A5033514558- Radiomics and Machine Learning in Medical Imaging
- Advanced X-ray and CT Imaging
- MRI in cancer diagnosis
- Lung Cancer Diagnosis and Treatment
- Sarcoma Diagnosis and Treatment
- COVID-19 diagnosis using AI
- Gastric Cancer Management and Outcomes
- Cerebrovascular and Carotid Artery Diseases
- Renal cell carcinoma treatment
- Colorectal Cancer Surgical Treatments
- Acute Ischemic Stroke Management
- Intracerebral and Subarachnoid Hemorrhage Research
- Colorectal and Anal Carcinomas
- Bladder and Urothelial Cancer Treatments
- Gastrointestinal Tumor Research and Treatment
- Intracranial Aneurysms: Treatment and Complications
- Adipose Tissue and Metabolism
- Glaucoma and retinal disorders
- Meningioma and schwannoma management
- Pancreatic and Hepatic Oncology Research
- Colorectal Cancer Screening and Detection
- Pelvic and Acetabular Injuries
- Hepatocellular Carcinoma Treatment and Prognosis
- Medical Imaging and Analysis
- Artificial Intelligence in Healthcare
Center for High Pressure Science & Technology Advanced Research
2020-2025
Shandong Provincial Hospital
2024
Yahoo (United Kingdom)
2023
Xiamen University
2014-2022
Zhejiang Cancer Hospital
2022
Jilin University
2020-2021
Union Hospital
2021
Union Hospital
2020-2021
West China Hospital of Sichuan University
2021
Sinosteel (China)
2021
Preoperative prediction of soft tissue sarcoma (STS) grade is important for treatment decisions. Therefore, formulation an STS model strongly needed.To develop and test magnetic resonance imaging (MRI)-based radiomics nomogram predicting the (low-grade vs. high grade).Retrospective POPULATION: One hundred eighty patients with confirmed by pathologic results at two independent institutions were enrolled (training set, N = 109; external validation 71).Unenhanced T1-weighted (T1WI)...
Acute vertebral fracture is usually caused by low-energy injury with osteoporosis and high-energy trauma. The AOSpine thoracolumbar spine classification system (AO classification) plays an important role in the diagnosis treatment of disease. description fractures according to scheme requires a great deal time energy for radiologists.To design validate multistage deep learning (multistage AO system) automatic detection, localization acute body on computed tomography.The CT images 1,217...
Abstract Background Global myopia prevalence poses a substantial public health burden with vision-threatening complications, necessitating effective prevention and control strategies. Precise prediction of spherical equivalent (SE), myopia, high onset is vital for proactive clinical interventions. Methods We reviewed electronic medical records pediatric adolescent patients who underwent cycloplegic refraction measurements at the Eye & Ear, Nose, Throat Hospital Fudan University between...
Brain invasion in meningioma has independent associations with increased risks of tumor progression, lesion recurrence, and poor prognosis. Therefore, this study aimed to construct a model for predicting brain WHO grade II by using preoperative MRI.One hundred seventy-three patients 111 without were included. Three mainstream features, namely, traditional semantic features radiomics from tumor-to-brain interface regions, acquired. Predictive models correspondingly constructed on each feature...
Background Developmental dysplasia of the hip (DDH) is a common orthopedic disease in children. In clinical surgery, it essential to quickly and accurately locate exact position lesion, there are still some controversies relating DDH status. We adopt artificial intelligence (AI) solve above problems. Methods this paper, automatic measurements classifications were achieved using three-stage pipeline. first stage, we used Mask-RCNN detect local features image segment bony pelvis, including...
Early noninvasive screening of patients who would benefit from neoadjuvant chemotherapy (NCT) is essential for personalized treatment locally advanced gastric cancer (LAGC). The aim this study was to identify radio-clinical signatures pretreatment oversampled computed tomography (CT) images predict the response NCT and prognosis LAGC patients.LAGC were retrospectively recruited six hospitals January 2008 December 2021. An SE-ResNet50-based prediction system developed CT preprocessed with an...
Abstract This study aimed to assess the performance of a deep learning algorithm in helping radiologist achieve improved efficiency and accuracy chest radiograph diagnosis. We adopted concurrently detect presence normal findings 13 different abnormalities radiographs evaluated its assisting radiologists. Each competing had determine or absence these signs based on label provided by AI. The 100 were randomly divided into two sets for evaluation: one without AI assistance (control group) with...
BACKGROUNDPerineural invasion (PNI), as a key pathological feature of tumor spread, has emerged an independent prognostic factor in patients with rectal cancer (RC).The preoperative stratification RC according to PNI status is beneficial for individualized treatment and improved prognosis.However, the evaluation still challenging. AIMTo establish radiomics model evaluating preoperatively patients. METHODSThis retrospective study enrolled 303 single institution from March 2018 October...
