Radiomics model based on preoperative gadoxetic acid-enhanced MRI for predicting liver failure

Zhu, Wangshu; Shi, Siya; Yang, Zehong; Song, Chao; Shen, Jun

doi:10.3748/wjg.v26.i11.1208

Cited by 25 publications

(18 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a study by Cai [31], the CT-based higher-order wavelet features were selected and radiomics score was calculated for the prediction of PHLF with an AUC of 0.82 and 0.76 in the training and test group, respectively. Zhu et al [32] reported an MRI-based radiomics model which combined rst order and texture features associated with PHLF, resulting in an accuracy of 80.9% in the test dataset. Similarly, Chen et al [33] developed a liver failure model by incorporating PLT count, tumor size and radiomics features from Gd-EOB-DTPA-enhanced MRI images, which shown a better performance than conventional clinical model.…”

Section: Discussionmentioning

confidence: 99%

CT Radiomics Nomogram for the Preoperative Prediction of Severe Post-Hepatectomy Liver Failure in Patients with Huge (≥10 cm) Hepatocellular Carcinoma

Fei

Liang

Yang

et al. 2021

Preprint

View full text Add to dashboard Cite

Background To establish a radiomics-based nomogram for predicting severe (grade B or C) post-hepatectomy liver failure (PHLF) in patients with huge (≥10 cm) hepatocellular carcinoma (HCC).Methods 186 patients with huge HCC (n = 131 for training dataset and n = 55 for test dataset) who underwent curative hepatic resection were included. The least absolute shrinkage and selection operator approach was applied to develop the radiomics signature for grade B or C PHLF prediction in the training dataset. A multivariable logistic regression model was used by incorporating radiomics signature and other clinical predictors to establish a radiomics nomogram. A decision tree was created to stratify the risk for severe PHLF.Results The radiomics signature consisting of nine features predicted severe PHLF with an AUC of 0.766 and 0.745 in the training and test datasets, respectively. The radiomics nomogram was generated by integrating the radiomics signature, the extent of resection and model for end-stage liver disease (MELD) score. The nomogram exhibited satisfactory discrimination and calibration, with an AUC of 0.842 and 0.863 in the training and test datasets, respectively. Decision tree split patients into 3 risk classes: low-risk patients with radiomics score < -0.247 and MELD score < 10 or，radiomics score ≥ -0.247 and underwent partial resections; intermediate-risk patients with radiomics score < -0.247 but MELD score ≥10; high-risk patients with radiomics score ≥ -0.247 and underwent extended resections.Conclusions The radiomics nomogram was able to predict severe PHLF in huge HCC patients. Decision tree may be useful in surgical decision-making for huge HCC hepatectomy.

show abstract

Section: Discussionmentioning

confidence: 99%

CT Radiomics Nomogram for the Preoperative Prediction of Severe Post-Hepatectomy Liver Failure in Patients with Huge (≥10 cm) Hepatocellular Carcinoma

Fei

Liang

Yang

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…A majority of the Table 2 Characteristics of gadoxetic acid-enhanced MRI-derived parameters BSA, body surface area; FLR, future liver remnant; FRLV(LMR), functional remnant liver volume corrected by liver-muscle ratio; functFLR, functional FLR; HUI, hepatic uptake index; LV, liver volume; NA, not available; remCER, contrast enhancement ratio of the liver remnant; remLV, the remnant liver volume; remRE Index, relative enhancement index of the liver remnant; remRLE, relative liver enhancement of the liver remnant; remSI Lpre , signal intensity of the liver remnant before contrast medium injection; remSI L20 , signal intensity of the liver remnant at 20 min after contrast medium injection; resSI L20 , signal intensity of the resected liver at 20 min after contrast medium injection; rHUI, hepatic uptake index of the liver remnant; rHUI-BSA, rHUI corrected by BSA; rHUI-BW, rHUI corrected by body weight; RF UR , sum of the uptake rate of the remnant liver regions; RLE, relative liver enhancement; SI HBP, liver signal intensity in hepatobiliary phase; SI L20 , signal intensity of the liver at 20 min after contrast medium injection; SI M20 , signal intensity of the muscle at 20 min after contrast medium injection; SI Mpre , signal intensity of the muscle before contrast medium injection; SI pre , liver signal intensity before contrast medium injection; SI S20 , signal intensity of the spleen at 20 min after contrast medium injection; SI TP , liver signal intensity in transitional phase; sRF UR , sum of the uptake rate of the remnant liver standardized by standard liver volume; included studies (11/15) compared the results of ICG test or its related parameters between PHLF and non-PHLF groups. Only five of those showed a significant difference: ICG-R15 test in two studies [32], ICG-plasma disappearance rate (ICG-PDR) test and its related parameters in one study [27], ICG clearance-related parameter in one study 22 , and both ICG-R15 and ICG-PDR tests in one study [33]. No studies showed a significantly greater AUC of ICG-test than that of gadoxetic acid-enhanced MRI parameters.…”

Section: Icg Test Between Phlf and Non-phlf Groupsmentioning

confidence: 94%

“…All studies were conducted in single centers. Table 1 illustrates the study characteristics of included studies [20][21][22][23][24][25][26][27][28][29][30][31][32][33]35].…”

