Arendt CT, Leithner D, Mayerhoefer ME, et al. - The present study was performed to assess the performance of radiomic features extracted from high-resolution computed tomography (HRCT) for the differentiation between cholesteatoma and middle ear inflammation (MEI), and to investigate the impact of post-reconstruction harmonization and data resampling. Researchers enrolled 100 individuals in this retrospective dual-center study: 48 with histology-proven cholesteatoma (center A: 23; center B: 25) and 52 with MEI (A: 27; B: 25). They used a multi-layer perceptron feed-forward artificial neural network for radiomics-based classification, with histopathology serving as the reference standard (70% of cases for training, 30% for validation). As per the results, radiomic features extracted from HRCT differentiate between cholesteatoma and MEI. The results indicate that data resampling and ComBat post-reconstruction harmonization clearly improve radiomics-based lesion classification when using multi-centric data obtained with differences in CT acquisition parameters.