{"paper":{"title":"FrequencyCT: Frequency Domain Self-supervised Low-dose CT Denoising","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Frequency-domain anchoring and perturbation generate pseudo-labels that train a denoiser on noisy low-dose CT data alone.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chong Chen, Guoquan Wei, Liu Shi, Qiegen Liu","submitted_at":"2026-05-11T13:55:03Z","abstract_excerpt":"Despite extensive research on computed tomography (CT) denoising, few studies exploit projection-domain data characteristics to mitigate noise correlation. To bridge this gap, this work proposes FrequencyCT, the first zero-shot self-supervised method for pseudo-sample generation in the frequency domain for low-dose CT denoising. Specifically, by exploiting the distinct frequency-domain distributions of noise and true signal, a regional low-frequency anchoring technique is proposed. Applying phase-preserving noise and mask perturbations to the high-frequency region generates pseudo-samples for "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"this work proposes FrequencyCT, the first zero-shot self-supervised method for pseudo-label generation in the frequency domain for low-dose CT denoising. [...] Evaluation results on multiple public and real-world datasets confirm the clinical application potential of this research, which will have a revolutionary impact on the field of denoising.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Leveraging the characteristic of the frequency domain that largely isolates noise from clean signals, a regional low-frequency anchoring technique is proposed.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"FrequencyCT generates pseudo-labels via regional low-frequency anchoring, phase-preserving modulation, and high-frequency mask perturbation for self-supervised low-dose CT denoising.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Frequency-domain anchoring and perturbation generate pseudo-labels that train a denoiser on noisy low-dose CT data alone.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"81cae4bcbd1583d3fec6398f6fddd93b09410793b26547a49984fcef33ffb773"},"source":{"id":"2605.10583","kind":"arxiv","version":2},"verdict":{"id":"e0f00b4c-6af8-4335-8a21-1c6c6286ce2d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T03:39:33.752574Z","strongest_claim":"this work proposes FrequencyCT, the first zero-shot self-supervised method for pseudo-label generation in the frequency domain for low-dose CT denoising. [...] Evaluation results on multiple public and real-world datasets confirm the clinical application potential of this research, which will have a revolutionary impact on the field of denoising.","one_line_summary":"FrequencyCT generates pseudo-labels via regional low-frequency anchoring, phase-preserving modulation, and high-frequency mask perturbation for self-supervised low-dose CT denoising.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Leveraging the characteristic of the frequency domain that largely isolates noise from clean signals, a regional low-frequency anchoring technique is proposed.","pith_extraction_headline":"Frequency-domain anchoring and perturbation generate pseudo-labels that train a denoiser on noisy low-dose CT data alone."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.10583/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T05:42:00.866888Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T14:40:58.983779Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T11:01:17.628969Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T09:10:04.958519Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"f9d71ef5282001e7fc6bc19d0d7dd3b33628fb7b22fa2e865acacb2364014777"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"decc2154e44355417b3af9e1c474ef8162d2f54243f5866ecafa88d89172b588"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}