Reader Comments
Post a new comment on this article
Post Your Discussion Comment
Please follow our guidelines for comments and review our competing interests policy. Comments that do not conform to our guidelines will be promptly removed and the user account disabled. The following must be avoided:
- Remarks that could be interpreted as allegations of misconduct
- Unsupported assertions or statements
- Inflammatory or insulting language
Thank You!
Thank you for taking the time to flag this posting; we review flagged postings on a regular basis.
closeA few of questions about the paper
Posted by wangwang5 on 31 Mar 2018 at 04:16 GMT
Dear Professors, it is really enlightening of your paper, but here I have several questions while I am reading your paper.
As follows:
1.Fig2 showed Davis grading of different patients(patient A, patient B and patient C), but why three fundus images in left row and 3 concatenated pictures in right row looks exactly the same fundus image? As if patients A B C share the same fundus image.
2.Fig3 figure legend C mentioned it is the visualization of four photograph(like image B: concatenated image), but I wonder is it the visualization of only one photograph(like image A: single one image)
3.Fig3 Visualization: can you illustrate more details about the methods of lesion visualization. It is achieved by manually setting different thresholds or how?
Thank you! Hope to hear from you soon!
Best regards,
Linyan
RE: A few of questions about the paper
htakahashi720 replied to wangwang5 on 08 May 2018 at 14:38 GMT
Dear Linyan,
I am sorry for confusing you.
1. In the Fig. 2, I used the same image as just backgrounds. Differentiation is represented by the red dots and red lightning bolts. I thought that it is not necessary to use different images.
2. Fig. 3 figure legend C mentioned it is the visualization of one photograph in the four photograph-trained GoogLeNet.
3. You can use DIGITS (https://developer.nvidia....) to visualize conv2/norm2 very easily.
Best regards,
Hidenori Takahashi