Automatic localization of target point for subthalamic nucleus-deep brain stimulation via hierarchical attention-UNet based MRI segmentation.

BACKGROUND: Deep brain stimulation of the subthalamic nucleus (STN-DBS) is an effective treatment for patients with advanced Parkinson's disease, the outcome of this surgery is highly dependent on the accurate placement of the electrode in the optimal target of STN. PURPOSE: In this study, we aim to develop a target localization pipeline for DBS surgery, considering that the heart of this matter is to achieve the STN and red nucleus segmentation, a deep learning-based automatic segmentation approach is proposed to tackle this issue. METHODS: To address the problems of ambiguous boundaries and variable shape of the segmentation targets, the hierarchical attention mechanism with two different attention strategies is integrated into an encoder-decoder network for mining both semantics and fine-grained details for segmentation. The hierarchical attention mechanism is utilized to suppress irrelevant regions in magnetic resonance (MR) images while build long-range dependency among segmentation targets. Specifically, the attention gate (AG) is integrated into low-level features to suppress irrelevant regions in an input image while highlighting the salient features useful for segmentation. Besides, the self-attention involved in the transformer block is integrated into high-level features to model the global context. Ninety-nine brain magnetic resonance imaging (MRI) studies were collected from 99 patients with Parkinson's disease undergoing STN-DBS surgery, among which 80 samples were randomly selected as the training datasets for deep learning training, and ground truths (segmentation masks) were manually generated by radiologists. RESULTS: We applied five-fold cross-validation on these data to train our model, the mean results on 19 test samples are used to conduct the comparison experiments, the Dice similarity coefficient (DSC), Jaccard (JA), sensitivity (SEN), and HD95 of the segmentation for STN are 88.20%, 80.32%, 90.13%, and 1.14 mm, respectively, outperforming the state-of-the-art STN segmentation method with 2.82%, 4.52%, 2.56%, and 0.02 mm respectively. The source code and trained models of this work have been released in the URL below: https://github.com/liuruiqiang/HAUNet/tree/master. CONCLUSIONS: In this study, we demonstrate the effectiveness of the hierarchical attention mechanism for building global dependency on high-level semantic features and enhancing the fine-grained details on low-level features, the experimental results show that our method has considerable superiority for STN and red nucleus segmentation, which can provide accurate target localization for STN-DBS.

Effect of advanced paternal age on reproductive outcomes in IVF cycles of non-male-factor infertility: a retrospective cohort study / 亚洲男科学杂志(英文版)

Advanced paternal age has been overlooked, and its effect on fertility remains controversial. Previous studies have focused mainly on intracytoplasmic sperm injection (ICSI) cycles in men with oligozoospermia. However, few studies have reported on men with semen parameters within reference ranges. Therefore, we conducted a retrospective cohort study analyzing the reproductive outcomes of couples with non-male-factor infertility undergoing in vitro fertilization (IVF) cycles. In total, 381 cycles included were subgrouped according to paternal age (<35-year-old, 35-39-year-old, or ≥40-year-old), and maternal age was limited to under 35 years. Data on embryo quality and clinical outcomes were analyzed. The results showed that fertilization and high-quality embryo rates were not significantly different (all P > 0.05). The pregnancy rate was not significantly different in the 35-39-year-old group (42.0%; P > 0.05), but was significantly lower in the ≥40-year-old group (26.1%; P < 0.05) than that in the <35-year-old group (40.3%). Similarly, the implantation rate significantly decreased in the ≥40-year-old group (18.8%) compared with that in the <35-year-old group (31.1%) and 35-39-year-old group (30.0%) (both P < 0.05). The live birth rate (30.6%, 21.7%, and 19.6%) was not significantly different across the paternal age subgroups (<35-year-old, 35-39-year-old, and ≥40-year-old, respectively; all P > 0.05), but showed a declining trend. The miscarriage rate significantly increased in the 35-39-year-old group (44.8%) compared with that in the <35-year-old group (21.0%; P < 0.05). No abnormality in newborn birth weight was found. The results indicated that paternal age over 40 years is a key risk factor that influences the assisted reproductive technology success rate even with good semen parameters, although it has no impact on embryo development.

Effects of different concentrations of nitrogen,phosphorus and potash on Glycyrrhiza uralensis and its relationship with soil element content / 中国中药杂志

With annual Glycyrrhiza uralensis seedlings as experimental material, using "3414" optimal regression design and applied fertilizer, through the sampling of G. uralensis at harvest, root fresh weight and content of active components were measured in Lanzhou, Bayan Nur city, Chifeng, Jiuquan. Combined with NPK content in soil, potted experiments were used to study the effects of different nitrogen and phosphorus ratios on the dry matter accumulation and accumulation of active components of G. uralensis. The results reported as follows: the optimum fertilizer treatment in Lanzhou, Bayan Nur city, Chifeng, Jiuquan was N₁P₂K₁,N₂P₂K₁,N₁P₁K₂ and N₂P₁K₂, respectively. The efforts of single fertilizer on the fresh root weight acted as parabolic type.There was no significant effect of fertilizer treatment on the accumulation of active components of G. uralensis. Furthermore, in terms of nitrogen and phosphorus, the type of fertilizers that restricted the growth of the region was the type of elements with lower content in the soil. The optimal fertilizer usage was in inverse proportion to content of elements in soil. When the content of phosphorus in soil was low, nitrogen fertilizer and potash fertilizer showed positive interaction with phosphorus fertilizer, whereas, they showed negative interaction.

Effects of different concentrations of nitrogen and phosphorus on growth and active components of Salvia miltiorrhiza / 中国中药杂志

With annual Salvia miltiorrhiza seedlings as experimental material, using "3414" optimal regression design recommended by the Ministry of Agriculture and regularly watered with nutrient solution, through the dynamic sampling of S. miltiorrhiza in different growing stages, and the growth index, dry weight of plant root and content of active components were measured. The potted experiments were applied to study the effects of different nitrogen and phosphorus ratios on the growth, dry matter accumulation and accumulation of active components of S. miltiorrhiza, in order to explore a compatible fertilization method of nitrogen and phosphorus ratio that are suitable for production and quality of S. miltiorrhiza. The results reported as follows：①High concentrations of nitrogen fertilizer was beneficial to dry matter accumulation of S. miltiorrhiza aerial parts, and low concentration of nitrogen fertilizer transferred the dry matter accumulation to underground, and N1P1 could make the transfer ahead of time;②Regression analysis showed that in the early growth stage (before early July), we could use the nitrogen and phosphorus as basic fertilizer at a concentration of 1.521,0.355 g•L⁻¹ respectively to promote the growth of S. miltiorrhiza and at a concentration of 2.281,0.710 g•L⁻¹ respectively to promote the dry matter accumulation of root (after mid-August);③Five kinds of active components of S. miltiorrhiza decreased with the increase of nitrogen concentration, and increased with the increase of the concentration of phosphate fertilizer. Nitrogenous fertilizer, phosphate fertilizer in N-P=2∶3 ratio was more suitable for the accumulation of salvianolic acids, in N-P=1∶2 ratio was more suitable for the accumulation of tanshinone.