HEROHE's dataset is publicly available for research purposes under the Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0) license. The citation should refer to arXiv:2111.04738 and 10.3390/jimaging6090082. Teams should notify the organizers of the challenge about any publication (partly) based on the results or data published on this site. The challenge organizers will maintain a public list of publications associated with the challenge so others may find appropriate references easily.
Last edition: Nov 15, 2021
Biological Background
Q1. Each slide in the dataset is labeled either as positive or negative. According to the challenge website "negative (score 0 or 1+), equivocal (score 2+), positive (score 3+), and indeterminate." I'd like to know if you have only provided 0/+1 as negative and 3+ as positive? And also specifically whether 2+ has been left out from the provided slides.
A1. We have positive cases (score 3+ and score 2+ ISH positive) and negative cases (score 0/1+ and score 2+ ISH negative). There are no indeterminate cases. We have cases with just IHC and cases with IHC and ISH. The final result is either IHC alone or IHC and ISH. We have all the scores from 0 to 3+.
Dataset size
Q1. What is the total size of the dataset.
A1. The DataSet has 755GB.
Q2. Could you consider providing the checksum of all data files?
A2. Checksums are available in file sha256sum.txt within the HEROHE_CHALLENGE folder.
Forum
Q1. Could you please add a forum page for question and answering?
A1. Of course. You can found it at:
- https://groups.google.com/forum/#!forum/herohe-grand-challenge or
- https://ecdp2020.grand-challenge.org/Forum/
FTP download
Q1. Which FTP account should I use?
A1. You can use an anonymous user with empty password.
Q2. I’m using FileZilla and the download is extremely slow. Is there any problem with your server?
A2. The bandwidth should be enough to allow the download in a few hours. You probably have defined some restrictions in the FileZilla settings. Try changing the Settings, namely the number of concurrent downloads and speed limits.