A5100785325- Radiomics and Machine Learning in Medical Imaging
- Medical Imaging Techniques and Applications
- AI in cancer detection
- Lung Cancer Diagnosis and Treatment
- Head and Neck Cancer Studies
- Brain Tumor Detection and Classification
- Environmental and Agricultural Sciences
- Gastric Cancer Management and Outcomes
- Advanced Neural Network Applications
- Cancer Immunotherapy and Biomarkers
- Endometrial and Cervical Cancer Treatments
- Educational Technology and Assessment
- Education and Work Dynamics
- Higher Education and Teaching Methods
- Advanced X-ray and CT Imaging
- Shoulder Injury and Treatment
- Elbow and Forearm Trauma Treatment
- Machine Learning and Data Classification
- Musculoskeletal pain and rehabilitation
- Image Enhancement Techniques
- Retinal and Optic Conditions
- Radiation Dose and Imaging
- Fuzzy Logic and Control Systems
- Stellar, planetary, and galactic studies
- Explainable Artificial Intelligence (XAI)
University of Kansas Medical Center
2023-2024
The University of Kansas Cancer Center
2023-2024
University of Central Missouri
2020-2022
The University of Texas Southwestern Medical Center
2017-2022
Wuhan Children's Hospital
2019-2020
Northeast Normal University
2007-2020
Huazhong University of Science and Technology
2020
Shanghai First People's Hospital
2016
Shanghai Jiao Tong University
2016
Huaiyin Institute of Technology
2012
Objective: Determine the performance of a computed tomography (CT) -based radiomics model in predicting early response to immunotherapy patients with metastatic melanoma. Methods: This retrospective study examined 50 melanoma who received treatment our hospital an anti-programmed cell death-1 (PD-1) agent or inhibitor cytotoxic T lymphocyte antigen-4 (CTLA-4). Thirty-four anti-PD-1 were training sample and 16 CTLA-4 validation sample. Patients true progressive disease (PD) poor group, those...
To evaluate diagnostic performances of CESM for breast diseases with comparison to MRI in China.Sixty-eight patients 77 lesions underwent MR and CESM. Two radiologists interpreted either or images, separately independently. BI-RADS 1-3 4-5 were classified into the suspicious benign malignant groups. Diagnostic accuracy parameters calculated. Receiver operating characteristic (ROC) curves constructed two modalities. The agreement correlation between maximum lesion diameter based on MRI,...
Deep learning based radiomics have made great progress such as CNN diagnosis and U-Net segmentation. However, the prediction of drug effectiveness on deep has fewer studies. Choroidal neovascularization (CNV) cystoid macular edema (CME) are diseases often leading to a sudden onset but progressive decline in central vision. And curative treatment using anti-vascular endothelial growth factor (anti-VEGF) may not be effective for some patients. Therefore, anti-VEGF patients is important. With...
Objectives Accurate identifying head and neck squamous cell cancer (HNSCC) patients at high risk of local persistence/recurrence (P/R) is importance for personalized patient management. Here we developed a multi-objective, multi-classifier radiomics model early HNSCC P/R prediction based on post-treatment PET/CT scans clinical data. Materials methods We retrospectively identified 328 individuals (69 have P/R) with treated definitive radiation therapy our institution. The median follow-up...
Purpose: Quantitative features from pre-treatment positron emission tomography (PET) have been used to predict treatment outcomes for patients with cervical carcinoma. The purpose of this study is use quantitative PET imaging and clinical parameters construct a multi-objective machine learning predictive model. Materials/Methods: Seventy-five stage IB2-IVA disease treated at our institution 2009–2012 were analyzed. Models predicting locoregional distant failure generated using (age, race,...
Objectives Our study aims to investigate the impact of B‐mode ultrasound (B‐US) imaging, color Doppler flow imaging (CDFI), strain elastography (SE), and patient age on prediction molecular subtypes in breast lesions. Methods Totally 2272 multimodal was collected from 198 patients. The ResNet‐18 network employed predict four B‐US CDFI, SE patients with different ages. All images were split into training testing datasets by ratio 80%:20%. predictive performance dataset evaluated through 5...
Computer english is a very special course in the computer science curriculum. Based on 6 round teaching practice, problems met activity are analyzed. The measures of organization to improve and studying quality presented, which include focusing target, choosing materials, applying new methods class adjusting final exam content. survey data show that result promising.
Distinguishing multiple primary lung cancer (MPLC) from intrapulmonary metastasis (IPM) is critical for their disparate treatment strategy and prognosis. This study aimed to establish a non-invasive model make the differentiation pre-operatively.We retrospectively studied 168 patients with cancers (307 pairs of lesions) including 118 cases modeling internal validation, 50 independent external validation. Radiomic features on computed tomography (CT) were extracted calculate absolute...
Positron emission tomography (PET) imaging has been widely explored for treatment outcome prediction. Radiomicsdriven methods provide a new insight to quantitatively explore underlying information from PET images. However, it is still challenging problem automatically extract clinically meaningful features prognosis. In this work, we develop PET-guided distant failure predictive model early stage non-small cell lung cancer (NSCLC) patients after stereotactic ablative radiotherapy (SABR) by...
An abstract is not available for this content so a preview has been provided. As you have access to content, full PDF via the ‘Save PDF’ action button.
Locoregional recurrence (LRR) remains one of leading causes in head and neck (H&N) cancer treatment failure despite the advancement multidisciplinary management. Accurately predicting LRR early stage can help physicians make an optimal personalized strategy. In this study, we propose end-to-end multi-modality multi-view convolutional neural network model (mMmV-CNN) for prediction H&N cancer. mMmV, a dimension reduction operator is designed, projecting 3D volume onto 2D images different...