Prediction of histological grade of hepatocellular carcinoma using quantitative diffusion-weighted MRI: a retrospective multivendor study

Differentiating Uterine Sarcoma From Atypical Leiomyoma on Preoperative Magnetic Resonance Imaging Using Logistic Regression Classifier: Added Value of Diffusion-Weighted Imaging-Based Quantitative Parameters

OBJECTIVE

To evaluate the added value of diffusion-weighted imaging (DWI)-based quantitative parameters to distinguish uterine sarcomas from atypical leiomyomas on preoperative magnetic resonance imaging (MRI).

MATERIALS AND METHODS

A total of 138 patients (age, 43.7 ± 10.3 years) with uterine sarcoma (n = 44) and atypical leiomyoma (n = 94) were retrospectively collected from four institutions. The cohort was randomly divided into training (84/138, 60.0%) and validation (54/138, 40.0%) sets. Two independent readers evaluated six qualitative MRI features and two DWI-based quantitative parameters for each index tumor. Multivariable logistic regression was used to identify the relevant qualitative MRI features. Diagnostic classifiers based on qualitative MRI features alone and in combination with DWI-based quantitative parameters were developed using a logistic regression algorithm. The diagnostic performance of the classifiers was evaluated using a cross-table analysis and calculation of the area under the receiver operating characteristic curve (AUC).

RESULTS

Mean apparent diffusion coefficient value of uterine sarcoma was lower than that of atypical leiomyoma (mean ± standard deviation, 0.94 ± 0.30 10-3 mm²/s vs. 1.23 ± 0.25 10-3 mm²/s; P < 0.001), and the relative contrast ratio was higher in the uterine sarcoma (8.16 ± 2.94 vs. 4.19 ± 2.66; P < 0.001). Selected qualitative MRI features included ill-defined margin (adjusted odds ratio [aOR], 17.9; 95% confidence interval [CI], 1.41-503, P = 0.040), intratumoral hemorrhage (aOR, 27.3; 95% CI, 3.74-596, P = 0.006), and absence of T2 dark area (aOR, 83.5; 95% CI, 12.4-1916, P < 0.001). The classifier that combined qualitative MRI features and DWI-based quantitative parameters showed significantly better performance than without DWI-based parameters in the validation set (AUC, 0.92 vs. 0.78; P < 0.001).

CONCLUSION

The addition of DWI-based quantitative parameters to qualitative MRI features improved the diagnostic performance of the logistic regression classifier in differentiating uterine sarcomas from atypical leiomyomas on preoperative MRI.

Use of radiomics containing an effective peritumoral area to predict early recurrence of solitary hepatocellular carcinoma ≤5 cm in diameter

Background

Hepatocellular carcinoma (HCC) is the sixth leading type of cancer worldwide. We aimed to develop a preoperative predictive model of the risk of early tumor recurrence after HCC treatment based on radiomic features of the peritumoral region and evaluate the performance of this model against postoperative pathology.

Method

Our model was developed using a retrospective analysis of imaging and clinicopathological data of 175 patients with an isolated HCC ≤5 cm in diameter; 117 patients were used for model training and 58 for model validation. The peritumoral area was delineated layer-by-layer for the arterial and portal vein phase on preoperative dynamic enhanced computed tomography images. The volume area of interest was expanded by 5 and 10 mm and the radiomic features of these areas extracted. Lasso was used to select the most stable features.

Results

The radiomic features of the 5-mm area were sufficient for prediction of early tumor recurrence, with an area under the curve (AUC) value of 0.706 for the validation set and 0.837 for the training set using combined images. The AUC of the model using clinicopathological information alone was 0.753 compared with 0.786 for the preoperative radiomics model (P >0.05).

Conclusions

Radiomic features of a 5-mm peritumoral region may provide a non-invasive biomarker for the preoperative prediction of the risk of early tumor recurrence for patients with a solitary HCC ≤5 cm in diameter. A fusion model that combines the radiomic features of the peritumoral region and postoperative pathology could contribute to individualized treatment of HCC.

The Roles of Diffusion Kurtosis Imaging and Intravoxel Incoherent Motion Diffusion-Weighted Imaging Parameters in Preoperative Evaluation of Pathological Grades and Microvascular Invasion in Hepatocellular Carcinoma

Background

Currently, there are disputes about the parameters of diffusion kurtosis imaging (DKI), intravoxel incoherent motion (IVIM), and diffusion-weighted imaging (DWI) in predicting pathological grades and microvascular invasion (MVI) in hepatocellular carcinoma (HCC). The aim of our study was to investigate and compare the predictive power of DKI and IVIM-DWI parameters for preoperative evaluation of pathological grades and MVI in HCC.

