Dataset Information

Differentiation of small (≤ 3 cm) hepatocellular carcinomas from benign nodules in cirrhotic liver: the added additive value of MRI-based radiomics analysis to LI-RADS version 2018 algorithm.

ABSTRACT:

Background

Accurate characterization of small nodules in a cirrhotic liver is challenging. We aimed to determine the additive value of MRI-based radiomics analysis to Liver Imaging Reporting and Data System version 2018 (LI-RADS v 2018) algorithm in differentiating small (≤ 3 cm) hepatocellular carcinomas (HCCs) from benign nodules in cirrhotic liver.

Methods

In this retrospective study, 150 cirrhosis patients with histopathologically confirmed small liver nodules (HCC, 112; benign nodules, 44) were evaluated from January 2013 to October 2018. Based on the LI-RADS algorithm, a LI-RADS category was assigned for each lesion. A radiomics signature was generated based on texture features extracted from T1-weighted, T2W, and apparent diffusion coefficient (ADC) images by using the least absolute shrinkage and selection operator regression model. A nomogram model was developed for the combined diagnosis. Diagnostic performance was assessed using receiver operating characteristic curve (ROC) analysis.

Results

A radiomics signature consisting of eight features was significantly associated with the differentiation of HCCs from benign nodules. Both LI-RADS algorithm (area under ROC [A_z] = 0.898) and the MRI-Based radiomics signature (A_z = 0.917) demonstrated good discrimination, and the nomogram model showed a superior classification performance (A_z = 0.975). Compared with LI-RADS alone, the combined approach significantly improved the specificity (97.7% vs 81.8%, p = 0.030) and positive predictive value (99.1% vs 92.9%, p = 0.031) and afforded comparable sensitivity (97.3% vs 93.8%, p = 0.215) and negative predictive value (93.5% vs 83.7%, p = 0.188).

Conclusions

MRI-based radiomics analysis showed additive value to the LI-RADS v 2018 algorithm for differentiating small HCCs from benign nodules in the cirrhotic liver.

SUBMITTER: Zhong X

PROVIDER: S-EPMC8028813 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:ObjectivesHepatocellular carcinoma (HCC) can be diagnosed non-invasively with contrast-enhanced ultrasound (CEUS) in cirrhosis if the characteristic pattern of arterial phase hyperenhancement followed by hypoenhancement is present. Recent studies suggest that diagnosis based on this "hyper-hypo" pattern needs further refinement. This study compares the diagnostic accuracies of standardized CEUS for HCC according to the current guideline definition and following the newly developed CEUS algorithms (CEUS LI-RADS®, ESCULAP) in a prospective multicenter real-life setting.MethodsCirrhotic patients with liver lesions on B-mode ultrasound were recruited prospectively from 04/2018 to 04/2019, and clinical and imaging data were collected. The CEUS standard included an additional examination point after 4-6 min in case of no washout after 3 min. The diagnostic accuracies of CEUS following the guidelines ("hyper-hypo" pattern), based on the examiner's subjective interpretation ("CEUS subjective"), and based on the CEUS algorithms ESCULAP and CEUS LI-RADS® were compared.ResultsIn total, 470 cirrhotic patients were recruited in 43 centers. The final diagnosis was HCC in 378 cases (80.4%) according to the reference standard (histology 77.4%, MRI 16.4%, CT 6.2%). The "hyper-hypo" pattern yielded 74.3% sensitivity and 63% specificity. "CEUS subjective" showed a higher diagnostic accuracy (sensitivity, 91.5%; specificity, 67.4%; positive predictive value, 92%; negative predictive value, 66%). Sensitivity was higher for ESCULAP (95%) and "CEUS subjective" (91.5%) versus CEUS LI-RADS® (65.2%; p < 0.001). Specificity was highest for CEUS LI-RADS® (78.6%; p < 0.001).ConclusionsCEUS has an excellent diagnostic accuracy for the non-invasive diagnosis of HCC in cirrhosis. CEUS algorithms may be a helpful refinement of the "hyper-hypo" pattern defined by current HCC guidelines.Key points• Contrast-enhanced ultrasound (CEUS) has a high diagnostic accuracy for the non-invasive diagnosis of hepatocellular carcinoma (HCC) in cirrhosis. • The CEUS algorithm ESCULAP (Erlanger Synopsis for Contrast-enhanced Ultrasound for Liver lesion Assessment in Patients at risk) showed the highest sensitivity, whereas the CEUS LI-RADS® (Contrast-Enhanced UltraSound Liver Imaging Reporting and Data System) algorithm yielded the highest specificity. • A standardized CEUS examination procedure with an additional examination point in the late phase, after 4-6 min in lesions with no washout after 3 min, is vital.

