DB-DCAFN: dual-branch deformable cross-attention fusion network for bacterial segmentation
Open Access
- 4 July 2023
- journal article
- research article
- Published by Springer Nature in Visual Computing for Industry, Biomedicine, and Art
- Vol. 6 (1) , 1-16
Abstract
Sputum smear tests are critical for the diagnosis of respiratory diseases. Automatic segmentation of bacteria from sputum smear images is important for improving diagnostic efficiency. However, this remains a challenging task owing to the high interclass similarity among different categories of bacteria and the low contrast of the bacterial edges. To explore more levels of global pattern features to promote the distinguishing ability of bacterial categories and maintain sufficient local fine-grained features to ensure accurate localization of ambiguous bacteria simultaneously, we propose a novel dual-branch deformable cross-attention fusion network (DB-DCAFN) for accurate bacterial segmentation. Specifically, we first designed a dual-branch encoder consisting of multiple convolution and transformer blocks in parallel to simultaneously extract multilevel local and global features. We then designed a sparse and deformable cross-attention module to capture the semantic dependencies between local and global features, which can bridge the semantic gap and fuse features effectively. Furthermore, we designed a feature assignment fusion module to enhance meaningful features using an adaptive feature weighting strategy to obtain more accurate segmentation. We conducted extensive experiments to evaluate the effectiveness of DB-DCAFN on a clinical dataset comprising three bacterial categories: Acinetobacter baumannii, Klebsiella pneumoniae, and Pseudomonas aeruginosa. The experimental results demonstrate that the proposed DB-DCAFN outperforms other state-of-the-art methods and is effective at segmenting bacteria from sputum smear images.Keywords
Funding Information
- Natural Science Foundation of Shandong Province (ZR2021MH213)
- Suzhou Municipal Science and Technology Bureau (SJC2021023)
This publication has 35 references indexed in Scilit:
- Fully Convolutional Networks for Semantic SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Fully convolutional networks for semantic segmentation2015
- Classification of Mycobacterium tuberculosis in Images of ZN-Stained Sputum SmearsIEEE Transactions on Information Technology in Biomedicine, 2009
- Acinetobacter baumannii : Emergence of a Successful PathogenClinical Microbiology Reviews, 2008
- Image processing techniques for identifying Mycobacterium tuberculosis in Ziehl-Neelsen stains.2008
- Acute Lower Respiratory Tract InfectionNew England Journal of Medicine, 2008
- Preparation of mycobacteria-containing artificial sputum for TB panel testing and microscopy of sputum smears.2006
- Lung Infection—A Public Health PriorityPLOS Medicine, 2006
- Rapid, efficient detection and drug susceptibility testing of Mycobacterium tuberculosis in sputum by microscopic observation of broth cultures. The Tuberculosis Working Group in Peru.2000