Predicting Microvascular Invasion in Hepatocellular Carcinoma Using CT-based Radiomics Model

Radiology, Год журнала: 2023, Номер 307(4)

Опубликована: Апрель 25, 2023

Background Prediction of microvascular invasion (MVI) may help determine treatment strategies for hepatocellular carcinoma (HCC). Purpose To develop a radiomics approach predicting MVI status based on preoperative multiphase CT images and to identify MVI-associated differentially expressed genes. Materials Methods Patients with pathologically proven HCC from May 2012 September 2020 were retrospectively included four medical centers. Radiomics features extracted tumors peritumor regions registration or subtraction images. In the training set, these used build five models via logistic regression after feature reduction. The tested using internal external test sets against pathologic reference standard calculate area under receiver operating characteristic curve (AUC). optimal AUC model clinical-radiologic characteristics combined hybrid model. log-rank was in outcome cohort (Kunming center) analyze early recurrence-free survival overall high versus low model-derived score. RNA sequencing data Cancer Image Archive gene expression analysis. Results A total 773 patients (median age, 59 years; IQR, 49–64 633 men) divided into set (n = 334), 142), 141), 121), analysis 35). AUCs models, respectively, 0.76 0.86 0.72 0.84 set. Early (P < .01) .007) can be categorized Differentially genes findings positive involved glucose metabolism. Conclusion showed best performance prediction MVI. © RSNA, 2023 Supplemental material is available this article. See also editorial by Summers issue.

Язык: Английский

---

Application of artificial intelligence radiomics in the diagnosis, treatment, and prognosis of hepatocellular carcinoma

Computers in Biology and Medicine, Год журнала: 2024, Номер 173, С. 108337 - 108337

Опубликована: Март 24, 2024

Hepatocellular carcinoma (HCC) is the most common type of primary liver cancer, with an increasing incidence and poor prognosis. In past decade, artificial intelligence (AI) technology has undergone rapid development in field clinical medicine, bringing advantages efficient data processing accurate model construction. Promisingly, AI-based radiomics played increasingly important role decision-making HCC patients, providing new technical guarantees for prediction, diagnosis, prognostication. this review, we evaluated current landscape AI management HCC, including its individual treatment, survival Furthermore, discussed remaining challenges future perspectives regarding application HCC.

Язык: Английский

---

Using deep learning to predict microvascular invasion in hepatocellular carcinoma based on dynamic contrast-enhanced MRI combined with clinical parameters

Journal of Cancer Research and Clinical Oncology, Год журнала: 2021, Номер 147(12), С. 3757 - 3767

Опубликована: Апрель 10, 2021

Язык: Английский

---

Deep Learning With 3D Convolutional Neural Network for Noninvasive Prediction of Microvascular Invasion in Hepatocellular Carcinoma

Journal of Magnetic Resonance Imaging, Год журнала: 2021, Номер 54(1), С. 134 - 143

Опубликована: Фев. 8, 2021

Background Microvascular invasion (MVI) is a critical prognostic factor of hepatocellular carcinoma (HCC). However, it could only be obtained by postoperative histological examination. Purpose To develop an end‐to‐end deep‐learning models based on MRI images for preoperative prediction MVI in HCC patients who underwent surgical resection. Study type Retrospective. Population Two hundred and thirty‐seven with histologically confirmed HCC. Field strength 1.5 T 3.0 T. Sequence Axial 2 ‐weighted (T ‐w) turbo spin echo sequence, ‐Spectral Presaturation Inversion Recovery ‐SPIR), dynamic contrast‐enhanced (DCE) imaging fat suppressed enhanced 1 high‐resolution isotropic volume Assessment The were randomly divided into training ( N = 158) validation 79) sets. Data augmentation random rotation was performed the set sample size increased to 1940 each MR sequence. A three‐dimensional convolutional neural network (3D CNN) used four models, including three single‐layer single‐sequence, fusion model combining sequences. status from pathology reports. Statistical Tests dice similarity coefficient (DSC) Hausdorff distance (HD) applied assess reproducibility between manual segmentations tumor two radiologists. Receiver operating characteristic curve analysis evaluate performance. identified 92 (38.8%) patients. Good interobserver DSCs 0.90, 0.89, 0.89 HDs 4.09, 3.67, 3.60 observed PVP, WI, ‐SPIR, respectively. achieved area under (AUC) 0.81, sensitivity 69%, specificity 79% 0.72, 55%, 81% set. Conclusion 3D CNN may serve as noninvasive tool predict HCC, whereas its accuracy needs larger cohort. Level Evidence 3 Technical Efficacy Stage

Язык: Английский

---

Lentinan progress in inflammatory diseases and tumor diseases

European journal of medical research, Год журнала: 2024, Номер 29(1)

Опубликована: Янв. 3, 2024

Abstract Shiitake mushrooms are a fungal food that has been recorded in Chinese medicine to nourish the blood and qi. Lentinan (lLNT) is an active substance extracted from shiitake with powerful antioxidant, anti-inflammatory, anti-tumor functions. Inflammatory diseases cancers leading causes of death worldwide, posing serious threat human life health enormous challenges global systems. There still lack effective treatments for inflammatory cancer. LNT approved as adjunct chemotherapy China Japan. Studies have shown plays important role treatment well oncological diseases. Moreover, clinical experiments confirmed combined drugs significant effect improving prognosis patients, enhancing their immune function reducing side effects lung cancer, colorectal cancer gastric However, relevant mechanism action signaling pathway Therefore, this article reviews research tumor recent years.

