List of Papers Browse by Subject Areas Author List
Abstract
Subretinal injection is a delicate vitreoretinal procedure requiring precise needle placement within the subretinal space while avoiding perforation of the retinal pigment epithelium (RPE), a layer directly beneath the target with extremely limited regenerative capacity. To enhance depth perception during cannula advancement, intraoperative optical coherence tomography (iOCT) offers high-resolution cross-sectional visualization of needle–tissue interaction; however, interpreting these images requires sustained visual attention alongside the en face microscope view, thereby increasing cognitive load during critical phases and placing additional demands on the surgeon’s proprioceptive control. In this paper, we propose a structured, real-time sonification framework designed for extensible mapping of iOCT-derived anatomical features into perceptual auditory feedback. The method employs a physics-inspired acoustic model driven by segmented retinal layers from a stream of iOCT B-scans, with needle motion and injection-induced retinal layer displacements serving as excitation inputs to the sound model, enabling perception of tool position and retinal deformation. In a controlled user study (n=34), the proposed sonification achieved high retinal layer identification accuracy and robust detection of retinal deformation–related events, significantly outperforming a state-of-the-art baseline in overall event identification (83.4% vs. 60.6%, p < 0.001), with gains driven primarily by enhanced detection of injection-induced retinal deformation. Participants also reported higher confidence with the proposed method correlating with correctness, indicating the auditory mapping was perceptually interpretable. Evaluation by experts (n=4) confirmed the clinical relevance and potential intraoperative applicability of the method. These results establish structured iOCT sonification as a viable complementary modality for real-time surgical guidance in subretinal injection.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026/paper/2423_paper.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: https://papers.miccai.org/miccai-2026/supp/2423_supp.zip
Link to the Code Repository
https://github.com/luisdavid64/ioct-subretinal-sonification
Link to the Dataset(s)
N/A
BibTex
@InProceedings{ReyLui_PhysicsBased_MICCAI2026,
author = { Reyes Vargas, Luis D. AND Ruozzi, Veronica AND Ross, Andrea K. M. AND Dehghani, Shervin AND Sommersperger, Michael AND Faridpooya, Koorosh AND Nasseri, Mohammad Ali AND Fairhurst, Merle AND Navab, Nassir AND Matinfar, Sasan},
title = { { Physics-Based iOCT Sonification for Real-Time Interaction Awareness in Subretinal Injection } },
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
1.The model is straightforward to construct and appears to be effective. The framework utilizes a mass-spring-damper system that is anchored to segmented retinal anatomy derived from intraoperative OCT. 2.unlike methods that focus primarily on tool localization, this system explicitly encodes interaction-driven retinal deformation.
- 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.
1.The system employs a two-dimensional mass-spring-damper acoustic model anchored to anatomical segmentations. 2.The full processing pipeline operates at approximately 36 FPS, ensuring it is compatible with interactive surgical workflows. 3.The framework showed particular strength in identifying subretinal bleb formation, with a 21.8% point increase in identification accuracy over the baseline.
- 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.
1.the accuracy for identifying the most critical safety boundaries showed only minor improvements or even slight declines. 2.Since damage to the RPE is irreversible and a primary concern in this surgery, the lack of robust improvement in this specific area is a limitation. 3.The physical parameters (mass, stiffness, damping) for the sound model are hand-crafted based on anatomical class labels and intensity statistics. These fixed mappings might not account for patient-specific variations in tissue properties, such as differences in retinal stiffness or thickness due to disease states.
- Please rate the clarity and organization of this paper
Satisfactory
- 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?
This deformation-aware approach effectively translates iOCT imaging into intuitive auditory cues while smartly using temporal jitter to flag low-confidence segmentation. However, this brilliance is tempered by the fact that the method showed no statistically significant improvement, and even a slight numerical decline, in detecting critical RPE contact. Combined with a participant pool heavily skewed toward novices (30 vs. 4 experts) and reports of sound roughness that could trigger alarm fatigue, the system proves its potential as a training tool but leaves its clinical safety edge unproven.
