Semi-supervised Learning for Network-Based Cardiac MR Image Segmentation

By Wenjia Bai, Ozan Oktay, Matthew Sinclair, Hideaki Suzuki, Martin Rajchl, Giacomo Tarroni, Ben Glocker, A. King, Paul M. Matthews, Daniel Rueckert. International Conference on Medical Image Computing and Computer-Assisted Intervention, 2017

431 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/1c8fd5102798a26270d98501703e38464ba4b805

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Disentangled representation learning in cardiac image analysis (2019, methodology): “Semi-supervised segmentation has been proposed for cardiac image analysis using an iterative approach and Conditional Random Fields (CRF) post-processing [Bai et al., 2017], and for gland segmentation using GANs [Zhang et al., 2017].”
Transformation-Consistent Self-Ensembling Model for Semisupervised Medical Image Segmentation (2019, methodology): “that our method gains higher performance consistently than other methods [18, 28, 52, 59] in both 10% and 20% settings, respectively.”
Annotation-efficient deep learning for automatic medical image segmentation (2020, background): “Compared to existing pseudo-label studies that update the pseudo-labels of all unlabeled data simultaneously during network learning 44,54,55 , label updating in AIDE is conducted in an orderly (label updating is conducted according to the calculated similarities between the temporal network…”
Contrastive learning of global and local features for medical image segmentation with limited annotations (2020, background): “Further, we compared with data augmentation [9, 61] and semi-supervised [6, 65] learning methods that have shown promising results for medical image segmentation.”
A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises (2020, methodology): “[63] implement such a method for cardiac MR segmentation.”
Semi-Supervised Medical Image Segmentation via Cross Teaching between CNN and Transformer (2021, methodology): “Due to the large inter-slice spacing, 2D segmentation is more suitable than direct 3D segmentation (Bai et al., 2017).”
A Topological Loss Function for Deep-Learning based Image Segmentation using Persistent Homology (2019, methodology): “For the CRF approach we used the method described in [31] with parameter settings which were tuned using a grid search to optimise performance on a CMR segmentation task [32].”
Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation (2023, neutral): “E.g. , self-training [1,48] generates pseudo-labels to supervise unlabeled data in a pseudo-supervised manner.”
Semi-supervised Medical Image Segmentation through Dual-task Consistency (2020, methodology): “Bai et al. (2017) developed an iterative framework where in each iteration, pseudo labels for unannotated images are predicted by the network and reﬁned by a Conditional Random Field (CRF) (Kr ¨ ahenb ¨ uhl and Koltun 2011), then the new pseudo labels are used to update the network.”
Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptation (2020, methodology): “[2] introduced a deep network based self-training framework with conditional random field (CRF) based iterative refinements for medical image segmentation.”