- Rating
- 1(−1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1(−1)
Read review
Paper summary
The paper proposes latent flow matching controlled by treatment adaptation and patient history, as well as time conditioning to produce the next state. Additionally, they collected multiple public datasets and are expected to share a homogenous test space for world models in GBM and Metastasis.
Critical strengths
Their dataset is huge and the comparison methods comprehensive. They actually show an improvement over trivial baselines like just keeping the last image and blurring the lesion, which is not the case for most baselines. To the best of my knowledge it is a novel conditioning approach well suited to the problem.
Critical weaknesses
- It is unclear why the authors combined metastasis and GBM datasets and the value of the dataset:
Both exhibit vastly different growth trajectories and cannot be distinguished from the MRI[1]. In some cases pathology reports are necessary to distinguish them. Given that the growth is not predictable from the images, it at least explains why the performance of all methods is really bad and often worse than just using the last baseline image. Even growth dice of their method is 0.18. One thing to note is that the registration between the cases does not look pixel accurate in Fig 6. Hence pixel wise metrics might be misleading and at least perceptual ones like LPIPS are preferable, where their method performs worse than baseline. In the figure there is SSIM and DICE and in the Table is PSNR, LPIPS and Change Agreement. The dice is reported in the appendix. Why not report the SSIM as well? In this regard, in Figure 6, is it actually predicting any growth? To me all the models are either copying the lesion or just fading it away and not accurately predicting the necrosis. Given these qualitative results the clinical impact of this work is questionable. In particular their result in FIg S2 row 1, where the lesion obviously was resected and the prediction that the lesion just stopped taking contrast agent makes no sense. At least the other methods just keep the lesion, which is a more likely outcome than what the methods of the authors provide.
- Flow matching is not well motivated:
From the text it looks like this is just an iterative refinement as there is no noise component in the flow matching. This makes the entire system deterministic. However, given that the results are not accurate, does it make sense to just provide a single future and not at least a likelihood of the next state. Also there is no motivation given, no ablation to other methods, even though this is their main workhorse to transition from one state to the next. The citations in this section are also generic flow matching papers and do not tell me if this is a good method for state transitions.
Minor comments:
- The related work sections could be significantly improved by highlighting the difference to existing work. It is unclear how this work is different from preceding works and why those baseline methods were chosen. The related work section just lists some works, but does not define which gap the authors are filling with their work.
- The AI Use statement does not actually follow the guidelines
[1] Ocaña-Tienda, Beatriz, and Victor M. Perez-Garcia. "Mathematical modeling of brain metastases growth and response to therapies: A review." Mathematical Biosciences 373 (2024): 109207.
Questions for authors
Clarifications:
-
Can you elaborate on the dataset, that you propose? Are the additional sequences relevant? Did a clinician look over any of the artifacts that you produced? Why does it make sense to combine metastasis and GBM? Does your system perform better or worse after including these extra datasets?
-
Do you use noisy inputs in the flow matching or do you just deterministically refine the prediction and why does it make sense to do it like this?
Future work:
- Can you elaborate, why the flow matching is superior to other methods, like RNNs or single step prediction models like Transformers or even just a CNN?
- Can you elaborate on the eligibility of the baselines. They all use the same conditioning, however it is unclear if this conditioning is causing issues. it would be prudent if they used the same conditioning as you do to isolate the contribution of each component or at least use their conditioning on your method.
12 comments
Response II
Q3 Figures show SSIM and Dice, while the table shows PSNR, LPIPS and change agreement. Why not report SSIM too?
Reply: Thank you for the suggestion. We left the 3D tumour SSIM out of Table 1 because it saturates at 0.985–0.990 for every method and at 0.987–0.995 across horizons, since the zeroed background enters the average (Appendix B.6). Following your suggestion, Table 1 now reports it for every method, also listed in Table R1.
