A fully automated CT-based airway segmentation and branch labeling algorithm using deep learning and conventional image processing

Nadeem, Syed Ahmed

doi:10.17077/etd.005427

Cited by 2 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The misclassified bronchus is bounded by a red box. In the above cases, TS-NN [8] could suffer from errors related to branching variability. LP [21] fails to distinguish the segments with similar angles.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…The qualitative analysis is shown in Fig. 3, the TS-NN [8] under-performance as it only focuses on local features but neglects the global topology of the airway. The hard-crafted feature-based LP [21] fails with segments that have similar angles.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…For deep learning based methods, Zhao et al [21] applied linear programming to post-process the airway structure predicted by neural models. Nadeem [8] proposed a neural network of two stages that label the lobar-level and segment-level bronchus respectively. Recently, graph-based methods [4,15,20,17] have been studied for the task.…”

Section: Related Workmentioning

confidence: 99%

“…Juarez et al [4] replaced the deepest convolutional layer in a U-Net with graph convolutions to improve the airway binary segmentation. However, the previous approaches either require hand-crafted feature [18,21,8] or need additional annotation [17,4], while they are not able to effectively handle the individual variance. Thus, there is a need to develop an efficient and effective framework that can embed both voxel-wise features and point-cloud topology into learnable representations for bronchus classification.…”

Section: Related Workmentioning

confidence: 99%

“…The second step is to label major anatomical branches based on bronchus classification. The automatic bronchial tree reconstruction can further assist more clinical processes, such as individual airway tree phenotype matching and lung lobe or lung segment classification [8,18]. There still exist two main obstacles: (1) the extreme unbalanced foreground and background in bronchus segmentation; (2) the ignorance of inherent topology or prior knowledge for bronchus segment classification.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

BronchusNet: Region and Structure Prior Embedded Representation Learning for Bronchus Segmentation and Classification

Huang¹,

Gong²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

CT-based bronchial tree analysis plays an important role in the computer-aided diagnosis for respiratory diseases, as it could provide structured information for clinicians. The basis of airway analysis is bronchial tree reconstruction, which consists of bronchus segmentation and classification. However, there remains a challenge for accurate bronchial analysis due to the individual variations and the severe class imbalance. In this paper, we propose a region and structure prior embedded framework named BronchusNet to achieve accurate segmentation and classification of bronchial regions in CT images. For bronchus segmentation, we propose an adaptive hard region-aware UNet that incorporates multi-level prior guidance of hard pixel-wise samples in the general Unet segmentation network to achieve better hierarchical feature learning. For the classification of bronchial branches, we propose a hybrid point-voxel graph learning module to fully exploit bronchial structure priors and to support simultaneous feature interactions across different branches. To facilitate the study of bronchial analysis, we contribute BRSC: an open-access benchmark of BRonchus imaging analysis with high-quality pixel-wise Segmentation masks and the Class of bronchial segments. Experimental results on BRSC show that our proposed method not only achieves the state-of-the-art performance for binary segmentation of bronchial region but also exceeds the best existing method on bronchial branches classification by 6.9%.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Section: Experiments and Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

BronchusNet: Region and Structure Prior Embedded Representation Learning for Bronchus Segmentation and Classification

Huang¹,

Gong²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

Comorbidity of Anxiety and Depression with Hypertension, Diabetes, and Cardiovascular Disease: A Selective Systematic Review from India

et al. 2022

View full text Add to dashboard Cite

Context: Non-communicable diseases (cardiovascular diseases, hypertension, and diabetes) and comorbid common mental disorders are of public health concern because of their high morbidity and mortality rates. The authors undertook a systematic review of studies that reported the prevalence of common mental disorders among non-communicable diseases, specifically in India. Evidence acquisition: Relevant databases (Medline, Google Scholar, EBSCO, and ProQuest) were searched until May 2021. Descriptive and observation studies from the mentioned databases were included. Evidence synthesis: Of the total 6,515 studies, the electronic literature search identified 4,307 studies. Manual cross-referencing identified an additional 2,208 studies. Only 17 studies met the criteria and were included for the review. Findings: Twelves studies focused on the prevalence of anxiety and depression in patients with diabetes, three studies focused on cardiovascular disease, two on non-communicable diseases, and one on the prevalence of depression in hypertension. The range of the prevalence of anxiety disorder and depression was 3.9–44% and 8–44%, respectively. Conclusion: High prevalence of anxiety and depression is seen in people with diabetes, indicating these are of serious public health concerns in India.

show abstract

A fully automated CT-based airway segmentation and branch labeling algorithm using deep learning and conventional image processing

Cited by 2 publications

References 0 publications

BronchusNet: Region and Structure Prior Embedded Representation Learning for Bronchus Segmentation and Classification

BronchusNet: Region and Structure Prior Embedded Representation Learning for Bronchus Segmentation and Classification

Comorbidity of Anxiety and Depression with Hypertension, Diabetes, and Cardiovascular Disease: A Selective Systematic Review from India

Contact Info

Product

Resources

About