bio.rodeo
ModelsOrganizationsProvidersLeaderboardAboutSign in
bio.rodeo

The authoritative source for evaluating biological foundation models. No hype, just honest analysis.

Categories
  • DNA & Gene
  • RNA
  • Protein
  • Small molecule
  • Single-cell
  • Spatial omics
  • Pathology
  • Imaging
  • Metabolomics
  • Biosignals
  • Language model
bio.rodeoModelsOrganizationsProvidersLeaderboardAboutFAQSubmit a modelTermsPrivacyContact
© 2026 Pulsatance. All rights reserved. ~
Built by Pulsatance
models / pathology / corepath
PathologyLanguage model
West China Hospital of Sichuan UniversitySichuan UniversityHong Kong University of Science and Technology (Guangzhou)Released August 2026

CorePath

Breast-specialized multimodal pathology foundation model for core needle biopsy diagnosis, with conformal risk control gating report release.

The short version

  • —Zero-shot breast biopsy subtyping from text prompts, with no per-label-system training set
  • —Drafts breast core needle biopsy diagnostic reports straight from the whole-slide image
  • —Weighted AUCs of 0.9526-0.9735 for five-class histological subtyping across centers
  • —Conformal gating releases a report, falls back to a subtype label, or defers the case
  • —Trains only Perceiver adapters in the slide encoder, keeping the language branch frozen
9Openness

Where to run it

No providers recorded yet. Browse all providers

Breast core needle biopsy (CNB) is the first diagnostic step for most suspected breast cancers, and one of the harder specimens to read. The sampled tissue is small, lesions are heterogeneous, and diagnostically adjacent entities overlap morphologically, so a report has to be built up in stages — cancer versus noncancer, then in situ versus invasive, then histological subtype. General-purpose pathology foundation models learn transferable slide-level representations, but they are trained for breadth across organs rather than for this particular diagnostic hierarchy.

CorePath is a breast-specialized multimodal pathology foundation model built for that setting. Pathologists and computer scientists at West China Hospital of Sichuan University, with collaborators at Sichuan University, HKUST (Guangzhou), and three partner hospitals, adapted PRISM — the slide-level vision-language model of Shaikovski et al., arXiv:2405.10254, and not the later PRISM2 — using 7,901 paired breast CNB whole-slide images and diagnostic reports from two centers. The adaptation is deliberately narrow: only adapters inside the Perceiver slide encoder are trained, so breast specialization accrues in the visual pathway while the language embedding space inherited from pretraining is left intact.

The release also includes CorePath-CRG, a conformalized report-generation wrapper that decides, per case, whether a generated report is trustworthy enough to release at all. Both were described in an August 2026 arXiv preprint that has not yet been peer reviewed.

#Key Features

  • Report-supervised breast adaptation: Paired WSI-report data supplies case-level diagnostic supervision directly, aligning slide morphology with the diagnostic language pathologists actually write rather than with a fixed label set.
  • Zero-shot hierarchical diagnosis: Diagnostic categories are supplied as text prompts at inference, so cancer detection, invasion assessment, and histological subtyping all run on one model with no task-specific classifier or retraining.
  • Three-tier selective release: CorePath-CRG routes each case to a synthesized report, a subtype-label-only fallback, or an "Unknown" deferral for pathologist review, using a release threshold calibrated by Learn-Then-Test.
  • Conformal confidence gating: Subtype predictions that fall inside conformal thresholds are retained as diagnostic evidence; unstable ones are masked before they can influence report synthesis.
  • Frozen language branch: Restricting updates to the visual side keeps the model from memorizing institutional reporting templates and exploiting text distribution biases.

#Technical Details

CorePath inherits PRISM's three-stage design: Virchow encodes tiles, a Perceiver slide encoder aggregates them into a slide embedding, and a BioGPT language branch handles text embedding, contrastive WSI-report alignment, and report decoding. Fine-tuning inserts bottleneck adapters (dimension 8, ReLU, residual scale 1.0) into feed-forward sublayers of the Perceiver — the FFN of the final transformer layer in the first block and the cross-attention FFNs of the first two blocks — leaving every other PRISM parameter frozen. Training ran 6 epochs on 8 NVIDIA RTX 3090 GPUs at an effective batch size of 640, learning rate 2e-4, with up to 2,560 tiles per slide and 768 text tokens. Chinese source reports were structured with DeepSeek-R1-Distill-Qwen-32B and translated to English with OpenBioLLM-70B before alignment.

On six independent private CNB cohorts, CorePath took the highest zero-shot weighted AUC in every cohort ahead of both PRISM and TITAN: 0.9669 to 0.9989 for cancer detection and 0.9643 to 0.9881 for invasion assessment, plus 0.9526 to 0.9735 for five-class histological subtyping in the five cohorts where subtype labels were available. On public benchmarks CorePath reached accuracy 0.8989 and weighted AUC 0.7780 for BCNB invasive carcinoma subtyping, and weighted AUCs of 0.8178 and 0.8252 for BRACS lesion stratification and fine-grained classification. In report generation, non-breast hallucinations fell from 30.1% to 2.8%; CorePath-CRG recorded none among released outputs, at the cost of full rejection rates between 19.15% and 38.58%.

#Applications

The intended user is a pathology service drafting breast CNB reports at volume. CorePath supplies a slide embedding queryable with clinically defined categories, which suits workflows whose label spaces shift between screening, invasion assessment, and subtyping without a labeled training set for each. CorePath-CRG targets the deployment question that usually blocks generative reporting in clinical settings: it releases free text only when calibrated evidence supports it, degrades to a bare subtype label when the narrative is unreliable, and defers the case otherwise.

#Impact

CorePath is evidence that a compact adapter fine-tune on a few thousand report-paired slides can specialize a general slide-level foundation model to one organ and specimen type while preserving zero-shot flexibility — a cheaper path than pretraining a new model per subspecialty. Pairing that with distribution-free risk control is the less common contribution: conformal methods have been applied to pathology classification and segmentation, but not to open-ended report generation. The study is retrospective, the fine-tuning data come from only two centers, and the exchangeability assumptions behind the conformal and Learn-Then-Test guarantees mean any new site needs local calibration. Code and weights are pledged to a public repository on acceptance; the repository is Apache-2.0 licensed but currently holds only a README, and the private WSI-report cohorts are not shareable.

At a glance

Released
August 2026
Category
Pathology
Organizations
West China Hospital of Sichuan University / Sichuan University / Hong Kong University of Science and Technology (Guangzhou)

Links

GitHub RepositoryResearch Paper

Tags

cancer_detectionhistologymultimodalreport_generationzero_shot

Something wrong?

Much of this page is generated or calculated automatically. Flag anything that looks off and we will re-run it.