Diagnostic value of whole-tumor apparent diffusion coefficient map radiomics analysis in predicting early recurrence of solitary hepatocellular carcinoma ≤ 5 cm

被引:11
作者
Wang, Leyao [1 ]
Feng, Bing [1 ]
Wang, Sicong [2 ]
Hu, Jiesi [3 ]
Liang, Meng [1 ]
Li, Dengfeng [1 ]
Wang, Shuang [1 ]
Ma, Xiaohong [1 ]
Zhao, Xinming [1 ]
机构
[1] Chinese Acad Med Sci & Peking Union Med Coll, Dept Diagnost Radiol, Natl Canc Ctr, Natl Clin Res Ctr Canc,Canc Hosp, Beijing 100021, Peoples R China
[2] Gen Elect Healthcare China, Magnet Resonance Imaging Res, Beijing 100176, Peoples R China
[3] Harbin Inst Technol Shenzhen, Inst Elect & Informat Engn, Shenzhen 518055, Peoples R China
关键词
Hepatocellular carcinoma; Early recurrence; Magnetic resonance imaging; Radiomics; Apparent diffusion coefficient; RADIOFREQUENCY ABLATION; RESECTION; SURVIVAL;
D O I
10.1007/s00261-022-03582-6
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
Purpose To evaluate the role of whole-tumor radiomics analysis of apparent diffusion coefficient (ADC) maps in predicting early recurrence (ER) of solitary hepatocellular carcinoma (HCC) <= 5 cm and compare the diagnostic efficiency of whole-tumor and single-slice ADC measurements. Methods One hundred and seventy patients with primary HCC were randomly divided into the training set (n = 119) and the test set (n = 51). The diagnostic efficiency was compared between the whole-tumor and single-slice ADC measurements. The clinical-radiological model was established by selected significant clinical characteristics and qualitative imaging features. The radiomics model was constructed using the least absolute shrinkage and selection operator (LASSO) logistic regression algorithm. The significant clinical-radiological risk factors and radiomics features were integrated to develop the combined model. Receiver operating characteristic (ROC) curves were used for evaluating the predictive performance. Results Cirrhosis, age, and albumin were significantly associated with ER in the clinical-radiological model selected by the random forest classifier. The diagnostic efficiency of the whole-tumor ADC measurements was slight higher than that of the single-slice (AUC = 0.602 and 0.586, respectively). The clinical-radiological model (AUC = 0.84 and 0.82 in the training and test sets, respectively) showed better diagnostic performance than the radiomics model (AUC = 0.70 and 0.69 in the training and test sets, respectively) in predicting ER. The combined model showed optimal predictive performance with the highest AUC values of 0.88 and 0.85 in the training and test sets, respectively. Conclusions The whole-tumor ADC measurements performed better than the single-slice ADC measurements. The clinical-radiological model performed better than the radiomics model for predicting ER in patients with solitary HCC <= 5 cm.
引用
收藏
页码:3290 / 3300
页数:11
相关论文
共 34 条
[1]   Hepatocellular carcinoma: preoperative gadoxetic acid-enhanced MR imaging can predict early recurrence after curative resection using image features and texture analysis [J].
Ahn, Su Joa ;
Kim, Jung Hoon ;
Park, Sang Joon ;
Kim, Seung Tack ;
Han, Joon Koo .
ABDOMINAL RADIOLOGY, 2019, 44 (02) :539-548
[2]   Role of baseline volumetric functional MRI in predicting histopathologic grade and patients' survival in hepatocellular carcinoma [J].
Ameli, Sanaz ;
Shaghaghi, Mohammadreza ;
Aliyari Ghasabeh, Mounes ;
Pandey, Pallavi ;
Hazhirkarzar, Bita ;
Ghadimi, Maryam ;
Rezvani Habibabadi, Roya ;
Khoshpouri, Pegah ;
Pandey, Ankur ;
Anders, Robert A. ;
Kamel, Ihab R. .
