Deep learning nomogram based on Gd-EOB-DTPA MRI for predicting early recurrence in hepatocellular carcinoma after hepatectomy

European Radiology - Tập 33 - Trang 4949-4961 - 2023
Meng Yan1, Xiao Zhang1,2, Bin Zhang1, Zhijun Geng3, Chuanmiao Xie3, Wei Yang4, Shuixing Zhang1, Zhendong Qi5, Ting Lin5, Qiying Ke6, Xinming Li5, Shutong Wang7, Xianyue Quan5
1Department of Radiology, The First Affiliated Hospital of Jinan University, Guangzhou, People’s Republic of China
2Neusoft Research of Intelligent Healthcare Technology, Co. Ltd., Artificial Intelligence and Clinical Innovation Research, Guangzhou, People’s Republic of China
3Department of Medical Imaging, Sun Yat-Sen University Cancer Center, Guangzhou, People’s Republic of China
4Guangdong Provincial Key Laboratory of Medical Image Processing, School of Biomedical Engineering, Southern Medical University, Guangzhou, People’s Republic of China
5Department of Radiology, Zhujiang Hospital, Southern Medical University, Guangzhou, People’s Republic of China
6Medical Imaging Center, the First Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, People’s Republic of China
7Department of Liver Surgery, The First Affiliated Hospital of Sun Yat-sen University, Guangzhou, People’s Republic of China

Tóm tắt

The accurate prediction of post-hepatectomy early recurrence in patients with hepatocellular carcinoma (HCC) is crucial for decision-making regarding postoperative adjuvant treatment and monitoring. We aimed to explore the feasibility of deep learning (DL) features derived from gadoxetate disodium (Gd-EOB-DTPA) MRI, qualitative features, and clinical variables for predicting early recurrence. In this bicentric study, 285 patients with HCC who underwent Gd-EOB-DTPA MRI before resection were divided into training (n = 195) and validation (n = 90) sets. DL features were extracted from contrast-enhanced MRI images using VGGNet-19. Three feature selection methods and five classification methods were combined for DL signature construction. Subsequently, an mp-MR DL signature fused with multiphase DL signatures of contrast-enhanced images was constructed. Univariate and multivariate logistic regression analyses were used to identify early recurrence risk factors including mp-MR DL signature, microvascular invasion (MVI), and tumor number. A DL nomogram was built by incorporating deep features and significant clinical variables to achieve early recurrence prediction. MVI (p = 0.039), tumor number (p = 0.001), and mp-MR DL signature (p < 0.001) were independent risk factors for early recurrence. The DL nomogram outperformed the clinical nomogram in the training set (AUC: 0.949 vs. 0.751; p < 0.001) and validation set (AUC: 0.909 vs. 0.715; p = 0.002). Excellent DL nomogram calibration was achieved in both training and validation sets. Decision curve analysis confirmed the clinical usefulness of DL nomogram. The proposed DL nomogram was superior to the clinical nomogram in predicting early recurrence for HCC patients after hepatectomy. • Deep learning signature based on Gd-EOB-DTPA MRI was the predominant independent predictor of early recurrence for hepatocellular carcinoma (HCC) after hepatectomy. • Deep learning nomogram based on clinical factors and Gd-EOB-DTPA MRI features is promising for predicting early recurrence of HCC. • Deep learning nomogram outperformed the conventional clinical nomogram in predicting early recurrence.

