CT 上自动测量的肝脾容积比可预测 B 病毒代偿性肝硬化患者

StephenW

CT 上自动测量的肝脾容积比可预测 B 病毒代偿性肝硬化患者的失代偿
Ji Hye Kwon 1、Seung Soo Lee 2、Jee Seok Yoon 3、Heung-Il Suk 3 4、Yu Sub Sung 5、Ho Sung Kim 5、Chul-Min Lee 6、Kang Mo Kim 7、So Jung Lee 5、So Yeon金 5
隶属关系
隶属关系

    1
    韩国首尔 Good-Jang 医院放射科。
    2
    韩国首尔牙山医学中心蔚山大学医学院放射学系和放射学研究所。 [email protected]。
    3
    韩国首尔高丽大学脑与认知工程系。
    4
    韩国首尔高丽大学人工智能系。
    5
    韩国首尔牙山医学中心蔚山大学医学院放射学系和放射学研究所。
    6
    韩国首尔汉阳大学医学院汉阳大学医学中心放射科。
    7
    韩国首尔牙山医学中心蔚山大学医学院胃肠病学系。

    PMID：34564961 DOI：10.3348/kjr.2021.0348

抽象的

目的：虽然基于 CT 的肝脾容积比（LSVR）反映了门静脉高压症，但其对肝硬化患者的预后作用尚未得到证实。我们评估了使用深度学习算法从 CT 图像自动测量的 LSVR 作为乙型肝炎病毒 (HBV) 代偿性肝硬化患者肝脏失代偿和无移植存活率的预测指标的效用。

材料和方法：使用深度学习算法测量 1027 名接受肝脏 CT 的 HBV 代偿性肝硬化患者（平均年龄 50.5 岁；675 名男性和 352 名女性）的 LSVR（2007-2010 年）。使用多变量 Cox 比例风险和竞争风险分析评估 LSVR 与肝失代偿和无移植生存的关联，考虑 Child-Pugh 评分（CPS）或终末期肝病模型（MELD）评分和其他变量。使用 Kaplan-Meier 分析和 Aalen-Johansen 估计器估计肝脏相关事件的风险。

结果：调整 CPS 或 MELD 和其他变量后，LSVR 被确定为肝失代偿（CPS 和 MELD 模型的 LSVR 风险比分别增加 1、0.71 和 0.68；p < 0.001）和移植的重要独立预测因子无生存（LSVR 的风险比分别增加 1、0.8 和 0.77；p < 0.001）。 LSVR < 2.9 (n = 381) 的患者 3 年肝失代偿（16.7% 对 2.5%，p < 0.001）和肝脏相关死亡或移植（10.0% 对 1.1%，p）的风险显着更高< 0.001) 比那些 LSVR ≥ 2.9 (n = 646)。当根据 CPS（Child-Pugh A 与 BC）和 MELD（< 10 与 ≥ 10）对患者进行分层时，与 LSVR ≥ 2.9 相比，< 2.9 的 LSVR 仍与更高的肝脏相关事件风险相关对于所有 Child-Pugh (p ≤ 0.045) 和 MELD (p ≤ 0.009) 分层。

结论：CT测量的LSVR可以预测HBV代偿期肝硬化患者的肝功能失代偿和无移植生存。

关键词：肝硬化；深度学习；乙型肝炎;肝脏;结果研究；脾。

版权所有 © 2021 韩国放射学会。

StephenW

Liver-to-Spleen Volume Ratio Automatically Measured on CT Predicts Decompensation in Patients with B Viral Compensated Cirrhosis
Ji Hye Kwon  1 , Seung Soo Lee  2 , Jee Seok Yoon  3 , Heung-Il Suk  3   4 , Yu Sub Sung  5 , Ho Sung Kim  5 , Chul-Min Lee  6 , Kang Mo Kim  7 , So Jung Lee  5 , So Yeon Kim  5
Affiliations
Affiliations

    1
    Department of Radiology, Good-Jang Hospital, Seoul, Korea.
    2
    Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Korea. [email protected].
    3
    Department of Brain and Cognitive Engineering, Korea University, Seoul, Korea.
    4
    Department of Artificial Intelligence, Korea University, Seoul, Korea.
    5
    Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Korea.
    6
    Department of Radiology, Hanyang University Medical Center, Hanyang University School of Medicine, Seoul, Korea.
    7
    Department of Gastroenterology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Korea.

    PMID: 34564961 DOI: 10.3348/kjr.2021.0348

Abstract

Objective: Although the liver-to-spleen volume ratio (LSVR) based on CT reflects portal hypertension, its prognostic role in cirrhotic patients has not been proven. We evaluated the utility of LSVR, automatically measured from CT images using a deep learning algorithm, as a predictor of hepatic decompensation and transplantation-free survival in patients with hepatitis B viral (HBV)-compensated cirrhosis.

Materials and methods: A deep learning algorithm was used to measure the LSVR in a cohort of 1027 consecutive patients (mean age, 50.5 years; 675 male and 352 female) with HBV-compensated cirrhosis who underwent liver CT (2007-2010). Associations of LSVR with hepatic decompensation and transplantation-free survival were evaluated using multivariable Cox proportional hazards and competing risk analyses, accounting for either the Child-Pugh score (CPS) or Model for End Stage Liver Disease (MELD) score and other variables. The risk of the liver-related events was estimated using Kaplan-Meier analysis and the Aalen-Johansen estimator.

Results: After adjustment for either CPS or MELD and other variables, LSVR was identified as a significant independent predictor of hepatic decompensation (hazard ratio for LSVR increase by 1, 0.71 and 0.68 for CPS and MELD models, respectively; p < 0.001) and transplantation-free survival (hazard ratio for LSVR increase by 1, 0.8 and 0.77, respectively; p < 0.001). Patients with an LSVR of < 2.9 (n = 381) had significantly higher 3-year risks of hepatic decompensation (16.7% vs. 2.5%, p < 0.001) and liver-related death or transplantation (10.0% vs. 1.1%, p < 0.001) than those with an LSVR ≥ 2.9 (n = 646). When patients were stratified according to CPS (Child-Pugh A vs. B-C) and MELD (< 10 vs. ≥ 10), an LSVR of < 2.9 was still associated with a higher risk of liver-related events than an LSVR of ≥ 2.9 for all Child-Pugh (p ≤ 0.045) and MELD (p ≤ 0.009) stratifications.

Conclusion: The LSVR measured on CT can predict hepatic decompensation and transplantation-free survival in patients with HBV-compensated cirrhosis.

Keywords: Cirrhosis; Deep learning; Hepatitis B; Liver; Outcomes research; Spleen.

Copyright © 2021 The Korean Society of Radiology.