Pneumonia detection based on RSNA dataset and anchor-free deep learning detector

Abstract

Pneumonia is a highly lethal disease, and research on its treatment and early screening tools has received extensive attention from researchers. Due to the maturity and cost reduction of chest X-ray technology, and with the development of artificial intelligence technology, pneumonia identification based on deep learning and chest X-ray has attracted attention from all over the world. Although the feature extraction capability of deep learning is strong, existing deep learning object detection frameworks are based on pre-defined anchors, which require a lot of tuning and experience to guarantee their excellent results in the face of new applications or data. To avoid the influence of anchor settings in pneumonia detection, this paper proposes an anchor-free object detection framework and RSNA dataset based on pneumonia detection. First, a data enhancement scheme is used to preprocess the chest X-ray images; second, an anchor-free object detection framework is used for pneumonia detection, which contains a feature pyramid, two-branch detection head, and focal loss. The average precision of 51.5 obtained by Intersection over Union (IoU) calculation shows that the pneumonia detection results obtained in this paper can surpass the existing classical object detection framework, providing an idea for future research and exploration.

An Efficient Hypertuned DNN Based Approach for Pneumonia Detection

“…Farukh H. M. employed a weighted classifier to identify pneumonia (11) . Studies (11,(16)(17)(18) highlighted the limitations imposed by the scarcity of datasets. A weakly supervised method was used in (19) to identify pneumonia cases, and lightweight DenseNet-121 was utilized in (20) to extract features.…”