Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation

By Lequan Yu, Shujun Wang, Xiaomeng Li, Chi-Wing Fu, P. Heng. International Conference on Medical Image Computing and Computer-Assisted Intervention, 2019

1,259 citations recorded by the source corpus.

Training deep convolutional neural networks usually requires a large amount of labeled data. However, it is expensive and time-consuming to annotate data for medical image segmentation tasks. In this paper, we present a novel uncertainty-aware semi-supervised framework for left atrium segmentation from 3D MR images. Our framework can effectively leverage the unlabeled data by encouraging consistent predictions of the same input under different perturbations. Concretely, the framework consists of a student model and a teacher model, and the student model learns from the teacher model by minimizing a segmentation loss and a consistency loss with respect to the targets of the teacher model. We design a novel uncertainty-aware scheme to enable the student model to gradually learn from the meaningful and reliable targets by exploiting the uncertainty information. Experiments show that our method achieves high performance gains by incorporating the unlabeled data. Our method outperforms the state-of-the-art semi-supervised methods, demonstrating the potential of our framework for the challenging semi-supervised problems.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/2341bd2d21bff49fb5c985130a070a6e4092ea35

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation (2023, neutral): “We strictly follow the setting used in SSNet [35], DTC [16] and UA-MT [41].”
Deep learning with noisy labels: exploring techniques and remedies in medical image analysis (2019, methodology): “lesion detection and classification, segmentation ([97]) [98] - image classification [69] - facial attribute recognition [99] - image classification [100]- image classification [101] - image classification, emotion recognition, object detection”
Semi-supervised Medical Image Segmentation through Dual-task Consistency (2020, methodology): “Yu et al. (2019) extended the mean teacher model (Tarvainen and Valpola 2017) with uncertainty map guidance for semi-supervised left atrium segmentation.”
A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges (2020, background): “5: A general view demonstrating the semi-supervised UA-MT framework applied to LA segmentation which is reproduced based on [36].”
In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning (2021, background): “In the SSL domain, (Yu et al., 2019; Xia et al., 2020) use uncertainty to improve consistency regularization learning for the segmentation of medical images.”
Mutual consistency learning for semi-supervised medical image segmentation (2021, methodology): “For example, Yu et al. (2019) proposed an uncertainty-aware mean-teacher model for semi-supervised left atrium segmentation.”
Semi-Supervised Medical Image Segmentation via Cross Teaching between CNN and Transformer (2021, methodology): “, 2017), 4) Uncertainty Aware Mean Teacher (UAMT) (Yu et al., 2019), 5) Interpolation Consistency Training (ICT) (Verma et al.”
SimCVD: Simple Contrastive Voxel-Wise Representation Distillation for Semi-Supervised Medical Image Segmentation (2021, methodology): “Our base architecture adopts V-Net [20] as the network backbone, which consists of an encoder network et : RH×W×D → RH ′×W′×D′×De and a decoder network dt : RH ′×W′×D′×De → [0,1]H×W×D × [−1,1]H×W×D for the teacher network, and similarly es, ds for the student network, i.”
Recent advances and clinical applications of deep learning in medical image analysis (2021, methodology): “…training (Xue et al., 2018; Zhang et al., 2020b), attention mechanism (Jetley et al., 2018; Anderson et al., 2018; Oktay et al., 2018; Nie et al., 2018; Sinha and Dolz, 2021), and uncertainty estimation (Wang et al., 2019; Yu et al., 2019; Baumgartner et al., 2019; Mehrtash et al., 2020).”
A Noise-Robust Framework for Automatic Segmentation of COVID-19 Pneumonia Lesions From CT Images (2020, methodology): “Our adaptive self-ensembling is extended from previous self-ensembling for semi-supervised learning [20], [21], and our adaptive mechanisms make it more suitable for dealing with noisy labels.”
LViT: Language Meets Vision Transformer in Medical Image Segmentation (2022, background): “In order to address the issue of under-annotated data, some approaches have gone beyond traditional supervised learning by training their models using both labeled and more widely available unlabeled data, such as semi-supervised learning [5, 6] and weakly supervised learning [7].”