Elizabeth Katherine Anna Triumbari, David Morland, Roberto Gatta, Luca Boldrini, Marco De Summa, Silvia Chiesa, Annarosa Cuccaro, Elena Maiolo, Stefan Hohaus, Salvatore Annunziata
{"title":"18F-FDG PET/CT两病变放射组学和传统模型对经典霍奇金淋巴瘤的预测能力：一项回顾性验证的比较研究。","authors":"Elizabeth Katherine Anna Triumbari, David Morland, Roberto Gatta, Luca Boldrini, Marco De Summa, Silvia Chiesa, Annarosa Cuccaro, Elena Maiolo, Stefan Hohaus, Salvatore Annunziata","doi":"10.1007/s00277-025-06190-8","DOIUrl":null,"url":null,"abstract":"<p><p>In a previous preliminary study, radiomic features from the largest and the hottest lesion in baseline <sup>18</sup>F-FDG PET/CT (bPET/CT) of classical Hodgkin's Lymphoma (cHL) predicted early response-to-treatment and prognosis. Aim of this large retrospectively-validated study is to evaluate the predictive role of two-lesions radiomics in comparison with other clinical and conventional PET/CT models. cHL patients with bPET/CT between 2010 and 2020 were retrospectively included and randomized into training-validation sets. Target lesions were: Lesion_A, with largest axial diameter (D<sub>max</sub>); Lesion_B, with highest SUV<sub>max</sub>. Total-metabolic-tumor-volume (TMTV) was calculated and 212 radiomic features were extracted. PET/CT features were harmonized using ComBat across two scanners. Outcomes were progression-free-survival (PFS) and Deauville Score at interim PET/CT (DS). For each outcome, three predictive models and their combinations were trained and validated: - radiomic model \"R\"; - conventional PET/CT model \"P\"; - clinical model \"C\". 197 patients were included (training = 118; validation = 79): 38/197 (19%) patients had adverse events and 42/193 (22%) had DS ≥ 4. In the training phase, only one radiomic feature was selected for PFS prediction in model \"R\" (Lesion_B F_cm.corr, C-index 66.9%). Best \"C\" model combined stage and IPS (C-index 74.8%), while optimal \"P\" model combined TMTV and D<sub>max</sub> (C-index 63.3%). After internal validation, \"C\", \"C + R\", \"R + P\" and \"C + R + P\" significantly predicted PFS. The best validated model was \"C + R\" (C-index 66.3%). No model was validated for DS prediction. In this large retrospectively-validated study, a combination of baseline <sup>18</sup>F-FDG PET/CT two-lesions radiomics and other conventional models showed an added prognostic power in patients with cHL. As single models, conventional clinical parameters maintain their prognostic power, while radiomics or conventional PET/CT alone seem to be sub-optimal to predict survival.</p>","PeriodicalId":8068,"journal":{"name":"Annals of Hematology","volume":" ","pages":""},"PeriodicalIF":3.0000,"publicationDate":"2025-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"The predictive power of <sup>18</sup>F-FDG PET/CT two-lesions radiomics and conventional models in classical Hodgkin's Lymphoma: a comparative retrospectively-validated study.\",\"authors\":\"Elizabeth Katherine Anna Triumbari, David Morland, Roberto Gatta, Luca Boldrini, Marco De Summa, Silvia Chiesa, Annarosa Cuccaro, Elena Maiolo, Stefan Hohaus, Salvatore Annunziata\",\"doi\":\"10.1007/s00277-025-06190-8\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>In a previous preliminary study, radiomic features from the largest and the hottest lesion in baseline <sup>18</sup>F-FDG PET/CT (bPET/CT) of classical Hodgkin's Lymphoma (cHL) predicted early response-to-treatment and prognosis. Aim of this large retrospectively-validated study is to evaluate the predictive role of two-lesions radiomics in comparison with other clinical and conventional PET/CT models. cHL patients with bPET/CT between 2010 and 2020 were retrospectively included and randomized into training-validation sets. Target lesions were: Lesion_A, with largest axial diameter (D<sub>max</sub>); Lesion_B, with highest SUV<sub>max</sub>. Total-metabolic-tumor-volume (TMTV) was calculated and 212 radiomic features were extracted. PET/CT features were harmonized using ComBat across two scanners. Outcomes were progression-free-survival (PFS) and Deauville Score at interim PET/CT (DS). For each outcome, three predictive models and their combinations were trained and validated: - radiomic model \\\"R\\\"; - conventional PET/CT model \\\"P\\\"; - clinical model \\\"C\\\". 