Table R1. 3D tumour SSIM of every method.
| Method | SSIM ↑ (masked volume) | SSIM ↑ (averaged over ) |
|---|---|---|
| Copy input | 0.9887 ± 0.0110 | 0.5167 ± 0.2762 |
| Δ-LFM | 0.9890 ± 0.0098 | 0.4796 ± 0.2150 |
| MambaControl | 0.9876 ± 0.0119 | 0.4183 ± 0.1746 |
| ImageFlowNet | 0.9895 ± 0.0101 | 0.5273 ± 0.2501 |
| GlioPREDICT | 0.9867 ± 0.0123 | 0.4495 ± 0.2093 |
| CardiacAging | 0.9886 ± 0.0107 | 0.5191 ± 0.2581 |
| CounterSynth | 0.9881 ± 0.0113 | 0.5068 ± 0.2689 |
| DiffuseMorph | 0.9886 ± 0.0108 | 0.5127 ± 0.2650 |
| MeWM | 0.9875 ± 0.0119 | 0.4817 ± 0.2362 |
| BrLP | 0.9866 ± 0.0133 | 0.4587 ± 0.2252 |
| TADM | 0.9876 ± 0.0113 | 0.4688 ± 0.2460 |
| SADM | 0.9846 ± 0.0115 | 0.3138 ± 0.1605 |
| TaDiff | 0.9862 ± 0.0106 | 0.3793 ± 0.2041 |
| LMWM° | 0.9895 ± 0.0098 | 0.4854 ± 0.2476 |
| LMWM† | 0.9873 ± 0.0117 | 0.5332 ± 0.2588 |
| LMWM | 0.9901 ± 0.0103 | 0.5967 ± 0.2195 |
On the masked volume, every method falls between 0.9846 and 0.9901, while cF1 spans 6.9% to 45.1% (Table 1), so this SSIM separates the methods little. LMWM has the highest value, 0.9901. Averaged over the tumour region only, SSIM separates the methods more (0.3138 to 0.5967), and LMWM is again the highest.
Q4 Does Figure 6 predict any growth? In Figure S2 row 1 the lesion was resected, yet LMWM shows it losing contrast, while other methods keep the lesion.
Reply:
Figure 6 (top) and Figure S2 (bottom) show tumours that shrink. LMWM is the only method whose forecast shrinks the tumour, as the observed change (the residual ground truth) shows, although by less than observed, while the other methods either blur the tumour or change its intensity.
Figure 6 (bottom) and Figure S2 (top) show resection cases. The other methods keep the lesion unchanged or over-blur it, whereas LMWM tries to remove only the tumour region, although the predicted cavity is still imprecise. The extent of the resection is known only from the follow-up scan, so no method receives it as an input.
Across the test set, LMWM also forecasts growth best, with growth AUC 76.2% (Table S1), and it has the highest cF1 inside necrosis (52.7%) and inside the resection cavity (46.3%) (Table R2). We will add more cases to supplement Figures 6 and S2.
On clinical impact, the paper shows that current methods mostly copy or blur the lesion, as you observe, and a blurred copy beats ten of the twelve baselines on cF1 (Table 1). We read this as the reason to develop the task with a benchmark that measures change. LMWM moves beyond copying, with growth AUC 76.2% against 50.0% for the copy (Table S1).
Table R2. cF1 (%) inside each lesion class.
| Method | Whole tumour | Necrosis | Enhancing | Oedema | Cavity |
|---|---|---|---|---|---|
| Copy input | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| Δ-LFM | 40.6 | 46.5 | 48.1 | 39.8 | 40.3 |
| MambaControl | 41.4 | 46.7 | 47.2 | 41.0 | 42.0 |
| ImageFlowNet | 28.1 | 29.1 | 30.1 | 27.8 | 27.1 |
| GlioPREDICT | 27.0 | 31.1 | 32.5 | 26.9 | 27.9 |
| CardiacAging | 21.3 | 22.9 | 24.7 | 20.9 | 22.8 |
| CounterSynth | 19.0 | 21.5 | 22.0 | 19.0 | 20.0 |
| DiffuseMorph | 6.9 | 6.1 | 7.8 | 6.5 | 8.5 |
| MeWM | 16.2 | 18.5 | 20.2 | 16.1 | 18.6 |
| BrLP | 15.8 | 18.5 | 21.5 | 14.1 | 19.5 |
| TADM | 13.4 | 15.1 | 16.8 | 12.1 | 15.1 |
| SADM | 17.5 | 18.3 | 23.7 | 15.3 | 18.9 |
| TaDiff | 19.8 | 23.8 | 24.2 | 19.7 | 18.6 |
| LMWM | 45.1 | 52.7 | 53.6 | 44.9 | 46.3 |
LMWM has the highest cF1 in every lesion class, including necrosis (52.7% against 46.7% for MambaControl) and the resection cavity (46.3% against 42.0%). So its change forecasts hold in each tissue class, including the resected tissue of Figure S2 row 1.
