24小时热门版块排行榜

返回列表

当前只显示满足指定条件的回帖，点击这里查看本话题的所有回帖

amzpotato

新虫 (初入文坛)

应助: 0 (幼儿园)
金币: 67
红花: 1
帖子: 21
在线: 3.9小时
虫号: 14870388
注册: 2019-04-13
专业: 人工智能与知识工程

[交流] 审稿大修已有15人参与

大家好，新人一枚！一个月前投了一个期刊，审稿意见为大修，编辑信如下。给了3个月时间修改，第一个审稿人提了很多充实论文的意见，这种情况修改后悲剧的可能性大吗？还有我大概修改多久提交比较好呢？跪求各位大佬帮俺解答一下。
A revised version of your manuscript that takes into account the comments of the referee(s) will be reconsidered for publication.

Please note that submitting a revision of your manuscript does not guarantee eventual acceptance, and that your revision may be subject to re-review by the referee(s) before a decision is rendered.

You can upload your revised manuscript and submit it through your Author Center. Log into https://mc.manuscriptcentral.com/ima  and enter your Author Center, where you will find your manuscript title listed under "Manuscripts with Decisions".

When submitting your revised manuscript, you will be able to respond to the comments made by the referee(s) in the space provided.  You can use this space to document any changes you make to the original manuscript.

Once again, thank you for submitting your manuscript to International Journal of Imaging Systems and Technology and I look forward to receiving your revision.

Sincerely,

Dr Mohamed Seghier
Editor, International Journal of Imaging Systems and Technology
imaeditorial@wiley.com

Referee(s)' Comments to Author:

Reviewing: 1

Comments to the Author
1- Some important and novel techniquse are missing in the literature part.
-Gu, Z., Cheng, J., Fu, H., Zhou, K., Hao, H., Zhao, Y., ... & Liu, J. (2019). CE-Net: Context Encoder Network for 2D Medical Image Segmentation. IEEE transactions on medical imaging.
-Öztürk S¸, Akdemir B. Celltype based semantic segmentation of histopathological images using deep convolutional neural networks. Int J Imaging Syst Technol. 2019;1 13. https://doi.org/10.1002/ima.22309
2- The most important contribution of this study is upsampling of feture maps. Authors have to show this at the figure 1. Figure 1 is unclear
3- What is the motivation of Xcception block? What is the formulation of Xception block?
4- Section 2.2 has to be explained detailed.
5- Section 2.3 has to be explained detailed.  (Authors has to explain their parameters, their contribution, the different part of their methods in Section 2.1, 2.2, 2.3)
6- Section 2.4 is not clear. Authors has to add figure.
7- TP, FN,FP explanations are generic. Authors have to explained these parameters according to their data.
8- Further research on the effects of network depth should be done and the results should be added.
9- Computational complexity should be added.
10- Visual comparison results should be added as a new figure.
11- More state-of-the-art algorithm results can be added.

Reviewing: 2

Comments to the Author
This paper conducted gliomas segmentation using multi-scale 3D Unet. To enhance the accuracy of segmentation masks, multi-scale features, 3D U-net with separable convolution block, and multi-pooling blocks were utilized. Performance was validated by comparison to multiple previous techniques using Dice, sensitivity, and PPV.

The manuscript is well written. But, I have a few inquiries and suggestions to improve this manuscript.

1. Table 2 shows the improvement of segmentation masks with respect to each component of your network, such as the convolution block, and pooling. Can you show the differences of segmentation masks according to each component?

2. Table 3 shows that the performance of the proposed method is less accurate than other methods. Can you explain other advantages of your technique (ex. number of parameters or FLOPs) in result and discussion section?

3. Table 3 shows that the proposed method can produce an accurate segmentation mask in whole but not in core and Enh. Can you discuss the reason for these results?

回复此楼