Methods

PubMed, Web of Science, and Embase databases were searched for relevant studies published from inception to October 2021. Review Manager 5.3 was used to summarize standardized mean differences (SMDs) of mean kurtosis (MK), mean diffusivity (MD), tissue diffusivity (D), pseudo diffusivity (D*), perfusion fraction (f), mean apparent diffusion coefficient (ADCmean), and minimum apparent diffusion coefficient (ADCmin). Stata12.0 was used to pool the sensitivity, specificity, and area under the curve (AUC). Overall, 42 up-to-standard studies with 3,807 cases of HCC were included in the meta-analysis.

Results

The SMDs of ADCmean, ADCmin, and D values, but not those of D* and f values, significantly differed between well, moderately, and poorly differentiated HCC (P < 0.01). The sensitivity, specificity, and AUC of the MK, D, ADCmean, and ADCmin for preoperative prediction of poorly differentiated HCC were 69%/94%/0.89, 87%/80%/0.89, 82%/75%/0.86, and 83%/64%/0.81, respectively. In addition, the sensitivity, specificity, and AUC of the D and ADCmean for preoperative prediction of well-differentiated HCC were 87%/83%/0.92 and 82%/88%/0.90, respectively. The SMDs of ADCmean, ADCmin, D, MD, and MK values, but not f values, showed significant differences (P < 0.01) between MVI-positive (MVI+) and MVI-negative (MVI-) HCC. The sensitivity and specificity of D and ADCmean for preoperative prediction of MVI+ were 80%/80% and 74%/71%, respectively; the AUC of the D (0.87) was significantly higher than that of ADCmean (0.78) (Z = −2.208, P = 0.027). Sensitivity analysis showed that the results of the above parameters were stable and reliable, and subgroup analysis confirmed a good prediction effect.

Conclusion

DKI parameters (MD and MK) and IVIM-DWI parameters (D value, ADCmean, and ADCmin) can be used as a noninvasive and simple preoperative examination method to predict the grade and MVI in HCC. Compared with ADCmean and ADCmin, MD and D values have higher diagnostic efficacy in predicting the grades of HCC, and D value has superior diagnostic efficacy to ADCmean in predicting MVI+ in HCC. However, f value cannot predict the grade or MVI in HCC.

Added Value of Quantitative Apparent Diffusion Coefficients for Identifying Small Hepatocellular Carcinoma from Benign Nodule Categorized as LI-RADS 3 and 4 in Cirrhosis

BACKGROUND AND AIMS

Correct identification of small hepatocellular carcinomas (HCCs) and benign nodules in cirrhosis remains challenging, quantitative apparent diffusion coefficients (ADCs) have shown potential value in characterization of benign and malignant liver lesions. We aimed to explore the added value of ADCs in the identification of small (≤3 cm) HCCs and benign nodules categorized as Liver Imaging Reporting and Data System (LI-RADS) 3 (LR-3) and 4 (LR-4) in cirrhosis.

METHODS

Ninety-seven cirrhosis patients with 109 small nodules (70 HCCs, 39 benign nodules) of LR-3 and 4 LR-4 based on major and ancillary magnetic resonance imaging features were included. Multiparametric quantitative ADCs of the lesions, including the mean ADC (ADC_mean), minimum ADC (ADC_min), maximal ADC (ADC_max), ADC standard deviation (ADC_std), and mean ADC value ratio of lesion-to-liver parenchyma (ADC_ratio) were calculated. Regarding the joint diagnosis, a nomogram model was plotted using multivariate logistic regression analysis. The performance was assessed using the area under the receiver operating characteristic curve (AUC).

RESULTS

The ADC_mean, ADC_min, ADC_ratio, and ADC_std were significantly associated with the identification of small HCC and benign nodules (p<0.001). For the joint diagnosis, the LI-RADS category (odds ratio [OR]=12.50), ADC_min (OR=0.14), and ADC_ratio (OR=0.12) were identified as independent factors for distinguishing HCCs from benign nodules. The joint nomogram model showed good calibration and discrimination, with a C-index of 0.947. Compared with the LI-RADS category alone, this nomogram model demonstrated a significant improvement in diagnostic performance, with AUC increasing from 0.820 to 0.967 (p=0.001).

CONCLUSIONS

The addition of quantitative ADCs could improve the identification of small HCC and benign nodules categorized as LR-3 and 4 LR-4 in patients with cirrhosis.

