Class attention to regions of lesion for imbalanced medical image recognition

Zhuang，Jia Xin1,4; Cai，Jiabin1; Zhang，Jianguo2,3; Zheng，Wei shi1; Wang，Ruixuan1,3

2023-10-28

10.1016/j.neucom.2023.126577

Neurocomputing   Impact Factor & Quartile

0925-2312

1872-8286

Automated medical image classification is the key component in intelligent diagnosis systems. However, most medical image datasets contain plenty of samples of common diseases and just a handful of rare ones, leading to major class imbalances. Currently, it is an open problem in intelligent diagnosis to effectively learn from imbalanced training data. In this paper, we propose a simple yet effective framework, named Class Attention to REgions of the lesion (CARE), to handle data imbalance issues by embedding attention into the training process of Convolutional Neural Networks (CNNs). The proposed attention module helps CNNs attend to lesion regions of rare diseases, therefore helping CNNs to learn their characteristics more effectively. In addition, this attention module works only during the training phase and does not change the architecture of the original network, so it can be directly combined with any existing CNN architecture. The CARE framework needs bounding boxes to represent the lesion regions of rare diseases. To alleviate the need for manual annotation, we further developed variants of CARE by leveraging the traditional saliency methods or a pretrained segmentation model for bounding box generation. Results show that the CARE variants with automated bounding box generation are comparable to the original CARE framework with manual bounding box annotations. A series of experiments on an imbalanced skin image dataset and a pneumonia dataset indicates that our method can effectively help the network focus on the lesion regions of rare diseases and remarkably improves the classification performance of rare diseases.

Attention for diagnosis Imbalanced data Pneumonia chest X-ray Skin diseases Small samples

English

Others

National Natural Science Foundation of China[62071502];National Natural Science Foundation of China[62276121];

COMPUTER SCIENCE

2-s2.0-85167998048

Scopus

1.Department of Computer Science and Engineering,Sun Yat-sen University,China
2.Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering,Southern University of Science and Technology,China
3.Peng Cheng Laboratory,China
4.Department of Computer Science and Engineering,Hong Kong University of Science and Technology,Hong Kong,China

Zhuang，Jia Xin,Cai，Jiabin,Zhang，Jianguo,et al. Class attention to regions of lesion for imbalanced medical image recognition[J]. Neurocomputing,2023,555.

Zhuang，Jia Xin,Cai，Jiabin,Zhang，Jianguo,Zheng，Wei shi,&Wang，Ruixuan.(2023).Class attention to regions of lesion for imbalanced medical image recognition.Neurocomputing,555.

Zhuang，Jia Xin,et al."Class attention to regions of lesion for imbalanced medical image recognition".Neurocomputing 555(2023).