Response III
each tissue class, including the resected tissue of Figure S2 row 1.
Q5 Flow matching has no noise and is deterministic refinement. Why a single future with no likelihood, and why no motivation or ablation against other transition models?
Reply: Thank you for the question. The transition is deterministic by design. Flow matching does not require noise as its input. It learns a mapping between two distributions, as rectified flow transports between two arbitrary distributions (Liu et al., ICLR 2023), and data-to-data bridges such as I²SB (Liu et al., ICML 2023) learn a flow directly between two data states.
We start the flow from the current state because most of the brain does not change between visits (median changed region 2.3%, Table S6), so the flow only has to learn the change. Table R3 tests this choice and the transition itself. It adds noise to the input , and it replaces the flow with the same transformer or a 3D CNN that regresses the next latent directly, under our conditioning and under the shared conditioning of the baselines.
LMWM gives a single forecast for a given treatment course, and a different course gives a different forecast, because the treatment field is an input. We agree that this is a limitation, and our next work will extend the transition to output several possible futures (e.g., stable disease or progression) for the same patient and treatment course, each with its likelihood.
On the citations, the paper already cites and discusses flow-based state transitions for longitudinal imaging, Δ-LFM (Chen et al., 2026) and ImageFlowNet (Liu et al., 2025a), in Appendix G. The revision adds Temporal Flow Matching (Disch et al., 2025), which also models only the change between scans, to Section 2.3. We also move the related work from the appendix into the main text, so that these differences are easier to find.
Table R3. Transition ablation. Components not listed follow LMWM.
| Model | Conditioning | Transition | PSNR ↑ | LPIPS ↓ | SSIM ↑ | cF1 ↑ | cPrec ↑ | cRec ↑ | ρ ↑ |
|---|---|---|---|---|---|---|---|---|---|
| LMWM | ours | flow w/o noise | 19.38 | 3.66 | 0.9901 | 45.1 | 63.8 | 39.3 | 49.7 |
| LMWM | ours | flow w/ noise | 19.04 | 4.17 | 0.9905 | 35.6 | 67.9 | 29.5 | 40.1 |
| transformer | ours | direct regression | 18.96 | 3.92 | 0.9897 | 42.8 | 69.0 | 37.2 | 43.2 |
| transformer | shared | direct regression | 17.92 | 4.81 | 0.9890 | 28.1 | 73.3 | 20.6 | 35.8 |
| 3D CNN | ours | direct regression | 18.77 | 4.52 | 0.9889 | 37.4 | 64.5 | 33.9 | 37.1 |
| 3D CNN | shared | direct regression | 17.58 | 4.86 | 0.9878 | 27.9 | 72.4 | 22.7 | 34.6 |
The flow from without noise gives the best change agreement. Adding noise lowers cF1 from 45.1% to 35.6% and ρ from 49.7% to 40.1%, which fits our motivation, since the flow then has to rebuild the unchanged brain as well as the change. Direct regression also falls below the flow, with cF1 42.8% for the same transformer and 37.4% for a 3D CNN. Our conditioning improves every transition, raising cF1 from 28.1% to 42.8% for the transformer and from 27.9% to 37.4% for the 3D CNN, so the treatment field and history add to any transition.
Q6 Related work lists papers without stating the differences, the gap, or why these baselines were chosen
Reply: Thank you, we agree. We added a new paragraph to the related work section, shown below.
