- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
RIVER targets sparse-view dynamic digital subtraction angiography. Geometry is time-invariant and only per-primitive attenuation varies, rendered by a differentiable X-ray projection. Relative to a 4DRGS-style predictor that queries , RIVER appends a 32-d relation vector produced by one round of degree-normalized message passing over nearest neighbors; carries no time input. Two graphs share the primitive support: a coverage graph for aggregation and a confidence graph () whose gated edges define vessel segments.
Critical strengths
The contribution is decomposed rather than reported as a single full-versus-base comparison. Table 4 isolates four effects -- capacity, self-processing, neighbor communication, and priors -- and includes a capacity-matched independent control, so the part of the gain attributable to each design choice is visible; the text also states directly that neighbor context alone does not improve CD over 4DRGS. Metrics on which the method does not lead (LPIPS at 20 and 30 views, CD at 10 views, clDice against R$^2$-Gaussian at all four settings) are reported in the tables, and the normalization and Otsu protocols are given in Section 4 with their scope stated.
The 10-view operating point is a real result: PSNR 31.40 against 29.76 for the strongest baseline, SSIM best at all four view counts, and HD best at all four 3D settings.
Critical weaknesses
Only FDK is used as a classical baseline, although TV, SART and learned primal-dual reconstruction are cited in the related work and are the standard sparse-view alternatives. Together with per-image min--max normalization and per-case Otsu thresholding, the reported metrics measure normalized fidelity rather than absolute attenuation; the limitations section states this, but no metric for it is given.
The main gain comes from capacity rather than from the relational mechanism, by the authors' own control. In Table 4 the 10-view PSNR is 28.76 for 4DRGS, 30.12 for the capacity-matched independent predictor, and 31.18 with neighbor context: 1.36 of the 2.64 dB is capacity, and the part attributable to neighborhood conditioning is 1.06 dB. The margin quoted against 4DRGS therefore includes a component unrelated to the proposed mechanism.
Questions for authors
Would TV, SART and a learned primal-dual reconstruction be feasible at 10 views? If so, a comparison would place the method in the standard sparse-view setting. Since images are min--max normalized and volumes Otsu-thresholded, an error metric on absolute attenuation, or an explicit statement that calibrated recovery is out of scope, would also help.
The confidence graph is gated by , and is itself optimized under the smoothness, floor and residual terms. How much of the segment structure would remain if were held at its initialization, or if edges were taken directly from the images?
This topic lies outside my primary area of expertise, so my reading of the reconstruction literature may be incomplete. I will weigh the response together with the other reviews before finalizing my rating.
5 comments
Rebuttals (2/3)
Q2: The confidence graph is gated by the directional states , which are themselves optimized under the smoothness, floor and residual terms. How much of the segment structure remains if is held at initialization, or if edges are taken directly from the images?
Response.
Thanks for the reviewer’s suggestions. The clinical dataset does not provide independently annotated branch identities and junction labels for evaluating graph connectivity. We therefore construct the synthetic vascular benchmark described in our response to Reviewer e48r, Question 1. It contains two explicitly disconnected vascular trees with ten branches and four labelled junctions, providing known references for assessing erroneous connections and structural preservation. These labels are used only for evaluation. We evaluate two controls corresponding to the alternatives raised by the reviewer. The frozen-state control fixes at its PCA initialization, including magnitude, to assess how much structure remains without learning the directional states. The image-derived affinity control uses image support to weight candidate edges while keeping the directional states trainable, testing whether image evidence can replace the learned affinity. All variants share the same candidate-edge construction rule, input projections, reconstruction budget, and evaluation protocol.
We evaluate the internal graphs from two perspectives: cross-component connection errors and preservation of the known junctions. Primitive centers are assigned to the nearest labelled reference branch within a tolerance of mm. Among retained edges whose endpoints are both mapped, connections between the two disconnected reference trees are counted as false edges. The false-edge rate is their number divided by the total number of mapped retained edges. A labelled junction is counted as preserved when an eligible mapped connection exists within its mm junction window. Table 14 reports these measurements at three edge-weight thresholds.