Section: Study Characteristicsmentioning

confidence: 99%

Predictive value of gadoxetic acid–enhanced MRI for posthepatectomy liver failure: a systematic review

Wang

Sparrelid

et al. 2021

Eur Radiol

View full text Add to dashboard Cite

Objectives Effective and non-invasive biomarkers to predict and avoid posthepatectomy liver failure (PHLF) are urgently needed. This systematic review aims to evaluate the efficacy of gadoxetic acid–enhanced MRI-derived parameters as an imaging biomarker in preoperative prediction of PHLF. Methods A systematic literature search was performed in the databases of PubMed/Medline, Web of Science, Embase, and Cochrane Library up to 11 December 2020. Studies evaluating the incidence of PHLF on patients who underwent hepatectomy with preoperative liver function assessment using gadoxetic acid–enhanced MRI were included. Data was extracted using pre-designed tables. The Quality In Prognostic Studies (QUIPS) tool was adopted to evaluate the risk of bias. Results A total of 15 studies were identified for qualitative synthesis and most studies were marked as low to moderate risk of bias in each domain of QUIPS. The most commonly used parameter was relative liver enhancement or its related parameters. The reported incidence of PHLF ranged from 3.9 to 40%. The predictive sensitivity and specificity of gadoxetic acid–enhanced MRI parameters varied from 75 to 100% and from 54 to 93% in ten reported studies. A majority of the studies revealed that the gadoxetic acid–enhanced MRI parameter was a predictor for PHLF. Conclusions Gadoxetic acid–enhanced MRI showed a high predictive capacity for PHLF and represents a promising imaging biomarker in prediction of PHLF. Multicenter, prospective trials with large sample size and reliable, unified liver function parameters are required to validate the efficacy of individual liver function parameters. Key Points • There is an obvious heterogeneity of the published studies, not only in variance of MRI liver function parameters but also in indication and extent of the liver resection. • Signal intensity (SI)–based parameters derived from gadoxetic acid–enhanced MRI are the commonly used method for PHLF prediction. • Gadoxetic acid–enhanced MRI-derived parameters showed high predictive efficacy for PHLF and can potentially serve as a predictor for the incidence of PHLF.

show abstract

“…Fan Y et al (16) 2021 of postoperative death, and the 5-year relapse rate after surgery is close to 70% (126). Improving the ability to preoperatively identify these high-risk patients will guide surgical management, postoperative monitoring, and treatment intervention (127,128). The radiomic model based on preoperative MRI can be used as a new tool to predict early relapse (18,19,(129)(130)(131)(132)(133)(134), relapsefree survival (135) and overall survival (OS) (136,137)…”

Section: Prediction Of Relapse and Prognosis After Surgical Resectionmentioning

confidence: 99%

Progress of MRI Radiomics in Hepatocellular Carcinoma

Gong

Tao

et al. 2021

Front. Oncol.

View full text Add to dashboard Cite

BackgroundHepatocellular carcinoma (HCC) is the sixth most common cancer in the world and the third leading cause of cancer-related death. Although the diagnostic scheme of HCC is currently undergoing refinement, the prognosis of HCC is still not satisfactory. In addition to certain factors, such as tumor size and number and vascular invasion displayed on traditional imaging, some histopathological features and gene expression parameters are also important for the prognosis of HCC patients. However, most parameters are based on postoperative pathological examinations, which cannot help with preoperative decision-making. As a new field, radiomics extracts high-throughput imaging data from different types of images to build models and predict clinical outcomes noninvasively before surgery, rendering it a powerful aid for making personalized treatment decisions preoperatively.ObjectiveThis study reviewed the workflow of radiomics and the research progress on magnetic resonance imaging (MRI) radiomics in the diagnosis and treatment of HCC.MethodsA literature review was conducted by searching PubMed for search of relevant peer-reviewed articles published from May 2017 to June 2021.The search keywords included HCC, MRI, radiomics, deep learning, artificial intelligence, machine learning, neural network, texture analysis, diagnosis, histopathology, microvascular invasion, surgical resection, radiofrequency, recurrence, relapse, transarterial chemoembolization, targeted therapy, immunotherapy, therapeutic response, and prognosis.ResultsRadiomics features on MRI can be used as biomarkers to determine the differential diagnosis, histological grade, microvascular invasion status, gene expression status, local and systemic therapeutic responses, and prognosis of HCC patients.ConclusionRadiomics is a promising new imaging method. MRI radiomics has high application value in the diagnosis and treatment of HCC.

show abstract

Radiomics model based on preoperative gadoxetic acid-enhanced MRI for predicting liver failure

Cited by 25 publications

References 34 publications

CT Radiomics Nomogram for the Preoperative Prediction of Severe Post-Hepatectomy Liver Failure in Patients with Huge (≥10 cm) Hepatocellular Carcinoma

CT Radiomics Nomogram for the Preoperative Prediction of Severe Post-Hepatectomy Liver Failure in Patients with Huge (≥10 cm) Hepatocellular Carcinoma

Predictive value of gadoxetic acid–enhanced MRI for posthepatectomy liver failure: a systematic review

Progress of MRI Radiomics in Hepatocellular Carcinoma

Contact Info

Product

Resources

About