List of Papers Browse by Subject Areas Author List
Abstract
Reliable identification of tissue transitions during ultrasound-guided needle insertion remains challenging, particularly when needle-tip visibility is degraded by imaging geometry or acoustic artifacts. Most prior work focuses on spatial localization, while fewer approaches address mechanically meaningful events such as boundary crossing between adjacent tissues. This study investigates whether proximal vibroacoustic (VA) sensing can detect tissue transitions during insertion. VA signals recorded at the needle hub were analyzed using a time–frequency representation, and statistical similarity to tissue-specific reference segments was quantified using the first-order Wasserstein distance. Transition time was derived from a log-distance ratio signal indicating regime change. Experiments were conducted on 42 controlled insertions in a layered ex-vivo biological phantom with synchronized ultrasound (US) video. Results show consistent regime shifts at tissue boundaries and temporal agreement with US-based annotations across different visibility conditions. These findings indicate that proximal VA sensing captures mechanical interaction changes associated with tissue transitions and may provide complementary feedback during US-guided procedures.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026/paper/3144_paper.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: https://papers.miccai.org/miccai-2026/supp/3144_supp.zip
Link to the Code Repository
N/A
Link to the Dataset(s)
N/A
BibTex
@InProceedings{UrrRob_Where_MICCAI2026,
author = { Urrutia, Robin AND Esmaeili, Nazila AND Boese, Axel AND Matinfar, Sasan AND Davaris, Nikolaos AND Arens, Christoph AND Hansen, Christian AND Illanes, Alfredo},
title = { { Where Is the Needle Tip? VA Sensing Reveals Hidden Needle-Tissue Transitions During US Guidance } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 16893},
month = {September},
page = {pending}
}
Reviews
Review #1
- Please describe the contribution of the paper
This paper presents Vibroacoustic Analysis (VA) to supplement US-guided needle tracking, where different environments cause different vibrations in the needle that can then be unmixed via signal processing and yield exact timings of when the needle traversed from one medium to the next. This is an extension of previously presented work where only VA was performed during initial insertion, not during tissue-to-tissue transition as now explored by the authors. The paper presents an initial demonstration using ex vivo tissue samples embedded in gelatin.
- Please list the major strengths of the paper: you should highlight 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 addresses an important limitation of US-guided needle guidance, which is a known challenge. By adding VA, the authors demonstrate for the first time that tissue-to-tissue needle transitions could be detected even in cases where the needle was poorly visualized under US imaging. The authors use reasonably realistic phantoms and perform 42 seperate insertions, giving great confidence in the presented data being reproducible. The signal processing steps are reasonably well described.
- Please list the major weaknesses of the paper. Please provide details: for instance, if you state that a formulation, way of using data, demonstration of clinical feasibility, or application is not novel, then you must provide specific references to prior work.
Some key parameters are missing, making it impossible for readers to reproduce the work:
- specifications of the VA sensor are absent: what is its bandwidth, sampling rate, and in which direction(s) does it sense? How many DoFs, if more than one?
- Neither the figures nor the video show scale bars, so as reader I am left guessing at the scale of the tissue layers, imaging depths, needle insertion velocities etc. Figs. 3+4 do not have units (fig 4) or any labels (fig 3).
- 42 needle insertions were performed, but it is not stated whether these were performed at different positions, phantoms, velocities, insertion angles, etc. How diverse were these repeat measurements? What was (approximately) the insertion velocity?
In addition, the signal processing could have been described r motivated in greater detail:
- Why was Wasserstein distance chosen as key metric, what is special about it? Would there have been alternatives or superior options?
- “an interactionsensitive frequency band is extracted” is insufficiently clear - the authors do not specify the values of this band here, and only mention it on page 6 “in passing”. Similar choices (e. g. the window length of the moving window, and the exact choice of reference window(s)) should also be clarified.
Finally, the paper is in my opinion too light on the clinical implications:
- a ca. 1s difference between US and VA transition times (Fig. 5) is significant and would arguably make any kind of guidance meaningless. What was the needle insertion speed, i. e. , what were the depth uncertainties corresponding to these timing differences? What precision is required? Arguably, the centimetre-regime (I assume; no scale bars provided) demonstrated here is of limited value, as that level of accuracy is certainly attainable using US imaging - or even markings on the needle. Image guidance becomes crucial at the (sub) millimetre scales; how would the method perform here?
- The video is a useful addition, but mostly casts “doubt” on the accuracy of the extraction of t_tc. I appreciate your algorithms specify this is the true time, but looking at the Wasserstein distance, arguably the regime change occurs BEFORE the software-determined t_tc in all three (high/mid/low visibility) cases. Especially when mm-scale scenarios are targeted, this could cause significant issues.
