Basic MRI for the liver oncologists and surgeons

Multiparametric MRI-based Machine Learning Radiomics for Predicting Treatment Response to Transarterial Chemoembolization Combined with Targeted and Immunotherapy in Unresectable Hepatocellular Carcinoma: A Multicenter Study

RATIONALE AND OBJECTIVES

To develop and validate multiple machine learning predictive models incorporating clinical features and pretreatment multiparametric magnetic resonance imaging (MRI) radiomic features for predicting treatment response to transarterial chemoembolization combined with molecular targeted therapy plus immunotherapy in unresectable hepatocellular carcinoma (HCC).

MATERIALS AND METHODS

This retrospective study involved 276 patients with unresectable HCC who received combination therapy from 4 medical centers. Patients were divided into one training cohort and two independent external validation cohorts. 16 radiomic features from six multiparametric MRI sequences and 2 clinical features were used to build six machine learning models. The models were evaluated using the area under the curve (AUC), decision curve analysis, and incremental predictive value.

RESULTS

Alpha-fetoprotein and neutrophil-to-lymphocyte ratio are clinical independent predictors of treatment response. In the training cohort and two external validation cohorts, the AUCs and 95% confidence intervals for predicting treatment response were respectively 0.782 (0.698-0.857) 0.695 (0.566-0.823), and 0.679 (0.542-0.810) for the clinical model; 0.942 (0.903-0.974), 0.869 (0.761-0.949), and 0.868 (0.769-0.942) for the radiomics model; and 0.956 (0.920-0.984), 0.895 (0.810-0.967), and 0.892 (0.804-0.957) for the combined clinical-radiomics model. In the three cohorts, the incremental predictive value of the radiomics model over the clinical model was 49.2% (P < 0.001), 28.8% (P < 0.001), and 31.5% (P < 0.001).

CONCLUSION

The combined clinical-radiomics model may provide a reliable and non-invasive tool to predict individual treatment responses and guide and improve clinical decision-making in combination therapy of HCC patients.

Colorectal liver metastases on gadoxetic acid-enhanced MRI: Typical characteristics decrease after chemotherapy

PURPOSE

To determine to what extent colorectal liver metastases (CRLM) display typical imaging characteristics on gadoxetic acid-enhanced magnetic resonance imaging (MRI) and what changes after chemotherapy.

METHODS

We retrospectively identified 258 patients with a gadoxetic acid-enhanced MRI between 2015 and 2021 and pathologically proven non-mucinous adenocarcinoma CRLM. 722 unique CRLMs were analyzed: 378 CRLM in only the chemotherapy-naïve analysis; 217 in post-chemotherapy analysis; and 127 CRLM were analyzed both pre- and post-chemotherapy. The following six characteristics were defined as typical; "hypovascular", "unenhanced T1-weighted (UE-T1W) hypointensity", "arterial rim enhancement", "non-enhancing during hepatobiliary phase", "T2-weighted (T2W) mild hyperintensity", and "diffusion restriction".

RESULTS

All six typical characteristics were found in 249/505 chemotherapy-naïve CRLM (49 %) and 87/344 post-chemotherapy CRLM (25 %). The occurrence of some typical characteristics decreased post-chemotherapy: UE-T1W hypointensity 485/505 (96 %) versus 311/336 (93 %), arterial rim enhancement 291/498 (58 %) versus 154/301 (51 %), T2W mild hyperintensity 478/505 (95 %) versus 269/338 (79 %), and diffusion restriction 435/497 (87 %) versus 200/306 (65 %). Almost all metastases showed a hypovascular appearance, both in the chemotherapy-naïve (495/504, 98 %) and post-chemotherapy group (330/331, 100 %). Additionally, all CRLM appeared non-enhancing compared to the liver in the hepatobiliary phase (100 %).

CONCLUSION

Most CRLM show various combinations of at least five typical characteristics on gadoxetic acid-enhanced MRI. Arterial rim enhancement is the least prevalent characteristic both in chemotherapy-naïve and post-chemotherapy patients. Post-chemotherapy the occurrence of typical MRI characteristics decreases, especially mild T2W hyperintensity and the presence of diffusion restriction.

Novel Noninvasive Imaging Techniques to Assess Structural, Functional, and Material Properties of Tendon, Ligament, and Cartilage: A Narrative Review of Current Concepts

Background

Novel noninvasive imaging modalities such as quantitative magnetic resonance imaging (qMRI) and shear wave elastography (SWE) allow for assessment of soft tissue microstructure and composition, which ultimately may be associated with functional and material properties.

Purpose

To provide a narrative review of the scientific techniques and clinical applications of qMRI and SWE for the evaluation of soft tissue about the knee and shoulder, including the meniscus, the anterior cruciate ligament (ACL), and the rotator cuff.

Study Design

Review.

Methods

A literature search was performed in October 2022 via PubMed using the following keywords: "quantitative MRI tendon," quantitative MRI ligament,""quantitative MRI cartilage," or "shear wave elastography tendon." Only articles related to clinical applications were included in this review.

Results

Conventional imaging techniques, including standard morphologic magnetic resonance imaging (MRI) and ultrasound imaging, have limited ability to evaluate the material and functional properties of soft tissue; qMRI builds on the limitations of conventional morphologic MRI by allowing for detection of early articular cartilage changes, differentiation of healed versus unhealed meniscal tissue, and quantification of ACL graft maturity. SWE can evaluate the material properties of rotator cuff and Achilles tendons after injury, which may provide insight into both the chronicity and the healing status of the aforementioned injuries.

