show that our proposed methods achieves the overall best performance on both accuracy and efficiency, demonstrating its great potential in lesion segmentations and more downstream tasks in real clinical scenarios.
AU  - Zhou,X
AU  - Wang,X
AU  - Ma,H
AU  - Zhang,J
AU  - Wang,X
AU  - Bai,X
AU  - Zhang,L
AU  - Long,J
AU  - Chen,J
AU  - Le,H
AU  - He,W
AU  - Zhao,S
AU  - Xia,J
AU  - Yang,G
DO  - 10.1016/j.compbiomed.2024.108990
PY  - 2024///
TI  - Customized T-time inner sampling network with uncertainty-aware data augmentation strategy for multi-annotated lesion segmentation.
T2  - Comput Biol Med
UR  - http://dx.doi.org/10.1016/j.compbiomed.2024.108990
UR  - https://www.ncbi.nlm.nih.gov/pubmed/39126788
VL  - 180
ER  -
Download

Contact

For enquiries about the MRI Physics Collective, please contact:

Mary Finnegan
Senior MR Physicist at the Imperial College Healthcare NHS Trust

Pete Lally
Assistant Professor in Magnetic Resonance (MR) Physics at Imperial College

Jan Sedlacik
MR Physicist at the Robert Steiner MR Unit, Hammersmith Hospital Campus