{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MMX2Q6W5CBJIPK7QRPPXZIZQ7E","short_pith_number":"pith:MMX2Q6W5","schema_version":"1.0","canonical_sha256":"632fa87add105287abf08bdf7ca330f9303babefad6c0ebda9d4a1190e6cc715","source":{"kind":"arxiv","id":"2504.04066","version":1},"attestation_state":"computed","paper":{"title":"Performance Analysis of Deep Learning Models for Femur Segmentation in MRI Scan","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Anning Tian, Jeongkyu Lee, Mengyuan Liu, Mozhi Shen, Tianchou Gong, Xinmeng Wu, Yixiao Chen","submitted_at":"2025-04-05T05:47:56Z","abstract_excerpt":"Convolutional neural networks like U-Net excel in medical image segmentation, while attention mechanisms and KAN enhance feature extraction. Meta's SAM 2 uses Vision Transformers for prompt-based segmentation without fine-tuning. However, biases in these models impact generalization with limited data. In this study, we systematically evaluate and compare the performance of three CNN-based models, i.e., U-Net, Attention U-Net, and U-KAN, and one transformer-based model, i.e., SAM 2 for segmenting femur bone structures in MRI scan. The dataset comprises 11,164 MRI scans with detailed annotations"},"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":"2504.04066","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2025-04-05T05:47:56Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"fc5e37dcfc89c67d5f9fa26205ba1cf802e9a3f460d268fc9effefb3b6739202","abstract_canon_sha256":"e76ac9df53b86db042a985cf413f857dcd8685a50e200a17a5adcb647eb4f42a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:21.453780Z","signature_b64":"UyHBdQeQJ/oi6ZttgaxEMFa2Df7/RIKgMPKR9dWfvyPP8uO7T2YbPBw1REYhZ/04AmmVPynCYbXb03gXQ2+rAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"632fa87add105287abf08bdf7ca330f9303babefad6c0ebda9d4a1190e6cc715","last_reissued_at":"2026-07-05T10:45:21.453280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:21.453280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Performance Analysis of Deep Learning Models for Femur Segmentation in MRI Scan","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Anning Tian, Jeongkyu Lee, Mengyuan Liu, Mozhi Shen, Tianchou Gong, Xinmeng Wu, Yixiao Chen","submitted_at":"2025-04-05T05:47:56Z","abstract_excerpt":"Convolutional neural networks like U-Net excel in medical image segmentation, while attention mechanisms and KAN enhance feature extraction. Meta's SAM 2 uses Vision Transformers for prompt-based segmentation without fine-tuning. However, biases in these models impact generalization with limited data. In this study, we systematically evaluate and compare the performance of three CNN-based models, i.e., U-Net, Attention U-Net, and U-KAN, and one transformer-based model, i.e., SAM 2 for segmenting femur bone structures in MRI scan. The dataset comprises 11,164 MRI scans with detailed annotations"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04066","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/2504.04066/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":"2504.04066","created_at":"2026-07-05T10:45:21.453356+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.04066v1","created_at":"2026-07-05T10:45:21.453356+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04066","created_at":"2026-07-05T10:45:21.453356+00:00"},{"alias_kind":"pith_short_12","alias_value":"MMX2Q6W5CBJI","created_at":"2026-07-05T10:45:21.453356+00:00"},{"alias_kind":"pith_short_16","alias_value":"MMX2Q6W5CBJIPK7Q","created_at":"2026-07-05T10:45:21.453356+00:00"},{"alias_kind":"pith_short_8","alias_value":"MMX2Q6W5","created_at":"2026-07-05T10:45:21.453356+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.06258","citing_title":"XAG-Net: A Cross-Slice Attention and Skip Gating Network for 2.5D Femur MRI Segmentation","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MMX2Q6W5CBJIPK7QRPPXZIZQ7E","json":"https://pith.science/pith/MMX2Q6W5CBJIPK7QRPPXZIZQ7E.json","graph_json":"https://pith.science/api/pith-number/MMX2Q6W5CBJIPK7QRPPXZIZQ7E/graph.json","events_json":"https://pith.science/api/pith-number/MMX2Q6W5CBJIPK7QRPPXZIZQ7E/events.json","paper":"https://pith.science/paper/MMX2Q6W5"},"agent_actions":{"view_html":"https://pith.science/pith/MMX2Q6W5CBJIPK7QRPPXZIZQ7E","download_json":"https://pith.science/pith/MMX2Q6W5CBJIPK7QRPPXZIZQ7E.json","view_paper":"https://pith.science/paper/MMX2Q6W5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.04066&json=true","fetch_graph":"https://pith.science/api/pith-number/MMX2Q6W5CBJIPK7QRPPXZIZQ7E/graph.json","fetch_events":"https://pith.science/api/pith-number/MMX2Q6W5CBJIPK7QRPPXZIZQ7E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MMX2Q6W5CBJIPK7QRPPXZIZQ7E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MMX2Q6W5CBJIPK7QRPPXZIZQ7E/action/storage_attestation","attest_author":"https://pith.science/pith/MMX2Q6W5CBJIPK7QRPPXZIZQ7E/action/author_attestation","sign_citation":"https://pith.science/pith/MMX2Q6W5CBJIPK7QRPPXZIZQ7E/action/citation_signature","submit_replication":"https://pith.science/pith/MMX2Q6W5CBJIPK7QRPPXZIZQ7E/action/replication_record"}},"created_at":"2026-07-05T10:45:21.453356+00:00","updated_at":"2026-07-05T10:45:21.453356+00:00"}