Sustainable Utilization of Machine-Vision-Technique-Based Algorithm in Objective Evaluation of Confocal Microscope Images

Round 1

Reviewer 1 Report

The research and paper shows a good effort on the behalf of the authors. Somehow, I do not see anything related to sustainability in this paper. You may reconsider the selection of a journal for this paper or may otherwise redesign your research to emphasize the context of sustainability.  

This paper is about analyzing, microscopic images  - focused on the field of biotechnology. The paper is a good read and must add scholarly information in the related field. But when I review it in connection with this Sustainability journal then it is completely out of scope.

How and why the authors call it sustainable use of Machine Vision technology??

The research has to be aligned with the notions of sustainability and must be connected with the SDGs  if the authors want it to be considered a sustainability issue. in its current form, this paper has nothing to do with sustainability in my view, except the word sustainability used in the title, in the abstract, and 3 to 4 times more in a very insignificant manner.  

The paper may better be submitted to some medical imaging or image analysis journal. No need for the word sustainable at any place in the paper. 

Author Response

Firstly, we would like to thank you very much for the valuable comments you provided for the manuscript. These comments have greatly improved the quality of the manuscript. Below is the response to your question and input about the manuscript.

 

How and why the authors call it sustainable use of Machine Vision technology??

It is a really good question that I want to answer here. According to Cambridge  dictionary, the term sustainability refers to “the idea that goods and services should be produced in ways that do not use resources that cannot be replaced and that do not damage the environment”

 

According to UNESCO, the definition of Sustainable engineering is “the process of using resources in a way that does not compromise the environment or deplete the materials for future generations.”

As the definition suggests, it is all about designing systems in a way that sustains resources and energy, in which they were used at a rate that does not compromise resources and save them for future generations to meet their needs. According to above definitions, sustainability actually impacts every aspect of our life. Sustainable engineering is essential to ensure continuing life with ease for the coming generations.

Our results save time and labor in biology laboratories through making the analysis of confocal microscope images easy, fast and computerized. It perfectly falls under the term sustainability and, eventually, fits the journal “sustainability”.

Thank you so much for your comments. 

 

Reviewer 2 Report

Please see the document attached.

Comments for author File: Comments.pdf

Author Response

Firstly, we would like to thank you very much for the valuable comments you provided for the manuscript. These comments have greatly improved the quality of the manuscript. Below is the response, point by point to your comments.

1. In this study, the authors present a confocal microscopy image analysis workflow that can provide a significant improvement in the required image analysis time and utilization of human workforce. The detailed methodology is a relevant contribution to the microscopy image analysis field, however, some unclear statements need to be addressed and the presentation quality needs to be improved before being considered for publication.

• The authors should provide solid proof to validate a sentence like this in the Conclusion section: “We believe that all published studies have an insufficient methodology to ensure accurate results of fluorescence quantification and protein localization”. Such a generalized statement is highly recommended to get revised.

Answer: revised, thank you.

• It is claimed in the Discussion section that “in the current approach, we are attempting to overcome those issues by providing a new method for the analysis of size distribution”, however, there is no object size distribution analysis presented in the study.
• “Our main contribution was the identification of the fluorescence of proteins from different backgrounds of images and discriminating different object shapes”. This is an additional vague statement as there is no object shape analysis presented in this work, thus claiming shape discrimination seems to be not proven. To keep this statement, related analysis results should be provided.

Answer: Thank you for the comment. The object shapes are detected by connected object algorithm then subtracting the unfamiliar shapes considering it as noise. This is actually discussed in lines 230 -234 and figures 7, and 8.

• In Figure 8, the term “intelligent selector” appears as a highly overstated term to use for a simple algorithm that is presented. It is not clear why the authors wanted especially to highlight this part of the algorithm in a form of a pseudocode, while pseudocodes for other relevant algorithm sections are not presented.

Answer: The Multiclass Adaptive Neuro-Fuzzy Classifier is what we call “intelligent selector”, so, it is a trained Artificial intelligent model shown in Figure 5. This is an important part because it achieves the ability of processing raw images directly from the confocal microscope. In addition, any image if wrongly directed to a different processing algorithm causes misleading results. 

• The quality of some figures should be improved:
• 13-17: Y axis title should be presented on each graph. A negative scale should only be presented if negative values are included. It is unclear what the actual objective evaluation and subjective evaluation values represent. Both graphs in the figures should be separately labeled (such as A, B) and explained in the figure caption. It is not obvious what the bottom graph in Fig. 13-17 represents.

Answer: Thank you for the important notes on the figures, we corrected them accordingly.

