Next Article in Journal
The Relationship between Planar and SPECT/CT Parameters and Functional Markers in Primary Hyperparathyroidism
Next Article in Special Issue
Artificial Intelligence in Coronary Artery Calcium Scoring Detection and Quantification
Previous Article in Journal
Characteristics of Patients with Laryngomalacia: A Tertiary Referral Center Experience of 106 Cases
Previous Article in Special Issue
Embracing AI: The Imperative Tool for Echo Labs to Stay Ahead of the Curve
 
 
Article
Peer-Review Record

TAVI-PREP: A Deep Learning-Based Tool for Automated Measurements Extraction in TAVI Planning

Diagnostics 2023, 13(20), 3181; https://doi.org/10.3390/diagnostics13203181
by Marcel Santaló-Corcoy 1,2,*,†, Denis Corbin 1,*,†, Olivier Tastet 1, Frédéric Lesage 1,2,3, Thomas Modine 4, Anita Asgar 1,2 and Walid Ben Ali 1,2
Reviewer 1: Anonymous
Reviewer 2:
Diagnostics 2023, 13(20), 3181; https://doi.org/10.3390/diagnostics13203181
Submission received: 1 September 2023 / Revised: 29 September 2023 / Accepted: 2 October 2023 / Published: 11 October 2023
(This article belongs to the Special Issue Artificial Intelligence in Cardiology Diagnosis )

Round 1

Reviewer 1 Report

The study is good and interesting, and there are some points that should be addressed as follows:

1. Abstract is incomplete. The most important results of the study must be discussed.

2. The introduction is unsatisfactory. The authors started with a satisfactory and good start, but did not address the problem and its solution. The importance of artificial intelligence in solving the problem of manual diagnosis must be discussed.

3. Discussing the most important contributions at the end of the introduction and concluding the introduction with outlines for dividing the rest of the study.

4. Can you support the “2.2. Segmentation” section with pictures and the most important segmentation areas after the segmentation process?

5. Was the segmentation method performed before inputting the images into the deep learning models?

6. How was hyperparameter tuning set and what deep learning models were applied in the study.

7. The study must be supported by a figure representing the methodology to make it easy for readers to follow it.

8. Are there results such as accuracy, sensitivity, specificity, AUC, etc.?

9. What are the most important limitations of the study and what are future works?

 

10. The conclusions section must be repeated to suit the study and review the most important results of the study.

 Minor editing of English language required

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

Thank you very much for the opportunity to review this interesting publication.

 

Overall, the article is well written and contributes to the development of TAVI.

 

However, there are some doubts that need to be resolved.

 

To what extent are automatic measurements able to predict post-procedure complications, such as paravalvular leaks?

Author Response

Please see the attachment

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

Accept in present form.

Minor editing of English language required.

Back to TopTop