- The text does not specify, but the video suggests all needle insertions were performed at constant velocity, which is not representative of actual needle placement, where image guidance informs repositioning and motion is often non-uniform. How will the VA method hold up in these cases, as vibrations due to “jagged” motion could well mask the VA signals?
- Please rate the clarity and organization of this paper
Good
- Please comment on the reproducibility of the paper. Please be aware that providing code and data is a plus, but not a requirement for acceptance.
The submission does not mention open access to source code or data, but provides a clear and detailed description of the algorithm to ensure reproducibility.
- Based on your review and your understanding of the MICCAI Scientific Code of Ethics, do you believe this submission may involve a potential ethics concern or violation?
N/A
- Optional: If you have any additional comments to share with the authors, please provide them here. Please also refer to our Reviewer’s guide on what makes a good review and pay specific attention to the different assessment criteria for the different paper categories: https://conferences.miccai.org/2026/en/REVIEWER-GUIDELINES.html
N/A
- Rate the paper on a scale of 1-6, 6 being the strongest (6-4: accept; 3-1: reject). Please use the entire range of the distribution. Spreading the score helps create a distribution for decision-making.
(4) Weak Accept — marginally above the acceptance threshold, but would not mind if rejected, dependent on rebuttal
- Please justify your recommendation. What were the major factors that led you to your overall score for this paper?
The work as presented is of interest and timely. However, without any discussion on future clinical relevance and translational aspects, it is at risk of becoming “white noise”, especially of some of the choices made when designing the algorithms are, presently, a bit ad hoc.
- Reviewer confidence
Very confident (4)
- [Post rebuttal] After reading the authors’ rebuttal, please state your final opinion of the paper.
N/A
- [Post rebuttal] Please justify your final decision from above.
N/A
Review #2
- Please describe the contribution of the paper
This paper describes the use of vibroacoustic (VA) sensing to detect tissue interfaces in a benchtop experiment of 42 needle insertions into a beef liver-chicken breast phantom and is used to complement ultrasound imaging. The study demonstrates the utility of VA signals for identifying the transition despite poor ultrasound visualization and stability within tissues coupled with changes at the boundary.
- Please list the major strengths of the paper: you should highlight 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.
Major strengths: 1.This paper addresses a persistent need in ultrasound imaging to localize needle tips even under variable visibility conditions and presents an approach without the need for burdensome hardware and workflow changes. 2.The evaluation is generally comprehensive within the space constraints of the paper and strongly supports the validity of the proposed approach. 3.The paper is well-written and logical, with attractive, easily interpreted figures.
- Please list the major weaknesses of the paper. Please provide details: for instance, if you state that a formulation, way of using data, demonstration of clinical feasibility, or application is not novel, then you must provide specific references to prior work.
Major weaknesses: 1.The primary weakness of this paper is the incremental novelty of the work. Although the paper well-done and does not overstate the impact, the contributions represent only small advancements over previous works and there appears to be missing relevant works on similar topics that are not acknowledged. For example, Sühn et al. (Vibro-acoustic sensing of tissue-instrument-interactions allows a differentiation of biological tissue in computerised palpation. Comput Biol Med. 2023 Sep;164:107272.doi: 10.1016/j.compbiomed.2023.107272) has previously described the intra-tissue stability listed in this paper as a main contribution but this work is not referenced or differences elucidated. 2.I would have liked to have seen a better ground truth used for comparison of the boundary timing as opposed to the US recording, given that one of the best use cases for this technology is when US visibility is poor. The authors acknowledge “timing differences between VA detection and US annotation increased under low-visibility conditions, this is consistent with greater uncertainty in manual tip identification” suggesting that an external verification method is necessary to assess true agreement.
- Please rate the clarity and organization of this paper
Good
- Please comment on the reproducibility of the paper. Please be aware that providing code and data is a plus, but not a requirement for acceptance.
The submission does not mention open access to source code or data, but provides a clear and detailed description of the algorithm to ensure reproducibility.
- Based on your review and your understanding of the MICCAI Scientific Code of Ethics, do you believe this submission may involve a potential ethics concern or violation?
N/A
- Optional: If you have any additional comments to share with the authors, please provide them here. Please also refer to our Reviewer’s guide on what makes a good review and pay specific attention to the different assessment criteria for the different paper categories: https://conferences.miccai.org/2026/en/REVIEWER-GUIDELINES.html
The major revisions are already described in the weaknesses section above. A few additional minor items:
1.In the Introduction, a more comprehensive description of the limitations of embedded force sensing approaches would be beneficial, as this is a more similar approach to the one proposed than the image-based methodologies. 2.There are some minor grammatical errors. The first paragraph of 2.2 contains multiple errors impacting the readability and clarity of this section. 3.Limitations are only superficially mentioned in the Discussion but should be more specifically identified and expressed.
