2 citations · 2 across the 2 of their papers we have counts for
2 papers
eess.IV2024
PI-Att: Topology Attention for Segmentation Networks through Adaptive Persistence Image Representation
Mehmet Bahadir Erden, Sinan Unver, Ilke Ali Gurses +2
Segmenting multiple objects (e.g., organs) in medical images often requires an understanding of their topology, which simultaneously quantifies the shape of the objects and their p…
cs.CV2023★ 2 cited
FourierLoss: Shape-Aware Loss Function with Fourier Descriptors
Mehmet Bahadir Erden, Selahattin Cansiz, Onur Caki +6
Encoder-decoder networks become a popular choice for various medical image segmentation tasks. When they are trained with a standard loss function, these networks are not explicitl…