A5101827264- Radiomics and Machine Learning in Medical Imaging
- Lung Cancer Diagnosis and Treatment
- COVID-19 diagnosis using AI
- Medical Imaging Techniques and Applications
- Advanced X-ray and CT Imaging
- COVID-19 Clinical Research Studies
- Machine Learning in Healthcare
- AI in cancer detection
- Medical Imaging and Pathology Studies
- Artificial Intelligence in Healthcare and Education
- Diet and metabolism studies
- Advanced MRI Techniques and Applications
- Advanced Decision-Making Techniques
- NMR spectroscopy and applications
- Biliary and Gastrointestinal Fistulas
- Management of metastatic bone disease
- Gastrointestinal Tumor Research and Treatment
- Brain Tumor Detection and Classification
- Congenital Diaphragmatic Hernia Studies
- Neurological Disease Mechanisms and Treatments
- Functional Brain Connectivity Studies
- Advanced NMR Techniques and Applications
- Foreign Body Medical Cases
- Statistical Methods in Clinical Trials
- Geotechnical Engineering and Analysis
Maastricht University
2020-2023
Huazhong University of Science and Technology
2022
Union Hospital
2022
Maastricht University Medical Centre
2021
University Medical Center
2020
Affiliated Zhongshan Hospital of Dalian University
2017-2020
University of Jyväskylä
2017
Creative Research Enterprises (United States)
2016
Dongguan People’s Hospital
2016
Guhua Hospital
2014
Background The outbreak of coronavirus disease 2019 (COVID-19) has globally strained medical resources and caused significant mortality. Objective To develop validate a machine-learning model based on clinical features for severity risk assessment triage COVID-19 patients at hospital admission. Method 725 were used to train the model. This included retrospective cohort from Wuhan, China 299 hospitalised 23 December 13 February 2020, five cohorts with 426 eight centres in China, Italy Belgium...
Abstract Detection and segmentation of abnormalities on medical images is highly important for patient management including diagnosis, radiotherapy, response evaluation, as well quantitative image research. We present a fully automated pipeline the detection volumetric non-small cell lung cancer (NSCLC) developed validated 1328 thoracic CT scans from 8 institutions. Along with performance detailed by slice thickness, tumor size, interpretation difficulty, location, we report an in-silico...
Background Solid components of part-solid nodules (PSNs) at CT are reflective invasive adenocarcinoma, but studies describing radiomic features PSNs and the perinodular region lacking. Purpose To develop to validate signatures diagnosing lung adenocarcinoma in compared with Brock, clinical-semantic features, volumetric models. Materials Methods This retrospective multicenter study (https://ClinicalTrials.gov, NCT03872362) included 291 patients (median age, 60 years; interquartile range,...
There are increasing reports of a type lung cancer that manifests as solitary cystic airspaces. The purpose this case series was to identify the CT features and possible mechanisms cancer, on basis observations pathologic characteristics. clinical, imaging, data 106 patients with were collected analyzed between January 2011 December 2017. images reviewed independently by three radiologists who blinded findings. Demographic clinical smoking status extracted from medical records. mean age 58.8...
To develop handcrafted radiomics (HCR) and deep learning (DL) based automated diagnostic tools that can differentiate between idiopathic pulmonary fibrosis (IPF) non-IPF interstitial lung diseases (ILDs) in patients using high-resolution computed tomography (HRCT) scans. In this retrospective study, 474 HRCT scans were included (mean age, 64.10 years ± 9.57 [SD]). Five-fold cross-validation was performed on 365 Furthermore, an external dataset comprising 109 used as a test set. An HCR model,...
Abstract Objectives Develop a CT-based radiomics model and combine it with frozen section (FS) clinical data to distinguish invasive adenocarcinomas (IA) from preinvasive lesions/minimally (PM). Methods This multicenter study cohort of 623 lung was split into training ( n = 331), testing 143), external validation dataset 149). Random forest models were built using selected features, results FS, lesion volume, semantic combinations thereof. The area under the receiver operator characteristic...
Objective To establish whether one can build a mortality prediction model for COVID-19 patients based solely on demographics and comorbidity data that outperforms age alone. Such could be precursor to implementing smart lockdowns vaccine distribution strategies. Methods The training cohort comprised 2337 inpatients from nine hospitals in Netherlands. clinical outcome was death within 21 days of being discharged. features were derived electronic health records collected during admission....
The most common idiopathic interstitial lung disease (ILD) is pulmonary fibrosis (IPF). It can be identified by the presence of usual pneumonia (UIP) via high-resolution computed tomography (HRCT) or with use a biopsy. We hypothesized that CT-based approach using handcrafted radiomics might able to identify IPF patients radiological histological UIP pattern from those an ILD normal lungs. A total 328 one center and two databases participated in this study. Each participant had their lungs...
Early and accurate diagnosis of invasive fungal infection (IFI) is pivotal for the initiation effective antifungal therapy patients with hematologic malignancies.This retrospective study involved 235 malignancies pulmonary infections diagnosed as IFIs (n=118) or bacterial pneumonia (n=117). Patients were randomly divided into training (n=188) validation (n=47) datasets. Four feature selection methods nine classifiers implemented to select optimal machine learning (ML) model using five-fold...
Rectal foreign bodies are man-made injury that occurs occasionally. The management depends on its depth and the consequence it caused. We here report a case of rectal body (a glass bottle measuring about 38 mm × 75 mm) which was located 13-15 cm from anus. patient had no sign perforation, we managed to remove using endoscopy with gastrolith forceps.
Objective: To investigate the image quality of ultralow-dose CT (ULDCT) chest reconstructed using a cycle-consistent generative adversarial network (CycleGAN)-based deep learning method in evaluation pulmonary tuberculosis.Materials and Methods: Between June 2019 November 2019, 103 patients (mean age, 40.8 ± 13.6 years; 61 men 42 women) with tuberculosis were prospectively enrolled to undergo standard-dose (120 kVp automated exposure control), followed immediately by ULDCT (80 10 mAs).The...
Key points Question How do nomograms and machine-learning algorithms of severity risk prediction triage COVID-19 patients at hospital admission perform? Findings This model was prospectively validated on six test datasets comprising 426 yielded AUCs ranging from 0.816 to 0.976, accuracies 70.8% 93.8%, sensitivities 83.7% 100%, specificities 41.0% 95.7%. The cut-off probability values for low, medium, high-risk groups were 0.072 0.244. Meaning findings this study suggest that our models...
OPINION article Front. Med., 14 May 2021Sec. Precision Medicine https://doi.org/10.3389/fmed.2021.640854