Latest developments in the imaging of fibrotic liver disease

Interpretable machine learning model integrating clinical and elastosonographic features to detect renal fibrosis in Asian patients with chronic kidney disease

BACKGROUND

Non-invasive renal fibrosis assessment is critical for tailoring personalized decision-making and managing follow-up in patients with chronic kidney disease (CKD). We aimed to exploit machine learning algorithms using clinical and elastosonographic features to distinguish moderate-severe fibrosis from mild fibrosis among CKD patients.

METHODS

A total of 162 patients with CKD who underwent shear wave elastography examinations and renal biopsies at our institution were prospectively enrolled. Four classifiers using machine learning algorithms, including eXtreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), Light Gradient Boosting Machine (LightGBM), and K-Nearest Neighbor (KNN), which integrated elastosonographic features and clinical characteristics, were established to differentiate moderate-severe renal fibrosis from mild forms. The area under the receiver operating characteristic curve (AUC) and average precision were employed to compare the performance of constructed models, and the SHapley Additive exPlanations (SHAP) strategy was used to visualize and interpret the model output.

RESULTS

The XGBoost model outperformed the other developed machine learning models, demonstrating optimal diagnostic performance in both the primary (AUC = 0.97, 95% confidence level (CI) 0.94-0.99; average precision = 0.97, 95% CI 0.97-0.98) and five-fold cross-validation (AUC = 0.85, 95% CI 0.73-0.98; average precision = 0.90, 95% CI 0.86-0.93) datasets. The SHAP approach provided visual interpretation for XGBoost, highlighting the features' impact on the diagnostic process, wherein the estimated glomerular filtration rate provided the largest contribution to the model output, followed by the elastic modulus, then renal length, renal resistive index, and hypertension.

CONCLUSION

This study proposed an XGBoost model for distinguishing moderate-severe renal fibrosis from mild forms in CKD patients, which could be used to assist clinicians in decision-making and follow-up strategies. Moreover, the SHAP algorithm makes it feasible to visualize and interpret the feature processing and diagnostic processes of the model output.

A nomogram based on shear wave elastography for assessment of renal fibrosis in patients with chronic kidney disease

BACKGROUND

Non-invasive evaluation of renal fibrosis is still challenging. This study aimed to establish a nomogram based on shear wave elastography (SWE) and clinical features for the assessment of the severity of renal fibrosis in patients with chronic kidney disease (CKD).

METHODS

One hundred and sixty-two patients with CKD who underwent kidney biopsy and SWE examination were prospectively enrolled between April 2019 and December 2021. Patients were classified into mildly or moderately-severely impaired group based on pathology results. All patients were randomly divided into a training (n = 113) or validation cohort (n = 49). Least absolute shrinkage and selection operator (LASSO) algorithm was used for data dimensionality reduction and feature selection. Then, a diagnostic nomogram incorporating the selected features was constructed using multivariable logistic regression analysis. Nomogram performance was evaluated for discrimination, calibration, and clinical utility in training and validation cohorts.

RESULTS

The established SWE nomogram, which integrated SWE value, hypertension, and estimated glomerular filtration rate, showed fine calibration and discrimination in both training (area under the receiver operator characteristic curve (AUC) = 0.94; 95% confidence interval (CI) 0.89-0.98) and validation cohorts (AUC = 0.84; 95% CI 0.71-0.96). Significant improvement in net reclassification and integrated discrimination indicated that the SWE value is a valuable biomarker to assess moderate-severe renal impairment. Furthermore, decision curve analysis revealed that the SWE nomogram has clinical value.

CONCLUSION

The proposed SWE nomogram showed favorable performance in determining individualized risk of moderate-severe renal pathological impairment in patients with CKD, which will help to facilitate clinical decision-making.

The history of magnetic resonance imaging and its reflections in Acta Radiologica

The first reports in Acta Radiologica on magnetic resonance imaging (MRI) were published in 1984, four years after the first commercial MR scanners became available. For the first two years, all MR papers originated from the USA. Nordic contributions started in 1986, and until 2020, authors from 44 different countries have published MR papers in Acta Radiologica. Papers on MRI have constituted, on average, 30%-40% of all published original articles in Acta Radiologica, with a high of 49% in 2019. The MR papers published since 1984 document tremendous progress in several areas such as magnet and coil design, motion compensation techniques, faster image acquisitions, new image contrast, contrast-enhanced MRI, functional MRI, and image analysis. In this historical review, all of these aspects of MRI are discussed and related to Acta Radiologica papers.