- Reviewer confidence
Somewhat confident (2)
- [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
The main contribution of this paper is a real time sonification framework for intraoperative OCT during subretinal injection. The goal is to convert cross sectional iOCT information into auditory feedback so that the surgeon can better perceive needle depth and tissue interaction without relying entirely on a second visual stream. This is clinically relevant because subretinal injection requires very precise control near the RPE, where even small overshoot can cause irreversible damage.
A second key contribution is that the proposed sonification goes beyond simple proximity cueing and explicitly encodes interaction driven deformation, especially subretinal bleb formation, using a physics inspired acoustic model anchored to segmented retinal anatomy. The paper’s main experimental claim is that this structured sonification is more interpretable and more effective than a parameter mapping baseline for identifying clinically relevant events such as ILM contact, RPE contact, and bleb onset, while remaining feasible for real time use.
- 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.
A major strength of the paper is that it addresses a clearly defined clinical problem in a procedure where the safety margin is extremely small. The manuscript explains that the macular retina is only about 250 µm thick on average and that the RPE lies directly beneath the target and has very limited regenerative capacity, which makes precise depth control essential during subretinal injection. The proposed use of sonification is therefore well motivated, because current workflows require surgeons to interpret both the en face microscope view and a cross sectional iOCT stream during a critical insertion phase, which can increase cognitive load and divide attention.
Another major strength is that the method is not only conceptually interesting but also supported by concrete results. The framework uses a physics inspired mass spring damper sound model tied to segmented ILM, retina, RPE, and needle geometry, and explicitly incorporates deformation aware cues rather than only static proximity information. In the user study with 34 analyzed participants, the proposed method improved overall event identification from 60.6% to 83.4% and showed its largest gain in bleb detection, improving from 63.6% to 85.5% with p < 0.001.The full system also ran in 27.8 ± 1.5 ms per frame, about 36 FPS, which supports its practical feasibility for real time use.
- 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.
A major weakness is that the evaluation stops at event identification accuracy rather than showing impact on the actual procedure. The user study demonstrates improved recognition of ILM contact, RPE contact, and bleb onset, but it does not test whether sonification improves needle placement, reduces overshoot, lowers RPE injury risk, or improves subretinal injection success during a realistic task. Therefore, the current evidence supports perceptual usefulness, but not yet clinical performance benefit.
A second weakness is that the method depends heavily on segmentation and hand crafted sonification design choices, but robustness is not analyzed in enough detail. The framework uses a pre trained U-Net, confidence weighted spline fitting, and a manual mapping from anatomical class and intensity to physical sound parameters, yet there is little quantitative discussion of how segmentation errors, missed layer boundaries, or parameter choices affect the final audio output. The expert assessment is also based on only 4 participants, which is too limited to draw strong conclusions about intraoperative usability.
- Please rate the clarity and organization of this paper
Satisfactory
- 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.
(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?
I lean toward accept because the paper addresses a clinically meaningful problem and presents a technically coherent solution with encouraging experimental support. The strongest aspects are the clear motivation, the structured physics based sonification design, and the fact that the method goes beyond simple proximity cueing to capture interaction driven deformation, especially bleb formation, which is highly relevant in subretinal injection. The evaluation is also stronger than many early stage guidance papers, with simulated and ex vivo data, a user study, runtime analysis, and expert feedback. The reported improvement in overall event identification from 60.6% to 83.4%, with the largest gains in bleb detection, makes the contribution practically interesting.
This is not a strong accept for me because the evaluation still stops short of showing impact on actual surgical performance, and the framework depends on segmentation quality and several hand crafted design choices whose robustness is not fully characterized. Still, I think the paper is above threshold because it is well motivated, methodologically thoughtful, and validated enough to support the core claim that structured iOCT sonification can serve as a meaningful complementary guidance modality.
- 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 proposed framework mainly combines existing components, including retinal layer/needle segmentation, spline-based temporal smoothing, and a physics-inspired sonification model, with the main novelty being their adaptation to the subretinal injection setting. Specifically, the method introduces a deformation proxy based on local ILM–RPE separation changes and a hand-crafted mapping from anatomy to sound parameters. The core contribution is a real-time sonification system that provides deformation-aware feedback to improve bleb detection and overall interaction awareness during subretinal injection.
