FRCNN-AA-CIF: An automatic detection model of colon polyps based on attention awareness and context information fusion

• Published in: Computers in biology and medicine 2023-05, Vol.158, p.106787, Article 106787
• Main Authors: Gong, Ruolin, He, SiJie, Tian, Tiantian, Chen, Jian, Hao, Yuewen, Qiao, Chen
• Format: Article
• Language: English
• Subjects: Accuracy; Air bubbles; Artificial neural networks; Attention; Attention awareness; Colon; Colon polyps; Colonic Polyps - diagnosis; Colonoscopy; Colonoscopy - methods; Computer networks; Context; Context information fusion; Data augmentation; Data integration; Deep learning; Feature extraction; Feature maps; Humans; Impurities; Information processing; Machine learning; Modules; Neural networks; Neural Networks, Computer; Object detection; Object recognition; Polyps
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2023.106787

It is noted that the foreground and background of the polyp images detected under colonoscopy are not highly differentiated, and the feature map extracted by common deep learning object detection models keep getting smaller as the number of networks increases. Therefore, these models tend to ignore the details in pictures, resulting in a high polyp missed detection rate. To reduce the missed detection rate, this paper proposes an automatic detection model of colon polyps based on attention awareness and context information fusion (FRCNN-AA-CIF) based on a two-stage object detection model Faster Region-Convolutional Neural Network (FR-CNN). First, since the addition of attention awareness can make the feature extraction network pay more attention to polyp features, we propose an attention awareness module based on Squeeze-and-Excitation Network (SENet) and Efficient Channel Attention Module (ECA-Net) and add it after each block of the backbone network. Specifically, we first use the 1*1 convolution of ECA-Net to extract local cross-channel information and then use the two fully connected layers of SENet to reduce and increase the dimension, to filter out the channels that are more useful for feature learning. Further, because of the presence of air bubbles, impurities, inflammation, and accumulation of digestive matter around polyps, we used context information around polyps to enhance the focus on polyp features. In particular, after the network extracts the region of interest, we fuse the region of interest with its context information to improve the detection rate of polyps. The proposed model was tested on the colonoscopy dataset provided by Huashan Hospital. Numerical experiments show that FRCNN-AA-CIF has the highest detection accuracy (mAP of 0.817), the lowest missed detection rate of 4.22%, and the best classification effect (AUC of 95.98%). Its mAP increased by 3.3%, MDR decreased by 1.97%, and AUC increased by 1.8%. Compared with other object detection models, FRCNN-AA-CIF has significantly improved recognition accuracy and reduced missed detection rate.