Chest X-ray Foreign Objects Detection Using Artificial Intelligence

Abstract

Diagnostic imaging has become an integral part of the healthcare system. In recent years, scientists around the world have been working on artificial intelligence-based tools that help in achieving better and faster diagnoses. Their accuracy is crucial for successful treatment, especially for imaging diagnostics. This study used a deep convolutional neural network to detect four categories of objects on digital chest X-ray images. The data were obtained from the publicly available National Institutes of Health (NIH) Chest X-ray (CXR) Dataset. In total, 112,120 CXRs from 30,805 patients were manually checked for foreign objects: vascular port, shoulder endoprosthesis, necklace, and implantable cardioverter-defibrillator (ICD). Then, they were annotated with the use of a computer program, and the necessary image preprocessing was performed, such as resizing, normalization, and cropping. The object detection model was trained using the You Only Look Once v8 architecture and the Ultralytics framework. The results showed not only that the obtained average precision of foreign object detection on the CXR was 0.815 but also that the model can be useful in detecting foreign objects on the CXR images. Models of this type may be used as a tool for specialists, in particular, with the growing popularity of radiology comes an increasing workload. We are optimistic that it could accelerate and facilitate the work to provide a faster diagnosis.

Keywords: artifacts; artificial intelligence; chest X-ray; convolutional neural network; foreign body.

Figure 1

Presentation of the labeling process in the LabelImg program. The image shows a selected necklace (structure in the blue area) with the appropriate color of the label.

Figure 2

The graph shows the Precision–Recall Curve for each of the foreign objects classes (endo, ICD, necklace, and port) as well as for all the classes. The mean average precision at intersection over union threshold equal to 0.5 was calculated.

Figure 3

Sample-labeled images used to test the model. Rectangle-shaped and square-shaped areas in yellow, orange, and pink colors are areas with marked foreign objects (bounding boxes).

Figure 4

The image shows a comparison of the placement of bounding boxes (rectangular-shaped and square-shaped areas in pink, yellow, and orange colours) labeled by the model and the annotator evaluating the X-ray images. Rows A and C represent images evaluated by the annotator, whereas rows B and D were labeled by the AI.