HyperAI

Multi Tissue Nucleus Segmentation On Kumar

Metrics

Dice
Hausdorff Distance (mm)

Results

Performance results of various models on this benchmark

Model Name
Dice
Hausdorff Distance (mm)
Paper TitleRepository
DSF-CNN (C8)0.82660Dense Steerable Filter CNNs for Exploiting Rotational Symmetry in Histology Images
G-CNN (C12)0.81453.4Roto-Translation Equivariant Convolutional Networks: Application to Histopathology Image Analysis
Steerable G-CNN (e)0.79151.0Learning Steerable Filters for Rotation Equivariant CNNs-
CIA-Net (e)0.81857.7CIA-Net: Robust Nuclei Instance Segmentation with Contour-aware Information Aggregation-
Mask R-CNN (e)0.76050.9Mask R-CNN
HoVer-Net (e)0.82659.7HoVer-Net: Simultaneous Segmentation and Classification of Nuclei in Multi-Tissue Histology Images
Steerable G-CNN (C12)0.81854.3Learning Steerable Filters for Rotation Equivariant CNNs-
G-CNN (C12)0.81151.9Roto-Translation Equivariant Convolutional Networks: Application to Histopathology Image Analysis
U-Net (e)0.75847.8U-Net: Convolutional Networks for Biomedical Image Segmentation
VF-CNN (C4)0.80049.9Rotation equivariant vector field networks
Micro-Net (e)0.79751.9Micro-Net: A unified model for segmentation of various objects in microscopy images-
Steerable G-CNN (C4)0.80954.2Learning Steerable Filters for Rotation Equivariant CNNs-
VF-CNN (C12)0.80850.7Rotation equivariant vector field networks
VF-CNN (C12)0.81351.4Rotation equivariant vector field networks
G-CNN (C4)0.79349.0Group Equivariant Convolutional Networks
GC-MHVN0.843-MRL: Learning to Mix with Attention and Convolutions-
FCN8 (e)0.79731.2Fully Convolutional Networks for Semantic Segmentation
Steerable G-CNN (C12)0.82055.8Learning Steerable Filters for Rotation Equivariant CNNs-
0 of 18 row(s) selected.