Innovative Tool for Automatic Detection of Arterial Stenosis on Cone Beam Computed Tomography
, Eleonora Barcali 1,3,†, Cosimo Lorenzetto 2, Eleonora Tiribilli 1,2, Vieri Rastrelli 3, Leonardo Manetti 2, Cosimo Nardi 3,*, Ernesto Iadanza 4,‡ and Leonardo Bocchi 1,‡
Round 1
Reviewer 1 Report
The article entitled “Innovative tool for automatic detection of arterial stenosis on
Cone Beam Computed Tomography” has been evaluated. This study provides a tool to support the medical doctor in planning endovascular surgery, allowing the rapid detection of stenotic vessels and the quantification of stenosis. Skeletonization is used to improve vessels visualization, and distance transform is used to obtain a linear representation of the diameter of critical vessels selected by the user. The system also estimates the exact distance between landmarks on the vascular tree and the occlusion, important information that can be used in the planning of the surgery.
Major Revision
1. The authors have performed this study n = 1; it would be perfect if this study had done n = 3 or more.
2. Is there a possibility of comparing this outcome with any positive or negative control?
Author Response
Please see the attachment.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
- A brief summary
Simoni et al. have done a good job at presenting a tool to help diagnose arterial stenosis on Cone Beam Computed Tomography. Their method builds the pipeline to extract diameter information from raw CT images and then shows a graphic representation of vessels, which is useful and accurate.
- General concept comments
I have the following concerns about the paper,
- On Page 4, are there any references to support the diameter analysis algorithm? From Line 110 to Line 126, no references are cited. More references are needed to prove the algorithm of diameter analysis, or if this is a new algorithm, more robust tests are needed.
- On Page 5, Line 181, the author claims, "The length of the window was chosen in order to analyze tracts 181 about 1.5 mm long." Is 1.5 mm a fixed length, or can it be adopted for both bigger and smaller lengths? This hyper-parameter needs to be justified or defined as a predefined parameter, and the authors need to report how to get or estimate it.
- Also, as the author mentioned in the conclusion, do you have any ideas or plans for improving the next step? Is it possible to do some model tests? For example, building a 3D model of some edges and hard cases and then generating a 3D CT image simulation and then testing whether the algorithm can successfully detect diameters.
- Specific comments
- Figure 1 and Figure 2 are too small to be seen clearly. Maybe rearrange the layout of the flow chart to make sure it is easier to view. For Figure 2, in particular, the ratio of fonts is compressed.
- Some long sentences can be rewritten into an easy-to-understand format. For example, on Page 1, "The realization of models before surgery is spreading more and more as it allows not only the surgeon to get an idea and act in a more targeted way but also the students to practice and learn techniques of intervention." I understand what the authors are saying, but their writing style could be improved.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
The authors justified the reason based on the reviewer’s comments. The manuscript can be acceptable for publication.
