x-ray, chest, foreign objects, abnormalities
AI-guided tools can help add healthcare quality. In an automated Chest X-Ray (CXR) screening process, foreign objects, such as coins/buttons, medical tubes and devices, and jewelry can adversely impact the performance [1,2,3,4]. In an automated process, conventional machine learning algorithms did not separately consider them into account, and as a consequence, they result in false-positive cases . In our work, we employed the You Only Look Once (YOLO) algorithm – a Deep Neural Network – to detect foreign objects in CXR images. On a set of 400 publicly available CXR images hosted by LHNCBC, U.S National Library of Medicine (NLM), National Institutes of Health (NIH), our results are encouraging as compared to previous work .
Roy, Shotabdi and Allu, Siva Sai Venkata, "Separating foreign objects from abnormalities in Chest X-rays" (2021). IdeaFest. 337.