Tài liệu tham khảo

Marasco G, Colecchia A, Colli A et al (2019) Role of liver and spleen stiffness in predicting the recurrence of hepatocellular carcinoma after resection. J Hepatol 70:440–448 Bruix J, Sherman M (2011) Management of hepatocellular carcinoma: an update. Hepatology 53:1020–1022 Ishizawa T, Hasegawa K, Aoki T et al (2008) Neither multiple tumors nor portal hypertension are surgical contraindications for hepatocellular carcinoma. Gastroenterology 134:1908–1916 Tung-Ping Poon R, Fan ST, Wong J (2000) Risk factors, prevention, and management of postoperative recurrence after resection of hepatocellular carcinoma. Ann Surg 232:10–24 Portolani N, Coniglio A, Ghidoni S et al (2006) Early and late recurrence after liver resection for hepatocellular carcinoma: prognostic and therapeutic implications. Ann Surg 243:229–235 Poon RT, Fan ST, Ng IO, Lo CM, Liu CL, Wong J (2000) Different risk factors and prognosis for early and late intrahepatic recurrence after resection of hepatocellular carcinoma. Cancer 89:500–507 Lee S, Kang TW, Song KD et al (2021) Effect of microvascular invasion risk on early recurrence of hepatocellular carcinoma after surgery and radiofrequency ablation. Ann Surg 273:564–571 Hirokawa F, Hayashi M, Asakuma M, Shimizu T, Inoue Y, Uchiyama K (2016) Risk factors and patterns of early recurrence after curative hepatectomy for hepatocellular carcinoma. Surg Oncol 25:24–29 Kwon SK, Yun SS, Kim HJ, Lee DS (2014) The risk factors of early recurrence after hepatectomy in hepatocellular carcinoma. Ann Surg Treat Res 86:283–288 Li X, Qi Z, Du H et al (2021) Deep convolutional neural network for preoperative prediction of microvascular invasion and clinical outcomes in patients with HCCs. Eur Radiol. https://doi.org/10.1007/s00330-021-08198-w Miao W, Nie P, Yang G et al (2021) An FDG PET/CT metabolic parameter-based nomogram for predicting the early recurrence of hepatocellular carcinoma after liver transplantation. Eur J Nucl Med Mol Imaging 48:3656–3665 Choi SY, Kim SH, Park CK et al (2018) Imaging features of gadoxetic acid-enhanced and diffusion-weighted MR imaging for identifying cytokeratin 19-positive hepatocellular carcinoma: a retrospective observational study. Radiology 286:897–908 Cho HJ, Kim B, Kim HJ et al (2020) Liver stiffness measured by MR elastography is a predictor of early HCC recurrence after treatment. Eur Radiol 30:4182–4192 Kim BR, Lee JM, Lee DH et al (2017) Diagnostic performance of gadoxetic acid-enhanced liver MR imaging versus multidetector CT in the detection of dysplastic nodules and early hepatocellular carcinoma. Radiology 285:134–146 Lee YJ, Lee JM, Lee JS et al (2015) Hepatocellular carcinoma: diagnostic performance of multidetector CT and MR imaging-a systematic review and meta-analysis. Radiology 275:97–109 Lee S, Kim SH, Lee JE, Sinn DH, Park CK (2017) Preoperative gadoxetic acid-enhanced MRI for predicting microvascular invasion in patients with single hepatocellular carcinoma. J Hepatol 67:526–534 An C, Kim DW, Park YN, Chung YE, Rhee H, Kim MJ (2015) Single hepatocellular carcinoma: preoperative MR imaging to predict early recurrence after curative resection. Radiology 276:433–443 Lambin P, Rios-Velazquez E, Leijenaar R et al (2012) Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer 48:441–446 Chong HH, Yang L, Sheng RF et al (2021) Multi-scale and multi-parametric radiomics of gadoxetate disodium-enhanced MRI predicts microvascular invasion and outcome in patients with solitary hepatocellular carcinoma ≤ 5 cm. Eur Radiol 31:4824–4838 Ben Naceur M, Akil M, Saouli R, Kachouri R (2020) Fully automatic brain tumor segmentation with deep learning-based selective attention using overlapping patches and multi-class weighted cross-entropy. Med Image Anal 63:101692 Zhang W, Fang M, Dong D et al (2020) Development and validation of a CT-based radiomic nomogram for preoperative prediction of early recurrence in advanced gastric cancer. Radiother Oncol 145:13–20 Lin T, Mai J, Yan M, Li Z, Quan X, Chen X (2021) A nomogram based on CT deep