基於放射學的非對比CT模型預測肝硬化：充分利用圖像數據

StephenW

A radiomics-based model on non-contrast CT for predicting cirrhosis: make the most of image data
Jin-Cheng Wang #  1   2 , Rao Fu #  1   2 , Xue-Wen Tao #  1   2 , Ying-Fan Mao  3 , Fei Wang  1   2 , Ze-Chuan Zhang  1   2 , Wei-Wei Yu  1 , Jun Chen  4 , Jian He  3 , Bei-Cheng Sun  1   2
Affiliations
Affiliations

    1
    Department of Hepatobiliary Surgery of Drum Tower Clinical Medical College, Nanjing Medical University, Nanjing, China.
    2
    Department of Hepatobiliary Surgery, The Affiliated Drum Tower Hospital of Nanjing University Medical School, 321 Zhongshan Road, Nanjing, 210008 Jiangsu Province China.
    3
    Department of Radiology, The Affiliated Drum Tower Hospital of Nanjing University Medical School, 321 Zhongshan Road, Nanjing, 210008 Jiangsu Province China.
    4
    Department of Pathology, The Affiliated Drum Tower Hospital of Nanjing University Medical School, 321 Zhongshan Road, Nanjing, 210008 Jiangsu Province China.

#
Contributed equally.

    PMID: 32963787 PMCID: PMC7499912 DOI: 10.1186/s40364-020-00219-y

Abstract

Background: To establish and validate a radiomics-based model for predicting liver cirrhosis in patients with hepatitis B virus (HBV) by using non-contrast computed tomography (CT).

Methods: This retrospective study developed a radiomics-based model in a training cohort of 144 HBV-infected patients. Radiomic features were extracted from abdominal non-contrast CT scans. Features selection was performed with the least absolute shrinkage and operator (LASSO) method based on highly reproducible features. Support vector machine (SVM) was adopted to build a radiomics signature. Multivariate logistic regression analysis was used to establish a radiomics-based nomogram that integrated radiomics signature and other independent clinical predictors. Performance of models was evaluated through discrimination ability, calibration and clinical benefits. An internal validation was conducted in 150 consecutive patients.

Results: The radiomics signature comprised 25 cirrhosis-related features and showed significant differences between cirrhosis and non-cirrhosis cohorts (P < 0.001). A radiomics-based nomogram that integrates radiomics signature, alanine transaminase, aspartate aminotransferase, globulin and international normalized ratio showed great calibration and discrimination ability in the training cohort (area under the curve [AUC]: 0.915) and the validation cohort (AUC: 0.872). Decision curve analysis confirmed the most clinical benefits can be provided by the nomogram compared with other methods.

Conclusions: Our developed radiomics-based nomogram can successfully diagnose the status of cirrhosis in HBV-infected patients, that may help clinical decision-making.

Keywords: Hepatitis B virus (HBV); Liver cirrhosis; Non-contrast computed tomography (CT); Radiomics model.

© The Author(s) 2020.

StephenW

基於放射學的非對比CT模型預測肝硬化：充分利用圖像數據
王金成＃1 2，饒夫＃1 2，陶學文＃1 2，毛應凡3，王菲1 2，張澤川1 2，余偉偉1，陳軍4，健和3，孫北成1 2
隸屬關係
隸屬關係

    1個
    南京醫科大學鼓樓臨床醫學院肝膽外科，南京
    2
    南京大學醫學院附屬鼓樓醫院肝膽外科，江蘇省南京市中山路321號，郵編210008。
    3
    江蘇省南京市中山路321號南京大學醫學院附屬鼓樓醫院放射科
    4
    南京大學中醫學院附屬鼓樓醫院病理科，江蘇南京210008

＃
貢獻均等。

    PMID：32963787 PMCID：PMC7499912 DOI：10.1186 / s40364-020-00219-y

抽象

背景：建立和驗證基於放射學的模型，通過使用非對比計算機斷層掃描（CT）來預測乙型肝炎病毒（HBV）患者的肝硬化。

方法：這項回顧性研究在144名HBV感染患者的訓練隊列中建立了一種基於放射學的模型。放射學特徵是從腹部非對比CT掃描中提取的。基於高度可複制的特徵，使用最小絕對收縮和算子（LASSO）方法執行特徵選擇。支持向量機（SVM）被用來建立放射學簽名。多變量logistic回歸分析用於建立基於放射學的列線圖，該圖綜合了放射學特徵和其他獨立的臨床預測指標。通過辨別能力，校準和臨床益處評估模型的性能。在150位連續患者中進行了內部驗證。

結果：放射組學特徵包括25個肝硬化相關特徵，並且在肝硬化和非肝硬化人群之間顯示出顯著差異（P <0.001）。基於放射線的諾模圖結合了放射線簽名，丙氨酸轉氨酶，天冬氨酸轉氨酶，球蛋白和國際標準化比例，在訓練隊列（曲線下面積[AUC]：0.915）和驗證隊列（AUC：0.872）中顯示出很高的校準和辨別能力。 ）。決策曲線分析證實，與其他方法相比，諾模圖可以提供最大的臨床益處。

結論：我們開發的基於放射組學的列線圖可以成功診斷HBV感染患者的肝硬化狀態，這可能有助於臨床決策。

關鍵字：乙型肝炎病毒（HBV）；肝硬化；非對比計算機斷層掃描（CT）； Radiomics模型。

©作者2020。

StephenW

https://biomarkerres.biomedcentr ... /s40364-020-00219-y