Transfer learning from a sparsely annotated dataset of 3D medical images

1 code implementation • 8 Nov 2023 • Gabriel Efrain Humpire-Mamani, Colin Jacobs, Mathias Prokop, Bram van Ginneken, Nikolas Lessmann

A base segmentation model (3D U-Net) was trained on a large and sparsely annotated dataset; its weights were used for transfer learning on four new down-stream segmentation tasks for which a fully annotated dataset was available.

Organ Segmentation Segmentation +1