Training-Free Medical Image Segmentation vs Trained Networks

A multi-domain data-efficiency study — frozen LLM polygon traces + a numpy genome + a gated SAM decoder, with zero gradient training.

6 modalitiesmeasured, from scratch GT-free at inferenceLLM-agnostic skills updated 2026-07-06

Results — best trained NN across N vs the LLM pipeline

Strongest trained NN per cell — max of SegFormer (mit_b2), pretrained U-Net (resnet34), and nnU-Net, 2-seed means — at matched budgets N = 10 / 25 / 50 / 100, against the LLM pipeline (re-measured from scratch via eval_all_domains.py). The LLM's only label-fit module is a ~5–8-param genome; localization and SAM are GT-free/frozen — so the LLM number is ~flat in N while the NN climbs. Bold = LLM ahead of the best NN at that budget.

Domain	best NN N=10	N=25	N=50	N=100	training-free LLM	few-shot decoder N=100 (oracle)
ISIC 2018 (derm)	0.815	0.829	0.832	0.868	0.880	0.911
MSD Spleen (CT)	0.633	0.802	0.859	0.907	0.920	0.953
Kvasir-SEG (endo)	0.756	0.824	0.833	0.889	0.8646	0.944
ChestXray (X-ray)	0.938	0.948	0.952	0.9546	0.922	0.9535
HC18 Fetal-Head (US) ·new	0.923	0.958	0.965	0.970	0.9225	0.9665 fs-deploy 0.9328
MSD Prostate (MRI) ·new	0.679	0.720	0.772	0.815	0.760	0.938

Two LLM columns: the training-free pipeline (zero gradient training — the study's headline) and the few-shot tuned decoder (generic-SAM init, encoder frozen, ~4M-param mask decoder tuned on N=100 labels, GT-box oracle). The few-shot decoder beats the from-scratch NN on four of six domains given a good box (ISIC/Spleen/Kvasir/Prostate) and ties the other two (CXR, HC18 — near-ceiling NNs at ~0.95–0.96) — the residual between it and the deployed training-free pipeline is mostly localization (the exception is CXR, where the frozen decoder was the wall — moved by few-shot tuning), detailed below.

CXR few-shot lane (N=100) — a separate, non-training-free result. The training-free CXR headline stays 0.922. Tuning only the ~4M-param SAM mask decoder on N=100 CXR labels (generic-vit_l init, image + prompt encoders frozen, box-jittered, leak-free) and re-decoding each lung's own mask-bbox reaches a deployable Dice of 0.9488 (median 0.9608, 102/107 improve / 5 regress) — essentially the from-scratch NN's 0.9546 (GT-box oracle 0.9535). This reverses the old "CXR is architecturally capped at ~0.93" claim: that cap was specific to the frozen SAM-HQ decoder — CXR's wall was the decoder, not localization, and a few-shot-tuned decoder moves it. It is few-shot (N=100 labels = the NN's own budget), not training-free — a distinct lane, never the training-free headline.

The LLM pipeline wins the scarce-label regime where it has a cue — ISIC through N=100 (best NN needs N=189 to reach 0.887), Spleen through N=100 (0.920 vs best-NN 0.907, via GT-free cross-slice + pyramid priors) — and on Kvasir polyp a frozen-DINOv2 dense-correspondence localizer (OP-SAM CPG + peak-CC box) lifts it 0.659→0.8646 — the gap was localization (frozen GT-box oracle 0.914 > NN), and this closes 89% of it; the median 0.9484 now beats the NN mean, though the mean stays just below best-NN 0.889. On Chest X-ray a static lung box (N=10) + a self-reprompt + a repair agent + a catastrophic fix + a letterbox trim lift the training-free LLM to 0.922 (localization, not architecture, was the deployed gap); the frozen-decoder cap at a GT-box ~0.93 that used to look architectural is now moved by a few-shot-tuned decoder to 0.9488 ≈ NN 0.9546 (a separate few-shot lane, above). SegFormer is the strongest NN in 10 of 12 sweep cells.

