Writing study: R2-Seg: Training-Free OOD Medical Tumor Segmentation via Anatomical Reasoning and Statistical Rejection

CVPR overviewCorpus atlasBy contribution typeVisual galleryRules & templateWriting patternsPaper studies

← CVPR 2026 oral writing corpus

Shuaike Shen, Ke Liu, Jiaqing Xie, Shangde Gao, Chunhua Shen, Ge Liu, Mireia Crispin-Ortuzar, Shangqi Gao · 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

≈ 8.04 page-equivalents

Main figures / tables

5 / 3

Attached appendix figures / tables

0 / 0

Attached appendix span

Separate file recorded below; not in this PDF total

Before references / appendix: ≈ 80.4%References / intervening material: ≈ 19.6%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	≈ 0.91 pp.	9.1%
2. Related Works	2	≈ 0.59 pp.	5.9%
3. Methods	2	≈ 2.44 pp.	24.4%
4. Experiments	5	≈ 2.91 pp.	29.1%
5. Discussion	8	≈ 0.62 pp.	6.2%
6. Conclusion	8	≈ 0.22 pp.	2.2%
References	9	≈ 1.96 pp.	19.6%

All detected figure and table locations

Main text

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

Attached appendix

No recognized caption labels.

Separate source files—excluded from canonical-PDF totals

A separate author version may repeat main text and references. Whole-file lengths and counts are not extra appendix material and are never added to the canonical PDF totals. Read the study's source scope for which sections received substantive reading versus layout inspection.

Additional source 1

Separate PDF (or ZIP containing it): whole-file layout of 9 physical pages; 3 detected figures and 4 tables. These may include overlapping main-text material.

Located appendix only: starts on physical p.1; ≈ 8.93 page-equivalents, 3 figure labels and 4 table labels. This interval is distinct from the whole file.

Detected heading	PDF page	Estimated span
Supplementary Material	1	≈ 0.02 pp.
1. Method Details	1	≈ 2.75 pp.
2. Implementation Details	3	≈ 0.94 pp.
3. Additional Results	4	≈ 5.22 pp.

• Figure 6 · p. 5
• Table 4 · p. 6
• Figure 7 · p. 7
• Table 5 · p. 7
• Table 6 · p. 7
• Table 7 · p. 8
• Figure 8 · p. 9

Argument and organization

1. Method §§3.1–3.2

   Explain feature-shift motivation, anatomical planning, segmentation/fusion and statistical rejection.

2. Experiments and discussion §§4–5

   Disclose patient-level splits, compare all-slice performance, examine detection trade-offs and test retained in-domain behavior.

Problem, claim and contribution

The introduction defines training-free precisely as no foundation-model parameter updates, then divides the proposed response into anatomical reasoning and false-positive rejection.

PDF pp. 1–2 · Main paper · Additional source 2

Argument and section order

Data/split details precede results, and the method distinguishes ROI proposal from statistical screening so improved recall and rejected positives have different explanatory roles.

§3.2, PDF pp. 3–5; §4.1, PDF p. 5 · Main paper · Additional source 2

Figures, captions and visual explanation

A conceptual embedding-shift diagram motivates the issue; the pipeline stacks planning, segmentation and statistical testing as separate stages, while FROC curves expose the sensitivity/false-positive trade-off.

Figure 1, PDF p. 3; Figure 2, PDF p. 4; Figure 4, PDF p. 7 · Main paper · Additional source 2

Tables, comparisons and evidence

Table 2 reports Dice, sensitivity, specificity, accuracy and class-average accuracy together. Its lower sensitivity for some cases remains visible rather than being hidden by a high accuracy headline.

Table 2 and §4.4, PDF p. 6 · Main paper · Additional source 2

Appendix and reproducibility

The supplement gives procedural algorithms, thresholds, latency breakdown, tumor-free-slice evaluation, prevalence sweeps and cautions for boundary-distance metrics on small or multifocal lesions.

Supplement §§1–3, PDF pp. 1–9; Algorithms 1–3 and Tables 4–7 · Main paper · Additional source 2

Clarity and writing conventions

The limitations explicitly discuss both over- and under-segmentation, acknowledging that removing false positives can also lose lesions; this qualifies the deployment language.

PDF p. 8, limitations · Main paper · Additional source 2

What to reuse—and what not to infer

Transferable lesson: For a medical adaptation paper, pair overlap scores with detection trade-offs, patient-level split details, tumor-free controls and a candid account of sensitivity loss.

Boundary: Higher specificity or class-average accuracy does not establish clinical safety. The frozen backbone, external anatomical prior and retrospective datasets constrain the demonstrated claim.

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

Writing-focused scan of the separate supplementary PDF, pp. 1–9, including its organization, captions, protocol/evidence detail and limitation material where present; proofs and code listings were inspected for exposition, not independently verified or executed. Supplement §§1–3, PDF pp. 1–9; Algorithms 1–3 and Tables 4–7. Linked video/audio demonstrations and non-PDF archive contents were not assessed.

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
• Official CVPR 2026 CVF supplementary PDF; retrieved 2026-09-26 · 9 pages