Next Article in Journal
Long-Term Effectiveness and Sustainability of Integrating Peer-Assisted Ultrasound Courses into Medical School—A Prospective Study
Next Article in Special Issue
Dedicated Cone-Beam Breast CT: Reproducibility of Volumetric Glandular Fraction with Advanced Image Reconstruction Methods
Previous Article in Journal
A Deep Learning Approach for Rapid and Generalizable Denoising of Photon-Counting Micro-CT Images
Previous Article in Special Issue
Multiclass Segmentation of Breast Tissue and Suspicious Findings: A Simulation-Based Study for the Development of Self-Steering Tomosynthesis
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Tomography
Volume 9
Issue 4
10.3390/tomography9040103
Review Report
tomography-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
Article
Peer-Review Record

Impact of Tomosynthesis Acquisition on 3D Segmentations of Breast Outline and Adipose/Dense Tissue with AI: A Simulation-Based Study

Tomography 2023, 9(4), 1303-1314; https://0-doi-org.brum.beds.ac.uk/10.3390/tomography9040103
by Bruno Barufaldi 1,*, Jordy Gomes 2, Thais G. do Rego 2, Yuri Malheiros 2, Telmo M. Silva Filho 3, Lucas R. Borges 4, Raymond J. Acciavatti 1, Suleman Surti 1 and Andrew D. A. Maidment 1
Reviewer 1: Anonymous
Reviewer 2:
Yan Liu
Tomography 2023, 9(4), 1303-1314; https://0-doi-org.brum.beds.ac.uk/10.3390/tomography9040103
Submission received: 11 April 2023 / Revised: 27 June 2023 / Accepted: 1 July 2023 / Published: 3 July 2023
(This article belongs to the Special Issue Artificial Intelligence in Breast Cancer Screening)

Round 1

Reviewer 1 Report

This study proposes U-Net- and VCT-based method to optimize the NGT acquisitions to (1) reduce the superposition of dense and adipose tissue in DBT reconstructions and, simultaneously, (2) segment the convex hull. 

I have some concerns and suggestions regarding the study:

1. Please make literature review section, and put it after introduction.

2. Regarding the simulation data:

- In the manuscript, it says "The percent of volumetric breast density (%VBD) was simulated and matched with the clinical data distribution of screening patients (Table 1)". does the simulation data is only matched to the distribution of actual clinical data? 

- Is there any inclusion or exclusion criteria?

- How do you measure or confirm that the simulation data is close to actual clinical data?

3. Please make a flowchart for the processes of Breast Outline Simulation and Breast Density Simulation 

4. Please interpret the findings using the latest guidelines regarding the performances (https://www.hindawi.com/journals/cmmm/2019/1891569/)

5. All point estimators should have associated 95% confidence intervals to allow an appropriate interpretation.

6. Please discuss the relevance for clinical practice of the reported results 

Author Response

Please, see attached file for revisions.

Author Response File: Author Response.docx

Reviewer 2 Report

The paper proposes a virtual clinical trial method to segment both breast tissues and the breast outline in DBT reconstructions. Comments are here: 1. The main contributions should be listed since the paper is not a pure clinical analysis but engineering one. 2. Why not to include realistic data? Do you think the result performance will  decrease significantly? 3. Why is only nnUNet employed?

Author Response

Please, see attached file for revisions.

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

The suggestions and comments have been addressed

Back to TopTop