Medical Oncology, Год журнала: 2025, Номер 42(7)
Опубликована: Май 27, 2025
Язык: Английский
European Journal of Radiology, Год журнала: 2025, Номер 183, С. 111912 - 111912
Опубликована: Янв. 5, 2025
Язык: Английский
Процитировано
0
PLoS ONE, Год журнала: 2025, Номер 20(1), С. e0318232 - e0318232
Опубликована: Янв. 28, 2025
Objective To develop a predictive model for microvascular invasion (MVI) in hepatocellular carcinoma (HCC) through radiomics analysis, integrating data from both enhanced computed tomography (CT) and magnetic resonance imaging (MRI). Methods A retrospective analysis was conducted on 93 HCC patients who underwent partial hepatectomy. The gold standard MVI based the histopathological diagnosis of tissue. were randomly divided into training validation groups 7:3 ratio. patients, including CT MRI, collected processed using 3D Slicer to delineate region interest (ROI) each tumor. Radiomics features extracted MRI Python. Lasso regression used select optimal group. selected establish prediction model. performance evaluated receiver operator characteristic curve (ROC), calibration curve, decision (DCA). Results After univariate multivariate analyses, it found that tumor diameter significantly different between positive negative groups. extracting 2153 phenotyping images Python, ten standardized coefficient non-zero finally determined by images. comprehensive with clinical variable established. area under (AUC) group 0.916 (95%CI: 0.843–1.000), sensitivity: 95.2%, specificity: 79.2%. In group, diagnosed AUC = 0.816 0.642–0.990), 84.2%, 75.0%. Conclusion joint integrated variables has good diagnostic specific applicability.
Язык: Английский
Процитировано
0
Tomography, Год журнала: 2025, Номер 11(3), С. 20 - 20
Опубликована: Фев. 20, 2025
Background/Objectives: Radiomic features exhibit a correlation with tumor size on pretreatment images. However, post-treatment images, this association is influenced by treatment efficacy and varies between responders non-responders. This study introduces novel model, called baseline-referenced Delta radiomics, which integrates the radiomic into radiomics to predict chemotherapy response in liver metastases from breast cancer (BC) colorectal (CRC). Materials Methods: A retrospective analyzed contrast-enhanced computed tomography (CT) scans of 83 BC patients 84 CRC patients. Among these, 57 106 lesions 37 109 underwent imaging after systemic chemotherapy. were extracted up three per patient following manual segmentation. Tumor was assessed measuring longest diameter classified according RECIST 1.1 criteria as progressive disease (PD), partial (PR), or stable (SD). Classification models developed using data only, radiomics. Model performance evaluated confusion matrix metrics. Results: Baseline-referenced performed comparably better than established predicting chemotherapy-treated metastases. The sensitivity, specificity, balanced accuracy ranged 0.66 0.97, 0.81 80% 90%, respectively. Conclusions: By integrating relationship offers promising approach for cancer.
Язык: Английский
Процитировано
0
La radiologia medica, Год журнала: 2025, Номер unknown
Опубликована: Фев. 24, 2025
Язык: Английский
Процитировано
0
Cancers, Год журнала: 2025, Номер 17(5), С. 768 - 768
Опубликована: Фев. 24, 2025
Radiomics has seen substantial growth in medical imaging; however, its potential optical coherence tomography (OCT) not been widely explored. We systematically evaluate the repeatability and reproducibility of handcrafted radiomics features (HRFs) from OCT scans benign nevi examine impact bin width (BW) selection on HRF stability. The effect using stable a classification model was also assessed. In this prospective study, 20 volunteers underwent test-retest imaging 40 nevi, resulting 80 scans. HRFs extracted manually delineated regions interest (ROIs) were assessed concordance correlation coefficients (CCCs) across BWs ranging 5 to 50. A unique set identified at each BW after removing highly correlated eliminate redundancy. These robust incorporated into multiclass classifier trained distinguish basal cell carcinoma (BCC), Bowen's disease. Six all BWs, with 25 emerging as optimal choice, balancing ability capture meaningful textural details. Additionally, intermediate (20-25) yielded 53 reproducible features. six achieved 90% accuracy AUCs 0.96 0.94 for BCC disease, respectively, compared 76% 0.86 0.80 conventional feature approach. This study highlights critical role enhancing stability provides methodological framework optimizing preprocessing radiomics. By demonstrating integration diagnostic models, we establish promising tool aid non-invasive diagnosis dermatology.
Язык: Английский
Процитировано
0
Meta-Radiology, Год журнала: 2025, Номер unknown, С. 100151 - 100151
Опубликована: Апрель 1, 2025
Язык: Английский
Процитировано
0
European Journal of Nuclear Medicine and Molecular Imaging, Год журнала: 2025, Номер unknown
Опубликована: Апрель 7, 2025
Abstract Purpose This study systematically reviews current evidence on radiogenomics applied to positron emission tomography (PET) imaging across oncological diseases. The primary objective is evaluate how PET-based aids in understanding tumor biology, prognostic stratification, and clinical outcome prediction, while identifying methodological challenges the field. Methods A systematic review was conducted following PRISMA guidelines, focusing English-language studies indexed Scopus, PubMed, Web of Science until October 31, 2024. Inclusion criteria targeted original research articles involving human oncology using radiomics genomics a comprehensive “omics” framework. Data extraction included patient cohorts, radiopharmaceuticals statistical methods. Studies were assessed for rigor reporting quality according scores (RQS 2.0). Results Eighteen 1780 patients included, with 75.8% focused lung cancer. Most retrospective (72.2%) single-center (77.7%). radiopharmaceutical [ 18 F]FDG (88.8%). Key findings demonstrated correlations between PET-derived radiomic features genomic alterations, such as KRAS, EGFR, TGFβ mutations cancer, biomarkers other malignancies. However, systemic shortcomings, including limited external validation, low reproducibility, inadequate harmonization, prevalent. None exceeded 50% RQS maximum score. Conclusion holds significant potential advancing precision by capturing heterogeneity improving stratification. limitations, particularly regarding design data transparency, hinder its applicability. Future should prioritize multicentric designs, robust validations, enhanced standardization fully realize discipline’s potential.
Язык: Английский
Процитировано
0
Clinical Imaging, Год журнала: 2025, Номер 123, С. 110494 - 110494
Опубликована: Май 9, 2025
Язык: Английский
Процитировано
0
Medical Oncology, Год журнала: 2025, Номер 42(7)
Опубликована: Май 27, 2025
Язык: Английский
Процитировано
0