Conclusion

Our review of the literature showed that quantitative imaging techniques, including qMRI and SWE, may both improve early detection of pathology and aid in comprehensive evaluation after treatment.

Accurate segmentation of liver tumor from multi-modality non-contrast images using a dual-stream multi-level fusion framework

The use of multi-modality non-contrast images (i.e., T1FS, T2FS and DWI) for segmenting liver tumors provides a solution by eliminating the use of contrast agents and is crucial for clinical diagnosis. However, this remains a challenging task to discover the most useful information to fuse multi-modality images for accurate segmentation due to inter-modal interference. In this paper, we propose a dual-stream multi-level fusion framework (DM-FF) to, for the first time, accurately segment liver tumors from non-contrast multi-modality images directly. Our DM-FF first designs an attention-based encoder-decoder to effectively extract multi-level feature maps corresponding to a specified representation of each modality. Then, DM-FF creates two types of fusion modules, in which a module fuses learned features to obtain a shared representation across multi-modality images to exploit commonalities and improve the performance, and a module fuses the decision evidence of segment to discover differences between modalities to prevent interference caused by modality's conflict. By integrating these three components, DM-FF enables multi-modality non-contrast images to cooperate with each other and enables an accurate segmentation. Evaluation on 250 patients including different types of tumors from two MRI scanners, DM-FF achieves a Dice of 81.20%, and improves performance (Dice by at least 11%) when comparing the eight state-of-the-art segmentation architectures. The results indicate that our DM-FF significantly promotes the development and deployment of non-contrast liver tumor technology.

Tumor Radiomic Features on Pretreatment MRI to Predict Response to Lenvatinib plus an Anti-PD-1 Antibody in Advanced Hepatocellular Carcinoma: A Multicenter Study

Introduction

Lenvatinib plus an anti-PD-1 antibody has shown promising antitumor effects in patients with advanced hepatocellular carcinoma (HCC), but with clinical benefit limited to a subset of patients. We developed and validated a radiomic-based model to predict objective response to this combination therapy in advanced HCC patients.

Methods

Patients (N = 170) who received first-line combination therapy with lenvatinib plus an anti-PD-1 antibody were retrospectively enrolled from 9 Chinese centers; 124 and 46 into the training and validation cohorts, respectively. Radiomic features were extracted from pretreatment contrast-enhanced MRI. After feature selection, clinicopathologic, radiomic, and clinicopathologic-radiomic models were built using a neural network. The performance of models, incremental predictive value of radiomic features compared with clinicopathologic features and relationship between radiomic features and survivals were assessed.

Results

The clinicopathologic model modestly predicted objective response with an AUC of 0.748 (95% CI: 0.656-0.840) and 0.702 (95% CI: 0.547-0.884) in the training and validation cohorts, respectively. The radiomic model predicted response with an AUC of 0.886 (95% CI: 0.815-0.957) and 0.820 (95% CI: 0.648-0.984), respectively, with good calibration and clinical utility. The incremental predictive value of radiomic features to clinicopathologic features was confirmed with a net reclassification index of 47.9% (p < 0.001) and 41.5% (p = 0.025) in the training and validation cohorts, respectively. Furthermore, radiomic features were associated with overall survival and progression-free survival both in the training and validation cohorts, but modified albumin-bilirubin grade and neutrophil-to-lymphocyte ratio were not.

Conclusion

Radiomic features extracted from pretreatment MRI can predict individualized objective response to combination therapy with lenvatinib plus an anti-PD-1 antibody in patients with unresectable or advanced HCC, provide incremental predictive value over clinicopathologic features, and are associated with overall survival and progression-free survival after initiation of this combination regimen.

Preclinical Long-term Magnetic Resonance Imaging Study of Silymarin Liver-protective Effects

BACKGROUND AND AIMS

Efficacy evaluations with preclinical magnetic resonance imaging (MRI) are uncommon, but MRI in the preclinical phase of drug development provides information that is useful for longitudinal monitoring. The study aim was to monitor the protective effectiveness of silymarin with multiparameter MRI and biomarkers in a thioacetamide (TAA)-induced model of liver injury in rats. Correlation analysis was conducted to assess compare the monitoring of liver function by MRI and biomarkers.

METHODS

TAA was injected three times a week for 8 weeks to generate a disease model (TAA group). In the TAA and silymarin-treated (TAA-SY) groups, silymarin was administered three times weekly from week 4. MR images were acquired at 0, 2, 4, 6, and 8 weeks in the control, TAA, and TAA-SY groups.

RESULTS

The area under the curve to maximum time (AUC_tmax) and T₂* values of the TAA group decreased over the study period, but the serological markers of liver abnormality increased significantly more than those in the control group. In the TAA-SY group, MRI and serological biomarkers indicated attenuation of liver function as in the TAA group. However, pattern changes were observed from week 6 to comparable levels in the control group with silymarin treatment. Negative correlations between either AUC_tmax or T₂* values and the serological biomarkers were observed.

CONCLUSIONS

Silymarin had hepatoprotective effects on TAA-induced liver injury and demonstrated the usefulness of multiparametric MRI to evaluate efficacy in preclinical studies of liver drug development.