Table 14. Confidence-graph comparison on the known-topology synthetic vascular benchmark.
| Configuration | Mapped retained edges | False edges | False-edge rate (%) | Junctions preserved | |
|---|---|---|---|---|---|
| 0.10 | RIVER | 25,970 | 70 | 0.2695 | 4/4 |
| 0.10 | Frozen states | 33,746 | 198 | 0.5867 | 4/4 |
| 0.10 | Image-derived graph | 47,922 | 342 | 0.7137 | 4/4 |
| 0.25 | RIVER | 25,970 | 70 | 0.2695 | 4/4 |
| 0.25 | Frozen states | 32,138 | 188 | 0.5850 | 4/4 |
| 0.25 | Image-derived graph | 9,958 | 0 | 0.0000 | 2/4 |
| 0.50 | RIVER | 25,970 | 70 | 0.2695 | 4/4 |
| 0.50 | Frozen states | 26,156 | 146 | 0.5582 | 4/4 |
| 0.50 | Image-derived graph | 0 | 0 | – | 0/4 |
At the operating threshold , the frozen-state control retains 26,156 mapped strong edges and all four junctions, showing that the measured junction structure remains preserved with the initial directional states. Learning these states improves connection selectivity: RIVER retains all four junctions while reducing false cross-component connections from 146 to 70 and the false-edge rate from 0.5582% to 0.2695%. The image-derived graph preserves all four junctions at , but only two at and none at . Thus, RIVER maintains junction preservation across the evaluated thresholds while suppressing erroneous connections.
We additionally evaluate the final reconstructed vessel masks using clDice. RIVER achieves 0.3209, compared with 0.2968 for frozen states and 0.2975 for the image-derived graph. This provides complementary evidence that the learned configuration improves centerline agreement in the final reconstruction, alongside improved selectivity of the internal confidence graph.
Rebuttals (3/3)
Q3: The main gain comes from capacity rather than from the relational mechanism: 4DRGS gives 28.76 dB, the capacity-matched independent predictor 30.12 dB, and neighbor context 31.18 dB. The margin quoted against 4DRGS therefore includes a component unrelated to the proposed mechanism.
Response.
We agree that increased capacity contributes substantially to the overall improvement. The capacity-matched independent predictor improves PSNR by 1.36 dB over 4DRGS, so the full 2.64 dB RIVER–4DRGS margin cannot be attributed entirely to neighborhood conditioning. We assess the relational contribution through the controlled comparisons in Table 15.
Table 15. Ten-view cohort ablation separating model capacity, self-processing, neighborhood conditioning, and auxiliary priors.
| Variant | PSNR | SSIM | CD (mm) | clDice |
|---|---|---|---|---|
| 4DRGS | 28.76 | 0.83 | 4.03 | 0.339 |
| Capacity-matched independent | 30.12 | 0.85 | 4.48 | 0.386 |
| Self context | 30.67 | 0.86 | 4.31 | 0.401 |
| Neighbor context, no priors | 31.18 | 0.86 | 4.26 | 0.409 |
| Priors only, no neighbor context | 30.94 | 0.86 | 4.19 | 0.421 |
| Full RIVER | 31.40 | 0.87 | 4.07 | 0.433 |
At matched capacity, neighbor context improves PSNR from 30.12 to 31.18 dB, demonstrating an additional benefit beyond increasing predictor capacity. The comparison with self context further distinguishes neighbor communication from processing each primitive’s own information: introducing neighboring information raises PSNR from 30.67 to 31.18 dB. Finally, Full RIVER improves over the priors-only configuration from 30.94 to 31.40 dB, showing that neighborhood conditioning remains useful when the auxiliary priors are already present. These comparisons support an incremental relational contribution without assigning the entire baseline margin to that mechanism.
The structural results also distinguish the contribution of neighborhood conditioning from that of the full design. Neighbor context alone improves clDice over 4DRGS but has a higher CD. Full RIVER achieves the highest clDice in the comparison, increasing it from 0.339 to 0.433, while its CD of 4.07 mm is close to the 4DRGS value of 4.03 mm. These results support improved centerline agreement from the combined configuration.
Rebuttals (1/3)
Q1: Would TV, SART and a learned primal–dual reconstruction be feasible at 10 views? If so, a comparison would place the method in the standard sparse-view setting. Since images are min–max normalized and volumes Otsu-thresholded, an error metric on absolute attenuation, or an explicit statement that calibrated recovery is out of scope, would also help.
Response.
Thanks for the suggestion.
Table 13. Ten-view reconstruction comparison on a single case, evaluated against 234 held-out measured DSA projections.
Learned primal–dual reconstruction is feasible in principle, but its original supervised formulation requires paired training data. We currently lack an independent training set matched to dynamic DSA, and the synthetic benchmark is reserved for evaluation. SART, TV-iTV, and 4DRGS can operate on the available acquisition without a separate supervised training dataset.
To assess intensity agreement without per-image normalization, we additionally report raw RMSE and MAE in Table 13. RIVER improves both metrics, showing that its projection-domain advantage also holds on the dataset’s original logarithmic DSA intensity scale. These measurements assess intensity fidelity on that scale.