{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:Z3343MU6HNRV3A6JQH3OCJ5775","short_pith_number":"pith:Z3343MU6","schema_version":"1.0","canonical_sha256":"cef7cdb29e3b635d83c981f6e127bfff5a4cbd756372719653692c893a43be67","source":{"kind":"arxiv","id":"1907.01376","version":2},"attestation_state":"computed","paper":{"title":"Multi-scale GANs for Memory-efficient Generation of High Resolution Medical Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Alex Frydrychowicz, Fabian Jacob, Heinz Handels, Hristina Uzunova, Jan Ehrhardt","submitted_at":"2019-07-02T13:59:24Z","abstract_excerpt":"Currently generative adversarial networks (GANs) are rarely applied to medical images of large sizes, especially 3D volumes, due to their large computational demand. We propose a novel multi-scale patch-based GAN approach to generate large high resolution 2D and 3D images. Our key idea is to first learn a low-resolution version of the image and then generate patches of successively growing resolutions conditioned on previous scales. In a domain translation use-case scenario, 3D thorax CTs of size 512x512x512 and thorax X-rays of size 2048x2048 are generated and we show that, due to the constan"},"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":"1907.01376","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2019-07-02T13:59:24Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"828673d7cfd9f5274d1f23d181b1ecd927af7c5c9b9b41a9b303402719a8da93","abstract_canon_sha256":"b3376bc3dfbdd8d79771309dde30111e26f7038d8b5bbbe485bff8f5847fb571"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:16.990071Z","signature_b64":"FY0psw8MWbFx3KWMDq8dwFBG42X9r9WZYMJJo1o8K9ubg/yrJ0AuKe42CB1fd4uDE5J2c31piqMiQqM4eoKQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cef7cdb29e3b635d83c981f6e127bfff5a4cbd756372719653692c893a43be67","last_reissued_at":"2026-05-17T23:41:16.989290Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:16.989290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-scale GANs for Memory-efficient Generation of High Resolution Medical Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Alex Frydrychowicz, Fabian Jacob, Heinz Handels, Hristina Uzunova, Jan Ehrhardt","submitted_at":"2019-07-02T13:59:24Z","abstract_excerpt":"Currently generative adversarial networks (GANs) are rarely applied to medical images of large sizes, especially 3D volumes, due to their large computational demand. We propose a novel multi-scale patch-based GAN approach to generate large high resolution 2D and 3D images. Our key idea is to first learn a low-resolution version of the image and then generate patches of successively growing resolutions conditioned on previous scales. In a domain translation use-case scenario, 3D thorax CTs of size 512x512x512 and thorax X-rays of size 2048x2048 are generated and we show that, due to the constan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.01376","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1907.01376","created_at":"2026-05-17T23:41:16.989434+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.01376v2","created_at":"2026-05-17T23:41:16.989434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.01376","created_at":"2026-05-17T23:41:16.989434+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z3343MU6HNRV","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z3343MU6HNRV3A6J","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z3343MU6","created_at":"2026-05-18T12:33:33.725879+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/Z3343MU6HNRV3A6JQH3OCJ5775","json":"https://pith.science/pith/Z3343MU6HNRV3A6JQH3OCJ5775.json","graph_json":"https://pith.science/api/pith-number/Z3343MU6HNRV3A6JQH3OCJ5775/graph.json","events_json":"https://pith.science/api/pith-number/Z3343MU6HNRV3A6JQH3OCJ5775/events.json","paper":"https://pith.science/paper/Z3343MU6"},"agent_actions":{"view_html":"https://pith.science/pith/Z3343MU6HNRV3A6JQH3OCJ5775","download_json":"https://pith.science/pith/Z3343MU6HNRV3A6JQH3OCJ5775.json","view_paper":"https://pith.science/paper/Z3343MU6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.01376&json=true","fetch_graph":"https://pith.science/api/pith-number/Z3343MU6HNRV3A6JQH3OCJ5775/graph.json","fetch_events":"https://pith.science/api/pith-number/Z3343MU6HNRV3A6JQH3OCJ5775/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z3343MU6HNRV3A6JQH3OCJ5775/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z3343MU6HNRV3A6JQH3OCJ5775/action/storage_attestation","attest_author":"https://pith.science/pith/Z3343MU6HNRV3A6JQH3OCJ5775/action/author_attestation","sign_citation":"https://pith.science/pith/Z3343MU6HNRV3A6JQH3OCJ5775/action/citation_signature","submit_replication":"https://pith.science/pith/Z3343MU6HNRV3A6JQH3OCJ5775/action/replication_record"}},"created_at":"2026-05-17T23:41:16.989434+00:00","updated_at":"2026-05-17T23:41:16.989434+00:00"}