NuSeC: A Dataset for Nuclei Segmentation in Breast Cancer Histopathology Images

TL;DR

The paper introduces NuSeC, a dataset of 100 breast cancer histopathology images with nuclei annotations, designed for nuclei segmentation research, with a clear train-test split for future method evaluation.

Contribution

It provides a new, publicly available dataset specifically for nuclei segmentation in breast cancer histopathology images, facilitating standardized benchmarking.

Findings

Dataset contains 100 images with nuclei annotations.

75 images for training, 25 for testing, covering around 36,000 nuclei.

Structured split ensures consistent evaluation for future research.

Abstract

The NuSeC dataset is created by selecting 4 images with the size of 1024*1024 pixels from the slides of each patient among 25 patients. Therefore, there are a total of 100 images in the NuSeC dataset. To carry out a consistent comparative analysis between the methods that will be developed using the NuSeC dataset by the researchers in the future, we divide the NuSeC dataset 75% as the training set and 25% as the testing set. In detail, an image is randomly selected from 4 images of each patient among 25 patients to build the testing set, and then the remaining images are reserved for the training set. While the training set includes 75 images with around 30000 nuclei structures, the testing set includes 25 images with around 6000 nuclei structures.