Conectar
by Ming Li, Jingang Ma, Jing Zhao
Since Transformers have demonstrated excellent performance in the segmentation of two-dimensional medical images, recent works have also introduced them into 3D medical segmentation tasks. For example, hierarchical transformers like Swin UNETR have reintroduced several prior knowledge of convolutional networks, further enhancing the model’s volumetric segmentation ability on three-dimensional medical datasets. The effectiveness of these hybrid architecture methods is largely attributed to the large number of parameters and the large receptive fields of non-local self-attention. We believe that large-kernel volumetric depthwise convolutions can obtain large receptive fields with fewer parameters. In this paper, we propose a lightweight three-dimensional convolutional network, LKDA-Net, for efficient and accurate three-dimensional volumetric segmentation. This network adopts a large-kernel depthwise convolution attention mechanism to simulate the self-attention mechanism of Transformers. Firstly, inspired by the Swin Transformer module, we investigate different-sized large-kernel convolution attention mechanisms to obtain larger global receptive fields, and replace the MLP in the Swin Transformer with the Inverted Bottleneck with Depthwise Convolutional Augmentation to reduce channel redundancy and enhance feature expression and segmentation performance. Secondly, we propose a skip connection fusion module to achieve smooth feature fusion, enabling the decoder to effectively utilize the features of the encoder. Finally, through experimental evaluations on three public datasets, namely Synapse, BTCV and ACDC, LKDA-Net outperforms existing models of various architectures in segmentation performance and has fewer parameters. Code: https://github.com/zouyunkai/LKDA-Net.The efficacy of radiotherapy and the satisfaction of patients can be significantly improved by adequately addressing their information needs. This process is impeded by the current lack of a comprehensive tool for assessing these needs.
To develop an Information Needs Questionnaire for patients with breast cancer undergoing radiotherapy and to assess its reliability and validity.
The initial item pool for the questionnaire was developed through a literature analysis and semi-structured interviews with 12 patients with breast cancer receiving radiotherapy. The Delphi method was employed to consult 16 experts and the questionnaire content was refined based on expert feedback and item ratings to form the first draft. A pre-investigation was conducted on 30 patients with breast cancer treated with radiotherapy to refine the item expression. From March–October 2024, item analysis, factor analyses, and reliability tests were conducted on 220 patients. This study adhered to STROBE guidelines.
The final questionnaire comprised 36 items. Exploratory factor analysis revealed 5 dimensions, with all item factor loading within their respective dimensions being ≥ 0.4 and no items exhibiting multiple loadings. These five factors accounted for 72.805% of the total variance. The overall content validity index was 0.980, with item-level content validity index ranging from 0.900 to 1.000. The Cronbach's α coefficient for the entire questionnaire was 0.959, and the coefficients for each dimension ranged from 0.786 to 0.958.
The Information Needs Questionnaire demonstrated excellent reliability and validity in patients with breast cancer undergoing radiotherapy. It can effectively guide medical staff to accurately assess the information needs of patients with breast cancer who are undergoing radiotherapy.
Identifying the authentic informational needs of breast cancer patients throughout the entire radiotherapy process is instrumental in enabling medical staff to devise personalised and targeted information support interventions.
A total of 220 participants provided perspectives on their information needs.
A common psychological problem among nurses is depression, potentially affecting their well-being and job performance. It is vital to explore how to alleviate nurses' depressive symptoms.
The current research explored the mediating impact of basic psychological needs satisfaction on the link of gratitude with depressive symptoms.
The nurses in this study were from mainland China. A total of 724 subjects completed an online questionnaire, which included measures of depressive symptoms, basic psychological needs satisfaction and gratitude.
Our research found that gratitude was negatively linked to depressive symptoms. Furthermore, basic psychological needs satisfaction had a partial mediation effect on the link of gratitude with depressive symptoms after controlling for five demographic variables. These results suggest that gratitude may influence depressive symptoms via basic psychological needs satisfaction.
Our study found that basic psychological need satisfaction partially mediates the gratitude-depression relationship in nurses. The result means that hospital administrators and nurse leaders should design gratitude interventions to alleviate nurses' depressive symptoms. They also help nurses decrease depressive symptoms by creating an environment that meets their basic psychological needs.
FreshRSS 