{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7SC6JUD3J4LQ4UOII3DPFQOB4W","short_pith_number":"pith:7SC6JUD3","schema_version":"1.0","canonical_sha256":"fc85e4d07b4f170e51c846c6f2c1c1e5bb4fc721799637b6df17f42a9aff315e","source":{"kind":"arxiv","id":"2407.07042","version":2},"attestation_state":"computed","paper":{"title":"ProtoSAM: One-Shot Medical Image Segmentation With Foundational Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hayit Greenspan, Lev Ayzenberg, Raja Giryes","submitted_at":"2024-07-09T17:04:08Z","abstract_excerpt":"This work introduces a new framework, ProtoSAM, for one-shot medical image segmentation. It combines the use of prototypical networks, known for few-shot segmentation, with SAM - a natural image foundation model. The method proposed creates an initial coarse segmentation mask using the ALPnet prototypical network, augmented with a DINOv2 encoder. Following the extraction of an initial mask, prompts are extracted, such as points and bounding boxes, which are then input into the Segment Anything Model (SAM). State-of-the-art results are shown on several medical image datasets and demonstrate aut"},"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":"2407.07042","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-09T17:04:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e5afc491a28e816945829cc4bd21d6a071b40bf97ea906386d83c4eeaf0faf81","abstract_canon_sha256":"db5fbf9984fbb035fc948fa205d31fc801cdeab21cb9316818b20bc79f7e3dab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:30.600068Z","signature_b64":"nS04QBzrdhwYt0/jZKNlqSL5OqPJnj3qSm08DzeczPLx5zOJrIZYFJGG9cnxGf3ZZWCTIyShd/lwEOZvJIHVAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc85e4d07b4f170e51c846c6f2c1c1e5bb4fc721799637b6df17f42a9aff315e","last_reissued_at":"2026-07-05T08:45:30.599651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:30.599651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProtoSAM: One-Shot Medical Image Segmentation With Foundational Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hayit Greenspan, Lev Ayzenberg, Raja Giryes","submitted_at":"2024-07-09T17:04:08Z","abstract_excerpt":"This work introduces a new framework, ProtoSAM, for one-shot medical image segmentation. It combines the use of prototypical networks, known for few-shot segmentation, with SAM - a natural image foundation model. The method proposed creates an initial coarse segmentation mask using the ALPnet prototypical network, augmented with a DINOv2 encoder. Following the extraction of an initial mask, prompts are extracted, such as points and bounding boxes, which are then input into the Segment Anything Model (SAM). State-of-the-art results are shown on several medical image datasets and demonstrate aut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07042","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.07042/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":"2407.07042","created_at":"2026-07-05T08:45:30.599708+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.07042v2","created_at":"2026-07-05T08:45:30.599708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07042","created_at":"2026-07-05T08:45:30.599708+00:00"},{"alias_kind":"pith_short_12","alias_value":"7SC6JUD3J4LQ","created_at":"2026-07-05T08:45:30.599708+00:00"},{"alias_kind":"pith_short_16","alias_value":"7SC6JUD3J4LQ4UOI","created_at":"2026-07-05T08:45:30.599708+00:00"},{"alias_kind":"pith_short_8","alias_value":"7SC6JUD3","created_at":"2026-07-05T08:45:30.599708+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26711","citing_title":"Mask to Concept: Auto-Promptable SAM3 via Efficient Test-Time Concept Embedding Search for Few-Shot Annotation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00744","citing_title":"Prototype Memory-Guided Training-Free Anomaly Classification and Localization in Prenatal Ultrasound","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26711","citing_title":"Mask to Concept: Auto-Promptable SAM3 via Efficient Test-Time Concept Embedding Search for Few-Shot Annotation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2603.07436","citing_title":"RPG-SAM: Reliability-Weighted Prototypes and Geometric Adaptive Threshold Selection for Training-Free One-Shot Polyp Segmentation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24719","citing_title":"DiffuSAM: Diffusion-Based Prompt-Free SAM2 for Few-Shot and Source-Free Medical Image Segmentation","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7SC6JUD3J4LQ4UOII3DPFQOB4W","json":"https://pith.science/pith/7SC6JUD3J4LQ4UOII3DPFQOB4W.json","graph_json":"https://pith.science/api/pith-number/7SC6JUD3J4LQ4UOII3DPFQOB4W/graph.json","events_json":"https://pith.science/api/pith-number/7SC6JUD3J4LQ4UOII3DPFQOB4W/events.json","paper":"https://pith.science/paper/7SC6JUD3"},"agent_actions":{"view_html":"https://pith.science/pith/7SC6JUD3J4LQ4UOII3DPFQOB4W","download_json":"https://pith.science/pith/7SC6JUD3J4LQ4UOII3DPFQOB4W.json","view_paper":"https://pith.science/paper/7SC6JUD3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.07042&json=true","fetch_graph":"https://pith.science/api/pith-number/7SC6JUD3J4LQ4UOII3DPFQOB4W/graph.json","fetch_events":"https://pith.science/api/pith-number/7SC6JUD3J4LQ4UOII3DPFQOB4W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7SC6JUD3J4LQ4UOII3DPFQOB4W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7SC6JUD3J4LQ4UOII3DPFQOB4W/action/storage_attestation","attest_author":"https://pith.science/pith/7SC6JUD3J4LQ4UOII3DPFQOB4W/action/author_attestation","sign_citation":"https://pith.science/pith/7SC6JUD3J4LQ4UOII3DPFQOB4W/action/citation_signature","submit_replication":"https://pith.science/pith/7SC6JUD3J4LQ4UOII3DPFQOB4W/action/replication_record"}},"created_at":"2026-07-05T08:45:30.599708+00:00","updated_at":"2026-07-05T08:45:30.599708+00:00"}