List of Papers Browse by Subject Areas Author List
Abstract
Mandibular reconstruction is crucial after oral tumor resection, yet current methods rely on premorbid geometric approximations and struggle with achieving reliable donor-native bone union. We propose a Bayesian optimization framework that enhances predicted bone union likelihood and facilitates computer-aided intervention by systematically varying key surgical parameters—resection plane orientation, donor bone positioning, and graft length—across three mandibular regions. Reconstruction performance is evaluated using two cost functions, coupled with a sensitivity analysis on modeling parameters. We validated the model using longitudinal patient-specific data from 5-day and 1-year postoperative CT and MRI scans. Our results show that optimization significantly enhances the predicted likelihood of bone union, with a relative improvement of up to 329% compared to the standard surgical practice. Additionally, validation shows a Dice coefficient of up to 0.76 between union prediction and actual postoperative imaging data. This study suggests that modifying the standard surgical plan can significantly improve bone union, underscoring the need for advanced optimization frameworks in surgical planning. The open-source code is available on GitHub.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2025/paper/3245_paper.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to the Code Repository
https://github.com/hamidreza-aftabi/OsteoOpt
Link to the Dataset(s)
N/A
BibTex
@InProceedings{AftHam_OsteoOpt_MICCAI2025,
author = { Aftabi, Hamidreza and Lloyd, John E. and Ding, Amanda and Sagl, Benedikt and Prisman, Eitan and Hodgson, Antony and Fels, Sidney},
title = { { OsteoOpt: A Bayesian Optimization Framework for Enhancing Bone Union Likelihood in Mandibular Reconstruction Surgery } },
booktitle = {proceedings of Medical Image Computing and Computer Assisted Intervention -- MICCAI 2025},
year = {2025},
publisher = {Springer Nature Switzerland},
volume = {LNCS 15962},
month = {September},
page = {453 -- 463}
}
Reviews
Review #1
- Please describe the contribution of the paper
This paper presents OsteoOpt, a novel Bayesian optimization framework aimed at enhancing bone union likelihood in mandibular reconstruction surgery. It proposes systematic variation and optimization of surgical parameters; specifically resection plane orientation, donor bone positioning, and graft length across three defect types: body (B), symphysis (S), and ramus-body (RB). The framework integrates biomechanical modeling, mesh refinement, and physics-based simulation using patient-specific imaging and validated anatomical models. The optimization process involves two custom cost functions: one focused on maximizing apposition symmetry and another that incorporates a safety factor to reduce mechanical failure risk.
- 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 application of Bayesian optimization to surgical planning is novel and highly relevant to improving clinical outcomes.
- The incorporation of a detailed, dynamic biomechanical simulation with individualized material properties, muscle forces, and plate-screw constructs adds depth to current manuscript.
- Sensitivity analysis on biomechanical parameters confirms robustness of the model.
- 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.
This was one of the strog papers I reviewed this year. I would request the authors to make the following changes to make the current work strong:
- Figure 1 can be used to explain the overall method better. Additional details of the figure title can summarize the process.
- How the highest potential points are selected in EI+ method needs to be discussed
- 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 authors claimed to release the source code and/or dataset upon acceptance of the submission.
- 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/2025/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?
This is an excellent paper that integrates biomechanics, surgical modeling, and Bayesian optimization into a coherent and clinically impactful framework. While there are certain limitations in validation and modeling assumptions, the novelty, rigor, and potential for clinical translation makes OsteoOpt a valuable contribution.
- 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 #2
- Please describe the contribution of the paper
The authors propose a Bayesian optimization framework that enhances predicted bone union likelihood and facilitates computer-aided intervention by systematically varying key surgical parameters—resection plane orientation, donor bone positioning, and graft length—across three mandibular regions. Reconstruction performance is evaluated using two cost functions, coupled with a sensitivity analysis on modeling parameters for Mandibular Reconstruction Surgery.
- 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 paper is well organised 2) The overall method seems to make sense 3) The results are impressive
- 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) Related works section is pretty weak 2) I would expect the authors to add a part in the paper which addresses major limitations/motivations behind this framework 3) Some tables in results would make some sense
- 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 has provided an anonymized link to the source code, dataset, or any other dependencies.
- 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/2025/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?
The paper can be accepted but I would expect some minor modifications
- 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 #3
- Please describe the contribution of the paper
The authors created a simulation to model donor-host bone healing after mandibular reconstruction surgery. The model optimizes parameters for the length and angular placement of donor tissue by assessing the degree of contact between mandible and donor bone tissue (apposition fraction) over a chewing cycle.
