Domain-guided data augmentation for deep learning on medical imaging

C Athalye, R Arnaout - PloS one, 2023 - journals.plos.org
While domain-specific data augmentation can be useful in training neural networks for
medical imaging tasks, such techniques have not been widely used to date. Our objective …

Data efficient deep learning for medical image analysis: A survey

S Kumari, P Singh - arXiv preprint arXiv:2310.06557, 2023 - arxiv.org
The rapid evolution of deep learning has significantly advanced the field of medical image
analysis. However, despite these achievements, the further enhancement of deep learning …

Anti-adversarial consistency regularization for data augmentation: Applications to robust medical image segmentation

H Cho, Y Han, WH Kim - … Conference on Medical Image Computing and …, 2023 - Springer
Modern deep learning methods for semantic segmentation require labor-intensive labeling
for large-scale datasets with dense pixel-level annotations. Recent data augmentation …

Uncertainty-aware diffusion-based adversarial attack for realistic colonoscopy image synthesis

M Jeong, H Cho, S Jung, WH Kim - International Conference on Medical …, 2024 - Springer
Automated semantic segmentation in colonoscopy is crucial for detecting colon polyps and
preventing the development of colorectal cancer. However, the scarcity of annotated data …

InstaBoost++: Visual Coherence Principles for Unified 2D/3D Instance Level Data Augmentation

J Sun, HS Fang, Y Li, R Wang, M Gou, C Lu - International Journal of …, 2023 - Springer
Instance-level perception tasks like object detection, instance segmentation, and 3D
detection require many training samples to achieve satisfactory performance. The …

Soft-cp: A credible and effective data augmentation for semantic segmentation of medical lesions

P Dai, L Dong, R Zhang, H Zhu, J Wu… - arXiv preprint arXiv …, 2022 - arxiv.org
The medical datasets are usually faced with the problem of scarcity and data imbalance.
Moreover, annotating large datasets for semantic segmentation of medical lesions is domain …

Learning Transferable Object-Centric Diffeomorphic Transformations for Data Augmentation in Medical Image Segmentation

N Kumar, PK Gyawali, S Ghimire, L Wang - International Conference on …, 2023 - Springer
Obtaining labelled data in medical image segmentation is challenging due to the need for
pixel-level annotations by experts. Recent works have shown that augmenting the object of …

Semi-supervised segmentation of abdominal organs and liver tumor: uncertainty rectified curriculum labeling meets X-fuse

P Lyu, W Liu, T Lin, J Zhang, Y Liu… - … Learning: Science and …, 2024 - iopscience.iop.org
Precise liver tumors and associated organ segmentation hold immense value for surgical
and radiological intervention, enabling anatomical localization for pre-operative planning …

Cut-Paste Consistency Learning for Semi-Supervised Lesion Segmentation

BP Yap, BK Ng - Proceedings of the IEEE/CVF Winter …, 2023 - openaccess.thecvf.com
Semi-supervised learning has the potential to improve the data-efficiency of training data-
hungry deep neural networks, which is especially important for medical image analysis tasks …

Self-supervised Brain Lesion Generation for Effective Data Augmentation of Medical Images

J Huo, S Ourselin, R Sparks - arXiv preprint arXiv:2406.14826, 2024 - arxiv.org
Accurate brain lesion delineation is important for planning neurosurgical treatment.
Automatic brain lesion segmentation methods based on convolutional neural networks have …