Язык: Английский

---

Identification and Validation of a Prognostic Model Based on Three MVI-Related Genes in Hepatocellular Carcinoma

International Journal of Biological Sciences, Год журнала: 2021, Номер 18(1), С. 261 - 275

Опубликована: Ноя. 10, 2021

MVI has significant clinical value for treatment selection and prognosis evaluation in hepatocellular carcinoma (HCC). We aimed to construct a model based on MVI-Related Genes (MVIRGs) risk assessment prediction patients with HCC. This study utilized various statistical analysis methods prognostic construction validation the Cancer Genome Atlas (TCGA) International Consortium (ICGC) cohorts, respectively. In addition, immunohistochemistry qRT-PCR were used analyze identify of our cohort. After analyses, 153 differentially expressed MVIRGs identified, three key genes selected model. The high-risk group showed significantly lower overall survival (OS), this trend was observed all subgroups: different age groups, genders, stages, grades. Risk score factor independent age, gender, stage, grade. Moreover, ICGC cohort validated corresponding TCGA. cohort, that had higher expression levels HCC samples than normal controls. High scores recurrence-free (RFS) OS, especially MVI-positive samples. Therefore, constructed by can reliably predict RFS OS is valuable guiding

Язык: Английский

---

Radiomics Models for Predicting Microvascular Invasion in Hepatocellular Carcinoma: A Systematic Review and Radiomics Quality Score Assessment

Cancers, Год журнала: 2021, Номер 13(22), С. 5864 - 5864

Опубликована: Ноя. 22, 2021

Preoperative prediction of microvascular invasion (MVI) is importance in hepatocellular carcinoma (HCC) patient treatment management. Plenty radiomics models for MVI have been proposed. This study aimed to elucidate the role and evaluate their methodological quality. The quality was assessed by Radiomics Quality Score (RQS), risk bias evaluated Assessment Diagnostic Accuracy Studies (QUADAS-2). Twenty-two studies using CT, MRI, or PET/CT were included. All retrospective studies, only two had an external validation cohort. AUC values ranged from 0.69 0.94 test Substantial heterogeneity existed, low, with average RQS score 10 (28% total). Most demonstrated a low unclear domains QUADAS-2. In conclusion, model could be accurate effective tool HCC patients, although has so far insufficient. Future prospective cohort accordance standardized workflow are expected supply reliable that translates into clinical utilization.

Язык: Английский

---

Radiomics models for preoperative prediction of microvascular invasion in hepatocellular carcinoma: a systematic review and meta-analysis

Abdominal Radiology, Год журнала: 2022, Номер 47(6), С. 2071 - 2088

Опубликована: Апрель 1, 2022

Язык: Английский

---

Preoperative Prediction of Microvascular Invasion in Patients With Hepatocellular Carcinoma Based on Radiomics Nomogram Using Contrast-Enhanced Ultrasound

Frontiers in Oncology, Год журнала: 2021, Номер 11

Опубликована: Сен. 7, 2021

Purpose This study aimed to develop a radiomics nomogram based on contrast-enhanced ultrasound (CEUS) for preoperatively assessing microvascular invasion (MVI) in hepatocellular carcinoma (HCC) patients. Methods A retrospective dataset of 313 HCC patients who underwent CEUS between September 20, 2016 and March 2020 was enrolled our study. The population randomly grouped as primary 192 validation 121 Radiomics features were extracted from the B-mode (BM), artery phase (AP), portal venous (PVP), delay (DP) images acquired each patient. After feature selection, BM, AP, PVP, DP scores (Rad-score) constructed dataset. four clinical factors used multivariate logistic regression analysis, then developed. We also built preoperative prediction model comparison. performance evaluated via calibration, discrimination, usefulness. Results Multivariate analysis indicated that PVP Rad-score, tumor size, AFP (alpha-fetoprotein) level independent risk predictors associated with MVI. incorporating these revealed superior discrimination (based size level) (AUC: 0.849 vs . 0.690; p &lt; 0.001) 0.788 0.661; = 0.008), good calibration. Decision curve confirmed clinically useful. Furthermore, significant improvement net reclassification index (NRI) integrated discriminatory (IDI) implied signatures may be very useful biomarkers MVI HCC. Conclusion CEUS-based showed favorable predictive value identification could guide more appropriate surgical planning.

Язык: Английский

---

Radiomics for the Preoperative Evaluation of Microvascular Invasion in Hepatocellular Carcinoma: A Meta-Analysis

Frontiers in Oncology, Год журнала: 2022, Номер 12

Опубликована: Апрель 7, 2022

Background Microvascular invasion (MVI) is an independent risk factor for postoperative recurrence of hepatocellular carcinoma (HCC). To perform a meta-analysis to investigate the diagnostic performance radiomics preoperative evaluation MVI in HCC and effect potential factors. Materials Methods A systematic literature search was performed PubMed, Embase, Cochrane Library studies focusing on with methods. Data extraction quality assessment retrieved were performed. Statistical analysis included data pooling, heterogeneity testing forest plot construction. Meta-regression subgroup analyses reveal explanatory factors [design, combination clinical factors, imaging modality, number participants, Quality Assessment Diagnostic Accuracy Studies 2 (QUADAS-2) applicability risk] performance. Results Twenty-two 4,129 patients prediction included. The pooled sensitivity, specificity area under receiver operating characteristic curve (AUC) 84% (95% CI: 81, 87), 83% 78, 87) 0.90 0.87, 0.92). Substantial observed among ( I² =94%, 95% 88, 99). showed that all investigative covariates contributed sensitivity P &lt; 0.05). Combined MRI, CT participants Subgroup AUC estimates similar or MRI. Conclusion Radiomics promising noninvasive method has high status. based MRI had comparable predictive HCC. Prospective, large-scale multicenter methods will improve power future. Systematic Review Registration https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=259363 , identifier CRD42021259363.

Язык: Английский

---