pith:7FWJ2TCP
Rethinking Cross-Dose PET Denoising: Mitigating Averaging Effects via Residual Noise Learning
Estimating noise directly from low-dose PET images avoids the averaging effect in cross-dose denoising models.
arxiv:2604.16925 v3 · 2026-04-18 · cs.CV
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{7FWJ2TCPUTMWNZ24JFZHHWNCJU}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
We propose a unified residual noise learning framework that estimates noise directly from low-dose PET images rather than predicting full-dose images. Experiments on large-scale multi-dose PET datasets from two medical centers demonstrate that the proposed method outperforms the one-size-for-all model, individual dose-specific U-Net models, and dose-conditioned approaches.
The central claim rests on the premise that the noise component in low-dose PET can be treated as an additive residual whose statistical properties are sufficiently independent of the underlying anatomy that a network can learn to predict it directly from the noisy input alone (abstract, paragraph on residual noise learning framework).
The work introduces a residual noise learning framework for cross-dose PET denoising that avoids averaged mappings by estimating noise directly from low-dose inputs and shows gains over one-size-for-all and dose-specific baselines on multi-center data.
References
Formal links
Receipt and verification
| First computed | 2026-05-20T00:00:38.356476Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
f96c9d4c4fa4d966e75c497273d9a24d00fd58b00b57a9c1e414b7145d321a5b
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/7FWJ2TCPUTMWNZ24JFZHHWNCJU \
| jq -c '.canonical_record' \
| python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: f96c9d4c4fa4d966e75c497273d9a24d00fd58b00b57a9c1e414b7145d321a5b
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "34e42e66d1ad0eb86f0982b6465cf0f5d1fd93df798f3bd8f940b25ccdf0718d",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.CV",
"submitted_at": "2026-04-18T09:16:38Z",
"title_canon_sha256": "ce8097f7837d50cc8b7b9793d2eb98235b073a1d8a239b1ed91184ec26667444"
},
"schema_version": "1.0",
"source": {
"id": "2604.16925",
"kind": "arxiv",
"version": 3
}
}