- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
They design an anatomically grounded VLM for CMR VQA task, and make anatomical-grounding VQA datsets from public CMR resources, which contains 128,915 grounding QA pairs, while quality-controlled image-derived measurements yield 42,799 clinical QA pairs across 14 tasks informed by clinical report analysis.
Critical strengths
They combine anatomical grounding pretraining with CARA to learnwhere to look for clinical question answering. Experiments across 14 clinical tasks show that CARA-VL outperforms the evaluated base-lines on all internal tasks and demonstrates promising external generalization. Ablations support the complementary benefits of anatomical grounding pretraining and CARA.
Critical weaknesses
The labels used for training contains segmentation masks, automatic measured results and predefined threshold generation, which may have human-rule bias. General medical VLM is evaluated by zero-shot way, but CARA-VL is trained on these method, which is not fair. CARA depends on 14 predefined tasks and fixed anatomical rules, which is hard to extend to other open-ended questions and compositional questions. The author uses some attention visualization to show that the model "learned where to look", but sometimes the attention does not provide a correct casual explanation. The author never report the means and standard deviations across several runs. Please add them in the experiments.
Questions for authors
Please see the weakness above to explain some details in your paper clearly. Moreover, some questions are listed as follows:
Why not use the same data in stage 2 to fine-tune the general medical VLM to obtain more fair comparison? I want to confirm whether the attention visualization is analysis in the whole test set, or you just show a few representative successful cases Please tell me whether the automatic segmentation results are evaluated by human experts. Could you please report the means and the standard deviations in multiple random seeds?
6 comments
Response to Question “Please tell me whether the automatic segmentation results are evaluated by human experts”
Yes. All automatically generated masks were visually screened by a PhD student with four years of research experience in cardiac segmentation and a medical imaging researcher with over ten years of experience. The screening focused on obvious anatomical errors, such as missing structures or gross misalignment, rather than fine-grained boundary accuracy. We have added these details to the mask quality-control description in the revised manuscript in Section C.5.1.
Response to Question “Could you please report the means and the standard deviations in multiple random seeds?”
We thank the reviewer for this valuable suggestion. Although multi-seed experiments are informative, repeating complete training runs is particularly costly for large VLMs, and comprehensive reporting across independent training seeds is not universal in current large-model research. Nevertheless, to strengthen the statistical assessment, we have added 95% confidence intervals based on 10,000 patient-cluster bootstrap resamples across the internal and external test sets (Appendix E.1). All QA instances and repeat examinations from each sampled patient are retained together. These intervals quantify test-cohort sampling uncertainty for the fixed trained model, while variability across training seeds remains unassessed.
Table 16 (Appendix E.1): patient-cluster bootstrap confidence intervals for CARA-VL. Entries are point estimates [95% CI] in percent. F1 denotes macro-F1 for classification and micro-F1 for regional tasks (†).
SAX
| Task | BA [95% CI] | F1 [95% CI] |
|---|---|---|
| Hypertrophy | 86.7 [81.5, 91.2] | 84.3 [75.7, 90.0] |
| LV size | 89.9 [83.6, 95.5] | 88.4 [80.6, 94.2] |
| RV size | 86.6 [75.9, 94.2] | 88.8 [79.1, 94.8] |
| EF | 92.1 [88.0, 95.7] | 90.4 [85.6, 94.9] |
| GRS | 92.6 [85.2, 98.3] | 92.6 [85.5, 98.0] |
| GCS | 96.4 [93.0, 99.0] | 95.7 [91.3, 98.6] |
| Six-task average | 90.7 [87.5, 93.4] | 90.0 [86.2, 92.7] |
| Regional hypertrophy† | — | 61.8 [51.0, 69.5] |
| Regional motion† | — | 55.8 [46.3, 62.8] |
Internal LGE (50 patients)
| Task | BA [95% CI] | F1 [95% CI] |
|---|---|---|
| Scar presence | 82.9 [78.7, 87.5] | 82.0 [77.6, 86.0] |
| Transmurality | 68.5 [57.5, 79.2] | 71.1 [58.6, 80.9] |
| Extent | 82.5 [75.9, 88.3] | 82.3 [74.8, 87.5] |
M&Ms-2: LAX
| Task | BA [95% CI] | F1 [95% CI] |
|---|---|---|
| EF | 78.1 [72.5, 83.6] | 74.9 [68.0, 81.6] |
