CT scanning is just awful for diagnosing Covid-19

March 23, 2020March 26, 2020 ~ lukeoakdenrayner ~ 23 Comments

Reports that CT scanning may be better than PCR testing for covid-19 are flawed and almost certainly wrong.

CheXNet: an in-depth review

January 24, 2018January 24, 2018 ~ lukeoakdenrayner ~ 24 Comments

Since the CheXNet paper came out in November 2017 I have been communicating with the author team. I'm finally ready to review the paper. Some of the things I found out surprised me.

Exploring the ChestXray14 dataset: problems

December 18, 2017December 18, 2017 ~ lukeoakdenrayner ~ 97 Comments

A couple of weeks ago, I mentioned I had some concerns about the ChestXray14 dataset. I said I would come back when I had more info, and since then I have been digging into the data. I've talked with Dr Summers via email a few times as well. Unfortunately, this exploration has only increased my concerns about the dataset.