Objectives: By comparing the prognostic performance of F-FDG PET/CT-based radiomics combining dose features [Includes Dosiomics feature and the dose volume histogram (DVH) features] with that of conventional radiomics in head and neck cancer (HNC), multidimensional prognostic models were constructed to investigate the overall survival (OS) in HNC.
Materials And Methods: A total of 220 cases from four centres based on the Cancer Imaging Archive public dataset were used in this study, 2260 radiomics features and 1116 dosiomics features and 8 DVH features were extracted for each case, and classified into seven different models of PET, CT, Dose, PET+CT, PET+Dose, CT+Dose and PET+CT+Dose. Features were selected by univariate Cox and Spearman correlation coefficients, and the selected features were brought into the least absolute shrinkage and selection operator (LASSO)-Cox model. A nomogram was constructed to visually analyse the prognostic impact of the incorporated dose features. C-index and Kaplan-Meier curves (log-rank analysis) were used to evaluate and compare these models.
Results: The cases from the four centres were divided into three different training and validation sets according to the hospitals. The PET+CT+Dose model had C-indexes of 0.873 (95% CI 0.812-0.934), 0.759 (95% CI 0.663-0.855) and 0.835 (95% CI 0.745-0.925) in the validation set respectively, outperforming the rest models overall. The PET+CT+Dose model did well in classifying patients into high- and low-risk groups under all three different sets of experiments (p < 0.05).
Conclusion: Multidimensional model of radiomics features combining dosiomics features and DVH features showed high prognostic performance for predicting OS in patients with HNC.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9925656 | PMC |
| http://dx.doi.org/10.1186/s13550-023-00959-6 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
PET-CT-based host metabolic (PETMet) features are associated with pathologic response in gastroesophageal adenocarcinoma.
Eur J Surg Oncol
January 2025
Division of Surgical Oncology, Department of Surgery, Northwell Health, New Hyde Park, NY, USA; Gastric and Mixed Tumor Service, Department of Surgery, Memorial Sloan Kettering Cancer Center, New York, NY, USA. Electronic address:
Background: F-FDG PET-CT-based host metabolic (PETMet) profiling of non-tumor tissue is a novel approach to incorporate the patient-specific response to cancer into clinical algorithms.
Materials And Methods: A prospectively maintained institutional database of gastroesophageal cancer patients was queried for pretreatment PET-CTs, demographics, and clinicopathologic variables. F-FDG PET avidity was measured in 9 non-tumor tissue types (liver, spleen, 4 muscles, 3 fat locations).
Semiquantitative 2-[F]FDG PET/CT-based parameters role in lymphoma.
Front Med (Lausanne)
December 2024
Dipartimento di Radiodiagnostica e Radioterapia, Fondazione Policlinico Universitario A. Gemelli IRCCS, Rome, Italy.
2-deoxy-2-[F]-fluoro-D-glucose (2-[F]FDG) positron emission tomography/computed tomography (PET/CT) plays a crucial role in the management of lymphoma in different settings, such as staging disease, assessing response to therapy, predicting prognosis, and planning RT. Beside visual analysis, several semiquantitative parameters were introduced to study lymphoma with promising results. These parameters can represent different disease characteristics, like body composition (such as sarcopenic index), dissemination of disease (Dmax), tumor burden (including metabolic tumor volume) and texture features.
View Article and Find Full Text PDFNon-invasive Prediction of Lymph Node Metastasis in NSCLC Using Clinical, Radiomics, and Deep Learning Features From F-FDG PET/CT Based on Interpretable Machine Learning.
Acad Radiol
December 2024
PET/CT Department, The Second Affiliated Hospital of Harbin Medical University, 246 Xuefu Road, Nangang District, Harbin, Heilongjiang, PR China. Electronic address:
Purpose: This study aimed to develop and evaluate a machine learning model combining clinical, radiomics, and deep learning features derived from PET/CT imaging to predict lymph node metastasis (LNM) in patients with non-small cell lung cancer (NSCLC). The model's interpretability was enhanced using Shapley additive explanations (SHAP).
Methods: A total of 248 NSCLC patients who underwent preoperative PET/CT scans were included and divided into training, test, and external validation sets.
F-FDG PET/CT-based habitat radiomics combining stacking ensemble learning for predicting prognosis in hepatocellular carcinoma: a multi-center study.
BMC Cancer
November 2024
Department of Molecular Imaging and Nuclear Medicine, Tianjin Medical University Cancer Institute and Hospital, Tianjin, 300060, China.
Article Synopsis
- - The study developed habitat radiomic models to predict overall survival in patients with hepatocellular carcinoma (HCC) by analyzing intratumoral heterogeneity using F-FDG PET/CT images.
- - Researchers analyzed data from 137 HCC patients, employing k-means clustering to identify intratumoral habitats and extracting 4032 radiomic features, ultimately creating multiple predictive models using machine learning techniques.
- - The best model, combining radiomic and clinical data, showed improved prediction accuracy for overall survival, achieving a C-index of 0.747 and outperforming other models in long-term survival predictions.
A F-FDG PET/CT-based deep learning-radiomics-clinical model for prediction of cervical lymph node metastasis in esophageal squamous cell carcinoma.
Cancer Imaging
November 2024
Thoracic Surgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan province, China.
Article Synopsis
- An AI-based model was developed to predict cervical lymph node metastasis (CLNM) in patients with esophageal squamous cell carcinoma (ESCC) using Radiomics and deep learning features from PET/CT images, combined with clinical data.
- The study involved 300 ESCC patients for training and testing, plus an additional 111 patients for external validation; various machine learning algorithms were tested, with logistic regression being the final model chosen.
- The final DL-Radiomics-Clinical (DRC) model showed the best performance metrics, including an AUC of 0.955 and high accuracy rates, indicating its potential as a non-invasive tool for predicting CLNM in ESCC patients.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!