{"paper":{"title":"A Fast and Generic Energy-Shifting Transformer for Hybrid Monte Carlo Radiotherapy Calculation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"A deep learning method called Energy-Shifting generates clinical 6 MV LINAC dose maps from monoenergetic inputs and passes 98 percent gamma criteria in prostate radiotherapy planning.","cross_cats":["cs.LG"],"primary_cat":"physics.med-ph","authors_text":"Chi-Hieu Pham, Didier Benoit, Dimitris Visvikis, Julien Bert, Ulrike Schick, Vincent Bourbonne","submitted_at":"2026-04-10T09:42:41Z","abstract_excerpt":"We introduce a novel learning framework for accelerated Monte Carlo (MC) dose calculation termed Energy-Shifting. This approach leverages deep learning to synthesize highly complex polyenergetic dose distributions directly from simple monoenergetic inputs under identical beam configurations. Unlike conventional denoising techniques, which rely on noisy low-count dose maps that compromise beam profile integrity, our method achieves superior cross-domain generalization on unseen datasets by integrating high-fidelity anatomical textures and source-specific beam similarity into the model's input s"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our proposed pipeline achieves a Gamma Passing Rate exceeding 98% (3%/3mm) compared to the MC reference, evaluated within the framework of a treatment planning system (TPS) for prostate radiotherapy.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That synthesizing dose from monoenergetic inputs under identical beam configurations preserves beam profile integrity and generalizes to unseen clinical datasets without introducing clinically relevant errors in heterogeneous anatomy.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A hybrid Transformer-UNet model with energy-shifting inputs generates 6 MV LINAC dose maps from monoenergetic data, achieving over 98% gamma passing rate (3%/3mm) versus full Monte Carlo for prostate radiotherapy.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A deep learning method called Energy-Shifting generates clinical 6 MV LINAC dose maps from monoenergetic inputs and passes 98 percent gamma criteria in prostate radiotherapy planning.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"43777d6250c669ec7430fcc1e01ba8f728c0f410b725f69ff2d7f6c673c4f569"},"source":{"id":"2604.09157","kind":"arxiv","version":2},"verdict":{"id":"cb06140b-5df0-40ff-9d2d-586ff891e1b7","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T16:53:39.598741Z","strongest_claim":"Our proposed pipeline achieves a Gamma Passing Rate exceeding 98% (3%/3mm) compared to the MC reference, evaluated within the framework of a treatment planning system (TPS) for prostate radiotherapy.","one_line_summary":"A hybrid Transformer-UNet model with energy-shifting inputs generates 6 MV LINAC dose maps from monoenergetic data, achieving over 98% gamma passing rate (3%/3mm) versus full Monte Carlo for prostate radiotherapy.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That synthesizing dose from monoenergetic inputs under identical beam configurations preserves beam profile integrity and generalizes to unseen clinical datasets without introducing clinically relevant errors in heterogeneous anatomy.","pith_extraction_headline":"A deep learning method called Energy-Shifting generates clinical 6 MV LINAC dose maps from monoenergetic inputs and passes 98 percent gamma criteria in prostate radiotherapy planning."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.09157/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":2,"snapshot_sha256":"263bdacf5049718b7e614961a4207cc7445415b54a93f68d1a6603649cc1115d"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}