Automated CT LI-RADS v2018 scoring of liver observations using machine learning: A multivendor, multicentre retrospective study.

Background & Aims: Assessment of computed tomography (CT)/magnetic resonance imaging Liver Imaging Reporting and Data System (LI-RADS) v2018 major features leads to substantial inter-reader variability and potential decrease in hepatocellular carcinoma diagnostic accuracy. We assessed the performance and added-value of a machine learning (ML)-based algorithm in assessing CT LI-RADS major features and categorisation of liver observations compared with qualitative assessment performed by a panel of radiologists. Methods: High-risk patients as per LI-RADS v2018 with pathologically proven liver lesions who underwent multiphase contrast-enhanced CT at diagnosis between January 2015 and March 2019 in seven centres in five countries were retrospectively included and randomly divided into a training set (n = 84 lesions) and a test set (n = 345 lesions). An ML algorithm was trained to classify non-rim arterial phase hyperenhancement, washout, and enhancing capsule as present, absent, or of uncertain presence. LI-RADS major features and categories were compared with qualitative assessment of two independent readers. The performance of a sequential use of the ML algorithm and independent readers were also evaluated in a triage and an add-on scenario in LR-3/4 lesions. The combined evaluation of three other senior readers was used as reference standard. Results: A total of 318 patients bearing 429 lesions were included. Sensitivity and specificity for LR-5 in the test set were 0.67 (95% CI, 0.62-0.72) and 0.91 (95% CI, 0.87-0.96) respectively, with 242 (70.1%) lesions accurately categorised. Using the ML algorithm in a triage scenario improved the overall performance for LR-5. (0.86 and 0.93 sensitivity, 0.82 and 0.76 specificity, 78% and 82.3% accuracy for the two independent readers). Conclusions: Quantitative assessment of CT LI-RADS v2018 major features is feasible and diagnoses LR-5 observations with high performance especially in combination with the radiologist's visual analysis in patients at high-risk for HCC. Impact and implications: Assessment of CT/MRI LI-RADS v2018 major features leads to substantial inter-reader variability and potential decrease in hepatocellular carcinoma diagnostic accuracy. Rather than replacing radiologists, our results highlight the potential benefit from the radiologist-artificial intelligence interaction in improving focal liver lesions characterisation by using the developed algorithm as a triage tool to the radiologist's visual analysis. Such an AI-enriched diagnostic pathway may help standardise and improve the quality of analysis of liver lesions in patients at high risk for HCC, especially in non-expert centres in liver imaging. It may also impact the clinical decision-making and guide the clinician in identifying the lesions to be biopsied, for instance in patients with multiple liver focal lesions.

Prostate Cancer and Reactive Haemophagocytic Lymphohistiocytosis.

We report the case of a 76-year-old man presenting with reactive haemophagocytic lymphohistiocytosis (rHLH) in the setting of disseminated prostate cancer. This often fatal syndrome must be diagnosed early in order to maximize survival. Treatment should be initiated whenever the clinical diagnosis is suspected, even if the HLH-2004 criteria are not met. The HScore is a useful diagnostic tool for rHLH. In case of neurological symptoms, an extensive assessment must be performed. The goal of this case report is to raise awareness of this rare syndrome among oncologists. LEARNING POINTS: The association of prostate cancer and reactive haemophagocytic lymphohistiocytosis (rHLH) has rarely been described.This often fatal syndrome must be recognized early in order to start specific treatment and maximize survival.Specific treatment for rHLH must be accompanied by treatment of the triggering factors.

Recapitulation of the EEF1A2 D252H neurodevelopmental disorder-causing missense mutation in mice reveals a toxic gain of function.

Heterozygous de novo mutations in EEF1A2, encoding the tissue-specific translation elongation factor eEF1A2, have been shown to cause neurodevelopmental disorders including often severe epilepsy and intellectual disability. The mutational profile is unusual; ~50 different missense mutations have been identified but no obvious loss of function mutations, though large heterozygous deletions are known to be compatible with life. A key question is whether the heterozygous missense mutations operate through haploinsufficiency or a gain of function mechanism, an important prerequisite for design of therapeutic strategies. In order both to address this question and to provide a novel model for neurodevelopmental disorders resulting from mutations in EEF1A2, we created a new mouse model of the D252H mutation. This mutation causes the eEF1A2 protein to be expressed at lower levels in brain but higher in muscle in the mice. We compared both heterozygous and homozygous D252H and null mutant mice using behavioural and motor phenotyping alongside molecular modelling and analysis of binding partners. Although the proteomic analysis pointed to a loss of function for the D252H mutant protein, the D252H homozygous mice were more severely affected than null homozygotes on the same genetic background. Mice that are heterozygous for the missense mutation show no behavioural abnormalities but do have sex-specific deficits in body mass and motor function. The phenotyping of our novel mouse lines, together with analysis of molecular modelling and interacting proteins, suggest that the D252H mutation results in a gain of function.

White blood cell counts in a geriatric hospitalized population: A poor diagnostic marker of infection.

INTRODUCTION: Older people suffer more often and from more severe infections than do younger people. Several studies have shown a correlation between higher white blood cell count (WBCC) and the presence of infection. The usefulness of increased WBCC to assess the presence of infection in geriatric patients is debated. To answer this question, we investigated the correlation between the total and differential WBCC and documented infection in hospitalized geriatric individuals. POPULATION AND METHODS: Clinical data (medical history, comorbidities, treatments, geriatric syndromes) and biological parameters were collected from 166 hospitalized geriatric patients (67-106 yrs) presenting with acute inflammation (C-reactive protein (CRP) > 10 mg/l) and were compared according to the presence/absence of infection. RESULTS: The mean WBCC was not significantly different (p = 0.71) according to the presence of infection or not, although the mean CRP level was higher in the infected group compared to the non-infected group (p = 0.0019). In regression analyses, the presence of infection was not associated with an increase in total and differential WBCC. Additionally, we found a positive correlation between cardiovascular risk factor and diseases (CVRF & diseases) and WBCC. CONCLUSION: In geriatric patients, WBCC is not a reliable biomarker for infection; however, combined with CRP, it represents a marker of cardiovascular disorders.