Quantitative magnetic resonance imaging for focal liver lesions: bridging the gap between research and clinical practice

Magnetic resonance imaging (MRI) is highly important for the detection, characterization, and follow-up of focal liver lesions. Several quantitative MRI-based methods have been proposed in addition to qualitative imaging interpretation to improve the diagnostic work-up and prognostics in patients with focal liver lesions. This includes DWI with apparent diffusion coefficient measurements, intravoxel incoherent motion, perfusion imaging, MR elastography, and radiomics. Multiple research studies have reported promising results with quantitative MRI methods in various clinical settings. Nevertheless, applications in everyday clinical practice are limited. This review describes the basic principles of quantitative MRI-based techniques and discusses the main current applications and limitations for the assessment of focal liver lesions.

Diffusion-Weighted Imaging Reflects Tumor Grading and Microvascular Invasion in Hepatocellular Carcinoma

BACKGROUND

To date, there are inconsistent data about relationships between diffusion-weighted imaging (DWI) and tumor grading/microvascular invasion (MVI) in hepatocellular carcinoma (HCC). Our purpose was to systematize the reported results regarding the role of DWI in prediction of tumor grading/MVI in HCC.

METHOD

MEDLINE library, Scopus, and Embase data bases were screened up to December 2019. Overall, 29 studies with 2,715 tumors were included into the analysis. There were 20 studies regarding DWI and tumor grading, 8 studies about DWI and MVI, and 1 study investigated DWI, tumor grading, and MVI in HCC.

RESULTS

In 21 studies (1,799 tumors), mean apparent diffusion coefficient (ADC) values (ADC_mean) were used for distinguishing HCCs. ADC_mean of G1-3 lesions overlapped significantly. In 4 studies (461 lesions), minimum ADC (ADC_min) was used. ADC_min values in G1/2 lesions were over 0.80 × 10^-3 mm²/s and in G3 tumors below 0.80 × 10^-3 mm²/s. In 4 studies (241 tumors), true diffusion (D) was reported. A significant overlapping of D values between G1, G2, and G3 groups was found. ADC_mean and MVI were analyzed in 9 studies (1,059 HCCs). ADC_mean values of MIV+/MVI- lesions overlapped significantly. ADC_min was used in 4 studies (672 lesions). ADC_min values of MVI+ tumors were in the area under 1.00 × 10^-3 mm²/s. In 3 studies (227 tumors), D was used. Also, D values of MVI+ lesions were predominantly in the area under 1.00 × 10^-3 mm²/s.

CONCLUSION

ADC_min reflects tumor grading, and ADC_min and D predict MVI in HCC. Therefore, these DWI parameters should be estimated for every HCC lesion for pretreatment tumor stratification. ADC_mean cannot predict tumor grading/MVI in HCC.

The diagnostic value of diffusion-weighted imaging in differentiating benign from malignant hepatic lesions

Background

Diffusion-weighted imaging (DWI) is a novel imaging technique with growing application in onco-imaging. This modality evaluates the diffusion of water molecules in various tissues, which is restricted in hyper cellular regions such as malignant tissue. Apparent diffusion co-efficient (ADC) is a method which can quantify the degree of restriction in tissues and can have diagnostic roles in characterization of hepatic lesions. In this study, 93 patients with proven hepatic lesions were included. These patients had undergone initial evaluation via ultrasonography and dynamic CT scan, and had a definite diagnosis confirmed by biopsy. These patients underwent DW imaging and ADC values of their lesions were calculated. Patients were divided into two groups, benign and malignant groups, based on their biopsy results; and ADC values of hepatic lesions were compared in the two groups.

Results

The two groups were gender matched. There was a significant difference in the age distribution between the two groups. Mean ADC values for benign and malignant hepatic lesions were 1.58 ± 0.35 (10-3 mm2/s) and 0.87 ± 0.16 (10-3 mm2/s), respectively. There was a statistically significant differences between benign and malignant hepatic lesions (p value < 10-3). DW imaging had a sensitivity of 97.6% and specificity of 98.7% in detecting malignant hepatic lesions from benign ones (p = 0.0001, AUC = 0.99).

Conclusion

DW MRI imaging can differentiate malignant and benign liver lesions with high sensitivity and specificity using ADC values generated; furthermore, each subgroup of hepatic lesions could be determined based on ADC values.

Noninvasive Evaluation of the Pathologic Grade of Hepatocellular Carcinoma Using MCF-3DCNN: A Pilot Study

Purpose

To evaluate the diagnostic performance of deep learning with a multichannel fusion three-dimensional convolutional neural network (MCF-3DCNN) in the differentiation of the pathologic grades of hepatocellular carcinoma (HCC) based on dynamic contrast-enhanced magnetic resonance images (DCE-MR images).

