Reader Comments

Post a new comment on this article

A 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

No competing interests declared.
report a concern respond to this posting

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

Competing interests declared: I am the author.
report a concern respond to this posting