Publications by authors named "Fangqun Chen"
Article Synopsis
- The study aimed to create a deep learning radiomics network (DLRN) that combines ultrasound images, radiomics, and clinical features to differentiate between parotid pleomorphic adenoma (PA) and adenolymphoma (AL).
- A total of 287 patients were used in various cohorts for training and validating machine learning classifiers that generated different models, including logistic regression and deep learning radiomics models.
- The DLRN model outperformed other models in distinguishing between PA and AL, demonstrating a significant enhancement in diagnostic accuracy and providing an important non-invasive solution for clinicians.
Objectives: To evaluate the diagnostic value of ultrasound-guided attenuation parameter (UGAP) in metabolic fatty liver disease (MAFLD) and to explore the correlation between the attenuation coefficient (AC) value of UGAP and commonly used clinical obesity indicators.
Methods: A total of 121 subjects who had physical examinations from November 2021 to March 2022 were prospectively selected; the height, weight, and waist circumference (WC) of all subjects were collected, and conventional ultrasound and UGAP examinations for all subjects.
Results: Under the standard of conventional ultrasound, among the 121 subjects, 53 had normal liver, 42 had mild fatty liver, 21 had moderate fatty liver, and 5 had severe fatty liver.
Objectives: To differentiate parotid pleomorphic adenoma (PA) from adenolymphoma (AL) using radiomics of grayscale ultrasonography in combination with clinical features.
Methods: This retrospective study aimed to analyze the clinical and radiographic characteristics of 162 cases from December 2019 to March 2023. The study population consisted of a training cohort of 113 patients and a validation cohort of 49 patients.
Background: The terrifying undiagnosed rate and high prevalence of diabetes have become a public emergency. A high efficiency and cost-effective early recognition method is urgently needed. We aimed to generate innovative, user-friendly nomograms that can be applied for diabetes screening in different ethnic groups in China using the non-lab or noninvasive semi-lab data.
View Article and Find Full Text PDF