- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes RESOLVE for predicting spot-level gene expression from H&E images. The model combines a base predictor with a residual branch guided by cell-type expression profiles from a single-cell reference. Both branches use image features from a frozen UNI2-h encoder followed by local and global attention. The residual branch learns to correct the base prediction, with a gate controlling the size of the correction at each spot. The authors evaluate 250 genes on three cancer spatial transcriptomics datasets and report higher PCC than the compared methods. Ablation studies examine the model components, and further analyses show that the residual branch mainly improves expression differences between slides. The authors interpret these corrections as cell-state-related variation.
Critical strengths
- The base-plus-residual design is a good idea. Keeping a separate base prediction allows the single-cell reference to guide the correction without determining the entire output. Local and global attention also give the model access to both nearby tissue context and broader slide structure.
- The authors compare against several recent methods, including CPNN, DKAN, and HyperST. They also use the same single-cell reference for CPNN, which makes that comparison more informative.
Critical weaknesses
- It is unclear whether the residual captures cell-state variation or differences in cell-type composition. Each spot contains multiple cells, and the prototype control, pathway enrichment, and between-slide analyses do not distinguish these explanations. An analysis controlling for cell-type composition would help. As a possible follow-up, paired H&E and Xenium data could be used to examine residual gains within the same cell type. I would not require this additional experiment, since adapting the model to single-cell resolution would take further work, and the larger number of cells could make global attention expensive.
- The folds are split by slide, although the datasets contain multiple slides from each patient. Can slides from the same patient appear in both training and validation sets? Patient-held-out results would be important for assessing generalization, particularly given the emphasis on correcting between-slide differences.
- RESOLVE uses UNI2-h features, while MERGE uses ResNet18. The comparison therefore does not isolate the contribution of the proposed method from that of the image encoder. It would be useful to compare the models using the same UNI2-h features and comparable training losses.
Questions for authors
- Can the authors distinguish residual corrections due to cell-state changes from those due to differences in cell-type composition? Does the residual still help after controlling for composition?
- Are all slides from a patient kept in the same fold? If not, how does the model perform when patients, rather than slides, are held out?
- Were any baselines evaluated using the same UNI2-h features as RESOLVE? How much of the improvement remains when the image encoder and training losses are matched?
9 comments
W1/Q1: Residual correction analysis
Response. W1 and Q1 address the same question: how much of the residual correction originates from cell-type composition versus state differences within the same cell type, and whether the residual remains effective after controlling for composition. The prototype control, Hallmark enrichment, and between-/within-slide decomposition originally cannot answer this question alone. We therefore add a composition-control analysis.
We use cell2location to deconvolve each spot over the same 29 cell types and 250-gene signature used for the prototypes, yielding composition vector p_k. The per-slide control applies within-slide centering. Within each training slide, expression and composition are each centered by subtracting the slide mean, and expression is then regressed per gene on the composition vector, removing only the within-slide component that covaries with composition. This avoids a cross-slide global regression mistaking between-slide mean differences for composition effects. That global regression yields negative R² on held-out slides (median −0.47) and is therefore not used. Before and after residualization, target mean and standard deviation remain at 2.508/1.002, so changes in ΔPCC are attributable to removal of the composition component rather than to a change in target scale. The between-slide control targets slide means. Each slide has only 29 composition dimensions and each training fold contains about 30 slides, so direct 29-dimensional regression would overfit. We therefore first compress composition to 3 principal components via PCA, retaining the dominant between-slide composition variation, and then regress slide-mean expression per gene and apply the result to held-out slides. Composition entropy H = −Σ p_k log p_k / log 29 is stratified into tertiles within each slide: high indicates relatively mixed composition across cell types, low indicates dominance by a single cell type, and mid lies between.
Table scEV-1a: Residual gains after composition control
| Setting | raw ΔPCC | after composition control | retained fraction |
|---|---|---|---|
| per-slide (primary metric) | 0.00446 | 0.00362 | 81% |
| between-slide (PCA-3) | 0.0340 | 0.0174 | 51% |
Table scEV-1b: Per-slide gains stratified by composition entropy
| Composition-entropy stratum (per-slide) | raw ΔPCC | after composition control | retained fraction |
|---|---|---|---|
| high (mixed composition) | 0.0080 | 0.0069 | 86% |
| mid | 0.0060 | 0.0054 | 90% |
| low (single-type dominated) | 0.0010 | 0.0003 | 30% |
After composition control on the within-slide component, ΔPCC drops from 0.00446 to 0.00362, retaining 81%. Composition thus explains only about 19% of this gain in ΔPCC terms. The stratified results are directionally consistent. The high and mid entropy groups retain 86% and 90%, respectively, whereas the gain in the low entropy group drops from 0.0010 to 0.0003 and essentially vanishes. This indicates that the state correction occurs mainly on spots with mixed composition, whereas on spots dominated by a single cell type the residual gain is largely explained by composition. The raw ΔPCC in the low entropy group is itself small, so the ratio is more sensitive to noise, but its direction is consistent with the high and mid groups. The between-slide control retains 51% (from 0.0340 to 0.0174). Composition accounts for a substantial share of slide-level differences, but a non-zero state component remains. After composition removal, the between-slide residual (0.0174) remains clearly larger than the within-slide residual (0.0036). The original conclusion that the residual is positioned as a between-slide signal therefore holds, although the description should be revised to a mixed correction of state and composition.
