A5017914498- Radiomics and Machine Learning in Medical Imaging
- Lung Cancer Diagnosis and Treatment
- Medical Imaging Techniques and Applications
- Advanced X-ray and CT Imaging
- COVID-19 diagnosis using AI
- Chronic Obstructive Pulmonary Disease (COPD) Research
- Medical Imaging and Pathology Studies
- Long-Term Effects of COVID-19
- Esophageal Cancer Research and Treatment
- Colorectal and Anal Carcinomas
- Interstitial Lung Diseases and Idiopathic Pulmonary Fibrosis
- COVID-19 and healthcare impacts
- Colorectal Cancer Surgical Treatments
- COVID-19 Clinical Research Studies
- Pleural and Pulmonary Diseases
- Advanced MRI Techniques and Applications
- Medical Imaging and Analysis
- Cardiovascular Function and Risk Factors
- Nuclear Physics and Applications
- Gastric Cancer Management and Outcomes
- Radiation Dose and Imaging
- Colorectal Cancer Treatments and Studies
- Lung Cancer Treatments and Mutations
Shanghai Changzheng Hospital
2023-2024
Weifang Medical University
2023-2024
Second Military Medical University
2023
Xuzhou Medical College
2023
Philips (China)
2023
Shanghai University of Finance and Economics
2023
Wuhan No.1 Hospital
2023
The study aims to investigate the value of intratumoral and peritumoral radiomics clinical-radiological features for predicting spread through air spaces (STAS) in patients with clinical stage IA non-small cell lung cancer (NSCLC). A total 336 NSCLC from our hospital were randomly divided into training cohort (n = 236) internal validation 100) at a ratio 7:3, 69 other two external hospitals collected as cohort. Univariate multivariate analyses used select construct model. GTV, PTV5, PTV10,...
Objective To develop and validate the model for predicting benign malignant ground-glass nodules (GGNs) based on whole-lung baseline CT features deriving from deep learning radiomics. Methods This retrospective study included 385 GGNs 3 hospitals, confirmed by pathology. We used 239 Hospital 1 as training internal validation set; 115 31 2 external test sets 2, respectively. An additional 32 stable with more than five years of follow-up were set 3. evaluated clinical morphological at chest...
Preoperative prediction of visceral pleural invasion (VPI) is important because it enables thoracic surgeons to choose appropriate surgical plans. This study aimed develop and validate a multivariate logistic regression model incorporating the maximum standardized uptake value (SUVmax) valuable computed tomography (CT) signs for non-invasive VPI status in subpleural clinical stage IA lung adenocarcinoma patients before surgery.A total 140 with peripheral were recruited divided into training...
Accurate prediction of visceral pleural invasion (VPI) in lung adenocarcinoma before operation can provide guidance and help for surgical postoperative treatment. We investigate the value intratumoral peritumoral radiomics nomograms preoperatively predicting status VPI patients diagnosed with clinical stage IA adenocarcinoma.
Abstract Purpose This study aims to assess the predictive value of 18 F-fluorodeoxyglucose positron emission tomography/computed tomography ( F-FDG PET/CT) radiological features and maximum standardized uptake (SUV max ) in determining presence spread through air spaces (STAS) clinical-stage IA non-small cell lung cancer (NSCLC). Methods A retrospective analysis was conducted on 180 cases NSCLC with postoperative pathological assessment STAS status, spanning from September 2019 2023. Of...
Preoperative accurate judgment of the degree invasiveness in subpleural ground-glass lung adenocarcinoma (LUAD) with a consolidation-to-tumor ratio (CTR) ≤50% is very important for choice surgical timing and planning. This study aims to investigate performance intratumoral peritumoral radiomics combined computed tomography (CT) features predicting LUAD presenting as nodule (GGN) CTR ≤50%.
Purpose: Reliable prediction of volume doubling time (VDT) is essential for the personalized management pulmonary ground-glass nodules (GGNs). We aimed to determine optimal VDT method by comparing different machine learning methods only based on baseline chest computed tomography (CT) images. Materials and Methods: Seven classical were evaluated in terms their stability performance prediction. The VDT, calculated preoperative CT, was divided into 2 groups with a cutoff value 400 days. A...
