Paper Info Reviews Meta-Review Author Feedback Post-rebuttal Meta-Reviews

Authors

Peng Wan, Chunrui Liu, Fang Chen, Jing Qin, Daoqiang Zhang

Abstract

Contrast-enhanced ultrasound (CEUS) has been one of the most promising imaging techniques in tumor differential diagnosis since the real-time view of intra-tumor blood microcirculation. Existing studies primarily focus on extracting those discriminative imaging features whereas lack medical explanations. However, accurate quantitation of some clinical experience-driven indexes regarding intra-tumor vascularity, such as tumor infiltration and heterogeneity, still faces significant limitations. To tackle this problem, we present a novel scheme to identify quantitative and explanatory tumor indexes from dynamic CEUS sequences. Specifically, our method mainly comprises three steps: 1) extracting the stable pixel-level perfusion pattern from dynamic CEUS imaging using an improved stable principal component pursuit (SPCP) algorithm; 2) performing local perfusion variation comparison by the proposed Phase-constrained Wasserstein (PCW) distance; 3) estimating three clinical knowledge-induced tumor indexes, i.e. infiltration, regularity, and heterogeneity. The effectiveness of this method was evaluated on our collected CEUS dataset of thyroid nodules, and the resulting infiltration and heterogeneity index with p < 0.05 between different pathological types validated the efficacy of this quantitation scheme in thyroid nodule diagnosis.

Link to paper

DOI: https://doi.org/10.1007/978-3-030-87237-3_61

SharedIt: https://rdcu.be/cymbo

Link to the code repository

N/A

Link to the dataset(s)

N/A

Reviews

Review #1

Please describe the contribution of the paper

Using Dynamic Contrast Enhanced Ultrasound to identify quantitative and explanatory tumor indexes. (CEU)
Please list the main strengths of the paper; you should write about a novel formulation, an original way to use data, demonstration of clinical feasibility, a novel application, a particularly strong evaluation, or anything else that is a strong aspect of this work. Please provide details, for instance, if a method is novel, explain what aspect is novel and why this is interesting.
1. Novel method : using DCEU for quantitative evaluation indexes of tumor.
2. Boxplot diagram helps to explain the result achievement.
3. Methods to be used were explained comprehensively.
Please list the main weaknesses of the paper. Please provide details, for instance, if you think a method is not novel, explain why and provide a reference to prior work.
1. Experimental setup of the research explanation is not enough for understanding of the process which can lead to confusion and misunderstanding. Maybe more explanation such as written for section method needed here.
2. Tools used for the experimentation were not mentioned, difficult to fathom how results were achieved. 3.Does author did comparison study of the method and how to achieve the indexes presented.
Please rate the clarity and organization of this paper

Very Good
Please comment on the reproducibility of the paper. Note, that authors have filled out a reproducibility checklist upon submission. Please be aware that authors are not required to meet all criteria on the checklist - for instance, providing code and data is a plus, but not a requirement for acceptance

No reproducibility criteria was selected. Citation for existing dataset were included in the paper writing.
Please provide detailed and constructive comments for the authors. Please also refer to our Reviewer’s guide on what makes a good review: https://miccai2021.org/en/REVIEWER-GUIDELINES.html
1. Very comprehensive methods used for the research were explained in detail.
2. It would be helpful to include diagram in the explaination of method.
Please state your overall opinion of the paper

accept (8)
Please justify your recommendation. What were the major factors that led you to your overall score for this paper?
1. Experiment done and results discussed in the paper help justify the proposed method.
What is the ranking of this paper in your review stack?

5
Number of papers in your stack

5
Reviewer confidence

Very confident

Review #2

Please describe the contribution of the paper

A method to quantify dynamic contrast-enhanced ultrasound (CEUS) images with is proposed. Three new measures are derived from the acquired signal on a pixel-by-pixel and analyzed for their usefulness as tumor indexes (tumor infiltration, shape regularity, and perfusion heterogeneity). The method is applied to the data acquired from 55 subjects with three pathological types of thyroid nodules showing some of the indexes can discriminate benign from malignant.
Please list the main strengths of the paper; you should write about a novel formulation, an original way to use data, demonstration of clinical feasibility, a novel application, a particularly strong evaluation, or anything else that is a strong aspect of this work. Please provide details, for instance, if a method is novel, explain what aspect is novel and why this is interesting.
This paper has the following strengths:
- Quantitative measures from CEUS, including novel algorithms to extract stable perfusion pattern to account for irregular microbubble destruction leading to inconsistent intensity changes.
- Use of phase-constrained Wasserstein distance for perfusion pattern analysis.
Please list the main weaknesses of the paper. Please provide details, for instance, if you think a method is not novel, explain why and provide a reference to prior work.
Some weaknesses:
- (minor) Some more details about the dataset could have been included (US equipment/vendor; same or different operators; acquisition parameters)
- (trivial) Need to define which of the three pathological types made up the benign and malignant classes.
- (minor) boxplots are presented for showing tumor indexes between three types but no statistical comparisons (though the boxplots seem to imply no statistically significant differences).
Please rate the clarity and organization of this paper

