Classification and Visualization of Chemotherapy-Induced Cognitive Impairment in Volumetric Convolutional Neural Networks.

Breast cancer is the most common female cancer worldwide, and breast cancer accounts for 30% of female cancers. Of all the treatment modalities, breast cancer survivors who have undergone chemotherapy might complain about cognitive impairment during and after cancer treatment. This phenomenon, chemo-brain, is used to describe the alterations in cognitive functions after receiving systemic chemotherapy. Few reports detect the chemotherapy-induced cognitive impairment (CICI) by performing functional MRI (fMRI) and a deep learning analysis. In this study, we recruited 55 postchemotherapy breast cancer survivors (C+ group) and 65 healthy controls (HC group) and extracted mean fractional amplitudes of low-frequency fluctuations (mfALFF) from resting-state fMRI as our input feature. Two state-of-the-art deep learning architectures, ResNet-50 and DenseNet-121, were transformed to 3D, embedded with squeeze and excitation (SE) blocks and then trained to differentiate cerebral alterations based on the effect of chemotherapy. An integrated gradient was applied to visualize the pattern that was recognized by our model. The average performance of SE-ResNet-50 models was an accuracy of 80%, precision of 78% and recall of 70%; on the other hand, the SE-DenseNet-121 model reached identical results with an average of 80% accuracy, 86% precision and 80% recall. The regions with the greatest contributions highlighted by the integrated gradients algorithm for differentiating chemo-brain were the frontal, temporal, parietal and occipital lobe. These regions were consistent with other studies and strongly associated with the default mode and dorsal attention networks. We constructed two volumetric state-of-the-art models and visualized the patterns that are critical for identifying chemo-brains from normal brains. We hope that these results will be helpful in clinically tracking chemo-brain in the future.

A multi-targeting strategy to ameliorate high-fat-diet- and fructose-induced (western diet-induced) non-alcoholic fatty liver disease (NAFLD) with supplementation of a mixture of legume ethanol extracts.

NAFLD (non-alcoholic fatty liver disease) is a multifactorial liver disease related to multiple causes or unhealthy conditions, including obesity and chronic inflammation. The accumulation of excess triglycerides, called steatosis, is known as a hallmark of an imbalance between the rates of hepatic fatty acid uptake/synthesis and oxidation/export. Furthermore, occurrence of NAFLD may lead to a cocktail of disease consequences caused by the altered metabolism of glucose, lipids, and lipoproteins, for instance, insulin resistance, type II diabetes, nonalcoholic steatohepatitis (NASH), liver fibrosis, and even hepatocarcinogenesis. Due to the complexity of the occurrence of NAFLD, a multi-targeting strategy is highly recommended to effectively address the issue and combat the causal loop. Ethanol extracts of legumes are popular supplements due to their richness and diversity in phytochemicals, especially isoflavones and anthocyanins. Although many of them have been reported to have efficacy in the treatment of different metabolic syndromes and obesity, there have not been many studies on them as a supplemental mixture. In this study, the alleviative effects of selected legume ethanol extracts (CrE) on high-fat-diet- and fructose-induced obesity, liver steatosis, and hyperglycemia are discussed. As revealed by the findings, CrE not only ameliorated obesity in terms of weight gained and enlargement of adipose tissue, but also significantly reduced the incidence of steatosis via phosphorylation of AMPK, resulting in inhibition of the downstream SREBP-1c/FAS pathway and an increase in an indicator of ß-oxidation (carnitine palmitoyl transferase 1a, CPT1A). Furthermore, CrE dramatically alleviated inflammatory responses, including both plasma and hepatic TNF-α, IL-6, and MCP-1 levels. CrE also had attenuating effects on hyperglycemia and insulin resistance and significantly reduced the fasting glucose level, fasting insulin level, and plasma leptin, and it exhibited positive effects in the Oral glucose tolerance test (OGTT) and Homeostatic Model Assessment for Insulin Resistance (HOMA-IR). At the molecular level, CrE could activate the PI3K/Akt/Glut2 pathway, which indicated an increase in insulin sensitivity and glucose uptake. Taken together, these results suggest that ethanol extracts of legumes could be potential supplements for metabolic syndromes, and their efficacy and effectiveness might facilitate the multi-targeting strategy required to mitigate NAFLD.

Connectome analysis of brain functional network alterations in breast cancer survivors with and without chemotherapy.

PURPOSE: Treatment modalities for breast cancer, the leading cause of cancer-related deaths in women worldwide, include surgery, radiotherapy, adjuvant chemotherapy, targeted therapy, and hormonal therapy. The advancement in medical technology has facilitated substantial reduction in breast cancer mortality. However, patients may experience cognitive impairment after chemotherapy. This phenomenon called chemotherapy-induced cognitive impairment (i.e., "chemobrain") is common among breast cancer survivors. However, cognitive function deficits may exist before chemotherapy initiation. This study examined the functional network alterations in breast survivors by using resting-state functional magnetic resonance imaging (fMRI). METHODS: We recruited 172 female participants and separated them into three groups: C+ (57 breast cancer survivors who had finished 3-12-month-long chemotherapy), C- (45 breast cancer survivors who had not undergone chemotherapy), and HC (70 participants with no breast cancer history). We analyzed mean fractional amplitudes of low-frequency fluctuation and graph theoretical topologies from resting-state fMRI and applied network-based analysis to portray functional changes among the three groups. RESULTS: Among the three groups, the C- group demonstrated hyperactivity in the prefrontal cortex, bilateral middle temporal gyrus, right inferior temporal gyrus and right angular gyrus. Only the left caudate demonstrated significantly more hypoactivity in the C- group than in the C+ group. Graph theoretical analysis demonstrated that the brains of the C+ group became inclined toward regular networks and the brains of the C- group became inclined toward random networks. CONCLUSION: Subtle alterations were noted in the brain activity and networks of our cancer survivors. Moreover, functional network disruptions occurred regardless of chemotherapeutic agent administration.