Semi-supervised Contrastive Learning for Label-Efficient Medical Image Segmentation

Hu, Xinrong; Zeng, Dewen; Xu, Xiaowei; Shi, Yiyu

doi:10.1007/978-3-030-87196-3_45

Cited by 65 publications

(39 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To also pre-train the decoder, the method in (Chaitanya et al, 2020) defined positive or negative embedding pairs based on their spatial distance in a feature map, those with a large distance considered as negative while those at the same spatial position but coming from different transformations as positives. Hu et al (2021) proposed using small set of pixel-wise annotations to guide the learning of dense features in pre-training. The feature embeddings of pixels with the same label are considered as positive pairs and are then clustered together by the contrastive loss.…”

Section: B Related Workmentioning

confidence: 99%

Boundary-aware Information Maximization for Self-supervised Medical Image Segmentation

Peng¹,

Wang²,

Pedersoli³

et al. 2022

Preprint

View full text Add to dashboard Cite

Unsupervised pre-training has been proven as an effective approach to boost various downstream tasks given limited labeled data. Among various methods, contrastive learning learns a discriminative representation by constructing positive and negative pairs. However, it is not trivial to build reasonable pairs for a segmentation task in an unsupervised way. In this work, we propose a novel unsupervised pre-training framework that avoids the drawback of contrastive learning. Our framework consists of two principles: unsupervised over-segmentation as a pre-train-task using Mutual information maximization and boundary-aware preserving learning. Experimental results on two benchmark medical segmentation datasets reveal our method's effectiveness in improving segmentation performance when few annotated images are available.

show abstract

Section: B Related Workmentioning

confidence: 99%

Boundary-aware Information Maximization for Self-supervised Medical Image Segmentation

Peng¹,

Wang²,

Pedersoli³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In contrast to camouflaged objects, salient objects are the most noticeable objects in an image. The research of salient object detection can promote image understanding [33], stereo matching [34,35] and medical disease detection [36][37][38]. In recent years, salient object detection based on deep learning has been improved mainly by multiscale feature fusion [39], attention mechanisms [40] and edge information [41].…”

Section: Salient Object Detection Based On Deep Learningmentioning

confidence: 99%

MAGNet: A camouflaged object detection network simulating the observation effect of a magnifier

Jiang

Cai

Jiang

et al. 2022

Preprint

View full text Add to dashboard Cite

In recent years, protecting important objects by simulating animal camouflage has been widely used in many fields. Therefore, camouflaged object detection (COD) technology has emerged. COD is more difficult than traditional object detection techniques because of the high degree of fusion of camouflaged objects with the background. In this paper, we strive to more accurately identify camouflaged objects. Inspired by the use of magnifiers to search for hidden objects in pictures, we propose a COD network that simulates the observation effect of a magnifier, called the MAGnifier Network (MAGNet). Specifically, our MAGNet contains two parallel modules, i.e., the ergodic magnification module (EMM) and the attention focus module (AFM). The EMM is designed to mimic the process of a magnifier enlarging an image, and AFM is used to simulate the observation process in which human attention is highly focused on a region. The two sets of output camouflaged object maps are merged to simulate the observation of an object by a magnifier. In addition, a weighted key point area perception loss function, which is more applicable to COD, is designed based on two modules to give higher attention to the camouflaged object. Extensive experiments demonstrate that compared with 14 cutting-edge detection models, MAGNet can achieve the best comprehensive effect on eight evaluation metrics on the public COD dataset, and the segmentation accuracy is significantly improved. We also validate the models' generalization ability on a military camouflaged object dataset constructed in-house. Finally, we experimentally explore some extended applications of COD.

show abstract

“…Combining supervised learning and contrastive learning, Khosla et al [31] proposed a SupCon Loss for natural image categorization. Hu et al [32] developed a supervised local contrastive loss to leverage limited pixel-wise annotation for cardiac segmentation following the SupCon [31]. Chartsias et al [33] proposed using contrastive learning to mitigate the labeling bottleneck for view classification of echocardiograms.…”

Section: Contrastive Representation Learning In Medical Visual Recogn...mentioning

confidence: 99%

CDNet: Contrastive Disentangled Network for Fine-Grained Image Categorization of Ocular B-Scan Ultrasound

Dan¹,

Li²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Precise and rapid categorization of images in the Bscan ultrasound modality is vital for diagnosing ocular diseases. Nevertheless, distinguishing various diseases in ultrasound still challenges experienced ophthalmologists. Thus a novel contrastive disentangled network (CDNet) is developed in this work, aiming to tackle the fine-grained image categorization (FGIC) challenges of ocular abnormalities in ultrasound images, including intraocular tumor (IOT), retinal detachment (RD), posterior scleral staphyloma (PSS), and vitreous hemorrhage (VH). Three essential components of CDNet are the weaklysupervised lesion localization module (WSLL), contrastive multizoom (CMZ) strategy, and hyperspherical contrastive disentangled loss (HCD-Loss), respectively. These components facilitate feature disentanglement for fine-grained recognition in both the input and output aspects. The proposed CDNet is validated on our ZJU Ocular Ultrasound Dataset (ZJUOUSD), consisting of 5213 samples. Furthermore, the generalization ability of CDNet is validated on two public and widely-used chest X-ray FGIC benchmarks. Quantitative and qualitative results demonstrate the efficacy of our proposed CDNet, which achieves state-ofthe-art performance in the FGIC task. Code is available at: https://github.com/ZeroOneGame/CDNet-for-OUS-FGIC.

show abstract

Semi-supervised Contrastive Learning for Label-Efficient Medical Image Segmentation

Cited by 65 publications

References 11 publications

Boundary-aware Information Maximization for Self-supervised Medical Image Segmentation

Boundary-aware Information Maximization for Self-supervised Medical Image Segmentation

MAGNet: A camouflaged object detection network simulating the observation effect of a magnifier

CDNet: Contrastive Disentangled Network for Fine-Grained Image Categorization of Ocular B-Scan Ultrasound

Contact Info

Product

Resources

About