Context-aware augmentation for liver lesion segmentation: shape uniformity, expansion limit and fusion strategy
Authors:
Open Access
- 1 August 2023
- journal article
- research article
- Published by AME Publishing Company in Quantitative Imaging in Medicine and Surgery
- Vol. 13 (8) , 5043-5057
Abstract
Background: Data augmentation with context has been an effective way to increase the robustness and generalizability of deep learning models. However, to our knowledge, shape uniformity, expansion limit, and fusion strategy of context have yet to be comprehensively studied, particularly in lesion segmentation of medical images. Methods: To examine the impact of these factors, we take liver lesion segmentation based on the well-known deep learning architecture U-Net as an example and thoroughly vary the context shape, the expansion bandwidth as well as three representative fusion methods. In particular, the context shape includes rectangular, circular and polygonal, the expansion bandwidth is scaled by a maximum value of 2 compared to the lesion size, and the context fusion weighting strategy is composed of average, Gaussian and inverse Gaussian. Results: Studies conducted on a newly constructed high-quality and large-volume dataset show that (I) uniform context improves lesion segmentation, (II) expanding the context with either 5 or 7 pixels yields the highest performance for liver lesion segmentation, depending on the lesion size, and (III) an unevenly distributed weighting strategy for context fusion is appreciated but in the opposite direction, depending on lesion size as well. Conclusions: Our findings and newly constructed dataset are expected to be useful for liver lesion segmentation, especially for small lesions.Keywords
This publication has 12 references indexed in Scilit:
- Automated knee cartilage segmentation for heterogeneous clinical MRI using generative adversarial networks with transfer learningQuantitative Imaging in Medicine and Surgery, 2022
- Multi-slice low-rank tensor decomposition based multi-atlas segmentation: Application to automatic pathological liver CT segmentationMedical Image Analysis, 2021
- United adversarial learning for liver tumor segmentation and detection of multi-modality non-contrast MRIMedical Image Analysis, 2021
- Domain knowledge augmentation of parallel MR image reconstruction using deep learningComputerized Medical Imaging and Graphics, 2021
- A deep semantic segmentation correction network for multi-model tiny lesion areas detectionBMC Medical Informatics and Decision Making, 2021
- Comparison of metrics for the evaluation of medical segmentations using prostate MRI datasetComputers in Biology and Medicine, 2021
- nnU-Net: a self-configuring method for deep learning-based biomedical image segmentationNature Methods, 2020
- On the Importance of Visual Context for Data Augmentation in Scene UnderstandingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2019
- Impact of intensively lowered low‐density lipoprotein cholesterol on deferred lesion prognosisCatheterization and Cardiovascular Interventions, 2019
- Fully Convolutional Networks for Semantic SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016