{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6FSR52S3DFPSSY5SINKAASQXHY","short_pith_number":"pith:6FSR52S3","schema_version":"1.0","canonical_sha256":"f1651eea5b195f2963b24354004a173e3139a5529c92fbea53e950369ef06de9","source":{"kind":"arxiv","id":"2007.04226","version":5},"attestation_state":"computed","paper":{"title":"Labelling imaging datasets on the basis of neuroradiology reports: a validation study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Aisha Al Busaidi, Antanas Montvila, David A. Wood, Emily Guilhem, Gareth Barker, James H. Cole, Jeremy Lynch, Juveria Siddiqui, Matthew Benger, Matthew Townend, Naveen Gadapa, Sebastian Ourselin, Sina Kafiabadi, Thomas C. Booth","submitted_at":"2020-07-08T16:12:10Z","abstract_excerpt":"Natural language processing (NLP) shows promise as a means to automate the labelling of hospital-scale neuroradiology magnetic resonance imaging (MRI) datasets for computer vision applications. To date, however, there has been no thorough investigation into the validity of this approach, including determining the accuracy of report labels compared to image labels as well as examining the performance of non-specialist labellers. In this work, we draw on the experience of a team of neuroradiologists who labelled over 5000 MRI neuroradiology reports as part of a project to build a dedicated deep "},"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":"2007.04226","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2020-07-08T16:12:10Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"79b9906eb58649216ccf8b64d2e14ae5f06de6db57a43af39702962eb8e3ed67","abstract_canon_sha256":"a7a0636f4ba1590012ae7b0c42a3de0d64ad17514f5635a6c5ed7cb47ca96e6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:21:14.660408Z","signature_b64":"lc1p1j+YVc4nWawHiNTcTzrWozlc8aaMk0eILsf7t5QFXIXwEG0k5nfhjwFm/YM/vEJlsPMbpvvWIhf3hBqxBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1651eea5b195f2963b24354004a173e3139a5529c92fbea53e950369ef06de9","last_reissued_at":"2026-07-05T02:21:14.659899Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:21:14.659899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Labelling imaging datasets on the basis of neuroradiology reports: a validation study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Aisha Al Busaidi, Antanas Montvila, David A. Wood, Emily Guilhem, Gareth Barker, James H. Cole, Jeremy Lynch, Juveria Siddiqui, Matthew Benger, Matthew Townend, Naveen Gadapa, Sebastian Ourselin, Sina Kafiabadi, Thomas C. Booth","submitted_at":"2020-07-08T16:12:10Z","abstract_excerpt":"Natural language processing (NLP) shows promise as a means to automate the labelling of hospital-scale neuroradiology magnetic resonance imaging (MRI) datasets for computer vision applications. To date, however, there has been no thorough investigation into the validity of this approach, including determining the accuracy of report labels compared to image labels as well as examining the performance of non-specialist labellers. In this work, we draw on the experience of a team of neuroradiologists who labelled over 5000 MRI neuroradiology reports as part of a project to build a dedicated deep "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.04226","kind":"arxiv","version":5},"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/2007.04226/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":"2007.04226","created_at":"2026-07-05T02:21:14.659958+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.04226v5","created_at":"2026-07-05T02:21:14.659958+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.04226","created_at":"2026-07-05T02:21:14.659958+00:00"},{"alias_kind":"pith_short_12","alias_value":"6FSR52S3DFPS","created_at":"2026-07-05T02:21:14.659958+00:00"},{"alias_kind":"pith_short_16","alias_value":"6FSR52S3DFPSSY5S","created_at":"2026-07-05T02:21:14.659958+00:00"},{"alias_kind":"pith_short_8","alias_value":"6FSR52S3","created_at":"2026-07-05T02:21:14.659958+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6FSR52S3DFPSSY5SINKAASQXHY","json":"https://pith.science/pith/6FSR52S3DFPSSY5SINKAASQXHY.json","graph_json":"https://pith.science/api/pith-number/6FSR52S3DFPSSY5SINKAASQXHY/graph.json","events_json":"https://pith.science/api/pith-number/6FSR52S3DFPSSY5SINKAASQXHY/events.json","paper":"https://pith.science/paper/6FSR52S3"},"agent_actions":{"view_html":"https://pith.science/pith/6FSR52S3DFPSSY5SINKAASQXHY","download_json":"https://pith.science/pith/6FSR52S3DFPSSY5SINKAASQXHY.json","view_paper":"https://pith.science/paper/6FSR52S3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.04226&json=true","fetch_graph":"https://pith.science/api/pith-number/6FSR52S3DFPSSY5SINKAASQXHY/graph.json","fetch_events":"https://pith.science/api/pith-number/6FSR52S3DFPSSY5SINKAASQXHY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6FSR52S3DFPSSY5SINKAASQXHY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6FSR52S3DFPSSY5SINKAASQXHY/action/storage_attestation","attest_author":"https://pith.science/pith/6FSR52S3DFPSSY5SINKAASQXHY/action/author_attestation","sign_citation":"https://pith.science/pith/6FSR52S3DFPSSY5SINKAASQXHY/action/citation_signature","submit_replication":"https://pith.science/pith/6FSR52S3DFPSSY5SINKAASQXHY/action/replication_record"}},"created_at":"2026-07-05T02:21:14.659958+00:00","updated_at":"2026-07-05T02:21:14.659958+00:00"}