An improved deep learning network for image detection and its application in Dendrobii caulis decoction piece.

In recent years, with the increasing demand for high-quality Dendrobii caulis decoction piece, the identification of D. caulis decoction piece species has become an urgent issue. However, the current methods are primarily designed for professional quality control and supervision. Therefore, ordinary consumers should not rely on these methods to assess the quality of products when making purchases. This research proposes a deep learning network called improved YOLOv5 for detecting different types of D. caulis decoction piece from images. In the main architecture of improved YOLOv5, we have designed the C2S module to replace the C3 module in YOLOv5, thereby enhancing the network's feature extraction capability for dense and small targets. Additionally, we have introduced the Reparameterized Generalized Feature Pyramid Network (RepGFPN) module and Optimal Transport Assignment (OTA) operator to more effectively integrate the high-dimensional and low-dimensional features of the network. Furthermore, a new large-scale dataset of Dendrobium images has been established. Compared to other models with similar computational complexity, improved YOLOv5 achieves the highest detection accuracy, with an average mAP@.05 of 96.5%. It is computationally equivalent to YOLOv5 but surpasses YOLOv5 by 2 percentage points in terms of accuracy.

Adjuvant chemotherapy or no adjuvant chemotherapy? A prediction model for the risk stratification of recurrence or metastasis of nasopharyngeal carcinoma combining MRI radiomics with clinical factors.

BACKGROUND: Dose adjuvant chemotherapy (AC) should be offered in nasopharyngeal carcinoma (NPC) patients? Different guidelines provided the different recommendations. METHODS: In this retrospective study, a total of 140 patients were enrolled and followed for 3 years, with 24 clinical features being collected. The imaging features on the enhanced-MRI sequence were extracted by using PyRadiomics platform. The pearson correlation coefficient and the random forest was used to filter the features associated with recurrence or metastasis. A clinical-radiomics model (CRM) was constructed by the Cox multivariable analysis in training cohort, and was validated in validation cohort. All patients were divided into high- and low-risk groups through the median Rad-score of the model. The Kaplan-Meier survival curves were used to compare the 3-year recurrence or metastasis free rate (RMFR) of patients with or without AC in high- and low-groups. RESULTS: In total, 960 imaging features were extracted. A CRM was constructed from nine features (seven imaging features and two clinical factors). In the training cohort, the area under curve (AUC) of CRM for 3-year RMFR was 0.872 (P <0.001), and the sensitivity and specificity were 0.935 and 0.672, respectively; In the validation cohort, the AUC was 0.864 (P <0.001), and the sensitivity and specificity were 1.00 and 0.75, respectively. Kaplan-Meier curve showed that the 3-year RMFR and 3-year cancer specific survival (CSS) rate in the high-risk group were significantly lower than those in the low-risk group (P <0.001). In the high-risk group, patients who received AC had greater 3-year RMFR than those who did not receive AC (78.6% vs. 48.1%) (p = 0.03). CONCLUSION: Considering increasing RMFR, a prediction model for NPC based on two clinical factors and seven imaging features suggested the AC needs to be added to patients in the high-risk group and not in the low-risk group.

Application of the whole-course care model (IWF/C Care) for postintensive care syndrome based on an early warning system in critically ill patients: a randomised controlled trial study protocol.

INTRODUCTION: Critically ill patients are at risk of developing postintensive care syndrome (PICS), which is manifested by physical, psychological and cognitive impairment. Currently, there are no programmes that combine early warning systems with interventions for PICS. We hypothesise that a comprehensive care model for PICS based on an early warning system would reduce medical costs and the incidence of PICS. METHODS AND ANALYSIS: The Intensive Care Unit (ICU) -Ward-Family/Community whole-course care (IWF/C Care) trial will be a unicentric, randomised, controlled trial. A total of 138 ICU patients from two ICUs at a university hospital in Guizhou province, China, will be enrolled in February 2023. The inclusion criteria are an age of 18 years or older, an ICU stay of more than 48 hours, provide informed consent and the ability to communicate normally. Patients will be followed for 12 months and randomised in a 1:1:1 ratio to three groups. INTERVENTIONS: Patients in intervention group 1 will be assessed by the PICS early warning system within 24 hours of ICU discharge, and precise interventions will be carried out according to the results; that is, high-risk patients will receive care based on the IWF/C Care model and low-risk patients will receive routine care. All patients in intervention group 2 will receive care based on the IWF/C Care model. The control group will receive routine care. The primary endpoints are the incidence of PICS and quality of life. The secondary endpoints include the incidence of adverse events: the unplanned readmission rate, cost-effectiveness, and the experiences and feelings of patients receiving care based on the IWF/C Care model. The incidence of PICS will be measured at ICU discharge, general ward discharge, the home/community stage and 1 month and 3, 6, 9, and 12 months after discharge. ETHICS AND DISSEMINATION: Ethics approval was obtained from Biomedical Research Ethics Committee of the Affiliated Hospital of Zunyi Medical University (approval number: KLL-2022-780). The results of this study will be distributed through peer-reviewed journals. TRIAL REGISTRATION NUMBER: ChiCTR2300068135.