Data-efficiency

Where is the wall — the decoder, or localization? A fair few-shot probe

Is the residual to the trained NN a decoder limit or a localization limit? MedSAM (SAM fine-tuned on ~1M medical masks) beats box-prompted SAM — but it is data-leaky (its training set likely includes these test distributions), so it is really "import a trained medical net." The fair, leak-free counterpart of the same operation: init from the generic SAM (no medical data), freeze the image + prompt encoders, and fine-tune only the ~4M-param mask decoder on our own N-label train split — GT never touches test. Given a good box (the GT-box oracle, which isolates the decoder), this few-shot-tuned decoder beats the from-scratch NN at every budget on 4 of 6 domains (ISIC/Spleen/Kvasir/Prostate — Prostate by +0.12) and ties on the other two (CXR, HC18 — both near-ceiling NNs at ~0.95–0.96), and it saturates at N=10 (pretrained features + a tiny adapted head), so its curve is flat-high while the NN climbs:

Domain (tuned decoder, oracle)	N=10	N=25	N=50	N=100	best NN N=100
ISIC 2018 (derm)	0.905	0.904	0.907	0.911	0.868
MSD Spleen (CT)	0.957	0.960	0.960	0.953	0.907
Kvasir-SEG (endo)	0.936	0.934	0.937	0.944	0.889
ChestXray (X-ray)	0.933	0.946	0.955	0.9535	0.9546
HC18 Fetal-Head (US) ·new	0.918	0.954	0.957	0.9665	0.970
MSD Prostate (MRI) ·new	0.906	0.931	0.932	0.938	0.815

Few-shot tuned decoder (oracle) vs trained NN vs training-free LLM — Few-shot tuned decoder (GT-box oracle, ◆) vs best trained NN (gray, from scratch) vs the training-free LLM pipeline (dotted, flat). The tuned decoder saturates at N=10 and sits at/above the NN at every budget on ISIC/Spleen/Kvasir and **Prostate** (+0.12 over the NN); CXR ties by N=50, and **Fetal-Head US ties** (0.9665 vs a near-ceiling NN 0.970). ★ = the **measured deployable** number (tuned decoder + the domain's real GT-free localizer).

Mostly localization — with CXR the telling exception. The oracle hands the decoder a good box; on most domains the gap between it and the deployed pipeline is localization. Kvasir is the proof: tuned-decoder oracle 0.944 vs the original deployed 0.659 — 0.285 of pure localization headroom, zero decoder; the frozen dense-correspondence localizer has since realized most of it (0.659→0.8646), exactly as this predicted, leaving only ~0.05 to the oracle box. Where localization is already solved, the tuned decoder is a clean deployable win over both production and the NN: CXR (static box + self-reprompt) few-shot decoder 0.9488 > production 0.922 ≈ NN 0.9546; Spleen (3D volume-prior box) 0.942 > production 0.920 > NN 0.907. This is few-shot (N=100 labels = the NN's budget), not training-free — an explicit, leak-free counterpart to MedSAM. CXR is the exception that sharpens the rule: its wall was the frozen decoder, not localization — a few-shot-tuned decoder moves the ceiling (0.922→0.9488). So of the residual "structural / architectural ceilings," the polyp boundary was a localization gap in disguise, while the CXR decoder was a real decoder wall that a few-shot (not training-free) decoder can breach.

Is the medical pretraining (MedSAM) worth it? — a leaky benchmark

MedSAM is SAM already fine-tuned on ~1M medical masks — a leaky upper reference (its training likely saw these test distributions). Arch-matched (both vit_b, GT-box oracle, N=100), few-shot tuning of the GENERIC SAM matches or beats the leaky MedSAM on 3 of 6 domains, and stays within 0.015 on the other 3 — its own pretraining distributions (derm/US/MRI). Medical pretraining buys no consistent edge once the decoder is adapted, and where generic SAM is already strong (Kvasir/Spleen) it starts above MedSAM even frozen. Bold = better of the two few-shot columns.

Domain (N=100 oracle, vit_b)	from-scratch NN	generic frozen	generic few-shot (fair)	MedSAM frozen (leaky)	MedSAM few-shot (leaky)
ISIC 2018 (derm)	0.868	0.870	0.915	0.921	0.943
MSD Spleen (CT)	0.907	0.941	0.956	0.909	0.946
Kvasir-SEG (endo)	0.889	0.917	0.936	0.888	0.918
ChestXray (X-ray)	0.9546	0.925	0.954	0.935	0.952
HC18 Fetal-Head (US) ·new	0.970	0.769	0.965	0.904	0.972
MSD Prostate (MRI) ·new	0.815	0.895	0.928	0.807	0.941

Fair few-shot generic SAM vs leaky MedSAM benchmark, N=100 oracle — Fair few-shot tuning of **generic** SAM (dark blue) vs the leaky **MedSAM** (orange), each frozen + few-shot-tuned, vs the from-scratch NN (gray) — arch-matched vit_b, N=100 GT-box oracle. The fair generic few-shot ≥ leaky MedSAM few-shot on Spleen/Kvasir/ChestXray (**3/6**); MedSAM leads on its own pretraining distributions — derm (ISIC), US (HC18), MRI (prostate) — but by **<0.015** once the generic decoder is tuned, and generic-frozen still beats MedSAM-frozen on prostate (0.895 vs 0.807). Medical pretraining helps most exactly where MedSAM saw the data, yet few-shot tuning of the generic decoder nearly erases it — decoder adaptation, not medical pretraining, is the lever.

