{"doi":"10.1002/mp.70183","title":"Efficient proton–photon patient selection via dose and NTCP prediction for head and neck cancer patients","abstract":"BACKGROUND: Compared to photon therapy (XT), proton therapy (PT) can often reduce normal tissue toxicity for head and neck (HN) cancer patients, despite being a limited resource. On the other hand, clinical decision-making process to select between PT and XT (e.g., treatment planning and then plan evaluation for comparing normal tissue complication probabilities (NTCP) between XT and PT) is time-consuming and resource demanding. PURPOSE: This study aims to develop and validate the feasibility of an artificial intelligence (AI)-based automated method for efficient patient selection between PT and XT. METHODS: A heterogeneous cohort of 104 bilateral HN patients with auto-planned PT and XT plans was analyzed, covering diverse tumor subsites and prescription dose levels. To ensure accurate dose and NTCP prediction, a joint-modality prediction framework was developed, incorporating a 3D attention-gated U-net with a multi-constrained loss function. A stratified 10-fold cross-validation strategy was employed to evaluate and compare model performance. The NTCP differences between XT and PT for grade II/III xerostomia/dysphagia exceeding certain thresholds are used to select patients for PT according to the Landelijk Indicatie Protocol Protonentherapie (versie 2.2) (LIPPv2.2). RESULTS: AI-assisted patient selection process took about 10.1 s per patient. Our method achieved an accuracy of 85.58% and a weighted accuracy of 81.11% in patient selection. For dysphagia grades ≥ 2 and ≥ 3, the predicted results exhibited consistent selection with the ground truth in 86.54% and 89.42% of cases, respectively. Compared to previous models, the average ΔNTCP prediction error (ΔNTCP ground truth-ΔNTCP predicted, mean ± SD) of the proposed method was 1.47 ± 1.80%, statistically lower than U-net (1.67 ± 2.20%) and hierarchically densely connected U-net (2.34 ± 3.25%). Moreover, the joint-modality prediction of PT and XT dose distributions using Attention U-net achieved comparable performance to separate single-modality predictions. CONCLUSION: This study highlights the potential of a novel AI-assisted framework with joint-modality prediction to enhance efficiency and precision for proton-photon patient selection in the heterogeneous dataset, demonstrating the generalizability and robustness of the proposed approach.","journal":"Medical Physics","year":2025,"id":554545,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":1,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9566,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2025-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1058553,"name":"Ya‐Nan Zhu","orcid":"0000-0002-7888-0138","position":1,"is_corresponding":false},{"id":1451863,"name":"Lyu Li","orcid":"0009-0000-8609-1123","position":2,"is_corresponding":false},{"id":586931,"name":"Zhong Chen","orcid":"0000-0003-4755-9357","position":3,"is_corresponding":false},{"id":1451864,"name":"Fazal Hameed Khan","orcid":"0000-0003-4627-0535","position":4,"is_corresponding":false},{"id":887029,"name":"Wangyao Li","orcid":"0000-0001-9312-4931","position":5,"is_corresponding":false},{"id":1254618,"name":"Chao Wang","orcid":"0000-0002-3243-3244","position":6,"is_corresponding":false},{"id":445081,"name":"Gregory N. Gan","orcid":"0000-0001-5090-0064","position":7,"is_corresponding":false},{"id":1284279,"name":"C.E. Lominska","orcid":"0000-0003-1829-1371","position":8,"is_corresponding":false},{"id":689182,"name":"Qiang Li","orcid":"0000-0003-0096-7679","position":9,"is_corresponding":false},{"id":1400261,"name":"Wei‐Qiang Chen","orcid":"0000-0002-7686-2331","position":10,"is_corresponding":false},{"id":1074642,"name":"Hao Gao","orcid":"0000-0002-4253-7418","position":11,"is_corresponding":false},{"id":1378045,"name":"Yuting Lin","orcid":"0009-0007-7771-0050","position":12,"is_corresponding":false},{"id":1304058,"name":"Jiaxin Li","orcid":"0000-0001-5360-0219","position":0,"is_corresponding":true}],"reference_count":28,"raw_metadata":null,"created_at":"2026-07-19T02:54:50.112989Z","pmid":"41345820","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}