{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:J2MYRZ5VOK4XW75JLUAGHRQ7FM","short_pith_number":"pith:J2MYRZ5V","schema_version":"1.0","canonical_sha256":"4e9988e7b572b97b7fa95d0063c61f2b14f2fe03807938256dd24c6f5533e71f","source":{"kind":"arxiv","id":"2404.02382","version":1},"attestation_state":"computed","paper":{"title":"Imaging transformer for MRI denoising with the SNR unit training: enabling generalization across field-strengths, imaging contrasts, and anatomy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.IV","authors_text":"Adrienne Campbell, Ahsan Javed, Azaan Rehman, Hui Xue, Iain Pierce, James Moon, Peter Kellman, Rajiv Ramasawmy, Rhodri Davies, Sarah Hooper, Thomas Treibel, W Patricia Bandettini, Yang Yang, Zheren Zhu","submitted_at":"2024-04-03T00:51:07Z","abstract_excerpt":"The ability to recover MRI signal from noise is key to achieve fast acquisition, accurate quantification, and high image quality. Past work has shown convolutional neural networks can be used with abundant and paired low and high-SNR images for training. However, for applications where high-SNR data is difficult to produce at scale (e.g. with aggressive acceleration, high resolution, or low field strength), training a new denoising network using a large quantity of high-SNR images can be infeasible.\n  In this study, we overcome this limitation by improving the generalization of denoising model"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2404.02382","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2024-04-03T00:51:07Z","cross_cats_sorted":[],"title_canon_sha256":"c741b03c5a1239481e45001a6b785f4a117ef2755230f7a1083394bf2263bffd","abstract_canon_sha256":"783031e51202ffeb1a8ca739c08ca324f4826b83e87362ecf9f629ee5508a730"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:55.203950Z","signature_b64":"8n19o1HvsTD2jgWy3KpOJ5xcq+DCMQqzVBKJ703BtSsz7v867cloeM9a3kCGuZo/xbmLOyQvMsY2wtK4XP1FBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e9988e7b572b97b7fa95d0063c61f2b14f2fe03807938256dd24c6f5533e71f","last_reissued_at":"2026-07-05T08:03:55.203483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:55.203483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Imaging transformer for MRI denoising with the SNR unit training: enabling generalization across field-strengths, imaging contrasts, and anatomy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.IV","authors_text":"Adrienne Campbell, Ahsan Javed, Azaan Rehman, Hui Xue, Iain Pierce, James Moon, Peter Kellman, Rajiv Ramasawmy, Rhodri Davies, Sarah Hooper, Thomas Treibel, W Patricia Bandettini, Yang Yang, Zheren Zhu","submitted_at":"2024-04-03T00:51:07Z","abstract_excerpt":"The ability to recover MRI signal from noise is key to achieve fast acquisition, accurate quantification, and high image quality. Past work has shown convolutional neural networks can be used with abundant and paired low and high-SNR images for training. However, for applications where high-SNR data is difficult to produce at scale (e.g. with aggressive acceleration, high resolution, or low field strength), training a new denoising network using a large quantity of high-SNR images can be infeasible.\n  In this study, we overcome this limitation by improving the generalization of denoising model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02382","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.02382/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"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":"2404.02382","created_at":"2026-07-05T08:03:55.203540+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.02382v1","created_at":"2026-07-05T08:03:55.203540+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02382","created_at":"2026-07-05T08:03:55.203540+00:00"},{"alias_kind":"pith_short_12","alias_value":"J2MYRZ5VOK4X","created_at":"2026-07-05T08:03:55.203540+00:00"},{"alias_kind":"pith_short_16","alias_value":"J2MYRZ5VOK4XW75J","created_at":"2026-07-05T08:03:55.203540+00:00"},{"alias_kind":"pith_short_8","alias_value":"J2MYRZ5V","created_at":"2026-07-05T08:03:55.203540+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09590","citing_title":"Fast Voxelwise SNR Estimation for Iterative MRI Reconstructions","ref_index":72,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J2MYRZ5VOK4XW75JLUAGHRQ7FM","json":"https://pith.science/pith/J2MYRZ5VOK4XW75JLUAGHRQ7FM.json","graph_json":"https://pith.science/api/pith-number/J2MYRZ5VOK4XW75JLUAGHRQ7FM/graph.json","events_json":"https://pith.science/api/pith-number/J2MYRZ5VOK4XW75JLUAGHRQ7FM/events.json","paper":"https://pith.science/paper/J2MYRZ5V"},"agent_actions":{"view_html":"https://pith.science/pith/J2MYRZ5VOK4XW75JLUAGHRQ7FM","download_json":"https://pith.science/pith/J2MYRZ5VOK4XW75JLUAGHRQ7FM.json","view_paper":"https://pith.science/paper/J2MYRZ5V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.02382&json=true","fetch_graph":"https://pith.science/api/pith-number/J2MYRZ5VOK4XW75JLUAGHRQ7FM/graph.json","fetch_events":"https://pith.science/api/pith-number/J2MYRZ5VOK4XW75JLUAGHRQ7FM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J2MYRZ5VOK4XW75JLUAGHRQ7FM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J2MYRZ5VOK4XW75JLUAGHRQ7FM/action/storage_attestation","attest_author":"https://pith.science/pith/J2MYRZ5VOK4XW75JLUAGHRQ7FM/action/author_attestation","sign_citation":"https://pith.science/pith/J2MYRZ5VOK4XW75JLUAGHRQ7FM/action/citation_signature","submit_replication":"https://pith.science/pith/J2MYRZ5VOK4XW75JLUAGHRQ7FM/action/replication_record"}},"created_at":"2026-07-05T08:03:55.203540+00:00","updated_at":"2026-07-05T08:03:55.203540+00:00"}