We established and evaluated a radiomics nomogram based on multislice computed tomography (MSCT) arterial phase contrast-enhanced images to distinguish between Crohn's disease (CD) ulcerative colitis (UC) objectively, quantitatively, reproducibly.MSCT phase-enhancement of 165 lesions (99 CD, 66 UC) in 87 patients with inflammatory bowel (IBD) confirmed by endoscopy or surgical pathology were retrospectively analyzed. A total 132 (80%) selected as the training cohort 33 (20%) test cohort....
Abstract Background To construct and assess a computed tomography (CT)-based deep learning radiomics nomogram (DLRN) for predicting the pathological grade of bladder cancer (BCa) preoperatively. Methods We retrospectively enrolled 688 patients with BCa (469 in training cohort, 219 external test cohort) who underwent surgical resection. extracted handcrafted (HCR) features (DL) from three-phase CT images (including corticomedullary-phase [C-phase], nephrographic-phase [N-phase]...
Accurate stratification of recurrence risk for bladder cancer (BCa) is essential precise individualized therapy. This study aimed to develop and validate a model predicting the in BCa patients postoperatively using 3-phase enhanced CT images.We retrospectively enrolled 874 across four centers between January 2006 December 2021. Patients from one center were used as training set, while remaining went into validation set. We trained deep learning (DL) based on convolutional neural networks...
To investigate whether intratumoral and peritumoral radiomics may predict pathological responses after neoadjuvant chemotherapy against advanced gastric cancer. Clinical, pathological, CT data from 231 patients with cancer who underwent at our hospital between July 2014 February 2022 were retrospectively collected. Patients randomly divided into a training group (n = 161) validation 70). The support vector machine classifier was used to establish models. A clinical model established based on...
Objective To develop a deep learning (DL) model for carotid plaque detection based on CTA images and evaluate the clinical application feasibility value of model. Methods We retrospectively collected data from patients with atherosclerotic plaques who underwent continuous examinations head neck at tertiary hospital October 2020 to 2022. The combined ResUNet Pyramid Scene Parsing Network (PSPNet) enhance segmentation. Patient were divided into training, validation, testing sets in ratio...
<title>Abstract</title> Background: Spondylitis, particularly infectious forms caused by Mycobacterium tuberculosis and Brucella species, presents significant clinical challenges due to overlapping symptoms diagnostic difficulties. Accurate differentiation is crucial for effective treatment, necessitating advanced imaging techniques radiomics enhance precision improve patient outcomes in cases of TB brucella spondylitis. Methods This retrospective cohort study included 165 patients diagnosed...
To examine the correlation of apparent diffusion coefficient (ADC), weighted imaging (DWI), and T1 contrast enhanced (T1-CE) with Ki-67 in primary central nervous system lymphomas (PCNSL). And to assess diagnostic performance MRI radiomics-based machine-learning algorithms differentiating high proliferation low groups PCNSL. 83 patients PCNSL were included this retrospective study. ADC, DWI T1-CE sequences collected their was examined using Spearman's analysis. The Kaplan-Meier method...
To construct and assess a deep learning (DL) signature that employs computed tomography imaging to predict the expression status of programmed cell death ligand 1 in patients with bladder cancer (BCa). This retrospective study included 190 from two hospitals who underwent surgical removal BCa (training set/external validation set, 127/63). We used convolutional neural network radiomics machine technology generate prediction models. then compared performance DL selected optimal build nomogram...
Background The traditional procedure of intracranial aneurysm (IA) diagnosis and evaluation in MRA is manually operated, which time-consuming labor-intensive. In this study, a deep learning model was established to diagnose measure IA automatically based on the original MR images. Methods A total 1,014 IAs (from 852 patients) from hospital 1 were included randomly divided into training, testing, internal validation sets 7:2:1 ratio. Additionally, 315 patients (179 cases with 136 without IA)...
Background Medulloblastoma (MB) and ependymoma (EM) in children share similarities terms of age group, tumor location, clinical presentation, which makes it challenging to clinically diagnose distinguish them. Purpose The present study aims explore the effectiveness T2-weighted magnetic resonance imaging (MRI)-based deep learning (DL) combined with features for differentiating MB from EM. Methods Axial MRI sequences obtained 201 patients across three centers were used model training testing....
Abstract In arthropods, retinoid X receptor (RXR) is a highly conserved nuclear hormone receptor. By forming heterodimeric complex with the ecdysone (EcR), RXR known to be vital importance for various physiological processes. However, in comparison EcR, signaling pathway and its roles crustacean reproduction are poorly understood. present study, mRNA was detected ovarian follicular cells of mud crab Scylla paramamosain (SpRXR) during maturation, expression level found increase significantly....