Can it be ONE domain-agnostic pipeline? — few-shot skills + a router, SAM frozen

Each domain has a distinct setup — so can it be a single domain-agnostic pipeline that few-shot-fits per domain WITHOUT tuning SAM? We test the transferable skill — a frozen-SAM-feature localizer prototype fit from N labeled images — with identical code across all six domains, SAM never touched.

Domain-agnostic few-shot skill transfer: skills few-shot-fit, topology is routed not tuned — **(A)** One fixed pipeline (prototype-sim localizer): the skill **few-shot-fits** — saturates by ~N=10 on every domain — and scores high where the target is prototype-localizable (ISIC 0.71, CXR 0.62, HC18 US 0.72), mid where it is a central structure (Prostate MRI 0.51), low where it needs a specialized localizer (Kvasir 0.35, Spleen 0.12). **(B)** **Routing** the per-domain topology (genome / static-box / op_sam dense-correspondence / volume-prior / ellipse-snap / volume-trajectory) + the few-shot skill recovers most of the deployed number (Kvasir 0.35→0.77→0.86, HC18 0.69→0.92, Prostate 0.51→0.76, Spleen 0.14→0.66→0.83@N=50).

Yes — a domain-agnostic pipeline = frozen SAM + a GT-free router + few-shot skills. The learning (localizer prototype + gate weights + genome) is domain-agnostic, few-shot (~10 labels; ~50 for the isodense spleen), and SAM-frozen — it transfers with identical code. The per-domain "distinct setup" you'd notice is which localizer topology to route to — a GT-free routing choice (learned config, the project's route.py), not SAM tuning. So onboarding a new domain is ~10 labels + a routing decision, zero gradient training. Robust localizer skill: the deployed default is now the op_sam frozen-DINOv2 dense-correspondence localizer (kvasir/HC18/prostate) — it transfers 10-shot support masks through the full patch cross-correlation, and superseded the earlier SAM+DINOv2 AMG-ranker ensemble on Kvasir (0.655→0.8646). The lesson holds and is now stronger: the polyp/fold and faint-skull walls yield to the right frozen feature space — dense correspondence, plus feature-diverse supports — not to distractor-verification tricks. The AMG-ranker ensemble (at/near the best single feature space on all three, Kvasir 0.65 / Spleen 0.64 / ISIC 0.67, never catastrophic where SAM-alone fails the isodense spleen 0.40) remains the LLM-agnostic fallback where a support set is too small for correspondence.

Qualitative examples — 3 best / 3 worst per dataset

Green = ground truth, red = prediction. Top row = 3 highest-Dice cases, bottom row = 3 lowest.

ISIC 2018 — skin lesion (pigment cue, LLM's best domain)

MSD Spleen — CT (localizer + cross-slice priors + SAM re-prompt polish)

Spleen best/worst — The worst cases are localizer failures (prediction lands on stomach/liver, Dice≈0). A GT-free cross-slice prior (centroid trajectory + sibling-mask seed), a selective multi-prototype re-decode, a SAM re-prompt boundary polish, and a final **pyramid keep-best** (crop→zoom→SAM-decode each tiny tip slice at higher resolution) recover them, lifting the spleen pipeline to **0.920** (0.786→0.840→0.868→0.875→0.903→0.920 this session) — now **beating** the best trained NN at N=100 (0.920 vs 0.907). Pyramid is complementary to the within-volume prior: the prior re-decodes a tip slice from its *siblings*, pyramid re-decodes it at higher *resolution*.

