LFANet: Lightweight feature attention network for abnormal cell segmentation in cervical cytology images

• Published in: Computers in biology and medicine 2022-06, Vol.145, p.105500-105500, Article 105500
• Main Authors: Zhao, Yanli, Fu, Chong, Xu, Sen, Cao, Lin, Ma, Hong-feng
• Format: Article
• Language: English
• Subjects: Accuracy; Artificial intelligence; Cancer; Cancer screening; Cellular biology; Cervical cancer; Cervical cytology; Cervix; Coders; Complexity; Computer applications; Computer-aided diagnosis; Cytology; Cytoplasm; Deep learning; Diagnosis; Feature extraction; Image processing; Image segmentation; Lightweight; Lightweight network; Machine learning; Medical diagnosis; Medical imaging; Methods; Modules; Neural networks; Object recognition; Segmentation; Semantics
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2022.105500

With the widely applied computer-aided diagnosis techniques in cervical cancer screening, cell segmentation has become a necessary step to determine the progression of cervical cancer. Traditional manual methods alleviate the dilemma caused by the shortage of medical resources to a certain extent. Unfortunately, with their low segmentation accuracy for abnormal cells, the complex process cannot realize an automatic diagnosis. In addition, various methods on deep learning can automatically extract image features with high accuracy and small error, making artificial intelligence increasingly popular in computer-aided diagnosis. However, they are not suitable for clinical practice because those complicated models would result in more redundant parameters from networks. To address the above problems, a lightweight feature attention network (LFANet), extracting differentially abundant feature information of objects with various resolutions, is proposed in this study. The model can accurately segment both the nucleus and cytoplasm regions in cervical images. Specifically, a lightweight feature extraction module is designed as an encoder to extract abundant features of input images, combining with depth-wise separable convolution, residual connection and attention mechanism. Besides, the feature layer attention module is added to precisely recover pixel location, which employs the global high-level information as a guide for the low-level features, capturing dependencies of channel features. Finally, our LFANet model is evaluated on all four independent datasets. The experimental results demonstrate that compared with other advanced methods, our proposed network achieves state-of-the-art performance with a low computational complexity. •We exposed the flaws of the segmentation method for abnormal cervical cells.•A novel end-to-end semantic segmentation paradigm is presented.•An ablation study illustrates the effect of different elements of the framework.•State-of-the-art methods are outperformed in both parameters and FLOPs.