197 patients were included (training = 118; validation = 79): 38/197 (19%) patients had adverse events and 42/193 (22%) had DS ≥ 4. In the training phase, only one radiomic feature was selected for PFS prediction in model \\\"R\\\" (Lesion_B F_cm.corr, C-index 66.9%). Best \\\"C\\\" model combined stage and IPS (C-index 74.8%), while optimal \\\"P\\\" model combined TMTV and D<sub>max</sub> (C-index 63.3%). After internal validation, \\\"C\\\", \\\"C + R\\\", \\\"R + P\\\" and \\\"C + R + P\\\" significantly predicted PFS. The best validated model was \\\"C + R\\\" (C-index 66.3%). No model was validated for DS prediction. In this large retrospectively-validated study, a combination of baseline <sup>18</sup>F-FDG PET/CT two-lesions radiomics and other conventional models showed an added prognostic power in patients with cHL. As single models, conventional clinical parameters maintain their prognostic power, while radiomics or conventional PET/CT alone seem to be sub-optimal to predict survival.</p>\",\"PeriodicalId\":8068,\"journal\":{\"name\":\"Annals of Hematology\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":3.0000,\"publicationDate\":\"2025-01-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Annals of Hematology\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1007/s00277-025-06190-8\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"HEMATOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Annals of Hematology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s00277-025-06190-8","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"HEMATOLOGY","Score":null,"Total":0}
The predictive power of 18F-FDG PET/CT two-lesions radiomics and conventional models in classical Hodgkin's Lymphoma: a comparative retrospectively-validated study.
In a previous preliminary study, radiomic features from the largest and the hottest lesion in baseline 18F-FDG PET/CT (bPET/CT) of classical Hodgkin's Lymphoma (cHL) predicted early response-to-treatment and prognosis. Aim of this large retrospectively-validated study is to evaluate the predictive role of two-lesions radiomics in comparison with other clinical and conventional PET/CT models. cHL patients with bPET/CT between 2010 and 2020 were retrospectively included and randomized into training-validation sets. Target lesions were: Lesion_A, with largest axial diameter (Dmax); Lesion_B, with highest SUVmax. Total-metabolic-tumor-volume (TMTV) was calculated and 212 radiomic features were extracted. PET/CT features were harmonized using ComBat across two scanners. Outcomes were progression-free-survival (PFS) and Deauville Score at interim PET/CT (DS). For each outcome, three predictive models and their combinations were trained and validated: - radiomic model "R"; - conventional PET/CT model "P"; - clinical model "C". 197 patients were included (training = 118; validation = 79): 38/197 (19%) patients had adverse events and 42/193 (22%) had DS ≥ 4. In the training phase, only one radiomic feature was selected for PFS prediction in model "R" (Lesion_B F_cm.corr, C-index 66.9%). Best "C" model combined stage and IPS (C-index 74.8%), while optimal "P" model combined TMTV and Dmax (C-index 63.3%). After internal validation, "C", "C + R", "R + P" and "C + R + P" significantly predicted PFS. The best validated model was "C + R" (C-index 66.3%). No model was validated for DS prediction. In this large retrospectively-validated study, a combination of baseline 18F-FDG PET/CT two-lesions radiomics and other conventional models showed an added prognostic power in patients with cHL. As single models, conventional clinical parameters maintain their prognostic power, while radiomics or conventional PET/CT alone seem to be sub-optimal to predict survival.
期刊介绍：
Annals of Hematology covers the whole spectrum of clinical and experimental hematology, hemostaseology, blood transfusion, and related aspects of medical oncology, including diagnosis and treatment of leukemias, lymphatic neoplasias and solid tumors, and transplantation of hematopoietic stem cells. Coverage includes general aspects of oncology, molecular biology and immunology as pertinent to problems of human blood disease. The journal is associated with the German Society for Hematology and Medical Oncology, and the Austrian Society for Hematology and Oncology.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
