Semantic decomposition Network with Contrastive and Structural Constraints for Dental Plaque Segmentation

  title={Semantic decomposition Network with Contrastive and Structural Constraints for Dental Plaque Segmentation},
  author={Jian Shi and Baoli Sun and Xinchen Ye and Zhihui Wang and Xiaolong Luo and Jin Liu and Heli Gao and Haojie Li},
  journal={IEEE transactions on medical imaging},
Segmenting dental plaque from images of medical reagent staining provides valuable information for diagnosis and the determination of follow-up treatment plan. However, accurate dental plaque segmentation is a challenging task that requires identifying teeth and dental plaque subjected to semantic-blur regions (i.e., confused boundaries in border regions between teeth and dental plaque) and complex variations of instance shapes, which are not fully addressed by existing methods. Therefore, we… 



CIA-Net: Robust Nuclei Instance Segmentation with Contour-aware Information Aggregation

A novel deep neural network, namely Contour-aware Informative Aggregation Network (CIA-Net) with multi-level information aggregation module between two task-specific decoders that leverages the merit of spatial and texture dependencies between nuclei and contour by bi-directionally aggregating task- specific features.

Deep Learning for Classification of Dental Plaque Images

An automated dental red autofluorescence plaque image classification model based on application of Convolutional Neural Networks (CNN) on Quantitative Light-induced Fluorescence (QLF) images outperforms other state of the art classification models.

Contrastive learning of global and local features for medical image segmentation with limited annotations

This work proposes novel contrasting strategies that leverage structural similarity across volumetric medical images and a local version of the contrastive loss to learn distinctive representations of local regions that are useful for per-pixel segmentation in the semi-supervised setting with limited annotations.

Boundary Coding Representation for Organ Segmentation in Prostate Cancer Radiotherapy

A novel boundary coding network is proposed to learn a discriminative representation for organ boundary and use it as the context information to guide the segmentation of prostate cancer radiotherapy images.

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

It is established that by including the limited label information in the pre-training phase, it is possible to boost the performance of contrastive learning and proposes a supervised local contrastive loss that leverages limited pixel-wise annotation to force pixels with the same label to gather around in the embedding space.

Semantic Correlation Promoted Shape-Variant Context for Segmentation

This work proposes a novel paired convolution to infer the semantic correlation of the pair and based on that to generate a shape mask, of which the receptive field is controlled by the shape mask that varies with the appearance of input.

Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs

This work brings together methods from DCNNs and probabilistic graphical models for addressing the task of pixel-level classification by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF).

TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation

It is argued that Transformers can serve as strong encoders for medical image segmentation tasks, with the combination of U-Net to enhance finer details by recovering localized spatial information, and empirical results suggest that the Transformer-based architecture presents a better way to leverage self-attention compared with previous CNN-based self-Attention methods.

Towards Efficient Medical Image Segmentation Via Boundary-Guided Knowledge Distillation

Two knowledge distillation modules are proposed, namely boundary-guided deep supervision and output space boundary embeddng alignment, to explicitly transfer boundary information.

Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank

The key element of this approach is the contrastive learning module that enforces the segmentation network to yield similar pixel-level feature representations for same-class samples across the whole dataset, maintaining a memory bank which is continuously updated with relevant and high-quality feature vectors from labeled data.