EUROPEAN RADIOLOGY, 2020, 30 (07) :3748-3758
[3]   Single Hepatocellular Carcinoma: Preoperative MR Imaging to Predict Early Recurrence after Curative Resection [J].
An, Chansik ;
Kim, Dong Wook ;
Park, Young-Nyun ;
Chung, Yong Eun ;
Rhee, Hyungjin ;
Kim, Myeong-Jin .
RADIOLOGY, 2015, 276 (02) :433-443
[4]   A non-smooth tumor margin in the hepatobiliary phase of gadoxetic acid disodium (Gd-EOB-DTPA)-enhanced magnetic resonance imaging predicts microscopic portal vein invasion, intrahepatic metastasis, and early recurrence after hepatectomy in patients with hepatocellular carcinoma [J].
Ariizumi, Shun-ichi ;
Kitagawa, Koichi ;
Kotera, Yoshihito ;
Takahashi, Yutaka ;
Katagiri, Satoshi ;
Kuwatsuru, Ryohei ;
Yamamoto, Masakazu .
JOURNAL OF HEPATO-BILIARY-PANCREATIC SCIENCES, 2011, 18 (04) :575-585
[5]   Diagnostic value of texture analysis of apparent diffusion coefficient maps for differentiating fat-poor angiomyolipoma from non-clear-cell renal cell carcinoma [J].
Arita, Yuki ;
Yoshida, Soichiro ;
Kwee, Thomas C. ;
Akita, Hirotaka ;
Okuda, Shigeo ;
Iwaita, Yuki ;
Mukai, Kiyoko ;
Matsumoto, Shunya ;
Ueda, Ryo ;
Ishii, Ryota ;
Mizuno, Ryuichi ;
Fujii, Yasuhisa ;
Oya, Mototsugu ;
Jinzaki, Masahiro .
EUROPEAN JOURNAL OF RADIOLOGY, 2021, 143
[6]   Cancer Statistics in China, 2015 [J].
Chen, Wanqing ;
Zheng, Rongshou ;
Baade, Peter D. ;
Zhang, Siwei ;
Zeng, Hongmei ;
Bray, Freddie ;
Jemal, Ahmedin ;
Yu, Xue Qin ;
He, Jie .
CA-A CANCER JOURNAL FOR CLINICIANS, 2016, 66 (02) :115-132
[7]   Multi-scale and multi-parametric radiomics of gadoxetate disodium-enhanced MRI predicts microvascular invasion and outcome in patients with solitary hepatocellular carcinoma ≤ 5 cm [J].
Chong, Huan-Huan ;
Yang, Li ;
Sheng, Ruo-Fan ;
Yu, Yang-Li ;
Wu, Di-Jia ;
Rao, Sheng-Xiang ;
Yang, Chun ;
Zeng, Meng-Su .
EUROPEAN RADIOLOGY, 2021, 31 (07) :4824-4838
[8]   Radiomics: Images Are More than Pictures, They Are Data [J].
Gillies, Robert J. ;
Kinahan, Paul E. ;
Hricak, Hedvig .
RADIOLOGY, 2016, 278 (02) :563-577
[9]   Pretreatment serum albumin as a predictor of cancer survival: A systematic review of the epidemiological literature [J].
Gupta, Digant ;
Lis, Christopher G. .
NUTRITION JOURNAL, 2010, 9
[10]   Prediction of tumor response via a pretreatment MRI radiomics-based nomogram in HCC treated with TACE [J].
Kong, Chunli ;
Zhao, Zhongwei ;
Chen, Weiyue ;
Lv, Xiuling ;
Shu, Gaofeng ;
Ye, Miaoqing ;
Song, Jingjing ;
Ying, Xihui ;
Weng, Qiaoyou ;
Weng, Wei ;
Fang, Shiji ;
Chen, Minjiang ;
Tu, Jianfei ;
Ji, Jiansong .
EUROPEAN RADIOLOGY, 2021, 31 (10) :7500-7511