Existing methods feed treatment or patient history to one network as extra inputs. LMWM instead learns one shared transition that predicts disease change from the current latent, and designs the treatment and history corrections from what each input carries. Surgery, radiotherapy and chemotherapy act at different places and on different time scales, so treatment enters as a response field with a spatial code and a learned time kernel for each class (Section 2.4). A patient's history is informative where the forecast errors of completed intervals recur in the same direction, so history enters as a map that keeps these consistent errors and cancels conflicting ones (Section 2.5). This adapts the forecast to each patient's care and course without per-patient fitting, and shows what each correction contributes (cF1 from 31.6% to 37.2% and 45.1%, Table 1).
The gap we fill is that existing generators do not show how treatment and patient history change shared disease dynamics, or what each contributes to the forecast. We chose the baselines to cover the three lines of work this gap touches. Δ-LFM, ImageFlowNet, TADM, SADM, BrLP and MambaControl forecast a follow-up scan from the current scan and elapsed time, so they test the shared transition. TaDiff, GlioPREDICT and MeWM condition on treatment, so they test the treatment field. CardiacAging, CounterSynth and DiffuseMorph test whether generic generation or registration forecasts change.
Response I
We thank the reviewer for recognising the scale of the dataset, the breadth of the comparison and the novelty of the conditioning, and that LMWM improves over copying and blurring the input where most baselines do not. We answer the questions below.
Reply: We appreciate the clinical viewpoint and thank you for the reference. Our goal is a standard benchmark for tumour progression, and each disease needs a large cohort to support analysis of its progression. Glioma and brain metastases are the two brain tumours that are close in setting, serial MRI under treatment, and large enough for this analysis, so we harmonize them in one resource that places scans, lesion masks and treatment records on each patient's timeline.
We agree that the two diseases grow differently, so the benchmark keeps them as separate cohorts and never mixes them in a forecasting task. In clinical use the disease type is known from the first diagnosis, and our model forecasts progression rather than distinguishing tumour types.
The two cohorts do show the difference as Ocaña-Tienda and Perez-Garcia (2024) describe, with a median changed region of 2.3% of the brain in glioma against 0.5% in metastases (Table S6). In this paper, forecasting is trained and evaluated on glioma only (Section 2.1). Metastasis scans enter only the autoencoder training, because their treatment records are scattered, and all methods that use an autoencoder share the same one trained on the same data.
Reply: Thank you for the insight. Predicting tumour growth from images is hard but feasible, as shown by deep learning on pre-treatment MRI that predicts where glioblastoma will later progress (Tran et al., npj Digital Medicine 2025), and by patient-specific growth models calibrated on MRI that predict tumour infiltration (Lipková et al., IEEE TMI 2019) and post-radiotherapy tumour size (Rockne et al., Physics in Medicine and Biology 2010). In our test, LMWM ranks first among all methods at telling which tumours will grow, with growth AUC 76.2% against 50% for chance (Table S1).
Core growth Dice is low because it scores only new tumour more than two voxels outside the baseline tumour (Table S3), a small region. Copying the last scan scores 0%, and LMWM's 18.3% is the highest of all methods (Table S1).
The registration results were checked and verified by clinicians, and cases with clear registration errors were removed. The registration cannot be perfect and comes with many problems, such as acquisition differences, the tumour condition, thick slices, truncated coverage, resampling distortion and inter-visit offsets, as stated in Appendix D.7 and Figure S4. These problems can cause pixel differences, which also make the task more difficult.
Image similarity is misleading for this task, as the paper states (Abstract), so we rank methods by change metrics rather than by pixel similarity. LPIPS measures perceptual appearance rather than structure (Zhang et al., CVPR 2018). Copying the input gets the best LPIPS while predicting no change (Table S1), which shows that LPIPS is not sensitive to tumour progression. The change metrics proposed in the paper are therefore preferred for measuring tumour change.
The low scores of current methods come from both the difficulty of the task and the limited research on it, and this is why we propose a benchmark to support further research on tumour progression forecasting.