List of Papers By topics Author List
| Paper Info | Reviews | Meta-review | Author Feedback | Post-Rebuttal Meta-reviews |
Authors
Maria Chiara Palumbo, Simone Saitta, Marco Schiariti, Maria Chiara Sbarra, Eleonora Turconi, Gabriella Raccuia, Junling Fu, Villiam Dallolio, Paolo Ferroli, Emiliano Votta, Elena De Momi, Alberto Redaelli
Abstract
The treatment of hydrocephalus is based on anatomical landmarks to guide the insertion of an External Ventricular Drain (EVD). This procedure can benefit from the adoption of Mixed Reality (MR) technology.
In this study, we assess the feasibility of a fully automatic MR and deep learning-based workflow to support emergency EVD placement, for which CT images are available and a fast and automatic workflow is needed. The proposed study provides a tool to automatically i) segment the skull, face skin, ventricles and Foramen of Monro from CT scans; ii) import the segmented model in the MR application; iii) register holograms on the patient’s head via a marker-less approach.
An ad-hoc evaluation approach including 3D-printed anatomical structures was developed to quantitatively assess the accuracy and usability of the registration workflow.
Link to paper
DOI: https://link.springer.com/chapter/10.1007/978-3-031-16449-1_15
SharedIt: https://rdcu.be/cVRUV
Link to the code repository
N/A
Link to the dataset(s)
N/A
Reviews
Review #1
- Please describe the contribution of the paper
The paper presents an augmented reality(AR) guidance system for ventriculostomy procedures. The system automatically registers the patient with a preoperative ct by aligning a model of the skin (segmented from CT) with the output of the depth sensor of the AR head-mounted display. Once registered, the segmented ventricules and sugical target (also derived from CT) are displayed in AR.
- 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 paper is very clear and well written *The validation method is sound for every aspect of the system presented *The validation procedure is run with a good number of surgeons
- 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 paper is mostly an integration of existing work and presents very little novelty. *Comparison between guided and blind navigation may be partly unfair
- Please rate the clarity and organization of this paper
Excellent
- 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
All the required methods are described in sufficient detail to reproduce the work, but no code or data is provided.
- Please provide detailed and constructive comments for the authors. Please also refer to our Reviewer’s guide on what makes a good review: https://conferences.miccai.org/2022/en/REVIEWER-GUIDELINES.html
The paper presents a very nice integration of existing methods to solve a specific and important problem. It demonstrates the validity of the method in a rigorous manner. Two question remains:
- The comparison between blind and navigated catheter insertion may be unfair compared to a real surgical procedure as the surgeon is usually informed by the resistance of the anatomy to insertion of the catheter.
- In a real procedure, surgical draping may invalidate registration. The registration procedure presented cannot be performed after surgical draping.
- Rate the paper on a scale of 1-8, 8 being the strongest (8-5: accept; 4-1: reject). Spreading the score helps create a distribution for decision-making
6
- Please justify your recommendation. What were the major factors that led you to your overall score for this paper?
The paper is strong on all aspects but lacks novelty.
- Number of papers in your stack
4
- What is the ranking of this paper in your review stack?
1
- Reviewer confidence
Very confident
- [Post rebuttal] After reading the author’s rebuttal, state your overall opinion of the paper if it has been changed
N/A
- [Post rebuttal] Please justify your decision
N/A
Review #2
- Please describe the contribution of the paper
This study proposes a fully automatic MR and deep learning-based workflow to support emergency EVD placement. It provides a tool to automatically segment essential anatomies and register holograms on the patient’s head via a marker-less approach.
- 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 main strength of the paper is the fully automatic MR and deep learning-based workflow, which can provide fast navigation for the emergency EVD placement.
- 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 main weaknesses are: 1) the display of the MR visualization results is not smooth, with some display delay. 2) this study doesn’t consider the brain shift during the EVD placement.
- 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 reproducibility of the paper is good.
- Please provide detailed and constructive comments for the authors. Please also refer to our Reviewer’s guide on what makes a good review: https://conferences.miccai.org/2022/en/REVIEWER-GUIDELINES.html
The MR guidance is a good way to assist the surgeons to accurately perform the EVD placement. To achieve better results, I recommend the authors to 1) improve the smoothness of the MR guidance. 2) analyze the brain shift during the EVD placement.
- Rate the paper on a scale of 1-8, 8 being the strongest (8-5: accept; 4-1: reject). Spreading the score helps create a distribution for decision-making
5
- Please justify your recommendation. What were the major factors that led you to your overall score for this paper?
Brain shift is an essential issue during the EVD placement. The surgical tool interacts with the brain soft tissue, which will shift due to the external interaction. The target region may move to another position, which will significantly impact the accuracy of the surgery.
- Number of papers in your stack
1
- What is the ranking of this paper in your review stack?
1
- Reviewer confidence
Confident but not absolutely certain
- [Post rebuttal] After reading the author’s rebuttal, state your overall opinion of the paper if it has been changed
N/A
- [Post rebuttal] Please justify your decision
N/A
Review #5
- Please describe the contribution of the paper
- A complete workflow for augmented-reality-guided external ventricular drain
- A deep-learning-based segmentation technique for ventricle segmentation
- 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.
- A complete workflow is proposed
- Meaningful application in the clinic
- 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 novelty of the techniques involved is limited
- Only two anatomical models were used for evaluation, and can be limited in terms of anatomical variability
- Please rate the clarity and organization of this paper
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
Sufficient details have been provided for replication, but due to data limitation, the difficulty can be high.
