Classification of computed tomography scans: a novel approach implementing an enforced random forest algorithm

Medical imaging faces critical challenges in radiation dose management and protocol standardisation. This study introduces a machine learning approach using a random forest algorithm to classify Computed Tomography (CT) scan protocols. By leveraging dose monitoring system data, we provide a data-driven solution for establishing Diagnostic Reference Levels while minimising computational resources.

We developed a classification workflow using a Random Forest Classifier to categorise CT scans into anatomical regions: head, thorax, abdomen, spine, and complex multi-region scans (thorax + abdomen and total body). The methodology featured an iterative "human-in-the-loop" refinement process involving data preprocessing, machine learning algorithm training, expert validation, and protocol classification. After training the initial model, we applied the methodology to a new, independent dataset.

By analysing 52,982 CT scan records from 11 imaging devices across five hospitals, we train the classificator to distinguish multiple anatomical regions, categorising scans into head, thorax, abdomen, and spine. The final validation on the new database confirmed the model's robustness, achieving a 97 % accuracy.

This research introduces a novel medical imaging protocol classification approach by shifting from manual, time-consuming processes to a data-driven approach integrating a random forest algorithm.

Our study presents a transformative approach to CT scan protocol classification, demonstrating the potential of data-driven methodologies in medical imaging. We have created a framework for managing protocol classification and establishing DRL by integrating computational intelligence with clinical expertise. Future research will explore applying this methodology to other radiological procedures.