Table scEV-2: Hallmark enrichment of between-slide surviving genes after composition adjustment (top-15)
| Term | Adjusted p | Odds ratio |
|---|---|---|
| Interferon Gamma Response | 3.2×10⁻⁶ | 50.7 |
| Allograft Rejection | 6.7×10⁻⁵ | 36.7 |
| Interferon Alpha Response | 1.8×10⁻⁴ | 52.9 |
| Apoptosis | 0.017 | 19.2 |
| Inflammatory Response | 0.021 | 15.4 |
Among genes that retain a between-slide gain after composition removal, IFN-γ, allograft rejection, IFN-α, apoptosis, and inflammatory response rank in the top 5. This enrichment pattern is consistent with a between-slide cell-state correction interpretation and is observed after the composition effect has been removed.
Overall, the residual contains both a cell-state and a cell-composition component. The within-slide main effect is dominated by state, with composition accounting for about 19%. In between-slide differences, composition accounts for a relatively high share (about half), but a non-zero state component remains, and this component is still enriched for IFN programs. The revision will change "pure cell-state correction" in the main text to a mixed correction of state and composition.
W2/Q2: Data-splitting protocol
Response. As stated under Reporting conventions, the original data-splitting scheme allowed slides from the same patient to appear in both training and validation sets. Following DKAN (AAAI 2026), we re-adopt a patient-based splitting scheme to evaluate the model's true generalization ability. Table scEV-3 reports the comparison of representative algorithms under the updated evaluation protocol. RESOLVE is best on all 9 metrics (PCC/MAE/MSE across three datasets). For example, on Her2ST, RESOLVE achieves a PCC of 0.3245, higher than DKAN's 0.3138 and MERGE's 0.1938.
Table scEV-3: Comparison of representative algorithms under patient-level splitting and the DKAN evaluation protocol
| Method | ST-Net PCC | ST-Net MAE | ST-Net MSE | Her2ST PCC | Her2ST MAE | Her2ST MSE | SCC PCC | SCC MAE | SCC MSE |
|---|---|---|---|---|---|---|---|---|---|
| TRIPLEX (CVPR 2024) | 0.1673 | 0.4673 | 0.3618 | 0.3016 | 0.6942 | 0.8002 | 0.4033 | 0.6885 | 0.7428 |
| MERGE (CVPR 2025) | 0.0780 | 0.4683 | 0.3644 | 0.1938 | 0.7553 | 0.8952 | 0.2940 | 0.7199 | 0.7600 |
| DKAN (AAAI 2026) | 0.1702 | 0.4535 | 0.3391 | 0.3138 | 0.7269 | 0.8542 | 0.4363 | 0.6786 | 0.7007 |
| HyperST (CVPR 2026) | 0.1479 | 0.4499 | 0.3392 | 0.2720 | 0.7034 | 0.8185 | 0.3931 | 0.6985 | 0.7604 |
| RESOLVE | 0.1813 | 0.4296 | 0.3027 | 0.3245 | 0.6906 | 0.7694 | 0.4517 | 0.6601 | 0.6819 |
Response to Reviewer scEV
We thank Reviewer scEV for recognizing the value of RESOLVE's base-plus-residual decomposition. We address all three questions below.
Reporting conventions. The original RESOLVE paper follows MERGE (CVPR 2025) exactly for data processing and splitting. Upon verification, we find that this splitting protocol (slide-level splitting) induces patient-level overlap, i.e., slides from the same patient may appear in both training and test sets. In addition, MERGE computes PCC per gene over spots pooled across all validation slides of a fold, which mixes inter-sample variation and may artificially affect correlation estimates, failing to faithfully reflect the model's ability to capture within-slide spatial expression patterns. Accordingly, all experiments in this response adopt a revised splitting protocol and PCC computation following DKAN (AAAI 2026). Splits are made at the patient level, and PCC is computed per gene across spots within each slide and then averaged over folds. For the prediction target, we retain MERGE's
counts_spcs_to_8npreprocessing, as MERGE explicitly argues that gene-aware smoothing is necessary to mitigate technical artifacts in ST data and is more biologically justified than earlier spatial smoothing. This preprocessing acts only on the prediction target and does not involve sample splitting. It is therefore orthogonal to the evaluation-protocol corrections above, so that performance differences can be attributed to the splitting and PCC corrections rather than to changes in input distribution.