Anomaly Detection in Chest X-rays Based on Dual-Attention Mechanism and Multi-Scale Feature Fusion

Abstract

The efficient and automatic detection of chest abnormalities is vital for the auxiliary diagnosis of medical images. Many studies utilize computer vision and deep learning approaches involving symmetry and asymmetry concepts to detect chest abnormalities, and achieve promising findings. However, an accurate instance-level and multi-label detection of abnormalities in chest X-rays remains a significant challenge. Here, a novel anomaly detection method for symmetric chest X-rays using dual-attention and multi-scale feature fusion is proposed. Three aspects of our method should be noted in comparison with the previous approaches. We improved the deep neural network with channel-dimensional and spatial-dimensional attention to capture the abundant contextual features. We then used an optimized multi-scale learning framework for feature fusion to adapt to the scale variation in the abnormalities. Considering the influence of the data imbalance and other factors, we introduced a seesaw loss function to flexibly adjust the sample weights and enhance the model learning efficiency. The rigorous experimental evaluation of a public chest X-ray dataset with fourteen different types of abnormalities demonstrates that our model has a mean average precision of 0.362 and outperforms existing methods.

Multimodality Risk Assessment of Patients with Ischemic Heart Disease Using Deep Learning Models Applied to Electrocardiograms and Chest X-rays

“…To assess the usefulness of risk assessment using deep learning models with multimodality data in patients with IHD, we referred to previous models for detecting LVSD from ECGs and for identifying cardiomegaly findings from CXRs. 6,[15][16][17][18] We trained a 12-lead ECG analysis model to detect LVSD from 12-lead ECG-echocardiography pairs from The University of Tokyo Hospital, and a CXR analysis model to detect cardiomegaly using the large open-access VinDr-CXR dataset. 19) This training was accomplished using 4 sets of Nvidia Tesla A100 80 GB graphics processing units (Nvidia Corporation, Santa Clara, CA, USA).…”