Artificial Intelligence Algorithms for Benign vs. Malignant Dermoscopic Skin Lesion Image Classification

In recent decades, the incidence of melanoma has grown rapidly. Hence, early diagnosis is crucial to improving clinical outcomes. Here, we propose and compare a classical image analysis-based machine learning method with a deep learning one to automatically classify benign vs. malignant dermoscopic skin lesion images. The same dataset of 25,122 publicly available dermoscopic images was used to train both models, while a disjointed test set of 200 images was used for the evaluation phase. The training dataset was randomly divided into 10 datasets of 19,932 images to obtain an equal distribution between the two classes. By testing both models on the disjoint set, the deep learning-based method returned accuracy of 85.4 ± 3.2% and specificity of 75.5 ± 7.6%, while the machine learning one showed accuracy and specificity of 73.8 ± 1.1% and 44.5 ± 4.7%, respectively. Although both approaches performed well in the validation phase, the convolutional neural network outperformed the ensemble boosted tree classifier on the disjoint test set, showing better generalization ability. The integration of new melanoma detection algorithms with digital dermoscopic devices could enable a faster screening of the population, improve patient management, and achieve better survival rates.

Gut-derived metabolites mediating cognitive development in 5-year-old children: Early-life transplant in mice has lasting effects throughout adulthood

The gut microbiota has been causally linked to cognitive development. We aimed to identify metabolites mediating its effect on cognitive development, and foods or nutrients related to most promising metabolites. Faeces from 5-year-old children (DORIAN-PISAC cohort, including 90 general population families with infants, 42/48 females/males, born in 2011-2014) were transplanted (FMT) into C57BL/6 germ-free mice. Children and recipient mice were stratified by cognitive phenotype, or based on protective metabolites. Food frequency questionnaires were obtained in children. Cognitive measurements in mice included five Y-maze tests until 23 weeks post-FMT, and (at 23 weeks) PET-CT for brain metabolism and radiodensity, and ultrasound-based carotid vascular indices. Children (faeces, urine) and mice (faeces, plasma) metabolome was measured by 1H NMR spectroscopy, and the faecal microbiota was profiled in mice by 16S rRNA amplicon sequencing. Cognitive scores of children and recipient mice were correlated. FMT-dependent modifications of brain metabolism were observed. Mice receiving FMT from high-cognitive or protective metabolite-enriched children developed superior cognitive-behavioural performance. A panel of metabolites, namely xanthine, hypoxanthine, formate, mannose, tyrosine, phenylalanine, glutamine, was found to mediate the gut-cognitive axis in donor children and recipient mice. Vascular indices partially explained the metabolite-to-phenotype relationships. Children's consumption of legumes, whole-milk yogurt and eggs, and intake of iron, zinc and vitamin D appeared to support protective gut metabolites. Overall, metabolites involved in inflammation, purine metabolism and neurotransmitter synthesis mediate the gut-cognitive axis, and holds promise for screening. The related dietary and nutritional findings offer leads to microbiota-targeted interventions for cognitive protection, with long-lasting effects.

Trust the gut: outcomes of gut microbiota transplant in metabolic and cognitive disorders

Type 2 diabetes mellitus (T2DM) is a main public health concern, with increasing prevalence and growingly premature onset in children, in spite of emerging and successful therapeutic options. T2DM promotes brain aging, and younger age at onset is associated with a higher risk of subsequent dementia. Preventive strategies should address predisposing conditions, like obesity and metabolic syndrome, and be started from very early and even prenatal life. Gut microbiota is an emerging target in obesity, diabetes and neurocognitive diseases, which could be safely modulated since pregnancy and infancy. Many correlative studies have supported its involvement in disease pathophysiology. Faecal material transplantation (FMT) studies have been conducted in clinical and preclinical settings to deliver cause-effect proof and mechanistic insights. This review provides a comprehensive overview of studies in which FMT was used to cure or cause obesity, metabolic syndrome, T2DM, cognitive decline and Alzheimer's disease, including the evidence available in early life. Findings were analysed to dissect consolidated from controversial results, highlighting gaps and possible future directions.

High-Resolution Cardiac Positron Emission Tomography/Computed Tomography for Small Animals

Positron emission tomography (PET) and computed tomography (CT) are among the most employed diagnostic imaging techniques, and both serve in understanding cardiac function and metabolism. In preclinical research, dedicated scanners with high sensitivity and high spatio-temporal resolution are employed, designed to cope with the demanding technological requirements posed by the small heart size and very high heart rates of mice and rats. In this paper, a bimodal cardiac PET/CT imaging protocol for experimental mouse and/or rat models of cardiac diseases is described, from animal preparation and image acquisition and reconstruction to image processing and visualization. In particular, the ¹⁸F-labeled fluorodeoxyglucose ([¹⁸F]FDG)-PET scan allows for the measurement and visualization of glucose metabolism in the different segments of the left ventricle (LV). Polar maps are convenient tools to display this information. The CT part consists of a time-resolved 3D reconstruction of the entire heart (4D-CT) using retrospective gating without electrocardiography (ECG) leads, allowing the morphofunctional evaluation of the LV and the subsequent quantification of the most important cardiac function parameters, such as ejection fraction (EF) and stroke volume (SV). Using an integrated PET/CT scanner, this protocol can be executed within the same anesthesia induction without the need to reposition the animal between different scanners. Hence, PET/CT can be seen as a comprehensive tool for the morphofunctional and metabolic evaluation of the heart in several small animal models of cardiac diseases.

