{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BVQCOUBMRT42SL6GHJBKFNTKED","short_pith_number":"pith:BVQCOUBM","schema_version":"1.0","canonical_sha256":"0d6027502c8cf9a92fc63a42a2b66a20c99ce5696ed241011060229238e4a4b8","source":{"kind":"arxiv","id":"2605.12567","version":1},"attestation_state":"computed","paper":{"title":"Pyramid Self-contrastive Learning Framework for Test-time Ultrasound Image Denoising","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Self-contrastive learning on sub-aperture signals produces denoised ultrasound images from a single test sample.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bingze Dai, Jiajing Zhang, Wei-Ning Lee, Xi Zhang, Yue Xu","submitted_at":"2026-05-12T09:27:21Z","abstract_excerpt":"The inherent electronic and speckle noise complicates clinical interpretation of ultrasound images. Conventional denoising methods rely on explicit noise assumptions whose validity diminishes under composite noise conditions. Learning-based methods require massive labeled data and model parameters. These pre-defined and pre-trained manners entail an inevitable domain shift in complex in vivo environments, so they are limited to a specific noise type and often blur structural details. In this study, we propose a pure test-time training framework for one-shot ultrasound image denoising and apply"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.12567","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T09:27:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"77c5da0b3ac853cbe93fa364ade39354eea4e48b2d4cbb2f28553185be13919a","abstract_canon_sha256":"7650691334ac4d0d8bbdb821da603a4adf9df0ff0fff7d60c1a3e5c011fd3dc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:10:01.840502Z","signature_b64":"S28HiUvlp3F2q8xPP6OA7+vQAs0DvTbnxnBIKTucLPuj0EYrH2dqofZ34VFX8evVJV49mxQpFrLtoQBVycnGAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d6027502c8cf9a92fc63a42a2b66a20c99ce5696ed241011060229238e4a4b8","last_reissued_at":"2026-05-18T03:10:01.839807Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:10:01.839807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pyramid Self-contrastive Learning Framework for Test-time Ultrasound Image Denoising","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Self-contrastive learning on sub-aperture signals produces denoised ultrasound images from a single test sample.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bingze Dai, Jiajing Zhang, Wei-Ning Lee, Xi Zhang, Yue Xu","submitted_at":"2026-05-12T09:27:21Z","abstract_excerpt":"The inherent electronic and speckle noise complicates clinical interpretation of ultrasound images. Conventional denoising methods rely on explicit noise assumptions whose validity diminishes under composite noise conditions. Learning-based methods require massive labeled data and model parameters. These pre-defined and pre-trained manners entail an inevitable domain shift in complex in vivo environments, so they are limited to a specific noise type and often blur structural details. In this study, we propose a pure test-time training framework for one-shot ultrasound image denoising and apply"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our Aperture-to-Aperture (A2A) framework disentangles anatomical similarity and noise randomness from shuffled sub-apertures through self-contrastive learning in pyramid latent spaces. The clean image is then decoded from the anatomy space, while discarding the noise space. Simulation experiments demonstrated an improvement of 69.3% SNR and 34.4% CNR by A2A. The in vivo results showed 84.8% SNR and 25.7% CNR gains using only two aperture data.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That sub-aperture signals in synthetic aperture ultrasound share sufficient anatomical content while differing primarily in independent noise realizations, allowing reliable disentanglement via self-contrastive learning in pyramid spaces even for complex in vivo composite noise without additional regularization or failure modes.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A2A achieves one-shot ultrasound denoising via pyramid self-contrastive learning on sub-aperture signals to disentangle anatomy from noise, yielding large SNR and CNR gains in simulations and in vivo scans.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Self-contrastive learning on sub-aperture signals produces denoised ultrasound images from a single test sample.