OOOE: Only-One-Object-Exists Assumption to Find Very Small Objects in Chest Radiographs
This addresses the challenge of detecting very small objects in medical imaging for automated analysis, though it appears incremental as it builds on existing deep learning approaches with a novel assumption.
The paper tackles the problem of localizing small medical tubes and anatomical structures in chest radiographs by proposing the Only-One-Object-Exists (OOOE) assumption, which recasts localization as a classification problem, and shows that it outperforms regression-based and pixel-wise methods on large datasets including over 100K radiographs and the RANZCR-CLiP dataset.
The accurate localization of inserted medical tubes and parts of human anatomy is a common problem when analyzing chest radiographs and something deep neural networks could potentially automate. However, many foreign objects like tubes and various anatomical structures are small in comparison to the entire chest X-ray, which leads to severely unbalanced data and makes training deep neural networks difficult. In this paper, we present a simple yet effective `Only-One-Object-Exists' (OOOE) assumption to improve the deep network's ability to localize small landmarks in chest radiographs. The OOOE enables us to recast the localization problem as a classification problem and we can replace commonly used continuous regression techniques with a multi-class discrete objective. We validate our approach using a large scale proprietary dataset of over 100K radiographs as well as publicly available RANZCR-CLiP Kaggle Challenge dataset and show that our method consistently outperforms commonly used regression-based detection models as well as commonly used pixel-wise classification methods. Additionally, we find that the method using the OOOE assumption generalizes to multiple detection problems in chest X-rays and the resulting model shows state-of-the-art performance on detecting various tube tips inserted to the patient as well as patient anatomy.