- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes CoroLift, a framework that leverages anatomical prior information to achieve rapid single-view 3D reconstruction of coronary arteries. The method integrates topological, positional, and morphological priors to resolve the depth ambiguity inherent in single-view reconstruction.
Critical strengths
-
The paper addresses an interesting and clinically relevant problem. Using anatomical priors to resolve depth ambiguity in single-view coronary reconstruction is a reasonable and interpretable approach.
-
The experimental evaluation encompasses comparisons with various baseline methods, ablation studies, and testing across different noise levels, acquisition angles, and scenarios involving incomplete observations. The reported reconstruction speed is also promising.
Critical weaknesses
-
The evaluation relies entirely on synthetic 2D projections from CCTA data. Although the results are promising, it is difficult to assess the practical value of the reconstruction without real angiographic data or downstream hemodynamic evaluation.
-
The final refinement improves morphological accuracy but increases CD compared with the intermediate result. It is also unclear whether the final reconstruction still satisfies the 2D reprojection constraint. In addition, the adaptation of existing baselines to the single-view setting needs further clarification.
Questions for authors
- Is the reported reconstruction accuracy sufficient for hemodynamic analysis? Could the authors provide vessel-radius errors or a downstream CFD evaluation?
- All 2D observations are synthetically generated from CCTA data. Have the authors evaluated CoroLift on real coronary angiograms?
- Does the final morphology refinement preserve 2D reprojection consistency? In Table 5, the intermediate result achieves a lower CD than the final reconstruction. Why is the final result preferred?
- How were the existing baselines adapted to the single-view setting? Were they sufficiently tuned for a fair comparison?
3 comments
W2 (a, b) / Q3. Reprojection consistency of the final result, and why it is preferred over the intermediate result.
The first table reports the reprojection error at each stage on the 82 test patients at 2 px noise.
| Stage | Median (px) | P95 (px) | Max (px) | > 2 px |
|---|---|---|---|---|
| 0.000 | 0.000 | 0.0001 | 0.00% | |
| 0.000 | 0.000 | 0.0001 | 0.00% | |
| 0.358 | 2.464 | 19.378 | 7.89% | |
| 0.284 | 1.510 | 1.999 | 0.00% | |
| (final) | 0.363 | 2.392 | 17.402 | 7.74% |
The final has a median reprojection error of 0.36 px, which is 0.16 mm, and 92.3% of its samples are within 2 px. The intermediate keeps all samples within 2 px. We have corrected the wording in the paper accordingly. On real angiograms the median is 0.25 px.
The second table reports accuracy and morphology at each stage.
| Stage | CD ↓ | HD95 ↓ | OV ↑ | Tort. ↓ | Curv. ↓ | Bif. angle ↓ |
|---|---|---|---|---|---|---|
| 3.832 | 8.834 | 0.127 | 0.243 | 0.595 | 33.32° | |
| 3.832 | 8.834 | 0.127 | 0.243 | 0.595 | 33.32° | |
| 3.973 | 9.338 | 0.105 | 0.041 | 0.055 | 24.33° | |
| 3.696 | 8.751 | 0.142 | 0.108 | 0.290 | 30.50° | |
| (final) | 3.854 | 9.190 | 0.110 | 0.042 | 0.054 | 24.19° |
Compared with the intermediate result, the final step changes CD by 0.16 mm and reduces the curvature error by 5.4 times, the tortuosity error by 2.6 times, and the bifurcation-angle error by 6.3°. We use by default because hemodynamic analysis needs smooth vessels. remains available when strict 2 px consistency is required.
W2 (c) / Q4. Adaptation and tuning of the baselines.
