A5101986474- Medical Image Segmentation Techniques
- AI in cancer detection
- Radiomics and Machine Learning in Medical Imaging
- Medical Imaging Techniques and Applications
- Cell Image Analysis Techniques
- Advanced Neural Network Applications
- Image Retrieval and Classification Techniques
- Morphological variations and asymmetry
- Advanced Neuroimaging Techniques and Applications
- 3D Shape Modeling and Analysis
- Digital Image Processing Techniques
- Advanced MRI Techniques and Applications
- Advanced Vision and Imaging
- Image and Object Detection Techniques
- Colorectal Cancer Surgical Treatments
- Pancreatic and Hepatic Oncology Research
- COVID-19 diagnosis using AI
- Robotics and Sensor-Based Localization
- Advanced X-ray and CT Imaging
- Sepsis Diagnosis and Treatment
- Advanced Measurement and Metrology Techniques
- Medical Imaging and Analysis
- Dental Radiography and Imaging
- Advanced Measurement and Detection Methods
- MRI in cancer diagnosis
Xi'an Shiyou University
2024-2025
Shenzhen University
2017-2025
China Pharmaceutical University
2020-2025
Ruijin Hospital
2025
Shanghai Jiao Tong University
2025
Shenzhen University Health Science Center
2018-2025
Johns Hopkins University
2025
University of Hong Kong - Shenzhen Hospital
2025
University of Hong Kong
2025
Huzhou University
2025
Convolutional Neural Networks (CNN) are state-of-theart models for many image classification tasks. However, to recognize cancer subtypes automatically, training a CNN on gigapixel resolution Whole Slide Tissue Images (WSI) is currently computationally impossible. The differentiation of based cellular-level visual features observed patch scale. Therefore, we argue that in this situation, patch-level classifier patches will perform better than or similar an image-level classifier. challenge...
Motivation: Identifying different cancer classes or subclasses with similar morphological appearances presents a challenging problem and has important implication in diagnosis treatment. Clustering based on gene-expression data been shown to be powerful method class discovery. Non-negative matrix factorization is one such was advantageous over other clustering techniques, as hierarchical self-organizing maps. In this paper, we investigate the benefit of explicitly enforcing sparseness process.
Sentinel lymph node (SLN) status is an important prognostic factor for patients with breast cancer, which currently determined in clinical practice by invasive SLN biopsy.To noninvasively predict metastasis cancer using dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) intra- and peritumoral radiomics features combined or without clinicopathologic characteristics of the primary tumor.Retrospective.A total 163 (55 positive 108 negative SLN).1.5T, T1 -weighted DCE-MRI.A 590...
<h3>Importance</h3> Most dermatologic cases are initially evaluated by nondermatologists such as primary care physicians (PCPs) or nurse practitioners (NPs). <h3>Objective</h3> To evaluate an artificial intelligence (AI)–based tool that assists with diagnoses of conditions. <h3>Design, Setting, and Participants</h3> This multiple-reader, multiple-case diagnostic study developed AI-based its utility. Primary NPs retrospectively reviewed enriched set representing 120 different skin...
Late Gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) imaging can be used to visualise regions of fibrosis and scarring in the left atrium (LA) myocardium. This important for treatment stratification patients with atrial fibrillation (AF) assessment after radio frequency catheter ablation (RFCA). In this paper we present a standardised evaluation benchmarking framework algorithms segmenting scar from LGE CMR images. The reported are response an open challenge that was put...
Well-curated sets of pathology image features will be critical to clinical studies that aim evaluate and predict treatment responses. Researchers require information synthesized across multiple biological scales, from the patient molecular scale, more effectively study cancer. This article describes a suite services web applications allow users select regions interest in whole slide tissue images, run segmentation pipeline on selected extract nuclei compute shape, size, intensity, texture...
Attenuation correction is a notable challenge associated with simultaneous PET/MRI, particularly in neuroimaging, where sharp boundaries between air and bone volumes exist. This leads to concerns about the visual and, more specifically, quantitative accuracy of PET reconstructions for data obtained PET/MRI. Recently developed techniques can synthesize attenuation maps using only MRI are likely adequate clinical use; however, little work has been conducted assess their suitability dynamic...
Deep tumor penetration, long blood circulation, rapid drug release, and sufficient stability are the most concerning dilemmas of nano-drug-delivery systems for efficient chemotherapy. Herein, we develop reduction/oxidation-responsive hierarchical nanoparticles co-encapsulating paclitaxel (PTX) pH-stimulated hyaluronidase (pSH) to surmount sequential biological barriers precise cancer therapy. Poly(ethylene glycol) diamine (PEG-dia) is applied collaboratively cross-link shell self-assembled...
Abstract Shown in every neuroanatomy textbook, a key morphological feature is the bumpy ridges, which we refer to as hippocampal dentation, on inferior aspect of hippocampus. Like folding cerebral cortex, dentation allows for greater surface area confined space. However, examining numerous approaches segmentation and morphology analysis, virtually all published 3D renderings hippocampus show be quite smooth or mildly irregular; have rarely seen characteristic structure reconstructed...
Methylenetetrahydrofolate dehydrogenase 2 (MTHFD2) is a tetramethylfolate enzyme involved in folate metabolism. The aim of this study to determine the effect MTHFD2 on proliferation and metastasis colorectal cancer (CRC).MTHFD2 was silenced or overexpressed CRC cells. qRT-PCR Western blotting were used analyze mRNA protein expression, respectively. MTT assay colony forming detect cell formation ability. cycle apoptosis changes detected by flow cytometry. Transwell experiments migration...
The planning and evaluation of left atrial ablation procedures are commonly based on the segmentation atrium, which is a challenging task due to large anatomical variations. In this paper, we propose an automatic approach for segmenting atrium from magnetic resonance imagery. problem formulated as in variational region growing. particular, method starts locally by searching seed MR slice. A global constraint imposed applying shape prior represented Zernike moments. overall growing process...
Convolutional Neural Networks (CNN) are state-of-the-art models for many image classification tasks. However, to recognize cancer subtypes automatically, training a CNN on gigapixel resolution Whole Slide Tissue Images (WSI) is currently computationally impossible. The differentiation of based cellular-level visual features observed patch scale. Therefore, we argue that in this situation, patch-level classifier patches will perform better than or similar an image-level classifier. challenge...
Artificial intelligence is used in people's daily lives, coping with various kinds of work almost every aspect our lives nowadays. Among AI, generative ranging from ChatGPT to AI painting, has been discussed most frequently. Some models have audio areas, such as denoising or generating audios recent years. Additionally, though different its own advantages, the diffusion model outstanding one among all those models, leaving people unforgettable impressions and infinite possibilities by taking...
The purpose of this study was to assess the severity hemifacial spasm (HFS) through quantitative measures that associated it with neurovascular contact (NVC). We enrolled 108 HFS patients (63 severe and 45 mild cases) implemented a human-in-the-loop approach develop NVC feature package. This process involved using interactive segmentation on three-dimensional volumetric interpolated breath-hold examination (VIBE) MR images delineate vascular nerve structures. From these segmentations, we...
Robotic-assisted dental implantation represents a transformative innovation in modern dentistry, offering enhanced surgical precision and reduced variability. Despite its clinical adoption, the impact of anatomical bone-related factors on placement accuracy remains underexplored. This retrospective study evaluated 54 implants placed 30 patients using cone-beam computed tomography (CBCT) virtual planning software to analyze deviations crown position, apex angulation. Significant regional...