Writing study: MDCS-MoAME: Multi-directional Composite Scanning with Mixture of Attention and Mamba Experts for Cancer Survival Prediction

CVPR overviewCorpus atlasBy contribution typeVisual galleryRules & templateWriting patternsPaper studies

← CVPR 2026 oral writing corpus

Linjie Qu, Jin Xiao, Xiangrong Liu, Changming Sun, Hui Cui, Yuqi Fang, Ran Su, Qiangguo Jin, leyi wei · Official CVPR 2026 oral record

Observed writing choices, not acceptance rules. This study examines the inspected manuscript version. It does not establish why the paper was accepted or that its presentation choices should be copied unchanged.

Figure, table and section ledger

Editorial contribution type: Domain-grounded methods & physical systems (primary).

Layout extraction, not a required paper template. Counts are distinct caption labels; a multi-panel figure counts once. Section spans are estimated from heading positions, including floats and whitespace. Method and limitations.

Canonical PDF

10 physical pages

Before references / appendix

≈ 8.05 page-equivalents

Main figures / tables

6 / 5

Attached appendix figures / tables

0 / 0

Attached appendix span

No boundary detected; not assumed zero

Before references / appendix: ≈ 80.5%References / intervening material: ≈ 19.5%Estimated layout envelopes, not text/artwork area. Unresolved appendix boundaries remain within the undivided post-body material.

Extraction notes: No attached appendix boundary detected. Zero means no recognized caption, not independently verified absence.

Section-by-section lengths and source pages

The title/abstract/front matter precede the first numbered heading. A span ends at the next detected top-level heading, not at the last sentence; end-page whitespace is included. References and statements are listed separately. These are not measurements of text-only or artwork area.

Top-level heading	Starts on PDF page	Estimated span	Share of entire PDF
1. Introduction	1	≈ 0.94 pp.	9.4%
2. Related Work	2	≈ 0.59 pp.	5.9%
3. Methodology	3	≈ 2.78 pp.	27.8%
4. Experiments	6	≈ 2.32 pp.	23.2%
5. Conclusion	8	≈ 0.48 pp.	4.8%
6. Acknowledgment	8	≈ 0.14 pp.	1.4%
References	9	≈ 1.95 pp.	19.5%

All detected figure and table locations

Main text

• Figure 1 · p. 1
• Figure 2 · p. 4
• Figure 3 · p. 4
• Table 1 · p. 7
• Table 2 · p. 7
• Table 3 · p. 7
• Table 4 · p. 7
• Table 5 · p. 7
• Figure 4 · p. 8
• Figure 5 · p. 8
• Figure 6 · p. 8

Attached appendix

No recognized caption labels.

Argument and organization

1. Modality-specific bottlenecks

   Motivate WSI and gene serialization before introducing multidirectional scans and expert fusion.

2. Prediction model and clinical-task evidence

   Define patient inputs and censoring, give the total objective, then compare modalities and component choices.

Problem, claim and contribution

The opening ties long-range WSIs and sparse genomic profiles to two different representation challenges, motivating a multimodal rather than image-only contribution.

Introduction and Figure 1, PDF pp. 1–2 · Main paper

Argument and section order

The method separates feature extraction, scanning, cross-modal interaction and prediction; the overall figure further expands the expert and routing internals.

Sections 3.1–3.4 and Figure 2, PDF pp. 3–5 · Main paper

Figures, captions and visual explanation

The page-6 layout finishes the weighted loss before the evaluation contract; the latter states cohort sizes and five-fold c-index reporting before any comparative interpretation.

Section 4, PDF p. 6; visual inspection · Main paper

Tables, comparisons and evidence

The main table reports mean and standard deviation, distinguishes single-modality from multimodal inputs, and flags reproduced unavailable-code baselines. Later checks cover hierarchy, scanning and computational complexity.

Tables 1–5, PDF p. 7 · Main paper

Appendix and reproducibility

No separate supplement is listed in the official record; the main paper carries the protocol, component ablations and Kaplan–Meier/log-rank evidence.

Section 4 and Figure 6, PDF pp. 6–8; official proceedings record · Main paper

Clarity and writing conventions

Named modules and corresponding ablations help navigate a dense acronym-heavy design, although a manuscript like this benefits from repeatedly tying each acronym to a function.

Sections 3–4, PDF pp. 3–8 · Main paper

What to reuse—and what not to infer

Transferable lesson: For multimodal clinical prediction, state the patient unit, censoring target, available modalities and uncertainty before showing a leaderboard; accompany fusion claims with unimodal comparisons.

Boundary: Cross-validation on TCGA does not establish prospective clinical utility or external-hospital generalization. C-index and risk-group separation are different evidence types.

Apply this lesson using the argument and evidence worksheet.

Inspection record and sources

Checked

2026-09-26

Reading status

Writing-focused manuscript scan + selected visuals inspected

Main text

Manuscript-wide writing scan of PDF pp. 1–10: framing, argument sequence, section organization, figure/table captions, evaluation interpretation and limitations; reference sections identified. This is a writing-focused scan, not an exhaustive technical proof or reproduction audit. Main PDF pages 3 and 6 were rendered and visually inspected.

Appendix / supplement

No separate supplemental PDF is listed in the official inventory; the writing study uses the main manuscript. Linked project demonstrations and external code were not executed.

Visually inspected PDF pages

3, 6

This is a writing-focused scan of the manuscript and the stated supplementary scope: framing, organization, visual explanation, evidence presentation and wording. It is not a line-by-line proof audit, reproduction of results or exhaustive scientific review.

• Official CVPR 2026 CVF open-access accepted manuscript; retrieved 2026-09-26 · 10 pages