Contrastive Rendering for Ultrasound Image Segmentation

Li, Haoming; Liang, Jiamin; Shi, Wenlong; Chen, Chao‐Yu; Dou, Haoran; Li, Rui; Gao, Rui; Zhou, Guang-Quan; Fang, Jinghui; Liang, Xiaowen; Huang, Ruobing; Frangi, Alejandro F.; Chen, Zhiyi; Ni, Dong

doi:10.1007/978-3-030-59716-0_54

Cited by 10 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep attention networks have also been proposed for improved segmentation performance in US imaging, such as the attention-guided dual-path network [53] and a U-Net-based network combining a channel attention module and VGG [54]. A contrastive learning-based framework [55] and a framework based on the generative adversarial network (GAN) [56] with progressive learning have been reported to improve the boundary estimation in US imaging [57]. The critical issues resulting from the instability of the viewpoint and cross-section often become apparent when the clinical indexes are calculated using segmentation.…”

Section: Algorithms For Us Imaging Analysismentioning

confidence: 99%

Towards Clinical Application of Artificial Intelligence in Ultrasound Imaging

Komatsu

Sakai

Dozen³

et al. 2021

Biomedicines

View full text Add to dashboard Cite

Artificial intelligence (AI) is being increasingly adopted in medical research and applications. Medical AI devices have continuously been approved by the Food and Drug Administration in the United States and the responsible institutions of other countries. Ultrasound (US) imaging is commonly used in an extensive range of medical fields. However, AI-based US imaging analysis and its clinical implementation have not progressed steadily compared to other medical imaging modalities. The characteristic issues of US imaging owing to its manual operation and acoustic shadows cause difficulties in image quality control. In this review, we would like to introduce the global trends of medical AI research in US imaging from both clinical and basic perspectives. We also discuss US image preprocessing, ingenious algorithms that are suitable for US imaging analysis, AI explainability for obtaining informed consent, the approval process of medical AI devices, and future perspectives towards the clinical application of AI-based US diagnostic support technologies.

show abstract

Section: Algorithms For Us Imaging Analysismentioning

confidence: 99%

Towards Clinical Application of Artificial Intelligence in Ultrasound Imaging

Komatsu

Sakai

Dozen³

et al. 2021

Biomedicines

View full text Add to dashboard Cite

show abstract

“…Contrastive learning has recently become a prevailing SSL method because of its superior performance. In contrastive learning, a contrastive loss [7] is used to enforce representations of positive pairs to be similar and those of negative pairs to be dissimilar [8,3,14,18,11,13]. MoCo [8] and SimCLR [3] are two different con-trastive learning frameworks that yield state-of-the-art results.…”

Section: Related Workmentioning

confidence: 99%

Positional Contrastive Learning for Volumetric Medical Image Segmentation

Zeng¹,

Wu²,

Hu³

et al. 2021

Preprint

View full text Add to dashboard Cite

The success of deep learning heavily depends on the availability of large labeled training sets. However, it is hard to get large labeled datasets in medical image domain because of the strict privacy concern and costly labeling efforts. Contrastive learning, an unsupervised learning technique, has been proved powerful in learning imagelevel representations from unlabeled data. The learned encoder can then be transferred or fine-tuned to improve the performance of downstream tasks with limited labels. A critical step in contrastive learning is the generation of contrastive data pairs, which is relatively simple for natural image classification but quite challenging for medical image segmentation due to the existence of the same tissue or organ across the dataset. As a result, when applied to medical image segmentation, most stateof-the-art contrastive learning frameworks inevitably introduce a lot of false negative pairs and result in degraded segmentation quality. To address this issue, we propose a novel positional contrastive learning (PCL) framework to generate contrastive data pairs by leveraging the position information in volumetric medical images. Experimental results on CT and MRI datasets demonstrate that the proposed PCL method can substantially improve the segmentation performance compared to existing methods in both semi-supervised setting and transfer learning setting.

show abstract

“…In the last few years, contrastive learning has been widely applied in computer vision tasks [13], [14], [15], [16], [17]. Contrastive learning is an approach to formulate the task of finding similar and dissimilar things for a deep learning model.…”

Section: Introductionmentioning

confidence: 99%

“…More recently, [16] propose to first pretrain the CNN feature extractor using a label-based contrastive loss for semantic segmentation task. [17] adopt point-wise contrastive learning to improve boundary estimation for ultrasound image segmentation. Inspired by [17], we extend contrastive learning to solve hard examples in mitochondria segmentation, based on the intra-class similarity of mitochondria textures and the inter-class discrepancy of textures between mitochondria and hard examples.…”

Section: Introductionmentioning

confidence: 99%

Contrastive Learning for Mitochondria Segmentation

Li¹,

Chen

Zhao³

et al. 2021

Preprint

View full text Add to dashboard Cite

Mitochondria segmentation in electron microscopy images is essential in neuroscience. However, due to the image degradation during the imaging process, the large variety of mitochondrial structures, as well as the presence of noise, artifacts and other sub-cellular structures, mitochondria segmentation is very challenging. In this paper, we propose a novel and effective contrastive learning framework to learn a better feature representation from hard examples to improve segmentation. Specifically, we adopt a point sampling strategy to pick out representative pixels from hard examples in the training phase. Based on these sampled pixels, we introduce a pixel-wise label-based contrastive loss which consists of a similarity loss term and a consistency loss term. The similarity term can increase the similarity of pixels from the same class and the separability of pixels from different classes in feature space, while the consistency term is able to enhance the sensitivity of the 3D model to changes in image content from frame to frame. We demonstrate the effectiveness of our method on MitoEM dataset as well as FIB-SEM dataset and show better or on par with state-of-the-art results.

show abstract

Contrastive Rendering for Ultrasound Image Segmentation

Cited by 10 publications

References 11 publications

Towards Clinical Application of Artificial Intelligence in Ultrasound Imaging

Towards Clinical Application of Artificial Intelligence in Ultrasound Imaging

Positional Contrastive Learning for Volumetric Medical Image Segmentation

Contrastive Learning for Mitochondria Segmentation

Contact Info

Product

Resources

About