人工智能驱动的身体成分监测及其在接受镥-177 PSMA放射性配体治疗的转移性去势抵抗性前列腺癌中的预后作用：一项回顾性单中心分析的见解

AI-driven body composition monitoring and its prognostic role in mCRPC undergoing lutetium-177 PSMA radioligand therapy: insights from a retrospective single-center analysis.

作者信息

Ruhwedel Tristan, Rogasch Julian, Galler Markus, Schatka Imke, Wetz Christoph, Furth Christian, Biernath Nadine, De Santis Maria, Shnayien Seyd, Kolck Johannes, Geisel Dominik, Amthauer Holger, Beetz Nick Lasse

机构信息

Department of Nuclear Medicine, Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Augustenburger Platz 1, 13353, Berlin, Germany.

Berlin Institute of Health at Charité - Universitätsmedizin Berlin, Charitéplatz 1, 10117, Berlin, Germany.

出版信息

EJNMMI Res. 2025 Aug 28;15(1):112. doi: 10.1186/s13550-025-01312-9.

DOI:10.1186/s13550-025-01312-9

PMID:40877457

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC12394111/

Abstract

BACKGROUND

Body composition (BC) analysis is performed to quantify the relative amounts of different body tissues as a measure of physical fitness and tumor cachexia. We hypothesized that relative changes in body composition (BC) parameters, assessed by an artificial intelligence-based, PACS-integrated software, between baseline imaging before the start of radioligand therapy (RLT) and interim staging after two RLT cycles could predict overall survival (OS) in patients with metastatic castration-resistant prostate cancer.

METHODS

We conducted a single-center, retrospective analysis of 92 patients with mCRPC undergoing [Lu]Lu-PSMA RLT between September 2015 and December 2023. All patients had [ Ga]Ga-PSMA-11 PET/CT at baseline (≤ 6 weeks before the first RLT cycle) and at interim staging (6-8 weeks after the second RLT cycle) allowing for longitudinal BC assessment.

RESULTS

During follow-up, 78 patients (85%) died. Median OS was 16.3 months. Median follow-up time in survivors was 25.6 months. The 1 year mortality rate was 32.6% (95%CI 23.0-42.2%) and the 5 year mortality rate was 92.9% (95%CI 85.8-100.0%). In multivariable regression, relative change in visceral adipose tissue (VAT) (HR: 0.26; p = 0.006), previous chemotherapy of any type (HR: 2.4; p = 0.003), the presence of liver metastases (HR: 2.4; p = 0.018) and a higher baseline De Ritis ratio (HR: 1.4; p < 0.001) remained independent predictors of OS. Patients with a higher decrease in VAT (< -20%) had a median OS of 10.2 months versus 18.5 months in patients with a lower VAT decrease or VAT increase (≥ -20%) (log-rank test: p = 0.008). In a separate Cox model, the change in VAT predicted OS (p = 0.005) independent of the best PSA response after 1-2 RLT cycles (p = 0.09), and there was no interaction between the two (p = 0.09).

CONCLUSIONS

PACS-Integrated, AI-based BC monitoring detects relative changes in the VAT, Which was an independent predictor of shorter OS in our population of patients undergoing RLT.

摘要

背景

进行身体成分（BC）分析以量化不同身体组织的相对含量，作为身体健康和肿瘤恶病质的一项指标。我们假设，通过基于人工智能的、集成于PACS的软件评估的身体成分（BC）参数在放射性配体治疗（RLT）开始前的基线成像与两个RLT周期后的中期分期之间的相对变化，可以预测转移性去势抵抗性前列腺癌患者的总生存期（OS）。

方法

我们对2015年9月至2023年12月期间接受[Lu]Lu-PSMA RLT的92例mCRPC患者进行了单中心回顾性分析。所有患者在基线（第一个RLT周期前≤6周）和中期分期（第二个RLT周期后6-8周）均进行了[Ga]Ga-PSMA-11 PET/CT检查，以便进行纵向BC评估。

结果

在随访期间，78例患者（85%）死亡。中位OS为16.3个月。幸存者的中位随访时间为25.6个月。1年死亡率为32.6%（95%CI 23.0-42.2%），5年死亡率为92.9%（95%CI 85.8-100.0%）。在多变量回归中，内脏脂肪组织（VAT）的相对变化（HR：0.26；p = 0.006）、任何类型的既往化疗（HR：2.4；p = 0.003）、肝转移的存在（HR：2.4；p = 0.018）和更高水平的基线德瑞蒂斯比值（HR：1.4；p < 0.001）仍然是OS的独立预测因素。VAT降低幅度较大（<-20%）的患者中位OS为10.2个月，而VAT降低幅度较小或VAT增加（≥-20%）的患者中位OS为18.5个月（对数秩检验：p = 0.008）。在一个单独的Cox模型中，VAT的变化独立于1-2个RLT周期后的最佳PSA反应预测OS（p = 0.005），且两者之间无相互作用（p = 0.09）。