Deep learning models for radiography body-part classification and chest radiograph projection/orientation classification: a multi-institutional study.

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: AUC 1.00 for most classifications, 0.99 for Incomplete Chest category

• Primary Outcome: AUC for radiograph classification accuracy

• Nnt Or Sensitivity: Sensitivity and specificity not reported, only AUC values provided

• Confidence Interval: 99% CI: 0.98-1.00 for Incomplete Chest, 1.00-1.00 for others

Clinical Application

Requires computational infrastructure and integration with existing PACS systems Relevant for Australian hospitals and imaging centres using digital radiography systems, could support TGA medical device software requirements and improve data quality for research collaborations Healthcare institutions using large radiographic databases for clinical care or research

Abstract

OBJECTIVES: Large-scale radiographic datasets often include errors in labels such as body parts or projection, which can undermine automated image analysis. Therefore, we aimed to develop and externally validate two deep-learning models-one for categorising radiographs by body part, and another for identifying projection and rotation of chest radiographs-using large, diverse datasets. MATERIALS AND METHODS: We retrospectively collected radiographs from multiple institutions and public repositories. For the first model (Xp-Bodypart-Checker), we included seven categories (Head, Neck, Chest, Incomplete Chest, Abdomen, Pelvis, Extremities). For the second model (CXp-Projection-Rotation-Checker), we classified chest radiographs by projection (anterior-posterior, posterior-anterior, lateral) and rotation (upright, inverted, left rotation, right rotation). Both models were trained, tuned, and internally tested on separate data, then externally tested on radiographs from different institutions. Model performance was assessed using overall accuracy (micro, macro, and weighted) as well as one-vs.-all area under the receiver operating characteristic curve (AUC). RESULTS: In the Xp-Bodypart-Checker development phase, we included 429,341 radiographs obtained from Institutions A, B, and MURA. In the CXp-Projection-Rotation-Checker development phase, we included 463,728 chest radiographs from CheXpert, PadChest, and Institution A. The Xp-Bodypart-Checker achieved AUC values of 1.00 (99% CI: 1.00-1.00) for all classes other than Incomplete Chest, which had an AUC value of 0.99 (99% CI: 0.98-1.00). The CXp-Projection-Rotation-Checker demonstrated AUC values of 1.00 (99% CI: 1.00-1.00) across all projection and rotation classifications. CONCLUSION: These models help automatically verify image labels in large radiographic databases, improving quality control across multiple institutions. KEY POINTS: Question This study examines how deep learning can accurately classify radiograph body parts and detect chest projection/orientation in large, multi-institutional datasets, enhancing metadata consistency for clinical and research workflows. Findings Xp-Bodypart-Checker classified radiographs into seven categories with AUC values of over 0.99 for all classes, while CXp-Projection-Rotation-Checker achieved AUC values of 1.00 across all projection and rotation classifications. Clinical relevance Trained on over 860,000 multi-institutional radiographs, our two deep-learning models classify radiograph body-part and chest radiograph projection/rotation, identifying mislabeled data and enhancing data integrity, thereby improving reliability for both clinical use and deep-learning research.

References

1. 1.Mitsuyama, Y., Takita, H., Walston, S. L., Watanabe, K., Ishimaru, S., Miki, Y., & Ueda, D. (2026). Deep learning models for radiography body-part classification and chest radiograph projection/orientation classification: a multi-institutional study. European Radiology. https://doi.org/10.1148/rg.230067