Kvasir-SEG — polyp (dense-correspondence localizer; the gap was localization, 89% closed)

Kvasir best/worst — Polyps share colour/texture with mucosa, so a *mean*-prototype / AMG-candidate ranker mislocalizes (~43/100 to Dice≈0) — and four verification signals (SAM self-consistency, FG-BG margin, cycle-consistency) all failed to rank the right blob. The unlock, grounded in the polyp-SAM literature (**OP-SAM**, ICCV'25, frozen Dice 0.845 on this exact dataset), is frozen-DINOv2 **dense-correspondence** label transfer (CPG): transfer 10 few-shot support masks onto the query via the *full* patch cross-correlation matrix — not a mean prototype (which washes out on polyp≈mucosa). The prior peak lands in the polyp **94%** of the time (vs the old LLM box's 0.46 box-IoU); a peak-**connected-component** box + prior-guided SAM mask selection then decodes it. Deployed **0.659 → 0.8646** (median **0.9484 — above the NN mean 0.889**), leak-free, frozen DINOv2+SAM, no tuning. A further lever closed the mislocalization tail: rebuilding the op_sam support set `kvasir_supports.npz` from the **first-30 (was first-10) train images** widens the dense-correspondence prior's appearance coverage (+0.032, two-split, leak-free, zero-code; one 0.000→0.834 recovery) — an **N=30 support budget** (30 train labels; still scarce, well under 100), a different quantity from the N=10 data-efficiency point above (0.824). Polyps want support *coverage/count*, not the FPS-*diversity* that wins on US/MRI (fps10 0.725 ≪ first10 0.826) — opposite knobs on the same support seam. The frozen GT-box oracle is 0.914 > NN, so Kvasir never had a decoder wall — its entire gap was localization, now 89% closed (was −0.230 to the NN, now −0.025); the residual is the known gate-bound polyp tail (no GT-free signal isolates the confidently-wrong mislocalizations). *Gallery shows the earlier LLM-box path; the correspondence localizer replaces the bottom-row localization misses.*

ChestXray — bilateral lungs (few-shot static box + self-reprompt → SAM)

CXR best/worst — Five GT-free skills: (1) a fixed few-shot lung box (mean of N=10 train GT boxes; box-IoU 0.545→0.67) replaces the heuristic box → 0.825→0.898; (2) a mask-bbox self-reprompt (box-IoU 0.67→0.83) → 0.898→0.911; (3) a **repair agent** that trims SAM's bright "out of lung" over-seg into the mediastinum (a decoder error a redraw loop can't reach), fire-gated + keep-best → 0.911→0.914 zero-regression; (4) a **catastrophic fix** — a SAM negative-point re-prompt (positive points on the dark lung, negative on the spill) that carves the worst engulfing masks the conservative trim can't → 0.914→0.920; (5) a **letterbox-component trim** that drops mask blobs sitting over near-black padding (on letterboxed films the misregistered atlas + darkness both score the black border as lung — only raw intensity separates it, since lung air is dark-*gray*, not pure black), fixing MCUCXR_0060 0.76→**0.88** zero-regression → 0.920→**0.922**. The remaining worst cases (bottom row) are a different, harder failure — inferior over-extension into the abdomen, a decoder-boundary error. Localization is not the gap here: even a perfect GT box caps the *frozen* SAM decoder at ~0.93, which long looked architectural. That cap was specific to the frozen decoder — a **few-shot-tuned decoder** (N=100 labels, encoder frozen, leak-free) re-decodes each lung's mask-bbox to **0.9488** ≈ the U-Net's 0.9546 (median 0.9608, 102/107 improve). So CXR's wall was the **decoder, not localization**, and it is breachable — but only in the **few-shot lane** (N=100 = the NN's own label budget), not training-free; the training-free headline stays 0.922.

HC18 Fetal-Head — ultrasound (op_sam CPG localizer + ellipse-snap + diverse supports + CLAHE prior) ·new