| EDV | 84.9 [78.8, 90.4] | 81.0 [74.4, 87.1] |
| GLS | 77.1 [68.4, 85.8] | 79.6 [70.5, 87.7] |
In-house B: Rule-based
| Task | BA [95% CI] | F1 [95% CI] |
|---|---|---|
| Hypertrophy | 87.1 [83.1, 90.4] | 90.7 [87.6, 93.1] |
| LV size | 82.5 [78.9, 85.6] | 66.6 [61.9, 70.9] |
| RV size | 62.5 [54.4, 70.1] | 59.1 [52.4, 65.4] |
| EF | 73.5 [70.9, 76.1] | 66.3 [62.7, 69.8] |
| GRS | 87.3 [83.5, 90.9] | 86.0 [82.3, 89.2] |
| GCS | 84.1 [79.1, 88.5] | 65.8 [60.8, 70.7] |
| Six-task average | 79.5 [77.5, 81.4] | 72.4 [70.4, 74.2] |
| Regional hypertrophy† | — | 55.1 [49.4, 60.1] |
| Regional motion† | — | 36.7 [31.9, 41.2] |
In-house B: Report-based
| Task | BA [95% CI] | F1 [95% CI] |
|---|---|---|
| Hypertrophy | 69.9 [65.5, 74.3] | 72.7 [67.3, 77.7] |
| LV size | 64.0 [60.6, 67.4] | 60.7 [56.5, 64.7] |
| RV size | 52.4 [51.1, 53.9] | 46.8 [44.0, 49.8] |
| EF | 72.6 [70.2, 75.1] | 58.2 [53.9, 62.3] |
| GRS | 62.7 [59.4, 66.2] | 64.5 [60.2, 68.9] |
| GCS | 75.0 [71.3, 78.6] | 77.2 [73.6, 80.7] |
| Six-task average | 66.1 [64.4, 67.8] | 63.4 [61.2, 65.4] |
| Regional hypertrophy† | — | 30.9 [24.3, 37.3] |
| Regional motion† | — | 34.5 [28.7, 40.2] |
Thanks for your response. It would be nice if you could show me more experiments instead of explanations. Could you please conduct more experiments and visualizations to demonstrate the correctness of your explanations?
Response to Weakness: “The labels used for training contains segmentation masks, automatic measured results and predefined threshold generation, which may have human-rule bias.”
We thank the reviewer for highlighting this concern. Our labelling criteria are informed by published clinical standards and quantitative measurement definitions, as described in Appendix C.1. For example, our EF grading is consistent with the 50/40/30% boundaries specified in the ACC/AHA clinical data standards. The task-specific labelling rules and exclusion intervals are detailed in Table 5 in Appendix C.1. Using explicit, shared criteria is intended to reduce subjective variability and makes our reference definitions transparent and reproducible. We nevertheless acknowledge that standardisation does not eliminate bias: the labels remain dependent on segmentation accuracy, measurement methods, and the chosen grading conventions, as discussed in our limitations.
Response to Question: Fine-Tuning Medical VLMs on the Same Stage-2 Data
We thank the reviewer for this constructive suggestion. We have now fine-tuned MedGemma-4B-it and Huatuo-Vision on the same 14-task Stage-2 training pool, using three training epochs and the same test sets and scoring protocol as CARA-VL (Tables 1–2; Appendix D.3). First, fine-tuning on our dataset substantially improves the original baselines. MedGemma-4B-it and Huatuo-Vision improve from 50.9% and 51.9% to 85.7% and 86.5% mean BA on internal SAX, respectively. These gains demonstrate that our dataset provides effective CMR-specific supervision for adapting existing medical VLMs, establishing its value beyond the proposed model. Second, CARA-VL remains stronger after these baselines receive the same Stage-2 supervision. CARA-VL achieves 90.7% mean BA on internal SAX, exceeding the fine-tuned MedGemma and Huatuo models by 5.0 and 4.2 percentage points, respectively, and also achieves higher mean SAX BA and macro-F1 on the external test sets. This supports the effectiveness of our proposed framework beyond clinical QA fine-tuning alone.
The newly added fine-tuned baseline results from Tables 1–2 are reproduced below. Classification entries report BA / macro-F1 (%); regional entries report micro-F1 (%). Avg. covers the six SAX classification tasks.
Table 1(a): ACDC test set (SAX).
Table 1(b–c): the 50-patient LGE test set and M&Ms-2 test set (LAX).
Table 2: In-house B external test set. Report-based GRS/GCS labels use WMS proxies.
Response to Question : Attention Visualization, Case Selection, and Causal Interpretation
We thank the reviewer for raising this point. Figure 3 serves an illustrative rather than statistical purpose: it is designed to make differences in spatial attention directly visible. Using the same SAX image for two clinical questions allows the attention patterns with and without CARA to be compared while keeping the visual input fixed. Accordingly, the figure presents case-level examples rather than a dataset-wide attention analysis. These visualizations illustrate the behavior of anatomical guidance and are not intended to establish a causal explanation of the predictions.