- 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 real-time system aspect together with the user study are positive points.
- 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.
1.The overall contribution does not feel strong enough. 2.The proposed framework mainly combines existing components, with the main novelty being their adaptation to the subretinal injection setting. Authors should better clarify what is genuinely new at the methodological level. 3.Several key design choices are largely hand-crafted and not sufficiently justified. This limits the technical depth of the work. 4.The experimental validation is limited. The main comparison is against a single parameter-mapping baseline, and the evaluation does not include broader comparisons to other sonification strategies or more realistic workflow settings. 4.The reported gains are mainly driven by improved bleb detection, while improvements on other key events are limited.
- Please rate the clarity and organization of this paper
Satisfactory
- 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.
(3) Weak Reject — marginally below the acceptance threshold, but would not mind if accepted, dependent on rebuttal
- Please justify your recommendation. What were the major factors that led you to your overall score for this paper?
1.The paper addresses an interesting and clinically relevant problem, but the overall contribution does not feel strong enough. The proposed framework mainly combines existing components, including retinal layer/needle segmentation, spline-based temporal smoothing, and a physics-inspired sonification model, with the main novelty being their adaptation to the subretinal injection setting. Authors should better clarify what is genuinely new at the methodological level and what is inherited from prior sonification and iOCT processing pipelines. 2.The method appears somewhat heuristic. Several key design choices, such as the mapping from anatomy to sound parameters and the deformation proxy based on local ILM–RPE separation changes, are largely hand-crafted and not sufficiently justified. This limits the technical depth of the work. The paper would benefit from stronger motivation for these choices, together with more ablation studies showing that the design is robust and not overly dependent on manual parameter tuning. 3.The experimental validation is somewhat limited. The main comparison is against a single parameter-mapping baseline, and the evaluation does not include broader comparisons to other sonification strategies or more realistic workflow settings. The authors could strengthen the empirical section by adding stronger baselines and, if feasible, comparisons under more comprehensive settings. 4.The reported gains are mainly driven by improved bleb detection, while improvements on other key events are limited. This makes the empirical evidence less convincing for the broader claim of improved overall interaction awareness. The authors should either narrow the main claim and emphasize deformation-aware feedback.
- 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 #4
- Please describe the contribution of the paper
In this work, the authors present a sonification method for visualizing instrument-tissue interaction status using real-time OCT imaging. By developing a series of models to encode OCT signal changes into acoustic output, this approach allows operators to more intuitively perceive and integrate critical surgical information.
- 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.
1.This work indeed addresses a practical problem in clinical practice. 2.The results section demonstrates that the proposed method achieves superior performance compared to the baseline methods. 3.To address tissue deformation in real-time imaging, the authors designed specific methods that are absent in traditional auditory feedback based on preoperative images. 4.The video in the supplementary materials effectively showcases the results of the work.
- 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.
1.The manuscript does not seem to address the consistency across different cases. How many puncture phantoms were used in the experiments? Furthermore, are the sound rendering effects identical across different phantoms and varying operator techniques? 2.The sound rendering appears to rely on image segmentation. Do all cases consistently yield such ideal segmentation results?
- Please rate the clarity and organization of this paper
Satisfactory
- 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.
(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?
This work addresses a practical clinical problem with a relatively novel research approach, and the findings demonstrate promising clinical applicability.
- 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
Author Feedback
We thank the reviewers and meta-reviewers for their encouraging and valuable feedback. We are pleased that the work was recognized as addressing a clinically meaningful problem with a technically coherent and practically relevant solution.
Several reviewer comments highlighted important future research directions that we are actively pursuing. In particular, we are currently investigating less hand-crafted and more adaptive parameterizations for the sonification model, as well as broader validation studies to further evaluate procedural benefit and intraoperative usability.
Once again, we appreciate the reviewers’ thoughtful suggestions and constructive feedback.
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.
The paper was evaluated by reviewers with expertise in the field who have enthusiasm for this work, e.g., “…clincally meaningful problem and presents a technically coherent solution with encouraging experimental support.”