Challenges for machine learning in clinical translation of big data imaging studies

NK Dinsdale, E Bluemke, V Sundaresan, M Jenkinson… - Neuron, 2022 - cell.com
Combining deep learning image analysis methods and large-scale imaging datasets offers
many opportunities to neuroscience imaging and epidemiology. However, despite these …

SDC-UDA: volumetric unsupervised domain adaptation framework for slice-direction continuous cross-modality medical image segmentation

H Shin, H Kim, S Kim, Y Jun, T Eo… - Proceedings of the …, 2023 - openaccess.thecvf.com
Recent advances in deep learning-based medical image segmentation studies achieve
nearly human-level performance in fully supervised manner. However, acquiring pixel-level …

CrossMoDA 2021 challenge: Benchmark of cross-modality domain adaptation techniques for vestibular schwannoma and cochlea segmentation

R Dorent, A Kujawa, M Ivory, S Bakas, N Rieke… - Medical Image …, 2023 - Elsevier
Abstract Domain Adaptation (DA) has recently been of strong interest in the medical imaging
community. While a large variety of DA techniques have been proposed for image …

Segmentation of vestibular schwannoma from MRI, an open annotated dataset and baseline algorithm

J Shapey, A Kujawa, R Dorent, G Wang, A Dimitriadis… - Scientific Data, 2021 - nature.com
Automatic segmentation of vestibular schwannomas (VS) from magnetic resonance imaging
(MRI) could significantly improve clinical workflow and assist patient management. We have …

Contrastive semi-supervised learning for domain adaptive segmentation across similar anatomical structures

R Gu, J Zhang, G Wang, W Lei, T Song… - … on Medical Imaging, 2022 - ieeexplore.ieee.org
Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance for
medical image segmentation, yet need plenty of manual annotations for training. Semi …

Source-free domain adaptation for image segmentation

M Bateson, H Kervadec, J Dolz, H Lombaert… - Medical Image …, 2022 - Elsevier
Abstract Domain adaptation (DA) has drawn high interest for its capacity to adapt a model
trained on labeled source data to perform well on unlabeled or weakly labeled target data …

Scribble-based boundary-aware network for weakly supervised salient object detection in remote sensing images

Z Huang, TZ **ang, HX Chen, H Dai - ISPRS Journal of Photogrammetry …, 2022 - Elsevier
Existing CNN-based salient object detection (SOD) models rely heavily on large-scale pixel-
level annotations, which are labor-intensive, time-consuming, and expensive. In contrast …

Label-efficient deep learning in medical image analysis: Challenges and future directions

C **, Z Guo, Y Lin, L Luo, H Chen - arxiv preprint arxiv:2303.12484, 2023 - arxiv.org
Deep learning has seen rapid growth in recent years and achieved state-of-the-art
performance in a wide range of applications. However, training models typically requires …

COSMOS: cross-modality unsupervised domain adaptation for 3D medical image segmentation based on target-aware domain translation and iterative self-training

H Shin, H Kim, S Kim, Y Jun, T Eo, D Hwang - arxiv preprint arxiv …, 2022 - arxiv.org
Recent advances in deep learning-based medical image segmentation studies achieve
nearly human-level performance when in fully supervised condition. However, acquiring …

Scribble2d5: Weakly-supervised volumetric image segmentation via scribble annotations

Q Chen, Y Hong - International Conference on Medical Image Computing …, 2022 - Springer
Image segmentation using weak annotations like scribbles has gained great attention, since
such annotations are easier to obtain compared to time-consuming and labor-intensive …