• 6: What is the reason for indicating a data point with a square marker?

Answer: We could not find the square marker in figure 6 which is “Inputs and output membership functions shape and intersections values.”

• In general, the English of the manuscript is appropriate, however, some language errors should be addressed, e.g.,
• 6: intersections values → intersection values (Corrected, thank you)
• “In the proposed approach, no need for the pre-preparations that might cause issues when performing the measurements.” (Corrected, thank you)
• Percentage should go after the related number (%100 → 100%). (Corrected, thank you)
• Line 129: “The Leica”  provide specific type as given in a later sentence. (Corrected, thank you)
• Line 138: “As can be inferred” →As it can be inferred. (Corrected, thank you)

 

Reviewer 3 Report

This is an interesting work with very good results. It is written in clear language and is easy to read. I think it can be published with minor corrections.

1. Many figures, especially those with results, are too large and take up an unnecessary amount of space. It creates a bad visual impression.

2. Some subtitles are not formatted in accordance with the others (line 147, line 217).

3. Figure 5 should be explained in more detail.

4. The legend in Figure 5 contains OR and NOT operations, but they are not visible in the figure.

5. Put the percent symbol after the number, not in front.

6. Parts of the text in lines 272 and 273 are not visible.

Author Response

Firstly, we would like to thank you very much for the valuable comments you provided for the manuscript. These comments have greatly improved the quality of the manuscript. Below is the response, point by point to your comments.

 

 

This is an interesting work with very good results. It is written in clear language and is easy to read. I think it can be published with minor corrections.

Response: Thank you so much for the feedback.

- Many figures, especially those with results, are too large and take up an unnecessary amount of space. It creates a bad visual impression.

Response: We rearranged figures according to the note.

- Some subtitles are not formatted in accordance with the others (line 147, line 217). (Corrected, thank you)

- Figure 5 should be explained in more detail. (Corrected, thank you)

- The legend in Figure 5 contains OR and NOT operations, but they are not visible in the figure.

Response:  the legend indicates that if there AND, OR and NOT operations, they will be symbolled as in the legend. In our design, there were not any OR and NOT rules generated in the system.

- Put the percent symbol after the number, not in front. (Corrected, thank you)

- Parts of the text in lines 272 and 273 are not visible. (Corrected, thank you)

 

Round 2

Reviewer 1 Report

Thank you for submitting V2, though nothing considerable is added. 

I still do not see any explicit explanation concerning sustainability which is the main focus of the journal in which you are submitting. 

For this there must be a proper sustainability evaluation of the proposed process. Although your research work is valuable for the research community but the sustainability aspect if undermined by the way you have presented it.   

Upto a minimum level there must be a section titled( for example) Sustainability Evaluation of the technique proposed, with two subsections Time sustainability aspect and effort sustainability aspects with a detailed explanation of how your technique is providing time and effort efficiency and how it is a benefit over the existing algorithms and how it is facilitating the sustainability goals. It must be a to-the-point objective description backed by figures from your experimentation. 

You have already written a lot about time efficiency but in between the lines and not explicitly and not much is discussed about effort efficiency. Proper explanation aligned with the sustainability goals is very critical to measure the effectiveness of your research in this direction.  

 

  

Author Response

Thank you so much for the valuable addition to the paper.

We have added the following paragraph based on your recommendation.

 

Sustainability Evaluation of the technique proposed

In general, designing algorithms can contribute to sustainability in a number of ways. Some of these ways include helping in optimizing the use of resources such as energy, water, and materials. In our work, we focused on analyzing Confocal Microscope Images. Image processing algorithms are designed to perform various tasks such as image enhancement, object recognition, and feature extraction automatically. These algorithms can process images faster and with more accuracy than humans in many cases, and they are particularly useful for tasks that require repetitive or time-consuming image analysis. However, it is important to note that algorithms are not capable of replacing human intuition, creativity, and judgment in all cases. In some situations, human input may be required to validate the results of image processing algorithms, or to make decisions based on the results of the processing. With this regard, we have three experts to evaluate the results in the obtained images (Table 2).

 

1. Sustainability with regard to time-saving

Algorithms can save time in image processing by automating many tasks that would otherwise require human effort. For example, algorithms can quickly analyze large number of images and identify patterns or features in images that may be difficult for a human to detect. This can include detecting edges and lines, identifying objects or patterns, and recognizing shapes and textures. Algorithms can also be designed to perform complex image manipulations, such as adjusting brightness and contrast, enhancing color or texture, and removing noise, much more efficiently than a human could. By automating these tasks, algorithms can significantly reduce the time required for image processing, freeing up time for more creative or high-level tasks. In our work, the average computation cost of the Intelligent machine spatial distribution quantification system is 0.1 second to one raw confocal microscope image and provides the objective evaluation of it. The experiment is implemented on a Windows 10, 64-bit intel machine with a 2.50 GHz core i5 CPU and 8 GB RAM. This is much faster than the regular time consumed by one expert who evaluated the same amount of data in at least 3 minutes. Also, in the case of time required to analyze large amounts of data, the usual time spent by humans in the laboratory is 8 hours per day. In the case of machine, it could continue for a longer time, in some cases up to 24 hours per day.

