List of Papers Browse by Subject Areas Author List
Abstract
Medical imaging plays a crucial role in assessing knee osteoarthritis (OA) risk by enabling early detection and disease monitoring. Recent machine learning methods have improved risk estimation (i.e., predicting the likelihood of disease progression) and predictive modelling (i.e., the forecasting of future outcomes based on current data) using medical images, but clinical adoption remains limited due to their lack of interpretability. Existing approaches that generate future images for risk estimation are complex and impractical. Additionally, previous methods fail to localize anatomical knee landmarks, limiting interpretability. We address these gaps with a new interpretable machine learning method to estimate the risk of knee OA progression via multi-task predictive modelling that classifies future knee OA severity and predicts anatomical knee landmarks from efficiently generated high-quality future images. Such image generation is achieved by leveraging a diffusion model in a class-conditioned latent space to forecast disease progression, offering a visual representation of how particular health conditions may evolve. Applied to the Osteoarthritis Initiative dataset, our approach improves the state-of-the-art (SOTA) by 2%, achieving an AUC of 0.71 in predicting knee OA progression while offering ~9× faster inference time.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2025/paper/1931_paper.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: https://papers.miccai.org/miccai-2025/supp/1931_supp.zip
Link to the Code Repository
N/A
Link to the Dataset(s)
BibTex
@InProceedings{ButDav_Risk_MICCAI2025,
author = { Butler, David and Hilton, Adrian and Carneiro, Gustavo},
title = { { Risk Estimation of Knee Osteoarthritis Progression via Predictive Multi-task Modelling from Efficient Diffusion Model using X-ray Images } },
booktitle = {proceedings of Medical Image Computing and Computer Assisted Intervention -- MICCAI 2025},
year = {2025},
publisher = {Springer Nature Switzerland},
volume = {LNCS 15973},
month = {September},
page = {551 -- 561}
}
Reviews
Review #1
- Please describe the contribution of the paper
This paper proposes a machine learning method to estimate the risk of knee osteoarthritis (OA) progression through multi-task predictive modeling that classifies future knee OA severity and predicts anatomical knee landmarks from generated future images. This is achieved by using a diffusion model in a class-conditioned latent space.
- 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 authors introduce an interpretable machine learning model for knee OA risk estimation via multi-task prediction modeling for KL classification and anatomical knee landmark localization using future images generated by a diffusion model. Also, they propose a compact diffusion model for the generation of future OA X-ray images conditioned only by current images.
- 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 paper lacks details.
The flowchart of the proposed model is not clear enough. - 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.
- 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?
Originality in the use of diffusion models beyond the original purpose for which they were intended.
- 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
The authors propose a novel interpretable AI method to estimate the risk of knee OA progression through a multi-task predictive modeling framework. This approach simultaneously classifies future knee OA severity and predicts anatomical landmarks.
- 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 well-written manuscript with comprehensive details of the proposed methods. Risk prediction of knee OA is a critical and timely research problem. The proposed method offers interpretable results while demonstrating improved performance over SOTA.
- 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.
KL grade progression in OA is generally considered irreversible. For example, if the baseline KL grade is 3, the KL grade at 12 months is typically ≥ 3. However, this irreversibility assumption does not appear to be incorporated into the current modeling approach.
- 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?
Risk prediction of knee OA is a critical and timely research problem. The proposed method offers interpretable results while demonstrating improved performance over SOTA. KL grade progression in OA is generally considered irreversible. For example, if the baseline KL grade is 3, the KL grade at 12 months is typically ≥ 3. However, this irreversibility assumption does not appear to be incorporated into the current modeling approach.
- 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 #3
- Please describe the contribution of the paper
They proposed a novel and interpretable machine learning model for assessing the risk of knee osteoarthritis (OA) progression. The approach employs multi-task predictive modeling to perform future knee OA severity classification and anatomical landmark prediction from efficiently generated future knee images. The method was evaluated on a publicly available dataset, demonstrating superior performance in terms of AUC for knee OA progression prediction, along with a 9× faster inference time compared to SOTA approache.
- 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 is well written and easy to follow, with a clear structure and logical flow.
-
The proposed application is clinically meaningful, addressing a relevant and impactful medical challenge.
-
The experiments demonstrate superior performance compared to state-of-the-art (SOTA) methods, highlighting the effectiveness of the approach.
-
Evaluation on a publicly available dataset promotes reproducibility and transparency, enabling other researchers to verify results and build upon the work.
-
The inclusion of an ablation study enhances the transparency of the method. By analyzing the contributions of different model components, the study provides valuable insights for further refinement and optimization.
-
- 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.
-
Limited Evaluation Metrics: The paper relies exclusively on mean AUC (mAUC) as the evaluation metric. Incorporating additional performance measures (e.g., accuracy, F1-score, sensitivity, specificity) would offer a more comprehensive assessment of the model’s effectiveness across different dimensions.
-
Single Dataset Evaluation: While evaluating a new model on a single dataset is a common initial step, it is generally advisable to test on multiple datasets. This would strengthen the evidence for the model’s generalizability and help mitigate the risk of overfitting to the specific characteristics of the chosen dataset.
-
- 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.
- 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 authors proposed a novel method for knee osteoarthritis (OA) risk assessment, leveraging a diffusion model to generate future knee images conditioned on current ones. This approach enhances the interpretability of the prediction process by providing a visual representation of potential disease progression. Given that knee OA is a prevalent condition and its early estimation is critical for effective treatment planning, the proposed method holds significant clinical relevance and potential for medical application.
- 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
Author Feedback
We would like to thank the reviewers for their constructive comments and feedback.
In the camera-ready version, we will report F1 score, sensitivity, and specificity for the system. We believe accuracy is not meaningful due to significant class imbalance.
We will clarify that samples showing a decrease in KL grade over 12 months are assumed to reflect noise and are therefore treated as stable in our study. Although the current system cannot predict decreases in KL grade, future work will explore methods to explicitly prevent the future classifier from assigning a lower KL grade than the current one.
Finally, we plan to evaluate our system on additional datasets in future work.
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