An improved 3D-UNet-based brain hippocampus segmentation model based on MR images.

OBJECTIVE: Accurate delineation of the hippocampal region via magnetic resonance imaging (MRI) is crucial for the prevention and early diagnosis of neurosystemic diseases. Determining how to accurately and quickly delineate the hippocampus from MRI results has become a serious issue. In this study, a pixel-level semantic segmentation method using 3D-UNet is proposed to realize the automatic segmentation of the brain hippocampus from MRI results. METHODS: Two hundred three-dimensional T1-weighted (3D-T1) nongadolinium contrast-enhanced magnetic resonance (MR) images were acquired at Hangzhou Cancer Hospital from June 2020 to December 2022. These samples were divided into two groups, containing 175 and 25 samples. In the first group, 145 cases were used to train the hippocampus segmentation model, and the remaining 30 cases were used to fine-tune the hyperparameters of the model. Images for twenty-five patients in the second group were used as the test set to evaluate the performance of the model. The training set of images was processed via rotation, scaling, grey value augmentation and transformation with a smooth dense deformation field for both image data and ground truth labels. A filling technique was introduced into the segmentation network to establish the hippocampus segmentation model. In addition, the performance of models established with the original network, such as VNet, SegResNet, UNetR and 3D-UNet, was compared with that of models constructed by combining the filling technique with the original segmentation network. RESULTS: The results showed that the performance of the segmentation model improved after the filling technique was introduced. Specifically, when the filling technique was introduced into VNet, SegResNet, 3D-UNet and UNetR, the segmentation performance of the models trained with an input image size of 48 × 48 × 48 improved. Among them, the 3D-UNet-based model with the filling technique achieved the best performance, with a Dice score (Dice score) of 0.7989 ± 0.0398 and a mean intersection over union (mIoU) of 0.6669 ± 0.0540, which were greater than those of the original 3D-UNet-based model. In addition, the oversegmentation ratio (OSR), average surface distance (ASD) and Hausdorff distance (HD) were 0.0666 ± 0.0351, 0.5733 ± 0.1018 and 5.1235 ± 1.4397, respectively, which were better than those of the other models. In addition, when the size of the input image was set to 48 × 48 × 48, 64 × 64 × 64 and 96 × 96 × 96, the model performance gradually improved, and the Dice scores of the proposed model reached 0.7989 ± 0.0398, 0.8371 ± 0.0254 and 0.8674 ± 0.0257, respectively. In addition, the mIoUs reached 0.6669 ± 0.0540, 0.7207 ± 0.0370 and 0.7668 ± 0.0392, respectively. CONCLUSION: The proposed hippocampus segmentation model constructed by introducing the filling technique into a segmentation network performed better than models built solely on the original network and can improve the efficiency of diagnostic analysis.

Fecal bacteria and metabolite responses to dietary lysozyme in a sow model from late gestation until lactation.

Lysozyme (LZM) is a natural anti-bacterial protein that is found in the saliva, tears and milk of all mammals including humans. Its anti-bacterial properties result from the ability to cleave bacterial cell walls, causing bacterial death. The current study was conducted to investigate the effects of dietary LZM on fecal microbial composition and variation in metabolites in sow. The addition of LZM decreased the fecal short-chain fatty acids (SCFAs). Zonulin and endotoxin in the serum, and feces, were decreased with lysozyme supplementation. Furthermore, fecal concentrations of lipocalin-2 and the pro-inflammatory cytokine TNF-α were also decreased while the anti-inflammatory cytokine IL-10 was increased by lysozyme supplementation. 16S rRNA gene sequencing of the V3-V4 region suggested that fecal microbial levels changed at different taxonomic levels with the addition of LZM. Representative changes included the reduction of diversity between sows, decreased Bacteroidetes, Actinobacteria, Tenericutes and Spirochaetes during lactation as well as an increase in Lactobacillus. These findings suggest that dietary lysozyme supplementation from late gestation to lactation promote microbial changes, which would potentially be the mechanisms by which maternal metabolites and inflammatory status was altered after LZM supplementation.

Effects of dietary supplementation with lysozyme during late gestation and lactation stage on the performance of sows and their offspring.

