Early Detection of Residual/Recurrent Lung Malignancies on Post-Radiation FDG PET/CT DOI Creative Commons
Liyuan Chen, Avanka Lowe, Jing Wang

et al.

Algorithms, Journal Year: 2024, Volume and Issue: 17(10), P. 435 - 435

Published: Oct. 1, 2024

Positron Emission Tomography/Computed Tomography (PET/CT) using Fluorodeoxyglucose (FDG) is an important imaging modality for assessing treatment outcomes in patients with pulmonary malignant neoplasms undergoing radiation therapy. However, distinguishing between benign post-radiation changes and residual or recurrent malignancies on PET/CT images challenging. Leveraging the potential of artificial intelligence (AI), we aimed to develop a hybrid fusion model integrating radiomics Convolutional Neural Network (CNN) architectures improve differentiation images. We retrospectively collected PET/CTs identified labels residual/recurrent lesions from 95 lung cancer who received Firstly, developed separate CNN models handcrafted self-learning features, respectively. Then, build more reliable model, fused probabilities two through evidential reasoning approach derive final prediction probability. Five-folder cross-validation was performed evaluate proposed radiomics, CNN, models. Overall, outperformed other terms sensitivity, specificity, accuracy, area under curve (AUC) values 0.67, 0.72, 0.69, Evaluation results three AI suggest that features learned may provide complementary information malignancy identification PET/CT.

Language: Английский

Prediction of EGFR mutation status and its subtypes in non-small cell lung cancer based on 18F-FDG PET/CT radiological features DOI

Yishuo Fan,

Yuang Liu,

Xiaohui Ouyang

et al.

Nuclear Medicine Communications, Journal Year: 2025, Volume and Issue: 46(4), P. 326 - 336

Published: Jan. 20, 2025

Prediction of epidermal growth factor receptor (EGFR) mutation status and subtypes in patients with non-small cell lung cancer (NSCLC) based on 18 F-fluorodeoxyglucose ( F-FDG) PET/computed tomography (CT) radiomics features. Retrospective analysis 201 NSCLC F-FDG PET/CT EGFR genetic testing was carried out. Radiomics features clinical factors were used to construct a combined model for identifying status. Mutation/wild-type models trained training cohort n = 129) validated an internal validation 41) vs external 50). A second predicting the 19/21 locus also built evaluated subset mutations (training cohort, 55; 14). The predictive performance net benefit assessed by area under curve (AUC) subjects, nomogram, calibration decision curve. AUC distinguishing 0.864 0.806 0.791 test sets respectively, site 0.971 0.867 respectively. curves individual showed better predictions (Brier score <0.25). Decision that had application. can predict patients, guiding targeted therapy, facilitate precision medicine development.

Language: Английский

Citations

1
Insights into radiomics: impact of feature selection and classification DOI Creative Commons
Alessandra Perniciano, Andrea Loddo, Cecilia Di Ruberto

et al.

Multimedia Tools and Applications, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 15, 2024

Radiomics is an innovative discipline in medical imaging that uses advanced quantitative feature extraction from radiological images to provide a non-invasive method of interpreting the intricate biological panorama diseases. This takes advantage unique characteristics imaging, where radiation or ultrasound combines with tissues, reveal disease features and important biomarkers are invisible human eye. plays crucial role healthcare, spanning diagnosis, prognosis, recurrences, treatment response assessment, personalized medicine. systematic approach includes image preprocessing, segmentation, extraction, selection, classification, evaluation. survey attempts shed light on roles selection classification play discovering forecasting directions despite challenges posed by high dimensionality (i.e., when data contains huge number features). By analyzing 47 relevant research articles, this study has provided several insights into key techniques used across different stages radiology workflow. The findings indicate 27 articles utilized SVM classifier, while 23 surveyed studies LASSO approach. demonstrates how these particular methodologies have been widely research. assessment did, however, also point out areas require more research, such as evaluating stability algorithms adopting novel approaches like ensemble hybrid methods. Additionally, we examine some emerging subfields within field radiomics.

Language: Английский

Citations

4
A model for prediction of recurrence of non-small cell lung cancer based on clinical data and CT imaging characteristics DOI
Xinfeng Yu, Dengfa Yang, Gang Xu

et al.

Clinical Imaging, Journal Year: 2025, Volume and Issue: unknown, P. 110416 - 110416

Published: Jan. 1, 2025

Language: Английский

Citations

0
Imaging of Lung Cancer Staging: TNM 9 Updates DOI
Lauren T. Erasmus, Chad D. Strange, Jitesh Ahuja

et al.

Seminars in Ultrasound CT and MRI, Journal Year: 2024, Volume and Issue: unknown

Published: July 1, 2024

Language: Английский

Citations

2
Predicting Regional Recurrence and Prognosis in Stereotactic Body Radiation Therapy-Treated Clinical Stage I Non-small Cell Lung Cancer Using a Radiomics Model Constructed With Surgical Data DOI
Jianjiao Ni,

Hongru Chen,

Yu Lu

et al.

International Journal of Radiation Oncology*Biology*Physics, Journal Year: 2024, Volume and Issue: 120(4), P. 1096 - 1106

Published: June 25, 2024

Language: Английский

Citations

1
A deep learning-informed interpretation of why and when dose metrics outside the PTV can affect the risk of distant metastasis in SBRT NSCLC patients DOI Creative Commons
D. Dudáš, Thomas J. Dilling, Issam El Naqa

et al.

Radiation Oncology, Journal Year: 2024, Volume and Issue: 19(1)

Published: Sept. 27, 2024

Language: Английский

Citations

1
Imaging Assessment of Interventional Therapies in Lung and Liver DOI
Jennifer H. Huang, Paul B. Shyn

Interventional oncology 360, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 16

Published: Jan. 1, 2024

Language: Английский

Citations

0
Early Detection of Residual/Recurrent Lung Malignancies on Post-Radiation FDG PET/CT DOI Creative Commons
Liyuan Chen, Avanka Lowe, Jing Wang

et al.

Algorithms, Journal Year: 2024, Volume and Issue: 17(10), P. 435 - 435

Published: Oct. 1, 2024

Positron Emission Tomography/Computed Tomography (PET/CT) using Fluorodeoxyglucose (FDG) is an important imaging modality for assessing treatment outcomes in patients with pulmonary malignant neoplasms undergoing radiation therapy. However, distinguishing between benign post-radiation changes and residual or recurrent malignancies on PET/CT images challenging. Leveraging the potential of artificial intelligence (AI), we aimed to develop a hybrid fusion model integrating radiomics Convolutional Neural Network (CNN) architectures improve differentiation images. We retrospectively collected PET/CTs identified labels residual/recurrent lesions from 95 lung cancer who received Firstly, developed separate CNN models handcrafted self-learning features, respectively. Then, build more reliable model, fused probabilities two through evidential reasoning approach derive final prediction probability. Five-folder cross-validation was performed evaluate proposed radiomics, CNN, models. Overall, outperformed other terms sensitivity, specificity, accuracy, area under curve (AUC) values 0.67, 0.72, 0.69, Evaluation results three AI suggest that features learned may provide complementary information malignancy identification PET/CT.

Language: Английский

Citations

0