An Efficient Framework for Accurate Liver Segmentation in Abdominal CT Images with Low Knowledge Requirement

Round 1

Reviewer 1 Report

This paper is well organized and written, and there are some small suggestions should be improved.

(1) Some technical details should be supplemented, such as the edge refinement method.

(2) The definitions of many symbols are confusing, which should be clearly defined.

(3) More experimental results are encouraged to report, such as the experimental setup, platform, and segmentation speed, etc.

(4) The title and analysis of Figure 8 are puzzling, so the author should re express its content.

(5) Can deep learning methods be applied to this task? More related work on applications of deep learning models should be discussed or compared for optimization, including “Improvement of generalization ability of deep CNN via implicit regularization in two-stage training process,” IEEE Access, vol. 6, pp. 15844-15869, 2018. “Faster Mean-shift: GPU-accelerated clustering for cosine embedding-based cell segmentation and tracking.” Medical Image Analysis 71 (2021): 102048. “Compound figure separation of biomedical images with side loss,” Deep Generative Models, and Data Augmentation, Labelling, and Imperfections. Springer, Cham, 2021. 173-183. “Pseudo RGB-D Face Recognition,” in IEEE Sensors Journal, vol. 22, no. 22, pp. 21780-21794, 15 Nov.15, 2022, doi: 10.1109/JSEN.2022.3197235.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

authors have presented a novel approach for CT image segmentation. some queries are to be included in the key highlights are 

1. why the authors have not used any of the deep learning models

2. why is only the presented conventional model efficient in terms of accuracy

3. illustrations of figures can be improved for example Fig. 7.

4. describe the sub-images fig 6 from (a) to (l)  

5. can include some review articles for image segmentation with doi as:

a.  https://doi.org/10.1007/s11831-018-9257-4

b. https://doi.org/10.1007/s11042-018-6005-6

 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

This paper proposed “An efficient framework for accurate liver segmentation in abdominal CT images with low knowledge requirement”. The proposed idea is interesting. The following questions should be taken into consideration.

1.     The abstract consists of different abbreviated sentences please include complete name for better understanding and also include the name of used dataset.

2.     In the introduction section author should include research gap and contributions precisely avoiding the unnecessarily details.

3.     Does author used any preprocessing technique for dataset preprocessing explanation needed?

4.     The methodology indicates more complex configurations that requires more powerful systems to execute the results, author should clarify system specification with time complexity that has been used in this particular study.

5.     The figure 7 in not clearly visible, please modify it?

6.     The conclusion part should clearly mention the contribution and befits of the applied approach.

7.     The article presents a number of errors in writing, style, terminology, formatting and quality of the figures need some improvement.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 3 Report

Dear Editor,

I agreed to the response of my comments, you may accept this paper for publication