TY - JOUR
T1 - Sample-based relationship for assisting diagnosis of pneumonia in medical care
AU - Chen, Hongkang
AU - Lu, Huijuan
AU - Zhu, Wenjie
AU - Zhou, Ye
AU - Yao, Yudong
AU - Wang, Renfeng
N1 - Publisher Copyright:
© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.
PY - 2024
Y1 - 2024
N2 - Deep neural networks have succeeded in learning balanced and imbalanced data in the field of pneumonia diagnosis. However, both require separate model designs in their respective domains. The pneumonia recognition methods have poor transfer performance between the two types of image distribution data. This paper proposes BeFormer, which focuses on sample relationships. BeFormer introduces two stages, feature extraction and establishing sample relationships, to solve the problem. Specifically, in the feature extraction stage, a new backbone network called PANet based on Multi-Scale Frequency Domain Attention (FPSA) is proposed. In establishing sample relationships, Deformable Transformer is used in parallel to model the relationships between partial regions of interest among the same and different samples in the pneumonia dataset. These two modules are connected in series to form BeFormer. Without making any changes to the model, this paper conducted experiments using BeFormer on both balanced and imbalanced pneumonia datasets. As compared to traditional pneumonia recognition models, the proposed method achieved significant improvements in the two different data distributions, demonstrating outstanding transfer performance.
AB - Deep neural networks have succeeded in learning balanced and imbalanced data in the field of pneumonia diagnosis. However, both require separate model designs in their respective domains. The pneumonia recognition methods have poor transfer performance between the two types of image distribution data. This paper proposes BeFormer, which focuses on sample relationships. BeFormer introduces two stages, feature extraction and establishing sample relationships, to solve the problem. Specifically, in the feature extraction stage, a new backbone network called PANet based on Multi-Scale Frequency Domain Attention (FPSA) is proposed. In establishing sample relationships, Deformable Transformer is used in parallel to model the relationships between partial regions of interest among the same and different samples in the pneumonia dataset. These two modules are connected in series to form BeFormer. Without making any changes to the model, this paper conducted experiments using BeFormer on both balanced and imbalanced pneumonia datasets. As compared to traditional pneumonia recognition models, the proposed method achieved significant improvements in the two different data distributions, demonstrating outstanding transfer performance.
KW - Balanced and imbalanced data learning
KW - Batch domain learning
KW - Pneumonia X-ray
KW - Sample relationship
KW - Transformer
UR - http://www.scopus.com/inward/record.url?scp=85188047046&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85188047046&partnerID=8YFLogxK
U2 - 10.1007/s11042-024-18848-y
DO - 10.1007/s11042-024-18848-y
M3 - Article
AN - SCOPUS:85188047046
SN - 1380-7501
JO - Multimedia Tools and Applications
JF - Multimedia Tools and Applications
ER -