Using AI and Gd-EOB-DTPA-enhanced MR imaging to assess liver function, comparing the MELIF score with the ALBI score

Abstract

Abstract Monitoring disease progression is particularly important for determining the optimal treatment strategy in patients with liver disease. Especially for patients with diseases that have a reversible course, there is a lack of suitable tools for monitoring liver function. The development and establishment of such tools is very important, especially in view of the expected increase in such diseases in the future. Image-based liver function parameters, such as the T1 relaxometry-based MELIF score, are ideally suited for this purpose. The determination of this new liver function score is fully automated by software developed with AI technology. In this study, the MELIF score is compared with the widely used ALBI score. The ALBI score was used as a benchmark, as it has been shown to better capture the progression of less severe liver disease than the MELD and Child‒Pugh scores. In this study, we retrospectively determined the ALBI and MELIF scores for 150 patients, compared these scores with the corresponding MELD and Child‒Pugh scores (Pearson correlation), and examined the ability of these scores to discriminate between good and impaired liver function (AUC: MELIF 0.8; ALBI 0.77) and to distinguish between patients with and without cirrhosis (AUC: MELIF 0.83, ALBI 0.79). The MELIF score performed more favourably than the ALBI score and may also be suitable for monitoring mild disease progression. Thus, the MELIF score is promising for closing the gap in the available early-stage liver disease monitoring tools (i.e., identification of liver disease at a potentially reversible stage before chronic liver disease develops).