A Semi-Supervised Framework for Breast Ultrasound Segmentation with Training-Free Pseudo-Label Generation and Label Refinement

A Semi-Supervised Framework for Breast Ultrasound Segmentation with Training-Free Pseudo-Label Generation and Label Refinement | Signal Canvas | ScienceToStartup

Page Freshness

Signal Canvas proof surface

Canonical route: /signal-canvas/a-semi-supervised-framework-for-breast-ultrasound-segmentation-with-training-free-pseudo-label-generation-and-label-refi

stale

Proof freshness: stale
Proof status: unverified
Display score: 8/10
Last proof check: 2026-04-02
Score updated: 2026-04-02
Score fresh until: 2026-05-02
References: 0
Source count: 0
Coverage: 17%

This page is showing the last landed evidence receipt and score bundle because the latest proof data is outside the freshness window.

Agent Handoff

Canonical ID a-semi-supervised-framework-for-breast-ultrasound-segmentation-with-training-free-pseudo-label-generation-and-label-refi | Route /signal-canvas/a-semi-supervised-framework-for-breast-ultrasound-segmentation-with-training-free-pseudo-label-generation-and-label-refi

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/signal-canvas/a-semi-supervised-framework-for-breast-ultrasound-segmentation-with-training-free-pseudo-label-generation-and-label-refi

MCP example

{
  "tool": "search_signal_canvas",
  "arguments": {
    "mode": "paper",
    "paper_ref": "a-semi-supervised-framework-for-breast-ultrasound-segmentation-with-training-free-pseudo-label-generation-and-label-refi",
    "query_text": "Summarize A Semi-Supervised Framework for Breast Ultrasound Segmentation with Training-Free Pseudo-Label Generation and Label Refinement"
  }
}

source_context

{
  "surface": "signal_canvas",
  "mode": "paper",
  "query": "A Semi-Supervised Framework for Breast Ultrasound Segmentation with Training-Free Pseudo-Label Generation and Label Refinement",
  "normalized_query": "2603.06167",
  "route": "/signal-canvas/a-semi-supervised-framework-for-breast-ultrasound-segmentation-with-training-free-pseudo-label-generation-and-label-refi",
  "paper_ref": "a-semi-supervised-framework-for-breast-ultrasound-segmentation-with-training-free-pseudo-label-generation-and-label-refi",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Evidence Receipt

Route status: building

Claims: 8

References: Pending verification

Proof: Verification pending

Freshness state: computing

Source paper: A Semi-Supervised Framework for Breast Ultrasound Segmentation with Training-Free Pseudo-Label Generation and Label Refinement

PDF: https://arxiv.org/pdf/2603.06167v1

Source count: Pending verification

Coverage: 17%

Last proof check: 2026-04-02T02:30:40.136Z

Signal Canvas receipt window

Watch and verify: A Semi-Supervised Framework for Breast Ultrasound Segmentation with Training-Free Pseudo-Label Generation and Label Refinement

/buildability/a-semi-supervised-framework-for-breast-ultrasound-segmentation-with-training-free-pseudo-label-generation-and-label-refi

Watchwatch

Subject: A Semi-Supervised Framework for Breast Ultrasound Segmentation with Training-Free Pseudo-Label Generation and Label Refinement

Verdict

Preparing verified analysis

GitHub Code Pulse

No public code linked for this paper yet.

Claim map

Strong 8Mixed 0Weak 0

Evidencepartial
Experiments on four BUS datasets demonstrate that our method achieves performance comparable to fully supervised models even with only 2.5% labeled data
Implicationpartial
Explicitly stated in abstract with clear performance comparison
Verificationpartial
partial
Evidencepartial
significantly outperforming existing SSL approaches
Implicationpartial
Directly stated in abstract with comparative context
Verificationpartial
partial
Evidencepartial
By leveraging simple appearance-based descriptions (e.g., dark oval), our method enables cross-domain structural transfer between natural and medical images
Implicationpartial
Explicitly described in abstract as core method component
Verificationpartial
partial
Evidencepartial
we further introduce uncertainty entropy weighted fusion and adaptive uncertainty-guided reverse contrastive learning to improve boundary discrimination
Implicationpartial
Directly stated as technical components of the method
Verificationpartial
partial
Evidencepartial
allowing VLMs to generate structurally consistent pseudo labels
Implicationpartial
Directly stated as a capability of the approach
Verificationpartial
partial
Evidencepartial
the proposed paradigm is readily extensible: for other imaging modalities or diseases, only a global appearance description is required to obtain reliable pseudo supervision
Implicationpartial
Explicitly stated as extensibility claim but requires inference about effectiveness
Verificationpartial
partial
Evidencepartial
Recent vision-language models (VLMs) provide a new opportunity for pseudo-label generation, yet their effectiveness on BUS images remains limited because domain-specific prompts are difficult to transfer
Implicationpartial
Directly stated as motivation for the research
Verificationpartial
partial
Evidencepartial
semi-supervised learning (SSL) has emerged as a promising paradigm for breast ultrasound (BUS) image segmentation, but it often suffers from unstable pseudo labels under extremely limited annotations
Implicationpartial
Directly stated as problem statement in abstract
Verificationpartial
partial

Author intelligence and commercialization panels stay hidden until the proof receipt is verified, cites at least 3 references, includes at least 2 sources, and clears 50% coverage. The paper narrative and citation surfaces remain public while verification is pending.

A Semi-Supervised Framework for Breast Ultrasound Segmentation with Training-Free Pseudo-Label Generation and Label Refinement

Use Signal Canvas as the narrative proof surface

Use this Signal Canvas via API or MCP

Signal Canvas proof surface