Prediction of Microvascular Invasion of Hepatocellular Carcinoma Based on Contrast-Enhanced MR and 3D Convolutional Neural Networks

Zhou, Wu; Jian, Wanwei; Cen, Xiaoping; Zhang, Lijuan; Guo, Hui; Liu, Zaiyi; Liang, Changhong; Wang, Guangyi

doi:10.3389/fonc.2021.588010

Cited by 30 publications

(37 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, with increasing recognition of MVI and its prognostic value on surgical outcomes of HCC, preoperative MVI prediction systems for surgical decision making have become a hot topic in recent researches. In recent years, some studies have reported the possibility of imaging findings to predict the MVI of HCC (24)(25)(26)(27). However, it still has a limited capacity to detect MVI and the precise detection of MVI needs further histological identification (28).…”

Section: Introductionmentioning

confidence: 99%

Revisiting Surgical Strategies for Hepatocellular Carcinoma With Microvascular Invasion

et al. 2021

View full text Add to dashboard Cite

Although liver resection (LR) and liver transplantation (LT) are widely considered as potentially curative therapies for selected patients with hepatocellular carcinoma (HCC); however, there is still high risk of tumor recurrence in majority of HCC patients. Previous studies demonstrated that the presence of microvascular invasion (MVI), which was defined as the presence of tumor emboli within the vessels adjacent to HCC, was one of the key factors of early HCC recurrence and poor surgical outcomes after LR or LT. In this review, we evaluated the impact of current MVI status on surgical outcomes after curative therapies and aimed to explore the surgical strategies for HCC based on different MVI status with evidence from pathological examination. Surgical outcomes of HCC patients with MVI have been described as a varied range after curative therapies due to a broad spectrum of current definitions for MVI. Therefore, an international consensus on the validated definition of MVI in HCC is urgently needed to provide a more consistent evaluation and reliable prediction of surgical outcomes for HCC patients after curative treatments. We concluded that MVI should be further sub-classified into MI (microvessel invasion) and MPVI (microscopic portal vein invasion); for HCC patients with MPVI, local R0 resection with a narrow or wide surgical margin will get the same surgical results. However, for HCC patients with MI, local surgical resection with a wide and negative surgical margin will get better surgical outcomes. Nowadays, MVI status can only be reliably confirmed by histopathologic evaluation of surgical specimens, limiting its clinical application. Taken together, preoperative assessment of MVI is of utmost significance for selecting a reasonable surgical modality and greatly improving the surgical outcomes of HCC patients, especially in those with liver cirrhosis.

show abstract

Section: Introductionmentioning

confidence: 99%

Revisiting Surgical Strategies for Hepatocellular Carcinoma With Microvascular Invasion

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Although practice varies between treatment centers, many lines of evidence suggest that the best method for detection of liver metastases from CRC are computed tomography (CT) and magnetic resonance imaging (MRI) ( 9 ). For lesions with a diameter of less than 10 mm, MRI is a more sensitive modality than CT ( 10 , 11 ), and specifically in hepatobiliary MRI with specific contrast enhancers (such as gadoxetate), showing a higher accuracy of lesion detection ( 12 – 15 ). Many studies have investigated the optimal modality for imaging hepatic metastases, finding pooled sensitivity on a per-lesion basis of 88% for MRI, 74% for CT, and 79% for positron emission tomography/computed tomography (PET/CT) ( 9 , 16 – 18 ).…”

Section: Introductionmentioning

confidence: 99%

The Value of 18F-FDG PET/CT and Abdominal PET/MRI as a One-Stop Protocol in Patients With Potentially Resectable Colorectal Liver Metastases