HC18 fetal-head best/worst — The fetal head IS an ellipse — a bright hyperechoic skull ring — so the paper-grounded upgrade fits an ellipse to the SAM mask and snaps to it, interpolating the acoustically-dropped walls (van den Heuvel HC18; YOSAM) → 0.854→0.859. The mean≪median tail then turned out **not** to be a perception floor: two stacking LLM-agnostic levers on the op_sam CPG localizer — **DINOv2-FPS diverse 20-shot supports** (feature-farthest-point-sampled; diversity not count) +0.0495, and **CLAHE prior-only enhancement** (enhance the correspondence prior while SAM decodes on the RAW image) +0.0226 — lift 0.859→**0.9225** (median 0.9522), narrowing the gap to U-Net to −0.048. Top: near-perfect ellipse fits (Dice ≈1.0). Bottom: the residual tail. Still loses to the trained U-Net at every budget (an easy-for-NN high-contrast skull), but the "perception floor" was disproven — it was support-diversity + contrast, not irreducible. The training-free headline stays **0.9225**. A **few-shot lane** now deploys on top of it: a **domain-agnostic box-tightening fixpoint** (generalizing the spleen/CXR self-reprompt loops into one config-driven `localize→decode→re-box(mask bbox)→re-decode` loop) wraps the N=100 tuned decoder with a GT-free boundary-gradient **keep-best gate**. On FetalHead the bright echogenic **skull ring** affords a **weak-but-valid** gate (within-image Spearman ρ ≈ **+0.2**), lifting the few-shot deployable **0.9225 → 0.9328** (+0.0103, median 0.9522→0.9587, **20 improve / 6 regress**) — harvesting **23% of the 0.9665 tuned-decoder GT-box oracle**. So the oracle-vs-deployable gap is only *partly* "box too loose" (multi-pass adds just +0.003 over single-pass) — it is mostly **ungateable per-image decoder noise**; the win comes from the weak gate the skull ring happens to afford. This is **few-shot (N=100 labels = the NN's budget), not training-free** — a distinct lane, exactly like CXR's 0.9488; never the training-free headline. The **gate is the deploy determinant**: the same loop **FAILS on Kvasir (ρ −0.09) and Prostate (ρ −0.02)** — no valid boundary gate — and is not ported. Deploys iff the gate is valid.

MSD Prostate — MRI (op_sam localizer, rho 1 tighter box + cross-slice trajectory + reprompt) ·new

prostate MRI best/worst — The prostate is a low-dimensional pose with a smooth cross-slice trajectory (PROMISE12; axial-symmetry prior), so the upgrade fits centroid(z)+area(z) per volume, re-decodes outliers, and reprompts the box → 0.664→0.715 (median 0.786). The 2026-07-05 agent research then tightened the op_sam box (**rho 2→1**, fewer CPG diffusion steps for this small isodense target; two-split validated, +0.038 val and test) → 0.744, then the meta-harness **auto-onboarder** surfaced **CLAHE prior-enhancement** (MRI is low-contrast like US — the same generic knob that lifted HC18) → **0.760** (median 0.803). Top: the small central gland found cleanly. Bottom: the residual tail. Beatable in principle (GT-box→SAM oracle 0.895 > NN 0.815), and there is real headroom — **+0.041 oracle** from keep-best over a boundary-refinement candidate family (the base slightly over-segments the isodense gland, so the residual is **boundary-precision, not localization**). Prostate is the cleanest instance of the project's **gate wall**: valid within-image gates DO exist (DINOv2 / SAM prototype-sim rank-ρ ≈ 0.70; cross-slice area ρ ≈ 0.51 — the boundary-gradient gate that works on spleen/CXR is invalid here, ρ=−0.36, no edge on the isodense gland), yet **none harvests the headroom**: unconstrained argmax caps at +0.007 (11/30 regress) and zero-regression collapses every gate to ≤+0.0034 (noise). The refined thesis: **a valid gate over the whole candidate family is not a valid gate at the DECISION BOUNDARY** — ρ=0.70 is earned by ranking the obviously-bad candidates last, while the top cluster (where the best candidate and the base are near-duplicates in both Dice and signal) makes argmax a coin-flip. Not wired; deployed stays **0.760**.

