Self-supervised pre-training of swin transformers for 3d medical image analysis
Abstract Vision Transformers (ViT) s have shown great performance in self-supervised
learning of global and local representations that can be transferred to downstream …
learning of global and local representations that can be transferred to downstream …
RetCCL: Clustering-guided contrastive learning for whole-slide image retrieval
Benefiting from the large-scale archiving of digitized whole-slide images (WSIs), computer-
aided diagnosis has been well developed to assist pathologists in decision-making. Content …
aided diagnosis has been well developed to assist pathologists in decision-making. Content …
A review of predictive and contrastive self-supervised learning for medical images
WC Wang, E Ahn, D Feng, J Kim - Machine Intelligence Research, 2023 - Springer
Over the last decade, supervised deep learning on manually annotated big data has been
progressing significantly on computer vision tasks. But, the application of deep learning in …
progressing significantly on computer vision tasks. But, the application of deep learning in …
[PDF][PDF] A review of self-supervised learning methods in the field of medical image analysis
J Xu - International Journal of Image, Graphics and Signal …, 2021 - mecs-press.org
In the field of medical image analysis, supervised deep learning strategies have achieved
significant development, while these methods rely on large labeled datasets. Self …
significant development, while these methods rely on large labeled datasets. Self …
Rethinking semi-supervised medical image segmentation: A variance-reduction perspective
For medical image segmentation, contrastive learning is the dominant practice to improve
the quality of visual representations by contrasting semantically similar and dissimilar pairs …
the quality of visual representations by contrasting semantically similar and dissimilar pairs …
Self-supervised learning for few-shot medical image segmentation
Fully-supervised deep learning segmentation models are inflexible when encountering new
unseen semantic classes and their fine-tuning often requires significant amounts of …
unseen semantic classes and their fine-tuning often requires significant amounts of …
Mine your own anatomy: Revisiting medical image segmentation with extremely limited labels
Recent studies on contrastive learning have achieved remarkable performance solely by
leveraging few labels in the context of medical image segmentation. Existing methods …
leveraging few labels in the context of medical image segmentation. Existing methods …
Medlsam: Localize and segment anything model for 3d medical images
The Segment Anything Model (SAM) has recently emerged as a groundbreaking model in
the field of image segmentation. Nevertheless, both the original SAM and its medical …
the field of image segmentation. Nevertheless, both the original SAM and its medical …
Geometric visual similarity learning in 3d medical image self-supervised pre-training
Learning inter-image similarity is crucial for 3D medical images self-supervised pre-training,
due to their sharing of numerous same semantic regions. However, the lack of the semantic …
due to their sharing of numerous same semantic regions. However, the lack of the semantic …
Anatomical invariance modeling and semantic alignment for self-supervised learning in 3d medical image analysis
Self-supervised learning (SSL) has recently achieved promising performance for 3D medical
image analysis tasks. Most current methods follow existing SSL paradigm originally …
image analysis tasks. Most current methods follow existing SSL paradigm originally …