Three-dimensional convolutional neural network-based classification of chronic kidney disease severity using kidney MRI.

A three-dimensional convolutional neural network model was developed to classify the severity of chronic kidney disease (CKD) using magnetic resonance imaging (MRI) Dixon-based T1-weighted in-phase (IP)/opposed-phase (OP)/water-only (WO) imaging. Seventy-three patients with severe renal dysfunction (estimated glomerular filtration rate [eGFR] < 30 mL/min/1.73 m2, CKD stage G4-5); 172 with moderate renal dysfunction (30 ≤ eGFR < 60 mL/min/1.73 m2, CKD stage G3a/b); and 76 with mild renal dysfunction (eGFR ≥ 60 mL/min/1.73 m2, CKD stage G1-2) participated in this study. The model was applied to the right, left, and both kidneys, as well as to each imaging method (T1-weighted IP/OP/WO images). The best performance was obtained when using bilateral kidneys and IP images, with an accuracy of 0.862 ± 0.036. The overall accuracy was better for the bilateral kidney models than for the unilateral kidney models. Our deep learning approach using kidney MRI can be applied to classify patients with CKD based on the severity of kidney disease.

The utility of automatic segmentation of kidney MRI in chronic kidney disease using a 3D convolutional neural network.

We developed a 3D convolutional neural network (CNN)-based automatic kidney segmentation method for patients with chronic kidney disease (CKD) using MRI Dixon-based T1-weighted in-phase (IP)/opposed-phase (OP)/water-only (WO) images. The dataset comprised 100 participants with renal dysfunction (RD; eGFR < 45 mL/min/1.73 m2) and 70 without (non-RD; eGFR ≥ 45 mL/min/1.73 m2). The model was applied to the right, left, and both kidneys; it was first evaluated on the non-RD group data and subsequently on the combined data of the RD and non-RD groups. For bilateral kidney segmentation of the non-RD group, the best performance was obtained when using IP image, with a Dice score of 0.902 ± 0.034, average surface distance of 1.46 ± 0.75 mm, and a difference of - 27 ± 21 mL between ground-truth and automatically computed volume. Slightly worse results were obtained for the combined data of the RD and non-RD groups and for unilateral kidney segmentation, particularly when segmenting the right kidney from the OP images. Our 3D CNN-assisted automatic segmentation tools can be utilized in future studies on total kidney volume measurements and various image analyses of a large number of patients with CKD.

Purification and identification of antihypertensive peptides from fermented buckwheat sprouts.

Buckwheat (Fagopyrum esculentum) is rich in antihypertensive compounds. This study investigated the effect of lactic-fermented buckwheat sprouts (neo-FBS) on level, identification, and potency of blood pressure-lowering (BPL) compounds. A single oral dose of 1.0 mg/kg body weight buckwheat sprouts (BS) in spontaneously hypertensive rats did not show significant BPL activity, whereas neo-FBS significantly decreased blood pressure. HPLC of neo-FBS identified two peaks absent in the profile of BS. The peak exhibiting potent BPL activity was fractionated, and six peptides (DVWY, FDART, FQ, VAE, VVG, and WTFR) and tyrosine were identified by LC-MS/MS and Edman degradation. Single oral dose administration of the peptides revealed significant BPL effect of all the peptides, with the most potent being DVWY, FQ, and VVG. DVWY, VAE, and WTFR are novel. This study demonstrates that lactic fermentation of BS produces new, highly potent antihypertensive peptides and increases active compounds GABA and tyrosine already present in BS.

Recreational music-making modulates immunological responses and mood states in older adults.

Given that previous studies have shown that recreational music-making has benefits for younger individuals, we explored two questions. (1) Could a recreational music-making protocol improve mood and modulate immunological responses in a direction opposite to that associated with chronic stress in older adults? (2) Would the protocol affect older and younger participants differently? Two groups of volunteers demarcated at age 65 years underwent identical one-hour recreational music-making interventions. Pre-and post-intervention data were collected using blood samples and mood state questionnaires. Data from 27 older and 27 younger volunteers were analyzed for cytokine production levels, natural killer cell activity, plasma catecholamines, and numbers of T cells, T cell subsets, B cells, and natural killer cells. Exercise expenditure was also recorded. In the older group, we found significant increases in the number of lymphocytes, T cells, CD4+ T cells, memory T cells, and production of interferon-gamma and interleukin-6. In the younger group, modulation was non-significant. Worthy of note was the specific immunological changes in the direction opposite to that expected with chronic stress in the older group. The increase in Th1 cytokine IFN-gamma and unchanged Th2 cytokine IL-4 and IL-10 levels in the older group suggests a shift to a Th1-dominant status, a shift opposite to that expected with stress. However, the immunological changes were not statistically different between the two groups. Mood states improved in both groups, but were also not statistically different between groups. Although no statistically significant difference was found between the two age groups, the improvement in immunological profile and mood states in the older group and the low level of energy required for participation suggest this music-making protocol has potential as a health improvement strategy for older individuals.