A5108827596- MRI in cancer diagnosis
- Radiomics and Machine Learning in Medical Imaging
- AI in cancer detection
- Medical Image Segmentation Techniques
- COVID-19 diagnosis using AI
- Advanced Neuroimaging Techniques and Applications
- Hepatocellular Carcinoma Treatment and Prognosis
- Liver Disease and Transplantation
- Organ Transplantation Techniques and Outcomes
- Advanced MRI Techniques and Applications
- Advanced Neural Network Applications
- Cholangiocarcinoma and Gallbladder Cancer Studies
- Liver Disease Diagnosis and Treatment
- Medical Imaging Techniques and Applications
- Pancreatic and Hepatic Oncology Research
- Organ Donation and Transplantation
- Advanced X-ray and CT Imaging
- Image Retrieval and Classification Techniques
- Medical Imaging and Analysis
- Anomaly Detection Techniques and Applications
- Gallbladder and Bile Duct Disorders
- Nanocomposite Films for Food Packaging
- Dyeing and Modifying Textile Fibers
- Lung Cancer Diagnosis and Treatment
- Time Series Analysis and Forecasting
Renji Hospital
2010-2024
Shanghai Jiao Tong University
2009-2024
Sir Run Run Shaw Hospital
2016
Zhejiang University
2016
Southern Medical University
2010
Purpose Volumetric pancreas segmentation can be used in the diagnosis of pancreatic diseases, research about diabetes and surgical planning. Since manual delineation is time‐consuming laborious, we develop a deep learning‐based framework for automatic three dimensional (3D) medical images. Methods A two‐stage designed delineation. In localization stage, Square Root Dice loss developed to handle trade‐off between sensitivity specificity. refinement novel 2.5D slice interaction network with...
Determining liver segmentation accurately from MRIs is the primary and crucial step for any automated perfusion analysis, which provides important information about blood supply to liver. Although implicit contour extraction methods, such as level set methods (LSMs) active contours, are often used segment livers, results not always satisfactory due presence of artifacts low-gradient response on boundary. In this paper, we propose a multiple-initialization, multiple-step LSM overcome leakage...
As digital medicine has exerted profound influences upon diagnosis and treatment of hepatobiliary diseases, our study aims to investigate the accuracy three-dimensional visualization evaluation (3DVE) system in assessing resectability hilar cholangiocarcinoma (hCCA), explores its potential clinical value.The discovery cohort, containing 111 patients from April 2013 December 2019, was retrospectively included determine according revised criteria for unresectability hCCA. 3D models were...
Purpose. To investigate the potential of diffusion and perfusion indices (ADC fraction <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M1"><mml:mrow><mml:mi>f</mml:mi></mml:mrow></mml:math>) from DWI at 3.0 T in monitoring treatment response to uterine artery embolization (UAE) 6-month follow-up. Methods. Twelve female patients with fibroids who underwent 3.0-T pelvic before 6 months after UAE were included. ADC id="M2"><mml:mrow><mml:mi>f</mml:mi></mml:mrow></mml:math>...
The incidence of liver tumors is among the top three in China. treatments benign and malignant are different. Accurate diagnosis plays an important role guiding treatment tumors.The aim this study to solve following: (1) blurred boundary between tumor other organs causes incorrect segmentation boundaries; (2) large difference size diversity texture grayscale major challenges classification tasks.Firstly, segmented from original CT images by a network, UNet++ with fusion loss atrous spatial...
Hepatic hemodynamic changes in grafts after living donor liver transplantation (LDLT) are complicated. In this study, computed tomography (CT) perfusion parameter values, especially portal vein (PVP), was retrospectively analyzed recipients both with and without small-for-size syndrome (SFSS). PVP significantly higher non-SFSS on post-operative day (POD) 14 or 28 than normal donors before donation (p < 0.001 p = 0.008, respectively), but it decreased between days post-operatively 0.007)....
Due to abdominal CT images' specific characteristics, a novel automatic liver segmentation method is introduced in this paper based on Gaussian blurring technique for binary images. This utilizes simple line search plane domain at first extract image composed of isolated white pixel clusters mainly from the part histogram distribution and spatial characteristics region obtained images; In following step, connect clusters; Threshold blurred after post-processing step mending holes size...
The European Union Digital Library (EUDL) is the central repository for all content published by different branches of Alliance Innovation (EAI). EUDL also hosts or indexes from selected partner member organizations and affiliates.
This study evaluates the diagnostic efficacy of contrast-enhanced MR imaging for preoperative POSTTEXT staging and prediction vascular involvement in pediatric hepatoblastoma after neoadjuvant chemotherapy. The findings revealed that has a good level agreement with reference standard. provides high predictive performance identifying portal vein moderate hepatic vein/inferior vena cava involvement.