et al. 2021

View full text Add to dashboard Cite

PurposeThe aim of this study was to evaluate the clinical value of simultaneous positron emission tomography/computed tomography (PET/CT) and abdominal positron emission tomography/magnet resonance imaging (PET/MRI) in the detection of liver metastases and extrahepatic disease (EHD) in patients with potentially resectable colorectal liver metastases (CLM).MethodsFifty-six patients with CLM underwent conventional imaging (chest and abdomen CT, liver contrast-enhanced CT or MRI) and PET imaging [fluorine-18 fluorodeoxyglucose (18F-FDG) PET/CT and subsequent liver PET/MRI] for staging or restaging. Diagnostic ability of PET imaging was compared with conventional imaging. Abnormal findings were correlated with follow-up imaging and/or histology. The influence of the PET imaging findings was categorized for each patient in relation to operability and other significant findings. The clinical management included three modalities (surgery for resectable CLM, unresectable CLM with conversion treatment, and systemic therapy). The clinical impact of the imaging modality was analyzed. The operative histopathological analysis and/or imaging follow-up were performed as the standard of reference.ResultsThis study enrolled a total of 56 patients (median age 60 years, 62.5% were male, 36 with colon cancer and 20 with rectal cancer). For EHD detection, PET/CT detected more EHD than conventional imaging (60.7% vs. 46.4%). PET/CT had different findings in 19 (33.9%) patients, including downstaging in 4 (7.1%) patients and upstaging in 15 (26.8%) patients. For liver lesion detection, PET/MRI showed comparable detection ability with CE-MRI and CE-CT (99.5%, 99.4%, and 86.5%, respectively) based on lesion analysis, much higher than PET/CT (47.5%). PET imaging had a major impact in 10/56 (17.9%) patients (4 from unresectable to resectable, 6 from resectable to unresectable) and a minor impact in 4/56 (7.1%) patients for changing the surgery extent. The therapeutic strategies had been altered in a total of 14/56 patients (25%) after PET/CT and PET/MRI scans.ConclusionThe results of this study indicate that simultaneous 18F-FDG PET/CT and abdominal PET/MRI scans can provide accurate information regarding CLM status and EHD, and can affect the management of 25% of the patients by changing the therapeutic strategies determined by conventional imaging. This new modality may serve as a new one-stop method in patients with potentially resectable CLM.

show abstract

“…A recent study using DL based on preoperative CT showed a considerable e cacy (AUC: 0.906) in predicting MVI 45 . Two other independent studies using DCE-MRI and 3D Convolutional Neural Networks instead of CT images to predict MVI achieved an AUC of 0.931 and 0.926 respectively 46,47 .…”

Section: Discussionmentioning

confidence: 97%

Deep-Learning Based Analysis of Preoperative MRI Predicts Microvascular Invasion and Outcome in Hepatocellular Carcinoma

Sun

Guan

et al. 2021

Preprint

View full text Add to dashboard Cite

Background & Aims: Preoperative prediction of microvascular invasion (MVI) is critical for treatment strategy making in patients with hepatocellular carcinoma (HCC). We aimed to develop a deep learning (DL) model based on preoperative dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) to predict the MVI status and clinical outcomes in patients with HCC. Methods We retrospectively included a total of 321 HCC patients with pathologically confirmed MVI status. Preoperative DCE-MRI of these patients were collected, annotated and further analyzed by DL in this study. A predictive model for MVI integrating DL-predicted MVI status (DL-MVI) and clinical parameters was constructed with multivariate logistic regression. Results Of 321 HCC patients, 136 patients were pathologically MVI absent and 185 patients were MVI present. Recurrence-free survival (RFS) and overall survival (OS) were significantly different between the DL-predicted MVI-absent and MVI-present. Among all clinical variables, only DL-predicted MVI status and AFP were independently associated with MVI: DL-MVI (odds ratio [OR]=35.738; 95% confidence interval [CI]: 14.027-91.056; p<0.001), AFP (OR=4.634, 95% CI: 2.576-8.336; p<0.001). To predict the presence of MVI, DL-MVI combined with AFP achieved an area under the curve (AUC) of 0.824. Conclusions Our predictive model combining DL-MVI and AFP achieved good performance for predicting MVI and clinical outcomes in patients with HCC.

show abstract

Prediction of Microvascular Invasion of Hepatocellular Carcinoma Based on Contrast-Enhanced MR and 3D Convolutional Neural Networks

Cited by 30 publications

References 34 publications

Revisiting Surgical Strategies for Hepatocellular Carcinoma With Microvascular Invasion

Revisiting Surgical Strategies for Hepatocellular Carcinoma With Microvascular Invasion

The Value of 18F-FDG PET/CT and Abdominal PET/MRI as a One-Stop Protocol in Patients With Potentially Resectable Colorectal Liver Metastases

Deep-Learning Based Analysis of Preoperative MRI Predicts Microvascular Invasion and Outcome in Hepatocellular Carcinoma

Contact Info

Product

Resources

About