CDT-CAD: Context-Aware Deformable Transformers for End-to-End Chest Abnormality Detection on X-Ray Images

Wu, Yirui; Kong, Qiran; Zhang, Lilai; Castiglione, Aniello; Nappi, Michele; Wan, Shaohua

doi:10.1109/tcbb.2023.3258455

Cited by 21 publications

(1 citation statement)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various methods and techniques have already been proposed where multiple architectures are exploited to perform detection in histopathological images effectively 21 , 22 . Deep CNNs are hierarchical models that learn domain-specific image representations dynamically 10 , 23 – 25 . Therefore, these days, automated detection systems are majorly based on CNNs 26 , 27 .…”

Section: Related Workmentioning

confidence: 99%

Lymphocyte detection for cancer analysis using a novel fusion block based channel boosted CNN

Rauf,

Khan,

Sohail

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Tumor-infiltrating lymphocytes, specialized immune cells, are considered an important biomarker in cancer analysis. Automated lymphocyte detection is challenging due to its heterogeneous morphology, variable distribution, and presence of artifacts. In this work, we propose a novel Boosted Channels Fusion-based CNN “BCF-Lym-Detector” for lymphocyte detection in multiple cancer histology images. The proposed network initially selects candidate lymphocytic regions at the tissue level and then detects lymphocytes at the cellular level. The proposed “BCF-Lym-Detector” generates diverse boosted channels by utilizing the feature learning capability of different CNN architectures. In this connection, a new adaptive fusion block is developed to combine and select the most relevant lymphocyte-specific features from the generated enriched feature space. Multi-level feature learning is used to retain lymphocytic spatial information and detect lymphocytes with variable appearances. The assessment of the proposed “BCF-Lym-Detector” show substantial improvement in terms of F-score (0.93 and 0.84 on LYSTO and NuClick, respectively), which suggests that the diverse feature extraction and dynamic feature selection enhanced the feature learning capacity of the proposed network. Moreover, the proposed technique’s generalization on unseen test sets with a good recall (0.75) and F-score (0.73) shows its potential use for pathologists’ assistance.

show abstract