Nuclei Segmentation via a Deep Panoptic Model with Semantic Feature Fusion

Authors: Dongnan Liu, Donghao Zhang, Yang Song, Chaoyi Zhang, Fan Zhang, Lauren O'Donnell, Weidong Cai

IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on three different histopathology datasets demonstrate that our method outperforms the state-of-the-art nuclei segmentation methods and popular semantic and instance segmentation models by a large margin.
Researcher Affiliation Academia 1School of Computer Science, University of Sydney, Australia 2School of Computer Science and Engineering, University of New South Wales, Australia 3Brigham and Women s Hospital, Harvard Medical School, USA
Pseudocode No The paper provides architectural diagrams and parameter tables but does not include structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any concrete statement or link indicating that the source code for their proposed method is publicly available.
Open Datasets Yes We used three public datasets in this study. The first dataset is from The Cancer Genome Atlas (TCGA) at 40 magnification [Kumar et al., 2017]. ... The second dataset from [Naylor et al., 2018] focuses in particular on Triple Negative Breast Cancer (TNBC). ... The third dataset is the MICCAI 2017 Digital Pathology Challenge dataset [Vu et al., 2018], also referred to as Cell17.
Dataset Splits Yes Among the 16 training images from four different organs, we randomly selected one image from each organ for validation and used the remaining 12 images for training.
Hardware Specification No The paper does not provide specific details about the hardware used for running the experiments, such as GPU/CPU models or specific computational resources.
Software Dependencies No The paper states 'We implemented our experiments using Pytorch [Paszke et al., 2017]' but does not provide specific version numbers for PyTorch or any other software dependencies.
Experiment Setup Yes In all experiments, we employed stochastic gradient descent (SGD) as the optimizer with a momentum of 0.9 and a weight decay of 0.0001 to train our model. The learning rate varies in each experiment with the same linear warming up in the first 500 iterations.