Methods and Materials

Fifty-one histologically proven HCCs from 42 consecutive patients from January 2015 to September 2017 were included in this retrospective study. Pathologic examinations revealed nine well-differentiated (WD), 35 moderately differentiated (MD), and seven poorly differentiated (PD) HCCs. DCE-MR images with five phases were collected using a 3.0 Tesla MR scanner. The 4D-tensor representation was employed to organize the collected data in one temporal and three spatial dimensions by referring to the phases and 3D scanning slices of the DCE-MR images. A deep learning diagnosis model with MCF-3DCNN was proposed, and the structure of MCF-3DCNN was determined to approximate clinical diagnosis experience by taking into account the significance of the spatial and temporal information from DCE-MR images. Then, MCF-3DCNN was trained based on well-labeled samples of HCC lesions from real patient cases by experienced radiologists. The accuracy when differentiating the pathologic grades of HCC was calculated, and the performance of MCF-3DCNN in lesion diagnosis was assessed. Additionally, the areas under the receiver operating characteristic curves (AUC) for distinguishing WD, MD, and PD HCCs were calculated.

Results

MCF-3DCNN achieved an average accuracy of 0.7396±0.0104 with regard to totally differentiating the pathologic grade of HCC. MCF-3DCNN also achieved the highest diagnostic performance for discriminating WD HCCs from others, with an average AUC, accuracy, sensitivity, and specificity of 0.96, 91.00%, 96.88%, and 89.62%, respectively.

Conclusions

This study indicates that MCF-3DCNN can be a promising technology for evaluating the pathologic grade of HCC based on DCE-MR images.

Improving the Quality of Diffusion-weighted Imaging of the Left Hepatic Lobe Using Weighted Averaging of Signals from Multiple Excitations

Background:

Diffusion-weighted imaging (DWI) is useful for detecting and characterizing liver lesions but is sensitive to organ motion artifact, especially in the left lobe.

Purpose:

To assess the signal intensity (SI) loss in the left hepatic lobe on DWI depending on motion-proving gradient (MPG) pulse direction (preliminary study) and to evaluate the usefulness of modified signal averaging to reduce the SI loss on DWI (application study).

Methods:

About 48 (preliminary) and 35 (application) patients were included. In the preliminary study, DWI with four different MPG directions, only a single MPG pulse direction (x-, y-, or z-axis) and all three directions combined (standard DWI), were reconstructed from the original data. In the application study, we examined the usefulness of the weighted averaging number of excitations (wNEX) method, in which a larger weighting factor is applied to the higher signal in pixel-by-pixel NEX signal averaging by comparing four reconstruction methods. We assumed that true signals would be the same in both lobes. The SI and apparent diffusion coefficient (ADC) ratios for the left versus right lobe were calculated by dividing the SI/ADC of the right lobe by that of the left lobe.

Results:

In the preliminary study, the SI ratio was significantly lower on DWI using only the x-axis but was significantly higher on DWI using only the z-axis (both P < 0.0001) when compared with standard DWI. In the application study, the SI (mean, 1.15–1.17) and ADC (0.90–0.92) ratios on DWI with wNEX were closer to 1.0 than those on standard DWI (SI ratio, 1.32–1.38; ADC ratio 0.80–0.81); the differences were significant (all P < 0.0001).

Conclusion:

The MPG pulse along the z-axis caused signal loss in the left hepatic lobe. The wNEX reconstruction method effectively reduced signal loss in the left lobe on DWI.

LI-RADS 2017: An update

The computed tomography / magnetic resonance imaging (CT/MRI) Liver Imaging Reporting & Data System (LI-RADS) is a standardized system for diagnostic imaging terminology, technique, interpretation, and reporting in patients with or at risk for developing hepatocellular carcinoma (HCC). Using diagnostic algorithms and tables, the system assigns to liver observations category codes reflecting the relative probability of HCC or other malignancies. This review article provides an overview of the 2017 version of CT/MRI LI-RADS with a focus on MRI. The main LI-RADS categories and their application will be described. Changes and updates introduced in this version of LI-RADS will be highlighted, including modifications to the diagnostic algorithm and to the optional application of ancillary features. Comparisons to other major diagnostic systems for HCC will be made, emphasizing key similarities, differences, strengths, and limitations. In addition, this review presents the new Treatment Response algorithm, while introducing the concepts of MRI nonviability and viability. Finally, planned future directions for LI-RADS will be outlined.

LEVEL OF EVIDENCE

5 Technical Efficacy: Stage 5 J. Magn. Reson. Imaging 2018;47:1459-1474.