Analyzing domain shift when using additional data for the MICCAI KiTS23 Challenge

arXiv:2309.02001v2 Announce Type: replace-cross
Abstract: Using additional training data is known to improve the results, especially for medical image 3D segmentation where there is a lack of training material and the model needs to generalize well from few available data. However, the new data could have been acquired using other instruments and preprocessed such its distribution is significantly different from the original training data. Therefore, we study techniques which ameliorate domain shift during training so that the additional data becomes …

abstract acquired arxiv challenge cs.ai cs.cv cs.lg data domain however image material medical results segmentation shift training training data training material type