Pneumothorax detection in chest radiographs: optimizing artificial intelligence system for accuracy and confounding bias reduction using in-image annotations in algorithm training

Rückel, Johannes; Huemmer, Christian; Fieselmann, Andreas; Ghesu, Florin-Cristian; Mansoor, Awais; Schachtner, Balthasar; Wesp, Philipp; Trappmann, Lena; Munawwar, Basel; Ricke, Jens; Ingrisch, Michael und Sabel, Bastian O. (2021): Pneumothorax detection in chest radiographs: optimizing artificial intelligence system for accuracy and confounding bias reduction using in-image annotations in algorithm training. In: European Radiology, Bd. 31, Nr. 10: S. 7888-7900

Abstract

Objectives Diagnostic accuracy of artificial intelligence (AI) pneumothorax (PTX) detection in chest radiographs (CXR) is limited by the noisy annotation quality of public training data and confounding thoracic tubes (TT). We hypothesize that in-image annotations of the dehiscent visceral pleura for algorithm training boosts algorithm's performance and suppresses confounders. Methods Our single-center evaluation cohort of 3062 supine CXRs includes 760 PTX-positive cases with radiological annotations of PTX size and inserted TTs. Three step-by-step improved algorithms (differing in algorithm architecture, training data from public datasets/clinical sites, and in-image annotations included in algorithm training) were characterized by area under the receiver operating characteristics (AUROC) in detailed subgroup analyses and referenced to the well-established CheXNet algorithm. Results Performances of established algorithms exclusively trained on publicly available data without in-image annotations are limited to AUROCs of 0.778 and strongly biased towards TTs that can completely eliminate algorithm's discriminative power in individual subgroups. Contrarily, our final algorithm 2 which was trained on a lower number of images but additionally with in-image annotations of the dehiscent pleura achieved an overall AUROC of 0.877 for unilateral PTX detection with a significantly reduced TT-related confounding bias. Conclusions We demonstrated strong limitations of an established PTX-detecting AI algorithm that can be significantly reduced by designing an AI system capable of learning to both classify and localize PTX. Our results are aimed at drawing attention to the necessity of high-quality in-image localization in training data to reduce the risks of unintentionally biasing the training process of pathology-detecting AI algorithms.

• Dokumententyp: Zeitschriftenartikel
• Fakultät: Medizin
• Themengebiete: 600 Technik, Medizin, angewandte Wissenschaften > 610 Medizin und Gesundheit
• ISSN: 0938-7994
• Sprache: Englisch