Fibrosis imaging: Current concepts and future directions

Fibrosis plays an important role in many different pathologies. It results from tissue injury, chronic inflammation, autoimmune reactions and genetic alterations, and it is characterized by the excessive deposition of extracellular matrix components. Biopsies are routinely employed for fibrosis diagnosis, but they suffer from several drawbacks, including their invasive nature, sampling variability and limited spatial information. To overcome these limitations, multiple different imaging tools and technologies have been evaluated over the years, including X-ray imaging, computed tomography (CT), ultrasound (US), magnetic resonance imaging (MRI), positron emission tomography (PET) and single-photon emission computed tomography (SPECT). These modalities can provide anatomical, functional and molecular imaging information which is useful for fibrosis diagnosis and staging, and they may also hold potential for the longitudinal assessment of therapy responses. Here, we summarize the use of non-invasive imaging techniques for monitoring fibrosis in systemic autoimmune diseases, in parenchymal organs (such as liver, kidney, lung and heart), and in desmoplastic cancers. We also discuss how imaging biomarkers can be integrated in (pre-) clinical research to individualize and improve anti-fibrotic therapies.

Non-invasive diagnosis of liver fibrosis and cirrhosis

The evaluation and follow up of liver fibrosis and cirrhosis have been traditionally performed by liver biopsy. However, during the last 20 years, it has become evident that this “gold-standard” is imperfect; even according to its proponents, it is only “the best” among available methods. Attempts at uncovering non-invasive diagnostic tools have yielded multiple scores, formulae, and imaging modalities. All are better tolerated, safer, more acceptable to the patient, and can be repeated essentially as often as required. Most are much less expensive than liver biopsy. Consequently, their use is growing, and in some countries the number of biopsies performed, at least for routine evaluation of hepatitis B and C, has declined sharply. However, the accuracy and diagnostic value of most, if not all, of these methods remains controversial. In this review for the practicing physician, we analyze established and novel biomarkers and physical techniques. We may be witnessing in recent years the beginning of the end of the first phase for the development of non-invasive markers. Early evidence suggests that they might be at least as good as liver biopsy. Novel experimental markers and imaging techniques could produce a dramatic change in diagnosis in the near future.

Exosomes mediate intercellular transfer of pro-fibrogenic connective tissue growth factor (CCN2) between hepatic stellate cells, the principal fibrotic cells in the liver

BACKGROUND

Fibrogenic pathways in the liver are principally regulated by hepatic stellate cells (HSC), which produce and respond to fibrotic mediators such as connective tissue growth factor (CCN2). The aim of this study was to determine whether CCN2 is shuttled between HSC in membranous nanovesicles, or "exosomes."

METHODS

Exosomes were incubated with HSC after isolation from conditioned medium of control or CCN2-green fluorescent protein (GFP)-transfected primary mouse HSC or human LX-2 HSC. Some exosomes were stained fluorescently with PKH26. HSC co-culture experiments were performed in the presence of GW4869 exosome inhibitor. CCN2 or CCN2-GFP were evaluated by quantitative real-time polymerase chain reaction or Western blot.

RESULTS

HSC-derived exosomes contained CCN2 or CCN2 mRNA, each of which increased in concentration during HSC activation or after transfection of HSC with CCN2-GFP. Exosomes, stained with either PKH26 or purified from CCN2-GFP-transfected cells, were taken up by activated or quiescent HSC resulting in CCN2-GFP delivery, as shown by their direct addition to recipient cells or by the GW4869-dependency of donor HSC.

CONCLUSION

CCN2 is packaged into secreted, nano-sized exosomes that mediate its intercellular transfer between HSC. Exosomal CCN2 may amplify or fine tune fibrogenic signaling and, in conjunction with other exosome constituents, may have utility as a noninvasive biomarker to assess hepatic fibrosis.