Liver and White/Brown Fat Dystrophy Associates with Gut Microbiota and Metabolomic Alterations in 3xTg Alzheimer’s Disease Mouse Model

Metabolic impairments and liver and adipose depots alterations were reported in subjects with Alzheimer’s disease (AD), highlighting the role of the liver–adipose–tissue–brain axis in AD pathophysiology. The gut microbiota might play a modulating role. We investigated the alterations to the liver and white/brown adipose tissues (W/BAT) and their relationships with serum and gut metabolites and gut bacteria in a 3xTg mouse model during AD onset (adulthood) and progression (aging) and the impact of high-fat diet (HFD) and intranasal insulin (INI). Glucose metabolism (¹⁸FDG-PET), tissue radiodensity (CT), liver and W/BAT histology, BAT-thermogenic markers were analyzed. 16S-RNA sequencing and mass-spectrometry were performed in adult (8 months) and aged (14 months) 3xTg-AD mice with a high-fat or control diet. Generalized and HFD resistant deficiency of lipid accumulation in both liver and W/BAT, hypermetabolism in WAT (adulthood) and BAT (aging), abnormal cytokine–hormone profiles, and liver inflammation were observed in 3xTg mice; INI could antagonize all these alterations. Specific gut microbiota–metabolome profiles correlated with a significant disruption of the gut–microbiota–liver–adipose axis in AD mice. In conclusion, fat dystrophy in liver and adipose depots contributes to AD progression, and associates with altered profiles of the gut microbiota, which candidates as an appealing early target for preventive intervention.

Evidence of a Gastro-Duodenal Effect on Adipose Tissue and Brain Metabolism, Potentially Mediated by Gut-Liver Inflammation: A Study with Positron Emission Tomography and Oral 18FDG in Mice

Interventions affecting gastrointestinal (GI) physiology suggest that the GI tract plays an important role in modulating the uptake of ingested glucose by body tissues. We aimed at validating the use of positron emission tomography (PET) with oral ¹⁸FDG administration in mice, and to examine GI effects on glucose metabolism in adipose tissues, brain, heart, muscle, and liver, and interfering actions of oral lipid co-administration. We performed sequential whole-body PET studies in 3 groups of 10 mice, receiving i.p. glucose and ¹⁸FDG or oral glucose and ¹⁸FDG ± lipids, to measure tissue glucose uptake (GU) and GI transit, and compute the absorption lumped constant (LCa) as ratio of oral ¹⁸FDG-to-glucose incremental blood levels. GI and liver histology and circulating hormones were tested to generate explanatory hypothesis. Median LCa was 1.18, constant over time and not significantly affected by lipid co-ingestion. Compared to the i.p. route, the oral route (GI effect) resulted in lower GU rates in adipose tissues and brain, and a greater steatohepatitis score (+17%, p = 0.03). Lipid co-administration accelerated GI transit, in relation to the suppression in GIP, GLP1, glucagon, PP, and PYY (GI motility regulators), abolishing GI effects on subcutaneous fat GU. Duodenal crypt size, gastric wall ¹⁸FDG uptake, and macro-vesicular steatosis were inversely related to adipose tissue GU, and positively associated with liver GU. We conclude that ¹⁸FDG-PET is a suitable tool to examine the role of the GI tract on glucose transit, absorption, and bio-distribution. The GI effect consists in the suppression of glucose metabolism selectively in organs responsible for energy intake and storage, and is blunted by lipid ingestion. Modulation of gut and liver inflammation, as reflected by high GU, may be involved in the acute signalling of the energy status.

Maturation of the Visceral (Gut-Adipose-Liver) Network in Response to the Weaning Reaction versus Adult Age and Impact of Maternal High-Fat Diet

Metabolic-associated fatty liver disease is a major cause of chronic pathologies, of which maternal obesity is a frequent risk factor. Gut wall and microbiota, visceral fat, and liver form a pre-systemic network for substrates and pro-inflammatory factors entering the body, undergoing accelerated maturation in early-life when the weaning reaction, i.e., a transitory inflammatory condition, affects lifelong health. We aimed to characterize organ metabolism in the above network, in relation to weaning reaction and maternal obesity. Weaning or 6-months-old offspring of high-fat-diet and normal-diet fed dams underwent in vivo imaging of pre-/post-systemic glucose uptake and tissue radiodensity in the liver, visceral fat, and intestine, a liver histology, and microbiota and metabolic pathway analyses. Weaning mice showed the dominance of gut Clostridia and Bacteroidia members, overexpressing pathways of tissue replication and inflammation; adulthood increased proneness to steatohepatitis, and Desulfovibrio and RF39 bacteria, and lipopolysaccharide, bile acid, glycosaminoglycan, and sphingolipid metabolic pathways. In vivo imaging could track organ maturation, liver inflammation, and protective responses. A maternal high-fat diet amplified the weaning reaction, elevating liver glucose uptake, triglyceride levels, and steatohepatitis susceptibility along the lifespan. The visceral network establishes a balance between metabolism and inflammation, with clear imaging biomarkers, and crucial modulation in the weaning time window.