- Please provide detailed and constructive comments for the authors. Please also refer to our Reviewer’s guide on what makes a good review: https://conferences.miccai.org/2022/en/REVIEWER-GUIDELINES.html
- The solutions introduced in the workflow lack of technical novelty
- As the point cloud-based registration relies on the facial features, registration validation should also consider points in regions that are not in the covered facial area but are often used in patient-image registration in the OR for fair assessment, such as the tragus and points on the head.
- No statistical tests were performed to confirm the results
- The manual EVD technique/protocol used to perform targeting as a comparison to the proposed method should be clearly elaborated. It is not clear if the participants are restricted to the holes as ROI for trajectory planning only. If yes, it is not the most ideal experimental condition.
- Although it is good to use the Foramen of Monro has a target for accuracy assessment, the EVD procedure does not necessarily need to target this point, but rather the catheter should in the ventricle at the level of the Foramen of Monro to ensure the pressure measure is valid. However, other protocols also exist depending on the position of the patient.
- Some discussion regarding the tolerance of accuracy will be appreciated for the particular application.
- The anatomical variability is lacking for the user tests, but it is key to demonstrate the robustness of the proposed method.
- Rate the paper on a scale of 1-8, 8 being the strongest (8-5: accept; 4-1: reject). Spreading the score helps create a distribution for decision-making
5
- Please justify your recommendation. What were the major factors that led you to your overall score for this paper?
Good engineering solution, but lacks of novel technical development and validation is limited.
- Number of papers in your stack
3
- What is the ranking of this paper in your review stack?
1
- Reviewer confidence
Very confident
- [Post rebuttal] After reading the author’s rebuttal, state your overall opinion of the paper if it has been changed
N/A
- [Post rebuttal] Please justify your decision
N/A
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 authors present an augmented reality guidance system for ventriculostomy using markerless registration (where the preoperative CT is aligned by using a model of the skin (segmented from CT) with the output of the depth sensor of an AR head-mounted display). The system was tested with surgeons and the methodology for validation is quite sound.
The reviewers agree about the clarity of the paper but also about the lack of novelty in the techniques. However, given the study I believe the paper would be a valuable addition the the MICCAI conference and encourage the authors to address the reviewers comments in order to make the paper acceptable.
- 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). If this paper is among the bottom 30% of your stack, feel free to use NR (not ranked).
4
Author Feedback
We thank Reviewers for their insightful comments and points of view. We agree that our work is mostly an integration of existing technological solutions, we would like to highlight that our main strength and focus is the automation of the proposed workflow based on mixed reality and deep learning, for which we proved the added benefit of improving EVD placement accuracy in a simulated scenario. Our workflow provides a fast and markerless navigation tool for the emergency EVD placement that otherwise is still a completely blind procedure. Reviewer 1 8.1: We agree with this comment and will add a sentence to the limitations section of our paper. We are already working on a phantom in which the brain and the ventricles are two separate structures with different resistance. However, a reported 50% inaccuracy rate [1] is a meaningful reason to believe that the haptic feedback while inserting the catheter is not enough for the success of the procedure and a tool assisting the surgeon would be of great impact. 8.2: We thank the reviewer for raising this point as it permits us to clarify that the registration procedure would be done before the surgical draping when the position of the head is already set and kept stable for the rest of the procedure. Reviewer 2 5.1: We thank the reviewer for this comment. Unfortunately, the recorded movie doesn’t allow to fully appreciate the smoothness and seamlessness of the holograms’ dynamics and registration. This is due to the limited device’s capability of recording movies, which gives the holograms a “fluctuating” appearance. The operator does not have this issue observing the holograms through the device itself. 5.2: We thank the reviewer for raising this point. Although brain shift is still considered one of the main limitations in image-guided surgery and navigation, the literature suggests that it does not constitute a crucial problem in EVD placement as it is a minimally invasive procedure, thus contributing to less brain retraction and brain tissue damage [2]. Reviewer 5 8.2.We thank the reviewer for this insightful comment. We fully agree with the Reviewer and we will consider this note for further improvements. At present, our work represents a proof of concept to verify the usability and feasibility of such a pipeline that has already been shown to improve registration; however, it can be perfected and our future efforts will surely focus on this aspect. 8.3: Thanks for this comment. We performed a paired t-test that resulted in significantly lower target distances (p=0.001) during hologram-guided procedures than in blind procedures. We will report these results in the final submission, as we agree with the reviewer on the need for complementing our current results. 8.4: Again, thank you for the comment. We will include a sentence to better clarify that the hole on the phantom is big enough not to limit or bias the choice of the insertion point, which is quite standardized.[1] 8.6: We fully agree with the reviewer on this point and we will provide further details in the final version of the paper. It is worth noting that the evaluated accuracy accounts for two superimposed errors: the one given by the measurements device (i.e., the optical tracker) and the one due to possible mismatches between the 3D printed phantom and the holographic model derived from CT images. 8.7: We thank the reviewer for raising this point. This work represents the first study to assess the usability and feasibility of the approach that will be further tested in our next paper using multiple anatomical models. [1]AlAzri, A. et al: Placement accuracy of external ventricular drain when comparing freehand insertion to neuronavigation guidance in severe traumatic brain injury. Acta neurochirurgica 159(8), 1399–1411 (2017) [2] Tang, Y. et al: Efficacy and safety of minimal invasive surgery treatment in hypertensive intracerebral hemorrhage:a systematic review and meta-analysis. BMC neurology, 18(1), 1-11,(2018)