learning signature: a potential tool for the prediction of overall survival in resected non-small cell lung cancer patients. Cancer Manag Res 13:2897–2906 Liu D, Liu F, Xie X et al (2020) Accurate prediction of responses to transarterial chemoembolization for patients with hepatocellular carcinoma by using artificial intelligence in contrast-enhanced ultrasound. Eur Radiol 30:2365–2376 Murphy A, Skalski M, Gaillard F (2018) The utilisation of convolutional neural networks in detecting pulmonary nodules: a review. Br J Radiol 91:20180028 Shin HC, Roth HR, Gao M et al (2016) Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans Med Imaging 35:1285–1298 Nam JY, Lee JH, Bae J et al (2020) Novel model to predict HCC recurrence after liver transplantation obtained using deep learning: a multicenter study. Cancers (Basel) 12:2791 Shi JY, Wang X, Ding GY et al (2021) Exploring prognostic indicators in the pathological images of hepatocellular carcinoma based on deep learning. Gut 70:951–961 Roayaie S, Blume IN, Thung SN et al (2009) A system of classifying microvascular invasion to predict outcome after resection in patients with hepatocellular carcinoma. Gastroenterology 137:850–855 Kawamura Y, Ikeda K, Seko Y et al (2011) Heterogeneous type 4 enhancement of hepatocellular carcinoma on dynamic CT is associated with tumor recurrence after radiofrequency ablation. AJR Am J Roentgenol 197:W665-673 Kawamura Y, Ikeda K, Hirakawa M et al (2010) New classification of dynamic computed tomography images predictive of malignant characteristics of hepatocellular carcinoma. Hepatol Res 40:1006–1014 Shimizu R, Tamai H, Mori Y et al (2016) The arterial tumor enhancement pattern on contrast-enhanced computed tomography is associated with primary cancer death after radiofrequency ablation for small hepatocellular carcinoma. Hepatol Int 10:328–339 Huang M, Liao B, Xu P et al (2018) Prediction of microvascular invasion in hepatocellular carcinoma: preoperative Gd-EOB-DTPA-dynamic enhanced MRI and histopathological correlation. Contrast Media Mol Imaging 2018:9674565 Ji G-W, Zhu F-P, Xu Q et al (2020) Radiomic features at contrast-enhanced CT predict recurrence in early stage hepatocellular carcinoma: a multi-institutional study. Radiology 294:568–579 Kim KA, Kim MJ, Jeon HM et al (2012) Prediction of microvascular invasion of hepatocellular carcinoma: usefulness of peritumoral hypointensity seen on gadoxetate disodium-enhanced hepatobiliary phase images. J Magn Reson Imaging 35:629–634 Li W, Li L, Zhuang BW et al (2021) Inter-reader agreement of CEUS LI-RADS among radiologists with different levels of experience. Eur Radiol 31:6758–6767 Liu X, Jiang H, Chen J, Zhou Y, Huang Z, Song B (2017) Gadoxetic acid disodium-enhanced magnetic resonance imaging outperformed multidetector computed tomography in diagnosing small hepatocellular carcinoma: a meta-analysis. Liver Transpl 23:1505–1518 Onishi H, Kim T, Imai Y et al (2012) Hypervascular hepatocellular carcinomas: detection with gadoxetate disodium-enhanced MR imaging and multiphasic multidetector CT. Eur Radiol 22:845–854 Carbonell G, Kennedy P, Bane O et al (2022) Precision of MRI radiomics features in the liver and hepatocellular carcinoma. Eur Radiol 32:2030–2040 Fiset S, Welch ML, Weiss J et al (2019) Repeatability and reproducibility of MRI-based radiomic features in cervical cancer. Radiother Oncol 135:107–114 Zhao Y, Wu J, Zhang Q et al (2021) Radiomics analysis based on multiparametric MRI for predicting early recurrence in hepatocellular carcinoma after partial hepatectomy. J Magn Reson Imaging 53:1066–1079 Zhang Y, Lv X, Qiu J et al (2021) Deep learning with 3D convolutional neural network for noninvasive prediction of microvascular invasion in hepatocellular carcinoma. J Magn Reson Imaging 54:134–143 Lambin P, Leijenaar RTH, Deist TM et al (2017) Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 14:749–762 Wei J, Jiang H, Zeng M et al (2021) Prediction of microvascular invasion in hepatocellular carcinoma via deep learning: a multi-center and