Boundary Constraint Network With Cross Layer Feature Integration for Polyp Segmentation

Yue, Guanghui; Jiang, Bin; Zhou, Tianwei; Cong, Runmin; Wang, Tianfu

doi:10.1109/jbhi.2022.3173948

Cited by 59 publications

(11 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, Psi-Net 14 was designed to learn three tasks simultaneously by generating contour and distance maps and predicting a mask. In addition to methods [14][15][16] for adding branches to extract information about boundaries, models using practical attention modules 7,[17][18][19] have been developed for natural images. Attention modules improve the performance of polyp detection methods by enabling a model to focus on the visual features of polyps.…”

Section: Introductionmentioning

confidence: 99%

SRaNet: Shallow and Reverse Attention Network for Colon Polyp Segmentation

Lee

Cho

Choi

2023

Preprint

View full text Add to dashboard Cite

Polyp segmentation is challenging because the boundary between polyps and mucosa is ambiguous. Several models have considered the use of attention mechanisms to solve this problem. However, these models use only finite information obtained from a single type of attention. We propose a new dual-attention network based on shallow and reverse attention modules for colon polys segmentation called SRaNet. The shallow attention mechanism removes background noise while emphasizing the locality by focusing on the foreground. In contrast, reverse attention helps distinguish the boundary between polyps and mucous membranes more clearly by focusing on the background. The two attention mechanisms are adaptively fused using a “Softmax Gate”. Combining the two types of attention enables the model to capture complementary foreground and boundary features. Therefore, the proposed model predicts the boundaries of polyps more accurately than other models. We present the results of extensive experiments on polyp benchmarks to show that the proposed method outperforms existing models on both seen and unseen data. Furthermore, the results show that the proposed dual attention module increases the explainability of the model.

show abstract

Section: Introductionmentioning

confidence: 99%

SRaNet: Shallow and Reverse Attention Network for Colon Polyp Segmentation

Lee

Cho

Choi

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Thanks to the powerful feature representation capabilities of deep learning, it has been widely used to address the computer vision task, such as enhancement [1]- [4], detection [5]- [14], super-resolution [15]- [20], and medical image processing including lung nodules segmentation [21], brain and braintumor segmentation [22], polyp segmentation [23], brain image synthesis [24], retinal image non-uniform illumination removal [25] etc. For each different task, due to the differences in imaging equipment and disease characteristics, different segmentation models need to be designed separately.…”

Section: Introductionmentioning

confidence: 99%

Boundary Guided Semantic Learning for Real-Time COVID-19 Lung Infection Segmentation System

Cong

Zhang

Yang

et al. 2022

IEEE Trans. Consumer Electron.

Self Cite

View full text Add to dashboard Cite

The coronavirus disease 2019 (COVID-19) continues to have a negative impact on healthcare systems around the world, though the vaccines have been developed and national vaccination coverage rate is steadily increasing. At the current stage, automatically segmenting the lung infection area from CT images is essential for the diagnosis and treatment of COVID-19. Thanks to the development of deep learning technology, some deep learning solutions for lung infection segmentation have been proposed. However, due to the scattered distribution, complex background interference and blurred boundaries, the accuracy and completeness of the existing models are still unsatisfactory. To this end, we propose a boundary guided semantic learning network (BSNet) in this paper. On the one hand, the dualbranch semantic enhancement module that combines the toplevel semantic preservation and progressive semantic integration is designed to model the complementary relationship between different high-level features, thereby promoting the generation of more complete segmentation results. On the other hand, the mirror-symmetric boundary guidance module is proposed to accurately detect the boundaries of the lesion regions in a mirrorsymmetric way. Experiments on the publicly available dataset demonstrate that our BSNet outperforms the existing state-ofthe-art competitors and achieves a real-time inference speed of 44 FPS. The code and results of our BSNet can be found from the link of https://github.com/rmcong/BSNet.

show abstract

“…Machine learning can transform measurement results into relevant predictive models, especially cancer models, based on the rapid development of large datasets and deep learning [ 12 ]. Previous studies have proposed a novel boundary-constrained network (BCNet) for accurate polyp segmentation [ 13 ]. However, most models are based on traditional ML algorithms created in the last century, including backpropagation neural networks (BPNN), multilayer perceptrons (MLP), decision trees, support vector machines (SVM), and Bayesian networks [ 14 ].…”

Section: Introductionmentioning

confidence: 99%

A Machine Learning Approach Using XGBoost Predicts Lung Metastasis in Patients with Ovarian Cancer

Yuan

Wang

Luo

et al. 2022

BioMed Research International

View full text Add to dashboard Cite

Background. Liver metastasis (LM) is an independent risk factor that affects the prognosis of patients with ovarian cancer; however, there is still a lack of prediction. This study developed a limit gradient enhancement (XGBoost) to predict the risk of lung metastasis in newly diagnosed patients with ovarian cancer, thereby improving prediction efficiency. Patients and Methods. Data of patients diagnosed with ovarian cancer in the Surveillance, Epidemiology, and Final Results (SEER) database from 2010 to 2015 were retrospectively collected. The XGBoost algorithm was used to establish a lung metastasis model for patients with ovarian cancer. The performance of the predictive model was tested by the area under the curve (AUC) of the receiver operating characteristic curve (ROC). Results. The results of the XGBoost algorithm showed that the top five important factors were age, laterality, histological type, grade, and marital status. XGBoost showed good discriminative ability, with an AUC of 0.843. Accuracy, sensitivity, and specificity were 0.982, 1.000, and 0.686, respectively. Conclusion. This study is the first to develop a machine-learning-based prediction model for lung metastasis in patients with ovarian cancer. The prediction model based on the XGBoost algorithm has a higher accuracy rate than traditional logistic regression and can be used to predict the risk of lung metastasis in newly diagnosed patients with ovarian cancer.

show abstract

Boundary Constraint Network With Cross Layer Feature Integration for Polyp Segmentation

Cited by 59 publications

References 53 publications

SRaNet: Shallow and Reverse Attention Network for Colon Polyp Segmentation

SRaNet: Shallow and Reverse Attention Network for Colon Polyp Segmentation

Boundary Guided Semantic Learning for Real-Time COVID-19 Lung Infection Segmentation System

A Machine Learning Approach Using XGBoost Predicts Lung Metastasis in Patients with Ovarian Cancer

Contact Info

Product

Resources

About