The baselines of Table 1 receive the same noisy 2D traces, labels, vessel widths and camera as CoroLift. They are trained on the same 671 trees and scored by the same pipeline. NeCA and 3DGR-CAR take a rendered vessel image, following their official protocol.
| Baseline | Single-view adaptation | Tuning |
|---|---|---|
| NN Retrieval | retrieve training tree with best-matching projection | validation split |
| Shape Model | PCA model fitted by reprojection error | validation split |
| Implicit Field | implicit field conditioned on labeled trace + test-time reprojection refinement | validation split |
| Soft Template | our topology + position priors, no morphology | validation split |
| Tree Regression | tree-recurrent 3D regression along the topology | validation split |
| NeCA, 3DGR-CAR | official code, one view | threshold best on test set |
The results on the 82 test patients at 2 px noise are listed below. CD, HD95 and Gap are in mm, and T, P and M denote the topology, position and morphology priors.
| Method | Priors | CD ↓ | HD95 ↓ | OV ↑ | Tort. ↓ | Curv. ↓ | Bif. angle ↓ | Gap ↓ | Time |
|---|---|---|---|---|---|---|---|---|---|
| NeCA (2024) | – | 11.18 | 52.04 | 0.051 | – | – | – | – | 6.5 min |
| 3DGR-CAR (2024) | – | 12.66 | 34.69 | 0.052 | – | – | – | – | 18 min |
| NN Retrieval | T, M | 7.884 | 17.556 | 0.017 | 0.037 | 0.036 | 26.71° | 16.62 | 1.27 s |
| Shape Model | T, M | 6.427 | 14.634 | 0.027 | 0.055 | 0.053 | 26.68° | 22.57 | 5.43 s |
| Implicit Field | P | 6.187 | 13.783 | 0.033 | 0.077 | 0.130 | 35.19° | 12.84 | 5.72 s |
| Soft Template | T, P | 6.145 | 15.318 | 0.074 | 0.253 | 0.611 | 34.65° | 24.33 | 0.11 s |
| Tree Regression | T, P | 5.251 | 11.172 | 0.035 | 0.157 | 0.261 | 48.64° | 6.13 | 0.10 s |
| CoroLift | T, P, M | 3.854 | 9.190 | 0.110 | 0.042 | 0.054 | 24.19° | 0.00 | 0.17 s |
Where a choice existed, it favors the baselines. NeCA and 3DGR-CAR use the threshold that is best on the test set, and a Shape Model that is given our slot correspondence improves from 6.43 to 5.21 mm. Among the methods of Table 1, CoroLift is still the only one that returns a connected tree.
Thank you for the additional experiments and clarifications, particularly the real-angiogram evaluation and hemodynamic analysis, which address most of my concerns. The 3D CFD validation remains limited in scope, and the hemodynamic benefit of the final refinement over the intermediate reconstruction has not yet been demonstrated. I will maintain my original rating.
Thank you for the constructive review. Where a question repeats a weakness, we answer both together.
W1 (a) / Q2. Evaluation on real coronary angiograms.
We evaluated CoroLift on the public CARDIAG dataset, which contains 645 real angiograms of 122 patients. The inputs are independent of our pipeline. The 2D traces and labels come from SYNTAX segment masks annotated by the dataset authors, and the C-arm geometry comes from the DICOM headers. No 3D information is used to prepare them. The models are trained on CCTA only and are applied without fine-tuning. Since no 3D ground truth exists, each view is reconstructed alone and scored at the branch junctions of the other views of the same patient. This gives 1527 view pairs with junction landmarks, from 109 patients. Because pairs from one patient are not independent, the intervals come from a patient-cluster bootstrap and the p-values from a Wilcoxon signed-rank test over patient and artery clusters.
CoroLift has the lowest landmark error overall, on both arteries, and at view separations of 60–90°. It closes 74% of the gap between a depth plane (8.11 mm) and the multi-view oracle (3.48 mm). Its depth correlates with the triangulated depth at r = 0.79, compared with 0.05 for the depth plane, and it reprojects onto its input view with a median error of 0.25 px.
W1 (b) / Q1. Hemodynamic evaluation: vessel-radius errors and CFD.
We now report the radius error, a reduced-order FFR proxy at 877 outlets, and a 3D CFD check.
Replacing our radius with the ground-truth radius lowers the FFR-proxy error from 0.056 to 0.010, while replacing our centerline with the ground-truth centerline leaves it at 0.055. Under this model the remaining error is therefore dominated by the radius rather than by the reconstructed centerline. The 3D CFD solution agrees, with a difference of 0.020 and a median of 0.004.