Classifying Microscopic Images of Reactive Lymphocytosis Using Two-Step Tandem AI Models
Round 1
Reviewer 1 Report
Reviewer’s Comments:
The manuscript “Approach to the identification of reactive lymphocytosis using two-step tandem AI models -Potential as a blood smear screening technology in clinical laboratories” is a very interesting work. In this work, the practical applications of automatic recognition and categorization technology for next-generation systems are desired in the clinical laboratory. We approached the identification of reactive lymphocytosis using artificial intelligence (AI) technology and studied its clinical usefulness for blood smear screening. This study created one- and two-step AI models for the identification of reactive lymphocytosis. The ResNet-101 model was applied for deep learning. The original image set for supervised AI training consisted of 5765 typical nucleated blood cell images. The subjects for clinical assessment were 25 healthy cases, 25 erythroblast cases, and 25 reactive lymphocytosis cases. While I believe this topic is of great interest to our readers, I think it needs major revision before it is ready for publication. So, I recommend this manuscript for publication with major revisions.
1. In this manuscript, the authors did not explain the importance of the lymphocytosis the introduction part. The authors should explain the importance of lymphocytosis.
2) Title: The title of the manuscript is not impressive. It should be modified or rewritten it.
3) Correct the following statement “The one- and two-step AI models showed sensitivity of 0.880 and 0.960 and specificity of 1.000 and 1.000, respectively. As our two-step AI model showed usefulness in blood smear screening in the clinical laboratory, we plan to apply this method to the development of AI models to identify reactive and neoplastic lymphocytosis”.
4) Keywords: The lymphocytosis is missing in the keywords. So, modify the keywords.
5) Introduction part is not impressive. The references cited are very old. So, Improve it with some latest literature such as 10.3390/molecules27217368, 10.3390/molecules27207129
6) The authors should explain the following statement with recent references, “As our two-step AI model showed usefulness in blood smear screening in the clinical laboratory, we plan to apply this method to the development of AI models to identify reactive and neoplastic lymphocytosis”.
7) Add space between magnitude and unit. For example, in synthesis “21.96g” should be 21.96 g. Make the corrections throughout the manuscript regarding values and units.
8) The author should provide reason about this statement “Table 8-C shows a matrix table for the identification of reactive lymphocytosis cases with the one-step AI model, and Table 8-D shows a matrix table for the identification of reactive lymphocytosis cases with the two-step AI model”.
9. Comparison of the present results with other similar findings in the literature should be discussed in more detail. This is necessary in order to place this work together with other work in the field and to give more credibility to the present results.
10) Conclusion part is very long. Make it brief and improve by adding the results of your studies.
11) There are many grammatic mistakes. Improve the English grammar of the manuscript.
Author Response
Dear Reviewer
The authors gratefully thank to the Referee for the constructive comments and recommendations, which definitely helped us improve the quality and readability of the paper. Please see the attachment for our reply.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
After examining the maximum research manuscript with the title
"Approach to the identification of reactive lymphocytosis using 2
two-step tandem AI models - Potential as a blood smear 3
screening technology in clinical laboratories"
I have to inform the authors of this manuscript that it is better to prepare a section to display the previous studies in the form of tables regarding the processing of blood smear images using artificial intelligence.
Unfortunately, many studies can be included in this research which is in line with this research, some of them can be listed below.
"A fast and efficient CNN model for B-ALL diagnosis and its subtypes classification using peripheral blood smear images"
"Automated detection model in classification of B-lymphoblast cells from normal B-lymphoid precursors in blood smear microscopic images based on the majority voting technique"
Of course, many articles have been written in this field. It is better to present them in a table
Author Response
Dear Reviewer
The authors gratefully thank to the Referee for the constructive comments and recommendations, which definitely helped us improve the quality and readability of the paper. Please see the attachment for our reply.
Author Response File: Author Response.pdf
Reviewer 3 Report
1. Add contribution of the proposed work in the introduction section
2. Add a statement regarding subsections in the Introduction section
3. Need to explain in more detail the one-step and two-step models in section 3.5. The development of AI models for the identification of reactive lymphocytosis cases.
4. Give experimental setup details and experimental parameters details
5. Compare results with published works
Author Response
Dear Reviewer
The authors gratefully thank to the Referee for the constructive comments and recommendations, which definitely helped us improve the quality and readability of the paper. Please see the attachment for our reply.
Author Response File: Author Response.pdf
Round 2
Reviewer 3 Report
Contribution of the proposed work is not clear
Compare proposed work results with existing published work
Author Response
Dear Reviewer
The authors gratefully thank to the Referee for the constructive comments and recommendations, which definitely helped us improve the quality and readability of the paper. Please see the attachment for our reply.
Author Response File: Author Response.pdf
Round 3
Reviewer 3 Report
Authors have included all observations. It can be processed for the next step