- 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 model appears robustly designed and the improvement in simulated apposition fraction over baseline is impressive.
The clear clinical applicability and potential for translation is a big strength.
- 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.
It is difficult to evaluate the impact of the model without more translational research. Would using this model as an intervention in surgical practice improve outcomes? How closely can surgeons match the optimized donor tissue angle and length recommendations of the model? Would using the model to guide surgery increase bone apposition? How much variation is there in patient outcomes overall? What portion of that cannot be explained by differences in bone apposition? These questions should be very relevant to future work, but are admittedly not within the scope of the current abstract.
N=1 for validation of the forward simulation is low.
- 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.
- 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/2025/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.
(6) Strong Accept — must be accepted due to excellence
- Please justify your recommendation. What were the major factors that led you to your overall score for this paper?
This work offers a very promising approach to optimizing and improving outcomes for mandibular reconstruction surgery. It will be very interesting to see how the technical performance translates into clinical performance.
- 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 for their constructive feedback and thoughtful comments. We are encouraged by the early acceptance of the paper and sincerely appreciate the opportunity to further clarify and enhance our work.
(R1W1: Figure 1) We will update Figure 1 as per R1’s recommendation in the camera-ready submission.
(R1W2: EI+ explanation) A detailed explanation of the EI+ metric will be added in the final version to ensure clarity and reproducibility.
(R2W1: Translational research) We share the reviewer’s view that additional experiments are required before clinical translation. These studies are already in progress and will be acknowledged in the future work section.
(R2W2: Usability) We will clarify that optimization is used only during pre-operative planning. Its output informs the virtual cutting-guide design and 3D printing, imposing no added constraints once surgery begins. All optimization parameters—such as tooth sacrifice, implant feasibility, and nerve preservation—were defined by the maxillofacial surgeon based on physiological limits. To accommodate intraoperative variability, we have also developed an image-guided system that provides real-time orientation of the cutting plane and donor segment.
(R2W3: Bone apposition) Our results show that following the optimized plan improves bony apposition. This is supported by patient-specific validation and a biomechanical model comprehensively validated against literature [1], accounting for micromovements due to scarring, condylar displacement, jaw movement, bite force, and muscle activation. We will revise the future-work section to better reflect upcoming experiments.
(R2W4: Patient variation) We agree this is an important point. While outcome variability has not yet been fully studied, we hypothesize that patients with similar defect types—based on Urken’s classification—will exhibit comparable responses. This will be explored further and noted in the final submission.
(R2W5: Number of patients) We are actively working to expand enrollment; however, the study is longitudinal and requires both one-year postoperative CT and MRI scans, which are not routine clinical care. Additional CT scans raise concerns about radiation exposure, particularly for patients receiving adjuvant therapy. These constraints limit recruitment and we will clearly explain these challenges in the final version.
(R2W6: Bone apposition contribution) We agree that bone healing in head-and-neck cancer patients is multifactorial. A study by Sabiq et al. [2] identified only two statistically significant predictors of non-union: (1) free-hand reconstruction and (2) poor native-bone apposition. No associations were found with sex, smoking, adjuvant therapy, or flap type. These findings highlight bone apposition as a key contributor to healing, which we will discuss in the final submission.
(R3W1: Related Work) Due to the 8-page limit in the initial submission, we prioritized describing the proposed method. We will expand the related work section in the final version.
(R3W2: Work motivation) We will clarify this point. Straight osteotomy cuts are commonly used but are not biomechanically ideal—non-union rates can reach 37%. Patient-specific fixation plates have been proposed to address this but increase the risk of plate exposure and reduce flexibility. In contrast, modifying the bone-cut shape offers adaptability and avoids hardware-related issues. Our study focuses on the impact of cut geometry on reconstruction outcomes.
(R3W3: Table) We appreciate the reviewer’s suggestion and will include a table summarizing key results.
References [1] Aftabi et al. To what extent can mastication functionality be restored following mandibular reconstruction surgery? A computer modeling approach. Computer Methods and Programs in Biomedicine, 2024. [2] Sabiq et al. Evaluating the benefit of virtual surgical planning on bony union rates in head and neck reconstructive surgery. Head & Neck, 2024.
Meta-Review
Meta-review #1
- Your recommendation
Provisional Accept
- If your recommendation is “Provisional Reject”, then summarize the factors that went into this decision. In case you deviate from the reviewers’ recommendations, explain in detail the reasons why. You do not need to provide a justification for a recommendation of “Provisional Accept” or “Invite for Rebuttal”.
N/A