This study investigated the effects of supplementing sow diets with lysozyme during the late gestation to lactation stage on the performance of sows and their offspring. Sixty sows (Yorkshire × Landrace, 3 to 6 of parity) at day 85 of gestation were allocated to the following 3 dietary treatments: 1) sows fed a basal diet from late gestation to lactation (control, n = 20), 2) sows fed a basal diet with lysozyme 150 g/t (LZM 150, n = 20), and 3) sows fed a basal diet with lysozyme 300 g/t (LZM 300, n = 20). During the lactation period, sows fed diets containing lysozyme had increased average daily feed intake (ADFI) (P < 0.01) and decreased weaning-to-estrus interval (WEI, P < 0.05), but there were no significant effects on backfat during the trial among treatments. Sows fed lysozyme diets had increased (P < 0.05) serum concentration of total protein (TP) compared with those fed the control diets. Serum immunoglobulin M (IgM) of the sows increased (P < 0.05) on day 1 of lactation, immunoglobulin A (IgA) and interleukin-10 (IL-10) increased (P < 0.05) on day 7 of lactation, and immunoglobulin G (IgG) had a tendency to increase (P = 0.05) during the lactation. Milk concentration of IgA increased (P < 0.05) on day 1 and 7 of lactation and tended to be greater (P = 0.06) on day 21 of lactation. No significant differences among the dietary treatments were observed in placental tissue mRNA expression of interleukin-6 (IL-6), IL-10, tumor necrosis factor-α (TNF-α), polymeric immunoglobulin receptor (pIgR), or the concentrations of IL-6, IL-10, TNF-α, or secretory immunoglobulin A (sIgA). Moreover, there was a decrease (P < 0.05) in stillborn in sows fed lysozyme diets. The diarrhea rate decreased (P < 0.05) and serum concentrations of IgA, IgG, IgM, and IL-10 increased (P < 0.05) in piglets from sows fed the diets containing lysozyme compared with piglets from sows fed the control diet. The serum concentrations of TP increased (P < 0.05), and albumin (ALB) and globulin (GLB) had a tendency to increase (P = 0.08, P = 0.06) in piglets from sows fed the diets containing lysozyme compared with piglets from sows fed the control diet. In conclusion, this study indicates that feeding sows diets supplemented with lysozyme from the late gestation through lactation stage increased sow ADFI during the lactation, shortened the WEI, and improved the maternal and offspring health status as indicated by immunological characteristics and a reduced incidence of diarrhea in piglets.

Effect of High Fat Dietary Intake during Maternal Gestation on Offspring Ovarian Health in a Pig Model.

Excessive fat intake is a global health concern as women of childbearing age increasingly ingest a high fat diet. We therefore determined the association of a maternal high fat diet in pregnancy with offspring ovarian health during the gestation and postnatal female offspring in pig a model. Thirty-two Yorkshire gilts with similar bodyweights mated at the third estrus were randomly assigned to two nutrition levels of either a control (CON, crude fat: 7.27%) or a high fat diet (HFD, crude fat: 11.78%). Ovary samples were collected during the fetal (Day 55 (g55) and Day 90 of gestation (g90)) and offspring (prepuberty Day 160 (d160) and age at puberty) period to detect ovary development, antioxidant status and apoptosis cells. Maternal HFD did not influence notch signaling gene expression, which regulates primordial follicle formation and transformation, and ovarian histological effect at g55 and g90. However, maternal HFD reduced the numbers of large follicles at d160 and small follicle numbers upon puberty compared to CON in offspring. The results also revealed that the antioxidant index of total antioxidative capability (T-AOC), cytoplasmic copper/zinc superoxide dismutase (CuZn-SOD), glutathione peroxidase (GPx) activities and mRNA expression were higher in the CON than the HFD at g90 and d160, whereas, malondialdehyde (MDA) concentration was decreased in the CON. Maternal HFD increased the inhibitor of the apoptosis-related gene of B-cell lymphoma-2 (bcl2) mRNA expression at g90 and d160, whereas, pro-apoptotic-related gene bcl-2 assaciated X protein (bax) was reduced. These data show that the maternal high fat diet does not delay fetal ovarian development, but it changes ovarian health by the induction of oxidative stress and accelerating cell apoptosis in offspring.