Project description:Potential use of sonographic TI-RADS classification combined with circulating miRNA expression profiling in the diagnosis of thyroid nodules was explored. Retrospective analysis was performed on clinical data of 121 patients with thyroid nodules. The biopsy specimens of patients obtained through ultrasound-guided aspiration and blood specimens were evaluated in Zhengzhou Central Hospital Affiliated to Zhengzhou University from June 2018 to June 2019. In addition, the blood specimen test results of 121 healthy volunteers (control group) who underwent physical examination were retrospectively analyzed. Results of sonographic TI-RADS classification and circulating miRNA expression profiling were compared with the pathological results. Of the 212 nodules, 2 fell into TI-RADS category 2 and were diagnosed as benign. Malignant nodules accounted for 4.35, 37.14, 84.78, 93.33 and 96.77% of those nodules that fell into TI-RADS categories 3, 4a, 4b, 4c and 5, respectively. Of the 121 patients, 92.55% had with nodular goiter, 3.31% had inflammatory nodules, 2.48% toxic nodular goiter, 0.83% thyroid cysts and 0.83% thyroid tumors. A nodule that fell into a higher TI-RADS classification category had a higher risk of malignancy. The expression levels of miRNA146b, miRNA187, miRNA375, miRNA-222-3p and miRNA-151a-5p were higher, while the level of miRNA138 was lower, in patients with either benign or malignant thyroid nodules compaed to those in the control group. The expression levels of miRNA146b, miRNA187, miRNA375, miRNA-222-3p and miRNA-151a-5p were higher, while the level of miRNA138 was lower, in patients with malignant thyroid nodules than those in patients with benign thyroid nodule (P<0.05). The AUC of the combined diagnostic method was 0.973, which was significantly different from the AUCs of the individual diagnostic method (P<0.05). In conclusion, sonographic TI-RADS classification combined with circulating miRNA expression profiling can improve the diagnosis of thyroid nodules.

Project description:BackgroundEarly diagnosis is crucial to the treatment of breast cancer, but conventional imaging detection is challenging. Radiomics has the potential to improve early diagnostic efficacy in a noninvasive manner. This study examined whether integrating computed tomography (CT) radiomics information based on ultrasound (US) models can improve the efficacy of breast cancer prediction.MethodsWe retrospectively analyzed 420 patients with pathologically confirmed benign or malignant breast tumors. Clinical data and examination images were collected, and the population was divided into training (n=294) and validation (n=126) groups at a ratio of 7:3. The region of interest (ROI) was manually segmented along the tumor boundary using MaZda software, and the features of each ROI was extracted. After dimension reduction and screening, the best features were retained. Subsequently, random forest (RF), support vector machines, and K-nearest neighbor classifiers were used to establish prediction models in an US and combined-methods group.ResultsFinally, 8 of the 379 features were retained in the US group. Random forest was found to be the best model, and the area under the curve (AUC) of the training and validation groups was 0.90 [95% confidence interval (CI): 0.852-0.942] and 0.85 (95% CI: 0.775-0.930), respectively. Meanwhile, 12 of the 750 features were retained in the combined group. In this regard, random forest proved to be the best model, and the AUC of the training and validation group was 0.95 (95% CI: 0.918-0.981) and 0.92 (95% CI: 0.866-0.969), respectively. The calibration curve showed a good fit of the model. The decision curve showed that the clinical net benefit of the combined group was far greater than that of any single examination, and the prediction model of the combined group exhibited a degree of practical clinical value.ConclusionsThe combined model based on US and CT images has potential application value in the prognostic prediction of benign and malignant breast diseases.