Very Good
Please comment on the reproducibility of the paper. Note, that authors have filled out a reproducibility checklist upon submission. Please be aware that authors are not required to meet all criteria on the checklist - for instance, providing code and data is a plus, but not a requirement for acceptance

The work will be difficult to reproduce as the data and code are not available and there are some parameters used without values specified.
Please provide detailed and constructive comments for the authors. Please also refer to our Reviewer’s guide on what makes a good review: https://miccai2021.org/en/REVIEWER-GUIDELINES.html

Overall a well-written paper. Addressing the noted weaknesses would lead to an excellent paper.
Please state your overall opinion of the paper

accept (8)
Please justify your recommendation. What were the major factors that led you to your overall score for this paper?

Novel application for generating tumor indexes from dynamic CEUS. Presentation of methods and results is organized and well written.
What is the ranking of this paper in your review stack?

3
Number of papers in your stack

5
Reviewer confidence

Very confident

Review #3

Please describe the contribution of the paper

The paper proposed an approach in which three quantitative tumor indexes are extracted from contrast-enhanced ultrasound. The introduced indexes might be useful in classification of patients which is important in timely diagnosis and treatment of diseases.
Please list the main strengths of the paper; you should write about a novel formulation, an original way to use data, demonstration of clinical feasibility, a novel application, a particularly strong evaluation, or anything else that is a strong aspect of this work. Please provide details, for instance, if a method is novel, explain what aspect is novel and why this is interesting.

The introduced indexes are novel while a well designed approach for extraction is proposed.
Please list the main weaknesses of the paper. Please provide details, for instance, if you think a method is not novel, explain why and provide a reference to prior work.
- The proposed indexes are not visualized in the feature domain to see how distinguishable they are.
- It is not clear why do the authors call the proposed indexes as clinical knowledge induced tumor indexes!
- The assumptions of the statistical analysis are not investigated to see whether the result of applied test is valid or not.
- The comparison between proposed method and other approached for tumor classification is not completed.
Please rate the clarity and organization of this paper

Very Good
Please comment on the reproducibility of the paper. Note, that authors have filled out a reproducibility checklist upon submission. Please be aware that authors are not required to meet all criteria on the checklist - for instance, providing code and data is a plus, but not a requirement for acceptance

I would think that the method is well explained and the results are reproducable.
Please provide detailed and constructive comments for the authors. Please also refer to our Reviewer’s guide on what makes a good review: https://miccai2021.org/en/REVIEWER-GUIDELINES.html
Here are my comments/questions:
- What does the abbreviation AUC stand for? is it area under the perfusion curve?
- I would be beneficial to compare the performance of the proposed method with other approached for tumor classification such as quantitative ultrasound, electrography, etc.
- It is necessary to investigate the distribution of your data. Are the data normally distributed? The corresponding test has to be completed before running t-test. I am not sure whether your result are valid or not.
- Details regarding your imaging settings such as transmit center frequency, sampling frequency, imaging technique, etc are missing.
- More information regarding the preprocessing steps that you have applied on the original Bmode images helps readers to better understand your method. The current explanation is vague.
- The proposed indexes have to be visualized in the feature domain to see how distinguishable they are.
Please state your overall opinion of the paper

accept (8)
Please justify your recommendation. What were the major factors that led you to your overall score for this paper?

Please see the answers to questions 3,4, and 7.
What is the ranking of this paper in your review stack?

1
Number of papers in your stack

5
Reviewer confidence

Somewhat confident

Primary Meta-Review

Please provide your assessment of this work, taking into account all reviews. Summarize the key strengths and weaknesses of the paper and justify your recommendation. In case you deviate from the reviewers’ recommendations, explain in detail the reasons why. In case of an invitation for rebuttal, clarify which points are important to address in the rebuttal.

The paper proposes a novel scheme for quantitative evaluation of contrast enhanced ultrasound (CEUS). Generally, the paper touches base on an interesting topic to the medical image computing, and there is a consensus among all reviewers about the novelty, clarity and merits, of the presented work. The paper is also well-organized and easy to follow. A few comments and suggestions related to datasets details and experiments settings (for reproducibility) should be addressed in the camera-ready version. Please add summary of the quantitative results to the abstract. I also agree with R3 to include a feature-domain visualization for the extracted index as well as a comparison with other approaches for tumor classification such as quantitative ultrasound. Please also define abbreviation (e.g., AUC)
What is the ranking of this paper in your stack? Use a number between 1 (best paper in your stack) and n (worst paper in your stack of n papers).

2

Author Feedback

N/A

back to top

Identifying Quantitative and Explanatory Tumor Indexes from Dynamic Contrast Enhanced Ultrasound