Publications by authors named "XiuYu Dong"
Article Synopsis
- The study focuses on improving the accuracy and efficiency of tumor target contouring and T staging for nasopharyngeal carcinoma using a deep learning model designed to automate these processes, which traditionally are time-consuming and labor-intensive.
- Researchers developed a multi-task transformer-based model that simultaneously identifies T-stage and delineates the Gross Tumor Volume (GTV), using contrast-enhanced T1-weighted images from 320 patients for training and validation.
- The model demonstrated strong performance with a median Dice similarity coefficient of 0.74 for contouring and an area under the ROC curve of 0.85 for T staging, showing better results than single-task models, particularly in distinguishing between early and advanced
Accurate T-staging of nasopharyngeal carcinoma (NPC) holds paramount importance in guiding treatment decisions and prognosticating outcomes for distinct risk groups. Regrettably, the landscape of deep learning-based techniques for T-staging in NPC remains sparse, and existing methodologies often exhibit suboptimal performance due to their neglect of crucial domain-specific knowledge pertinent to primary tumor diagnosis. To address these issues, we propose a new cross-domain mutual-assistance learning framework for fully automated diagnosis of primary tumor using H&N MR images.
View Article and Find Full Text PDFArticle Synopsis
- The study explored how seaweed cellulose (SC) affects metabolic disorders caused by a high fat-sugar diet (HFSD) in mice, highlighting its potential as a dietary intervention.
- Mice treated with SC showed reduced obesity, improved insulin sensitivity, and less liver damage while also restoring gut microbiota balance by increasing beneficial bacteria.
- Higher doses of SC led to a significant rise in beneficial short-chain fatty acids, suggesting that the size and crystallinity of SC particles enhance its prebiotic effects as dietary fiber.
MsGoF: Breast lesion classification on ultrasound images by multi-scale gradational-order fusion framework.
Comput Methods Programs Biomed
March 2023
Background And Objective: Predicting the malignant potential of breast lesions based on breast ultrasound (BUS) images is a crucial component of computer-aided diagnosis system for breast cancers. However, since breast lesions in BUS images generally have various shapes with relatively low contrast and present complex textures, it still remains challenging to accurately identify the malignant potential of breast lesions.
Methods: In this paper, we propose a multi-scale gradational-order fusion framework to make full advantages of multi-scale representations incorporating with gradational-order characteristics of BUS images for breast lesions classification.
Accurate-staging is important when planning personalized radiotherapy. However,-staging via manual slice-by-slice inspection is time-consuming while tumor sizes and shapes are heterogeneous, and junior physicians find such inspection challenging. With inspiration from oncological diagnostics, we developed a multi-perspective aggregation network that incorporated various diagnosis-oriented knowledge which allowed automated nasopharyngeal carcinoma-staging detection (TSD Net).
View Article and Find Full Text PDFArticle Synopsis
- The study compared the effectiveness of three immunosuppressants (azathioprine, mycophenolate mofetil, and rituximab) in treating neuromyelitis optica spectrum disorder (NMOSD) and analyzed factors linked to relapse and disability.
- A total of 83 NMOSD patients were treated, showing significant reductions in annual relapse rates, although differences between groups were not statistically significant due to small sample sizes.
- Key predictors of relapse and disability included age, duration of the disease, and history of severe attacks, indicating potential areas for improving patient prognosis.
This study aimed to assess the physical, emotional, medical, and socioeconomic conditions of patients with neuromyelitis optica spectrum disorder (NMOSD) in North China. A cross-sectional survey of patients with NMOSD was performed, based on an established questionnaire from the Multiple Sclerosis Patient Survival Report 2018. Logistic regression analysis was conducted to define the significant determinants of certain physical or emotional characteristics of patients.
View Article and Find Full Text PDFEffect of jianpiyiwei capsule on gastric precancerous lesions in rats.
World J Gastroenterol
August 2002
Aim: To evaluate the therapeutic effect of compound Chinese drugs, Jianpiyiwei capsule (JPYW) on gastric precancerous lesions in rats and to explore its mechanism of action.
Methods: Model of gastric precancerous lesions was constructed in male Wistar rats: a metal spring was inserted and fixed through pyloric sphincter. One week after recovery, each rat was given 50-60 degrees hot paste containing 150 g/L NaCl 2 mL orally, twice a week for 15 weeks.