prospective validation study. Cancers (Basel) 13:2368 Zhang XP, Chen ZH, Zhou TF et al (2019) A nomogram to predict early postoperative recurrence of hepatocellular carcinoma with portal vein tumour thrombus after R0 liver resection: a large-scale, multicenter study. Eur J Surg Oncol 45:1644–1651 Chan AWH, Zhong J, Berhane S et al (2018) Development of pre and post-operative models to predict early recurrence of hepatocellular carcinoma after surgical resection. J Hepatol 69:1284–1293 Zou ZM, Chang DH, Liu H, Xiao YD (2021) Current updates in machine learning in the prediction of therapeutic outcome of hepatocellular carcinoma: what should we know? Insights Imaging 12:31 Ahn JC, Connell A, Simonetto DA, Hughes C, Shah VH (2021) Application of artificial intelligence for the diagnosis and treatment of liver diseases. Hepatology 73:2546–2563 Zhang Z, Jiang H, Chen J et al (2019) Hepatocellular carcinoma: radiomics nomogram on gadoxetic acid-enhanced MR imaging for early postoperative recurrence prediction. Cancer Imaging 19:22 Kim S, Shin J, Kim DY, Choi GH, Kim MJ, Choi JY (2019) Radiomics on gadoxetic acid-enhanced magnetic resonance imaging for prediction of postoperative early and late recurrence of single hepatocellular carcinoma. Clin Cancer Res 25:3847–3855 Kooi T, Litjens G, van Ginneken B et al (2017) Large scale deep learning for computer aided detection of mammographic lesions. Med Image Anal 35:303–312 Hosny A, Parmar C, Coroller TP et al (2018) Deep learning for lung cancer prognostication: a retrospective multi-cohort radiomics study. PLoS Med 15:e1002711 Yang X, Kwitt R, Styner M, Niethammer M (2017) Quicksilver: fast predictive image registration - a deep learning approach. Neuroimage 158:378–396 Yasaka K, Akai H, Abe O, Kiryu S (2018) Deep learning with convolutional neural network for differentiation of liver masses at dynamic contrast-enhanced CT: a preliminary study. Radiology 286:887–896 Chaudhary K, Poirion OB, Lu L, Garmire LX (2018) Deep learning-based multi-omics integration robustly predicts survival in liver cancer. Clin Cancer Res 24:1248–1259 Kong C, Zhao Z, Chen W et al (2021) Prediction of tumor response via a pretreatment MRI radiomics-based nomogram in HCC treated with TACE. Eur Radiol 31:7500–7511 Song D, Wang Y, Wang W et al (2021) Using deep learning to predict microvascular invasion in hepatocellular carcinoma based on dynamic contrast-enhanced MRI combined with clinical parameters. J Cancer Res Clin Oncol 147:3757–3767 Zhang L, Xia W, Yan ZP et al (2020) Deep learning predicts overall survival of patients with unresectable hepatocellular carcinoma treated by transarterial chemoembolization plus sorafenib. Front Oncol 10:593292 Sung YS, Park B, Park HJ, Lee SS (2021) Radiomics and deep learning in liver diseases. J Gastroenterol Hepatol 36:561–568 Yang G, Nie P, Zhao L et al (2020) 2D and 3D texture analysis to predict lymphovascular invasion in lung adenocarcinoma. Eur J Radiol 129:109111 Shen C, Liu Z, Guan M et al (2017) 2D and 3D CT radiomics features prognostic performance comparison in non-small cell lung cancer. Transl Oncol 10:886–894 Friemel J, Rechsteiner M, Frick L et al (2015) Intratumor heterogeneity in hepatocellular carcinoma. Clin Cancer Res 21:1951–1961 Yang F, Wang Y, Li Q et al (2017) Intratumor heterogeneity predicts metastasis of triple-negative breast cancer. Carcinogenesis 38:900–909 Ji GW, Zhu FP, Xu Q et al (2019) Machine-learning analysis of contrast-enhanced CT radiomics predicts recurrence of hepatocellular carcinoma after resection: a multi-institutional study. EBioMedicine 50:156–165 Dai H, Lu M, Huang B et al (2021) Considerable effects of imaging sequences, feature extraction, feature selection, and classifiers on radiomics-based prediction of microvascular invasion in hepatocellular carcinoma using magnetic resonance imaging. Quant Imaging Med Surg 11:1836–1853 Ni M, Zhou X, Lv Q et al (2019) Radiomics models for diagnosing microvascular invasion in hepatocellular carcinoma: which model is the best model? Cancer Imaging 19:60