{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZXABBL6VVEFWT63JVDUOALNVAD","short_pith_number":"pith:ZXABBL6V","schema_version":"1.0","canonical_sha256":"cdc010afd5a90b69fb69a8e8e02db500ceecc80f548176306b9ba74ee7ff52e3","source":{"kind":"arxiv","id":"2110.07919","version":1},"attestation_state":"computed","paper":{"title":"Combining CNNs With Transformer for Multimodal 3D MRI Brain Tumor Segmentation With Self-Supervised Pretraining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Danylo-Ivan Kolinko, Mariia Dobko, Ostap Viniavskyi, Yurii Yelisieiev","submitted_at":"2021-10-15T08:03:27Z","abstract_excerpt":"We apply an ensemble of modified TransBTS, nnU-Net, and a combination of both for the segmentation task of the BraTS 2021 challenge. In fact, we change the original architecture of the TransBTS model by adding Squeeze-and-Excitation blocks, an increasing number of CNN layers, replacing positional encoding in Transformer block with a learnable Multilayer Perceptron (MLP) embeddings, which makes Transformer adjustable to any input size during inference. With these modifications, we are able to largely improve TransBTS performance. Inspired by a nnU-Net framework we decided to combine it with our"},"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":"2110.07919","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2021-10-15T08:03:27Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"bc95f2b7c5a276b8014d673dcb922779062ca0e8d74269c30d15ba03760de273","abstract_canon_sha256":"ab59c0ba6260ef5eb4a630ca7bcf833a40c78f4ea4dd1131bfb13ea1fa006aae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:51.393091Z","signature_b64":"D44byMs50x3DzFOZ/nBODqqcN5yRBYQNVBtNeRh2qS/I0t8VeLhF1eyIPGJg+1Dh5A78k/0ThrTi/gFSbfYVBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdc010afd5a90b69fb69a8e8e02db500ceecc80f548176306b9ba74ee7ff52e3","last_reissued_at":"2026-07-05T03:22:51.392670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:51.392670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Combining CNNs With Transformer for Multimodal 3D MRI Brain Tumor Segmentation With Self-Supervised Pretraining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Danylo-Ivan Kolinko, Mariia Dobko, Ostap Viniavskyi, Yurii Yelisieiev","submitted_at":"2021-10-15T08:03:27Z","abstract_excerpt":"We apply an ensemble of modified TransBTS, nnU-Net, and a combination of both for the segmentation task of the BraTS 2021 challenge. In fact, we change the original architecture of the TransBTS model by adding Squeeze-and-Excitation blocks, an increasing number of CNN layers, replacing positional encoding in Transformer block with a learnable Multilayer Perceptron (MLP) embeddings, which makes Transformer adjustable to any input size during inference. With these modifications, we are able to largely improve TransBTS performance. Inspired by a nnU-Net framework we decided to combine it with our"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07919","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/2110.07919/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":"2110.07919","created_at":"2026-07-05T03:22:51.392729+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.07919v1","created_at":"2026-07-05T03:22:51.392729+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07919","created_at":"2026-07-05T03:22:51.392729+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZXABBL6VVEFW","created_at":"2026-07-05T03:22:51.392729+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZXABBL6VVEFWT63J","created_at":"2026-07-05T03:22:51.392729+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZXABBL6V","created_at":"2026-07-05T03:22:51.392729+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/ZXABBL6VVEFWT63JVDUOALNVAD","json":"https://pith.science/pith/ZXABBL6VVEFWT63JVDUOALNVAD.json","graph_json":"https://pith.science/api/pith-number/ZXABBL6VVEFWT63JVDUOALNVAD/graph.json","events_json":"https://pith.science/api/pith-number/ZXABBL6VVEFWT63JVDUOALNVAD/events.json","paper":"https://pith.science/paper/ZXABBL6V"},"agent_actions":{"view_html":"https://pith.science/pith/ZXABBL6VVEFWT63JVDUOALNVAD","download_json":"https://pith.science/pith/ZXABBL6VVEFWT63JVDUOALNVAD.json","view_paper":"https://pith.science/paper/ZXABBL6V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.07919&json=true","fetch_graph":"https://pith.science/api/pith-number/ZXABBL6VVEFWT63JVDUOALNVAD/graph.json","fetch_events":"https://pith.science/api/pith-number/ZXABBL6VVEFWT63JVDUOALNVAD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZXABBL6VVEFWT63JVDUOALNVAD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZXABBL6VVEFWT63JVDUOALNVAD/action/storage_attestation","attest_author":"https://pith.science/pith/ZXABBL6VVEFWT63JVDUOALNVAD/action/author_attestation","sign_citation":"https://pith.science/pith/ZXABBL6VVEFWT63JVDUOALNVAD/action/citation_signature","submit_replication":"https://pith.science/pith/ZXABBL6VVEFWT63JVDUOALNVAD/action/replication_record"}},"created_at":"2026-07-05T03:22:51.392729+00:00","updated_at":"2026-07-05T03:22:51.392729+00:00"}