2. Sustainability in labor

Our proposed algorithm contributes to saving human effort in biotechnology laboratories by automating image processing and streamlining many tasks that would otherwise require manual effort. This includes tasks such as image recognition, object detection, segmentation, and classification, which are repetitive for humans to perform and require more than one expert to check an validate the results. By using algorithms, these tasks can be accomplished much faster and with a higher degree of accuracy and consistency, freeing up human resources to focus on more strategic and creative tasks in the laboratory. Additionally, algorithms can analyze vast amounts of data and perform complex calculations, enabling them to make decisions and draw insights that would be beyond the capacity of human effort alone. Another aspect to be taken into consideration, which is the performance of humans. The accuracy of analysis by humans may vary depending on the time that the expert does the analysis. If the person is sick or can not perform perfectly for any reason, the evaluation of the image will not be as accurate as the healthy person.

Reviewer 2 Report

 

In their response, the authors did not address the Reviewer’s point about size distribution analysis. It is still not clear, why it is claimed in the Discussion section that “in the current approach, we are attempting to overcome those issues by providing a new method for the analysis of size distribution”, however, there is no object size distribution analysis presented in the study.

The authors highlight the analysis of spatial distribution. Spatial distribution is not equivalent to size distribution. If the authors want to include their statement about size distribution, they should provide related data that validate the size distribution analysis of their method, e.g. comparing the analyzed data with reference measurements.

The authors improved the quality of the figures according to reviewer comments. Additional comments related to figures:

- In Fig. 13, 15, and 16, the fitted line looks to be forced to the (0,0) coordinate. In the similar case of Fig. 16 and 17, the fitter line is not forced to (0,0). What is the reason for this difference?

- In Fig. 16, what is the reason for applying 0-120 scale in the X axis? All other similar plots are scaled in the 0-100 range.

Additional comment:

- Percentages are still before numeric values in some cases (e.g., Line 274, 427, 430).

 

 

 

Author Response

Thank you so much for the valuable comments.

Here are the responses to the comments.

In their response, the authors did not address the Reviewer’s point about size distribution analysis. It is still not clear, why it is claimed in the Discussion section that “in the current approach, we are attempting to overcome those issues by providing a new method for the analysis of size distribution”, however, there is no object size distribution analysis presented in the study.

The authors highlight the analysis of spatial distribution. Spatial distribution is not equivalent to size distribution. If the authors want to include their statement about size distribution, they should provide related data that validate the size distribution analysis of their method, e.g. comparing the analyzed data with reference measurements.

Answer: Thank you for the valuable comment. the statement was removed. It is a writing mistake (mixed with another project we work on).

Comment: The authors improved the quality of the figures according to reviewer comments. Additional comments related to figures:

- In Fig. 13, 15, and 16, the fitted line looks to be forced to the (0,0) coordinate. In the similar case of Fig. 16 and 17, the fitter line is not forced to (0,0). What is the reason for this difference?

Answer: Thanks. Done, it is scaled automatically by MATLAB, we fixed it to fit the range exactly without extra range.

- In Fig. 16, what is the reason for applying 0-120 scale in the X-axis? All other similar plots are scaled in the 0-100 range.

Answer: Thank you for the comment. Done, Same mistake, It is scaled automatically, we fixed it to fit the range exactly without extra range.

Additional comment:

- Percentages are still before numeric values in some cases (e.g., Line 274, 427, 430).

Answer: Thank you so much. Corrected.

Round 3

Reviewer 1 Report

Thank you for enhancing the scholarly contribution of your work according to the guideline. 

It now presents an appropriate information regarding sustainability benefits of your work. . 

One minor change -

Instead of writing "our work" , "our algorithm"  mention it as " the proposed algorithm"   all references to the must be in indirect speech (especially in the added text and also in the whole paper) , replace all first person references ( I, we , etc. ) with indirect speech. 

It will make the presentation more clear and standard from the language point of view.

 

Best of luck. 

Author Response

Thank you so much for the valuable comments. We appreciate your revisions, and all of your comments applied to the manuscript.