Does Vendor Image Processing Matter? Learning Echocardiography Display Appearance from Native Beamspace Data

Elias Stenhede, Arian Ranjbar

Most echocardiography datasets contain vendor-processed images, but processing is often undocumented and may affect model performance and robustness. To address this, we train a small convolutional neural network to reproduce General Electric display appearance from native beamspace brightness-mode ultrasound, using 8 406 recordings from 605 unique patients. The beamspace CNN reduces test mean absolute error by 43% over the optimal pointwise brightness map, outperforms an equivalent Cartesian CNN and runs in real time on a CPU. Across the EchoXFlow and CAMUS datasets, unfiltered training followed by filtered evaluation yields the lowest mean Dice for every class, suggesting filtering may be useful as augmentation when evaluation data are filtered or their processing is unknown. Code and pretrained weights: https://github.com/Ahus-AIM/EchoAppearance