- Rate the paper on a scale of 1-6, 6 being the strongest (6-4: accept; 3-1: reject). Please use the entire range of the distribution. Spreading the score helps create a distribution for decision-making.
(4) Weak Accept — marginally above the acceptance threshold, but would not mind if rejected, dependent on rebuttal
- Please justify your recommendation. What were the major factors that led you to your overall score for this paper?
Overall, this paper is well-written and interesting on a long-standing challenging topic in the image-guidance space. It provides promising results using techniques that would be of interest to the MICCAI community; however, has limited novel additions to the field and some methodological improvements in the evaluation scheme would improve the work.
- Reviewer confidence
Confident but not absolutely certain (3)
- [Post rebuttal] After reading the authors’ rebuttal, please state your final opinion of the paper.
N/A
- [Post rebuttal] Please justify your final decision from above.
N/A
Review #3
- Please describe the contribution of the paper
The main contribution of this paper is a needle-guided interventional system that detects tissue boundaries using vibro-acoustic signal analysis. This feature can be particularly helpful during US-guided interventions where the needle tip may be difficult or impossible to see directly, or when the needle needs to be placed within a tissue region defined by fascial boundaries. This project proposes a transducer placed at the needle’s distal end (external to the patient) to record vibrations generated as the needle penetrates fascial boundaries. The two main contributions include demonstrating that tissue-to-tissue transitions can be identified from proximal VA measurements, even when needle visibility is limited, and that the VA signal is stable within tissue type but shows distinct changes at boundary crossings. These findings support proximal VA sensing as a complementary perception channel and provide a rationale for interaction-based tissue characterization. This approach is significant because it adds an inexpensive sensor to the proximal end of the needle via a standard Luer lock connection, without otherwise changing the needle-guidance configuration.
- Please list the major strengths of the paper: you should highlight 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 is a compelling example of how multi-sensor input can complement a widely used procedure to address a perennial problem! It relies on capturing information (sound produced by the interaction of a needle with tissue) that is inherently present for every procedure, but is not captured. This approach requires a simple, inexpensive attachment to a standard needle guidance setup that causes minimal disruption to the standard workflow. It is readily implementable in the clinic. The system is entirely passive. It clearly complements the visualization of needle position relative to tissue boundaries when ultrasound does not provide this information.
- Please list the major weaknesses of the paper. Please provide details: for instance, if you state that a formulation, way of using data, demonstration of clinical feasibility, or application is not novel, then you must provide specific references to prior work.
The current display modality is somewhat non-intuitive. A sentence indicating how this might actually be used in the clinic – what the user interface to this additional information might look like - would be helpful. The rationale for using CWT and the Wasserstein distance framework. is not immediately clear. A brief discussion would be appreciated.
- Please rate the clarity and organization of this paper
Good
- Please comment on the reproducibility of the paper. Please be aware that providing code and data is a plus, but not a requirement for acceptance.
The submission does not provide sufficient information for reproducibility.
- Based on your review and your understanding of the MICCAI Scientific Code of Ethics, do you believe this submission may involve a potential ethics concern or violation?
N/A
- Optional: If you have any additional comments to share with the authors, please provide them here. Please also refer to our Reviewer’s guide on what makes a good review and pay specific attention to the different assessment criteria for the different paper categories: https://conferences.miccai.org/2026/en/REVIEWER-GUIDELINES.html
N/A
- Rate the paper on a scale of 1-6, 6 being the strongest (6-4: accept; 3-1: reject). Please use the entire range of the distribution. Spreading the score helps create a distribution for decision-making.
(5) Accept — should be accepted, independent of rebuttal
- Please justify your recommendation. What were the major factors that led you to your overall score for this paper?
It is innovative. Provides useful clinically relevant information; Has the potential to streamline needle-guided interventions. A company already exists to manufacture the sensor device – so it can be readily deployed. It is non-invasive and subject to minimal regulatory requirements.
- Reviewer confidence
Very confident (4)
- [Post rebuttal] After reading the authors’ rebuttal, please state your final opinion of the paper.
N/A
- [Post rebuttal] Please justify your final decision from above.
N/A
Author Feedback
N/A
Meta-Review
Meta-review #1
- Your recommendation
Provisional Accept
- Please justify your decision. 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.
This submission proposes a needle tip tracking methodology in the context of US-guided interventions where the target may not always be visible. The authors propose to track surrounding tissue motions as a proxy for needle motion whenever this structure is not visible. The method is validated in repeated phantom trials under different levels of visibility.
