5 files

BreCaHAD: A Dataset for Breast Cancer Histopathological Annotation and Diagnosis

posted on 28.01.2019, 14:22 by Alper Aksac, Douglas J. Demetrick, Tansel Özyer, Reda Alhajj
This dataset consists of 1 .xlsx file, 2 .png files, 1 .json file and 1 .zip file:

annotation_details.xlsx: The distribution of annotations in the previously mentioned six classes (mitosis, apoptosis, tumor nuclei, non-tumor nuclei, tubule, and non-tubule) is presented in a Excel spreadsheet.

original.png: The input image.

annotated.png: An example from the dataset. In the annotated image, blue circles indicate the tumor nuclei, pink circles show non-tumor nuclei such as blood cells, stroma nuclei, and lymphocytes; orange and green circles are mitosis and apoptosis, respectively; light blue circles are true lumen for tubules, and yellow circles represent white regions (non-lumen) such as fat, blood vessel, and broken tissues.

data.json: The annotations for the BreCaHAD dataset are provided in JSON (JavaScript Object Notation) format. In the given example, the JSON file (ground truth) contains two mitosis and only one tumor nuclei annotations. Here, x and y are the coordinates of the centroid of the annotated object, and the values are between [0, 1] (divided by width and height of an image).

BreCaHAD.zip: An archive file containing dataset. Three folders are included: images (original images), groundTruth (json files), and groundTruth_display (groundTruth applied on original images)