Home Response to the Letter from LUNGx Challenge
Post
Cancel

Response to the Letter from LUNGx Challenge

First, I (corresponding author) clarify the following two points: (I) Because I and the other coauthor have moved to other affiliations, this response is related with neither the other coauthor nor my previous affiliation; (II) I obtain permission of referring to my personal e-mails which were sent/received from/to organizers of LUNGx Challenge although Academic Radiology asks me not to include contents of my personal e-mails in this response.

This response is divided into the following five sections: (i) Rule of LUNGx Challenge; (ii) Our results of LUNGx Challenge; (iii) Use of our results of LUNGx Challenge; (iv) Usefulness of our paper; and (v) Intention of database creator.

  • (i) Rule of LUNGx Challenge

LUNGx Challenge was performed under its rule, and participants of LUNGx Challenge had to obey the rule. In my opinion, there was an ambiguous point in the rule of LUNGx Challenge; training data were not provided in LUNGx Challenge, and the rule of LUNGx Challenge about how to prepare the training data was not clarified. As a result, I speculate that some (or many) participants were confused with LUNGx Challenge, and that the participants could not fully optimize their CADx system in LUNGx Challenge (the details are described in Reference ).

  • (ii) Our results of LUNGx Challenge

Get Radiology Tree app to read full this article<

Get Radiology Tree app to read full this article<

Get Radiology Tree app to read full this article<

Get Radiology Tree app to read full this article<

Get Radiology Tree app to read full this article<

Get Radiology Tree app to read full this article<

Get Radiology Tree app to read full this article<

Get Radiology Tree app to read full this article<

Get Radiology Tree app to read full this article<

Get Radiology Tree app to read full this article<

References

  • 1. Armato S.G., Hadjiiski L., Tourassi G.D., et. al.: LUNGx Challenge for computerized lung nodule classification: reflections and lessons learned. J Med Imaging (Bellingham) 2015; 2: pp. 020103. Apr

  • 2. E-mail from jurader@yahoo.co.jp to kdrukker@uchicago.edu (date, 2015/1/21).

  • 3. E-mail from tourassig@ornl.gov to m-nishio@fbri.org (date, 2015/2/11).

  • 4. Nishio M., Nagashima C.: Computer-aided diagnosis for lung cancer: usefulness of nodule heterogeneity. Acad Radiol 2017; 24: pp. 328-336. Mar

This post is licensed under CC BY 4.0 by the author.