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"3b3ba93090d562b27ae53fa0464822e6f87a0e827a1df4550f37cf822863b362"},"source":{"id":"2605.12567","kind":"arxiv","version":1},"verdict":{"id":"c2c5ae81-eab7-4e6a-81ed-8e51e4b314f1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:57:03.150351Z","strongest_claim":"Our Aperture-to-Aperture (A2A) framework disentangles anatomical similarity and noise randomness from shuffled sub-apertures through self-contrastive learning in pyramid latent spaces. The clean image is then decoded from the anatomy space, while discarding the noise space. Simulation experiments demonstrated an improvement of 69.3% SNR and 34.4% CNR by A2A. The in vivo results showed 84.8% SNR and 25.7% CNR gains using only two aperture data.","one_line_summary":"A2A achieves one-shot ultrasound denoising via pyramid self-contrastive learning on sub-aperture signals to disentangle anatomy from noise, yielding large SNR and CNR gains in simulations and in vivo scans.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That sub-aperture signals in synthetic aperture ultrasound share sufficient anatomical content while differing primarily in independent noise realizations, allowing reliable disentanglement via self-contrastive learning in pyramid spaces even for complex in vivo composite noise without additional regularization or failure modes.","pith_extraction_headline":"Self-contrastive learning on sub-aperture signals produces denoised ultrasound images from a single test sample."},"references":{"count":68,"sample":[{"doi":"","year":2006,"title":"J. A. Jensen, S. I. Nikolov, K. L. Gammelmark, M. H. Pedersen, Syntheticapertureultrasoundimaging,Ultrasonics44(2006)e5–e15","work_id":"2fc608b0-e044-4d2e-822f-5bf04f89b740","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2014,"title":"C. Papadacci, M. Pernot, M. Couade, M. Fink, M. Tanter, High- contrastultrafastimagingoftheheart,IEEEtransactionsonultrason- ics, ferroelectrics, and frequency control 61 (2) (2014) 288–301","work_id":"be2f8727-66e2-41f2-9c0f-66339dbf1347","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2005,"title":"K. Krissian, R. Kikinis, C.-F. Westin, K. Vosburgh, Speckle- constrained filtering of ultrasound images, in: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05),","work_id":"3882f29b-6e3e-4cb1-b1e8-0f02422d6d04","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2002,"title":"H. Xie, L. E. Pierce, F. T. Ulaby, Statistical properties of logarith- mically transformed speckle, IEEE transactions on geoscience and remote sensing 40 (3) (2002) 721–727","work_id":"0931a0c2-7ff5-4f4d-8ad0-a7f6853a7255","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1987,"title":"T. Loupas, W. McDicken, P. Allan, Noise reduction in ultrasonic images by digital filtering, The British journal of radiology 60 (712) (1987) 389–392","work_id":"6f36b4c8-5ba9-4f7d-a3d5-275d499f4b8b","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":68,"snapshot_sha256":"ba988434bc4a3bb33dc9858cdccb4e6cbc56e7259c1fdce2b4c6c6f11e958d84","internal_anchors":2},"formal_canon":{"evidence_count":1,"snapshot_sha256":"5d11a1761b0028d439a9f913006ee873bd0727d434448a1b109670a5bec7f6d7"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.12567","created_at":"2026-05-18T03:10:01.839904+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.12567v1","created_at":"2026-05-18T03:10:01.839904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12567","created_at":"2026-05-18T03:10:01.839904+00:00"},{"alias_kind":"pith_short_12","alias_value":"BVQCOUBMRT42","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"BVQCOUBMRT42SL6G","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"BVQCOUBM","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BVQCOUBMRT42SL6GHJBKFNTKED","json":"https://pith.science/pith/BVQCOUBMRT42SL6GHJBKFNTKED.json","graph_json":"https://pith.science/api/pith-number/BVQCOUBMRT42SL6GHJBKFNTKED/graph.json","events_json":"https://pith.science/api/pith-number/BVQCOUBMRT42SL6GHJBKFNTKED/events.json","paper":"https://pith.science/paper/BVQCOUBM"},"agent_actions":{"view_html":"https://pith.science/pith/BVQCOUBMRT42SL6GHJBKFNTKED","download_json":"https://pith.science/pith/BVQCOUBMRT42SL6GHJBKFNTKED.json","view_paper":"https://pith.science/paper/BVQCOUBM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.12567&json=true","fetch_graph":"https://pith.science/api/pith-number/BVQCOUBMRT42SL6GHJBKFNTKED/graph.json","fetch_events":"https://pith.science/api/pith-number/BVQCOUBMRT42SL6GHJBKFNTKED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BVQCOUBMRT42SL6GHJBKFNTKED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BVQCOUBMRT42SL6GHJBKFNTKED/action/storage_attestation","attest_author":"https://pith.science/pith/BVQCOUBMRT42SL6GHJBKFNTKED/action/author_attestation","sign_citation":"https://pith.science/pith/BVQCOUBMRT42SL6GHJBKFNTKED/action/citation_signature","submit_replication":"https://pith.science/pith/BVQCOUBMRT42SL6GHJBKFNTKED/action/replication_record"}},"created_at":"2026-05-18T03:10:01.839904+00:00","updated_at":"2026-05-18T03:10:01.839904+00:00"}