{"doi":"10.3788/cjl250803","title":"基于光学相干层析成像与深度学习的肿瘤类器官无损动态分析及其药物作用评估新框架","abstract":null,"journal":"Chinese Journal of Lasers","year":2025,"id":644908,"datarank":0.26876392038420827,"base_score":1.791759469228055,"endowment":1.791759469228055,"self_citation_contribution":0.26876392038420827,"citation_network_contribution":0.0,"self_endowment_contribution":0.26876392038420827,"citer_contribution":0.0,"corpus_percentile":41.5,"corpus_rank":7866,"citation_count":5,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":true,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1678898,"name":"马飞越 Ma Feiyue","orcid":null,"position":1,"is_corresponding":false},{"id":1678900,"name":"郭经 Guo Jing","orcid":null,"position":2,"is_corresponding":false},{"id":1678902,"name":"王万利 Wang Wanli","orcid":null,"position":3,"is_corresponding":false},{"id":1678903,"name":"毛川伟 Mao Chuanwei","orcid":null,"position":4,"is_corresponding":false},{"id":1678904,"name":"梁霄 Liang Xiao","orcid":null,"position":5,"is_corresponding":false},{"id":1678905,"name":"王玲 Wang Ling","orcid":null,"position":6,"is_corresponding":false},{"id":1678906,"name":"徐铭恩 Xu Ming'en","orcid":null,"position":7,"is_corresponding":false},{"id":1678895,"name":"杨珊珊 Yang Shanshan","orcid":null,"position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"resolved":true,"title":"基于光学相干层析成像与深度学习的肿瘤类器官无损动态分析及其药物作用评估新框架","abstract":"作为新型体外肿瘤模型，肿瘤类器官在肿瘤生物学研究及个体化药物敏感性评估中具有重要价值。现有基于人工接种类器官和破坏性终点测试的方法虽然能够表征类器官的药物作用，但要求样本间具有高度的均一性，并且缺乏对药物作用的动态监测能力，严重制约了其转化应用。为此，本文提出了基于无标记光学相干层析成像（OCT）的类器官分割、表征、生长水平分析框架，该框架涵盖了基于深度学习的类器官分割、单个类器官的三维形态表征以及类器官簇生长水平/生长率分析等。该框架的核心挑战在于类器官三维形态的复杂性和生长动态的多样性。本团队首次提出了一种基于SAM2和CNN的新型并行编码器结构网络——ParaSAM2CNN，该网络结合ResNet的深度特征提取能力以及SAM2的多尺度特征捕获能力，有效解决了类器官分割中的三维不连续性问题，实现了三维培养微环境中类器官的自动化、精准分割（Dice系数达0.8026）。在此基础上，开发了类器官三维表面自适应粗糙度表征算法，并采用该算法对类器官簇内单个类器官进行了纵向、准确、并行的多维形态学表征。通过无监督聚类分析对类器官的形态表型（比如空腔类、实心类）进行分类，并结合主成分分析法揭示形态学参数、生长动力学、药物作用效果之间的关联机制。最终，构建类器官簇生长水平模型，并验证了类器官生长水平模型与传统生化测试——三磷酸腺苷（ATP）测试结果的高度一致性（90.45%）。结果表明，该框架能够有效替代传统破坏性测试方法，为基于患者来源的肿瘤类器官（PDTOs）的新药筛选和个性化治疗提供一种高效、无损的预测工具。","is_dataset_classified":null,"base_score":1.791759469228055,"endowment":1.791759469228055,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"19910364","pmcid":null,"openalex_id":"https://openalex.org/W4413436364","authors":[],"funders":[],"total_grants":0,"fwci":2.729,"citation_percentile":0.91272226,"influential_citations":0,"citation_trend":[{"year":2026,"count":5}],"oa_status":"closed","license":null,"oa_locations":[{"url":"http://www.opticsjournal.net/Articles/GetArticlePDF/OJ6a5d1cb4f005d064","host_type":"publisher"},{"url":"https://doi.org/10.3788/cjl250803","host_type":"journal"}],"fields_of_study":["Advanced Neural Network Applications","Smart Agriculture and AI"],"mesh_terms":[],"keywords":["Computer science"],"sdg_mappings":[],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[],"source":"live","citation_network_status":"fetched"},"created_at":"2026-08-09T02:23:41.078806Z","pmid":null,"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":[]}