The aim of this study is to construct a combined model that integrates radiomics, clinical risk factors and machine learning algorithms predict para-laryngeal lymph node metastasis in esophageal squamous cell carcinoma.
Extracellular volume (ECV) fraction has been used in cardiovascular diseases, pancreatic fibrosis, and hepatic fibrosis. The diagnostic value of ECV for focal lung lesions remains to be explored. aim this study was evaluate the feasibility derived from a dual-layer detector computed tomography (DLCT) differentiate cancer (LC) benign (BLLs).Retrospectively, 128 consecutive patients with pathologically confirmed LC (n=86) or BLLs (n=42) were included. Conventional (CT) characteristics spectral...
To assess the quantification accuracy of pulmonary nodules using virtual monoenergetic images (VMIs) derived from spectral-detector computed tomography (CT) under an ultra-low-dose scan protocol.A chest phantom consisting 12 was scanned CT at 100 kVp/10 mAs, kVp/20 120 and kVp/30 mAs. Each scanning protocol repeated three times. reconstructed utilizing filtered back projection, hybrid iterative reconstruction, model reconstruction (IMR), VMIs 40-100 keV. The signal-to-noise ratio air noise...
Coronavirus disease 2019 (COVID-19) still poses a threat to people's physical and mental health. We proposed new semi-quantitative visual classification method for COVID-19, this study aimed evaluate the clinical usefulness feasibility of lung field-based severity score (LFSS).
Objectives The purpose of this study was to develop and validate a new feature fusion algorithm improve the classification performance benign malignant ground-glass nodules (GGNs) based on deep learning. Methods We retrospectively collected 385 cases GGNs confirmed by surgical pathology from three hospitals. utilized 239 Hospital 1 as training internal validation set, 115 31 2 3, respectively, external test sets 2. Among these GGNs, 172 were 203 malignant. First, we evaluated clinical...
Objective To explore the predictive value of radiomics nomogram combining with CT features and clinical for postoperative early recurrence in patients BRAF-mutant colorectal cancer. Methods A total 220 surgically pathologically confirmed cancer from 2 institutions were retrospectively included. All institution 1 randomized at a 7:3 ratio into training cohort (n = 108) an internal validation 45), used as external 67). The association between was assessed verified cohort. Furthermore,...
Abstract Background COVID‐19 remains widespread and poses a threat to people's physical mental health, especially middle‐aged elderly individuals. Early identification of patients at high risk progressing critical disease helps improve overall patient outcomes healthcare efficiency. Purpose To develop radiomics nomogram predict the newly admitted disease. Methods A total 794 (aged 40 years or above) were retrospectively included in study from two institutions, all them with non‐critical on...
Background: Chronic obstructive pulmonary disease (COPD) is a major global health concern, and while traditional function tests are effective, recent radiomics advancements offer enhanced evaluation by providing detailed insights into the heterogeneous lung changes. Purpose: To develop validate nomogram based on clinical whole-lung computed tomography (CT) features to stratify COPD severity. Patients Methods: One thousand ninety-nine patients with (including 308, 132, 659 in training,...
Purpose: This study aimed to screen out computed tomography (CT) morphological features and clinical characteristics of patients with lung cancer identify chronic obstructive pulmonary disease (COPD). Further, we develop validate different diagnostic nomograms for predicting whether is comorbid COPD. Patients Methods: retrospective examined data from 498 (280 COPD, 218 without COPD; 349 in training cohort, 149 validation cohort) two centers. Five 20 CT were evaluated. Differences all...
Abstract Purpose To investigate the value of intratumoral and peritumoral radiomics nomograms for preoperatively predicting presence visceral pleural invasion (VPI) in patients diagnosed with clinical stage IA lung adenocarcinoma (LUAD) . Methods A total 404 from our hospital were randomly assigned to a training set (n = 283) an internal validation 121) using 7:3 ratio, while 81 two other hospitals constituted external set. We extracted 1218 CT-based features gross tumor volume (GTV) as well...