What we learned

ISIC: the LLM pipeline beats nnU-Net at every budget (+0.116 at N=10 → +0.025 at N=100) — genuinely more label-efficient for dermoscopy.
Spleen: a stack of GT-free skills — within-volume prior, cross-slice geometry, selective multi-prototype, a SAM re-prompt boundary polish, and a pyramid keep-best (higher-resolution re-decode of the tiny tip slices) — lifts 0.786 → 0.920, now beating the best trained NN at N=100 (0.920 vs 0.907; CV held-out). The pyramid and the volume prior see the tip slices two different ways — resolution vs siblings — and combine additively via a valid soft-tissue gate.
Kvasir: a frozen-DINOv2 dense-correspondence localizer (OP-SAM CPG label transfer + peak-connected-component box) lifts the polyp 0.659→0.8646 — the biggest single gain in the study, closing 89% of the−0.230 gap to the NN. The gap was pure localization (the frozen GT-box→SAM oracle is 0.914 > NN 0.889, so there is no decoder wall); the unlock is transferring few-shot support masks by dense correspondence, not a mean prototype (which washes out on polyp≈mucosa, and defeated four verification signals). The prior peak lands in the polyp 94% of the time; median 0.9484 now beats the NN mean, the mean stays just below best-NN 0.889 (residual = a gate-bound tail of hard localizations). A support-coverage lever — rebuilding the op_sam supports from the first-30 (was first-10) train images (+0.032, an N=30 support budget, still scarce; polyps want coverage/count, not FPS-diversity) — closed most of the remaining tail. Grounded in the domain's published frozen-SAM SOTA (OP-SAM, ICCV'25), leak-free, no tuning.
Chest X-ray: a few-shot static lung box + a mask-bbox self-reprompt + a repair agent (trims out-of-lung over-seg) + a catastrophic fix (SAM negative-point re-prompt on the worst spilled masks) + a letterbox trim (drops blobs over near-black padding) lift the training-free LLM 0.825→0.898→0.911→0.914→0.920→0.922 — the deployed gap was box localization, not architecture. The frozen decoder does cap even a perfect GT box at ~0.93, which long looked architectural — but that cap is specific to the frozen decoder: a few-shot-tuned decoder (N=100 labels, encoder frozen, leak-free) re-decodes to 0.9488 ≈ the U-Net's 0.9546. So CXR's real wall was the decoder, not localization, and it is breachable — but only in the few-shot lane (N=100 = the NN's own budget), not the training-free headline, which stays 0.922.

When does iterative feedback deploy? — the fix is general, the gate is the wall

We built a full repair-agent → verbal + visual feedback → SAM re-prompt → keep-best loop: the repair stage renders a diagnosis overlay (current mask + a GT-free "out-of-region" heat-map + a coordinate grid), the vision LLM looks, says what is wrong verbally, and marks the over-segmentation as SAM negative points; SAM re-decodes; a GT-free keep-best gate accepts or rejects; repeat. On chest X-ray the LLM's visual negatives beat the heuristic catastrophic fix (CHNCXR_0447 0.849→0.902, MCUCXR_0055 0.860→0.955).

CXR loop vs feed-forward — The cases the GT-free gate accepted (top = feed-forward catfix, bottom = the loop). The LLM's visual negatives tighten SAM off the mediastinum/abdomen better than the spill heuristic. Full-107: 0.9216→**0.9240** (+0.0024), zero-regression, gate near-perfect (oracle 0.9241).

But the fix is domain-general — the LLM can place negatives on any over-seg it sees. What decides deployability is the gate: whether a GT-free signal can rank candidate masks by true Dice. We measured that gate↔Dice correlation on all four domains:

Gate-validity across domains — The loop deploys **iff the GT-free gate is valid** — a property of the *domain*, not the loop. CXR (+0.63, lung darkness+atlas) and Spleen (+0.56, soft-tissue) have valid gates and the loop deploys; Kvasir (+0.04 — polyp≈mucosa, no signal) and ISIC (−0.23 — the gate prefers over-grown high-contrast masks) do not, so no amount of good feedback can be deployed. **2 of 4 domains.**

The core lesson. Iteration is not the lever — perception, or its GT-free proxy, is. The same wall shows up as the SIZE law, the structural-ceiling taxonomy, and here as gate-validity: a feedback loop is only as deployable as the GT-free mask-quality signal in that domain. Where the target is cheaply separable (dark lung air, soft-tissue organ edges) a gated fix pays off; where it is not (polyp on mucosa) neither a loop nor a single fix can deploy without ground truth.

Honest-reporting note: earlier drafts carried optimistic hardcoded values (ISIC 0.885, Kvasir 0.860, CXR 0.855). This report uses numbers re-measured from scratch with the current pipeline: ISIC 0.880, Spleen 0.920 (CV-held-out), Kvasir 0.8646, CXR 0.922 (training-free). (Kvasir was 0.659 before the dense-correspondence localizer.)

Pipeline

One image, end to end. A GT-free router selects skills per image; the drawer seam (amber) is the only model-coupled point — one config-driven dispatch_localizer picks per domain among an LLM polygon drawer, a frozen SAM-feature prototype, a frozen-DINOv2 dense-correspondence (CPG) localizer, or a static box — and everything downstream is numpy/config. Green boxes (🔄) are iterative loops: SAM fixed-point re-prompts and the spleen two-pass within-volume prior.

agenticSeg · training-free LLM+SAM medical segmentation · github.com/R9-Hu/agenticSeg
Skills are LLM-agnostic numpy/config; every result reproducible via eval_all_domains.py. AI-assisted (Claude Code).