[18F]FDG-PET/CT Radiomics and Artificial Intelligence in Lung Cancer: Technical Aspects and Potential Clinical Applications

Manafi‐Farid, Reyhaneh; Askari, Emran; Shiri, Isaac; Pirich, Christian; Asadi, Masoumeh; Khateri, Maziar; Zaidi, Habib; Beheshti, Mohsen

doi:10.1053/j.semnuclmed.2022.04.004

Cited by 43 publications

(16 citation statements)

References 229 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous studies used machine learning, deep learning, and radiomics for the analysis of [ 18 F]FDG PET/CT images of lung cancer patients in different clinical contexts. They reported AUC values up to 0.97 in the diagnosis of lung cancer using deep learning algorithms [ 7 , 22 ]. In the prediction of treatment response and prognosis, AUC values up to 0.95 were achieved using machine learning algorithms [ 7 , 22 ].…”

Section: Discussionmentioning

confidence: 99%

Machine Learning and Texture Analysis of [18F]FDG PET/CT Images for the Prediction of Distant Metastases in Non-Small-Cell Lung Cancer Patients

Hakkak Moghadam Torbati,

Pellegrino,

Fonti

et al. 2024

Biomedicines

View full text Add to dashboard Cite

The aim of our study was to predict the occurrence of distant metastases in non-small-cell lung cancer (NSCLC) patients using machine learning methods and texture analysis of 18F-labeled 2-deoxy-d-glucose Positron Emission Tomography/Computed Tomography {[18F]FDG PET/CT} images. In this retrospective and single-center study, we evaluated 79 patients with advanced NSCLC who had undergone [18F]FDG PET/CT scan at diagnosis before any therapy. Patients were divided into two independent training (n = 44) and final testing (n = 35) cohorts. Texture features of primary tumors and lymph node metastases were extracted from [18F]FDG PET/CT images using the LIFEx program. Six machine learning methods were applied to the training dataset using the entire panel of features. Dedicated selection methods were used to generate different combinations of five features. The performance of selected machine learning methods applied to the different combinations of features was determined using accuracy, the confusion matrix, receiver operating characteristic (ROC) curves, and area under the curve (AUC). A total of 104 and 78 lesions were analyzed in the training and final testing cohorts, respectively. The support vector machine (SVM) and decision tree methods showed the highest accuracy in the training cohort. Seven combinations of five features were obtained and introduced in the models and subsequently applied to the training and final testing cohorts using the SVM and decision tree. The accuracy and the AUC of the decision tree method were higher than those obtained with the SVM in the final testing cohort. The best combination of features included shape sphericity, gray level run length matrix_run length non-uniformity (GLRLM_RLNU), Total Lesion Glycolysis (TLG), Metabolic Tumor Volume (MTV), and shape compacity. The combination of these features with the decision tree method could predict the occurrence of distant metastases with an accuracy of 74.4% and an AUC of 0.63 in NSCLC patients.

show abstract

Section: Discussionmentioning

confidence: 99%

Machine Learning and Texture Analysis of [18F]FDG PET/CT Images for the Prediction of Distant Metastases in Non-Small-Cell Lung Cancer Patients

Hakkak Moghadam Torbati,

Pellegrino,

Fonti

et al. 2024

Biomedicines

View full text Add to dashboard Cite

show abstract

“…Radiomic features can then be correlated with clinical, histological, and molecular findings. Over the last decade, FDG PET/CT radiomics has been applied to improve staging accuracy, as well as to predict histology, tumor biomarkers, response to therapy, and prognosis [54][55][56][57][58][59]. Mu et al reported the value of pretreatment FDG PET/CT radiomics in predicting severe immune-related adverse events among patients with advanced non-small cell lung cancer treated with immunotherapy, which is important in optimizing treatment strategies and mitigating future complications with early interventions [57].…”

Section: Pet/ct For Lung Cancermentioning

confidence: 99%

Lung Cancer Staging: Imaging and Potential Pitfalls

Erasmus,

Strange,

Agrawal

et al. 2023

Diagnostics

View full text Add to dashboard Cite

Lung cancer is the leading cause of cancer deaths in men and women in the United States. Accurate staging is needed to determine prognosis and devise effective treatment plans. The International Association for the Study of Lung Cancer (IASLC) has made multiple revisions to the tumor, node, metastasis (TNM) staging system used by the Union for International Cancer Control and the American Joint Committee on Cancer to stage lung cancer. The eighth edition of this staging system includes modifications to the T classification with cut points of 1 cm increments in tumor size, grouping of lung cancers associated with partial or complete lung atelectasis or pneumonitis, grouping of tumors with involvement of a main bronchus regardless of distance from the carina, and upstaging of diaphragmatic invasion to T4. The N classification describes the spread to regional lymph nodes and no changes were proposed for TNM-8. In the M classification, metastatic disease is divided into intra- versus extrathoracic metastasis, and single versus multiple metastases. In order to optimize patient outcomes, it is important to understand the nuances of the TNM staging system, the strengths and weaknesses of various imaging modalities used in lung cancer staging, and potential pitfalls in image interpretation.

show abstract

“…The eld of radiomics, a non-invasive framework to extract high-dimensional quantitative features from medical images and to build predictive/prognostic models via machine-learning pipelines [5], is being extensively applied in positron emission tomography (PET) [6], including lung cancer [7]. Although promising results have been reported in the differential diagnosis of lung cancer [8], histological subtyping [9], treatment response assessment [10], and prognosis analysis [11], still, there remains signi cant concerns about i) the poor reproducibility, ii) inaccurate prediction, and iii) limited generalizability of radiomics studies caused by variations of imaging parameter, imbalanced distributions of data, and the lack of multi-center validation [12][13][14].…”

Section: Introductionmentioning

confidence: 99%

Impact of harmonization and oversampling methods on radiomics analysis of multi-center imbalanced datasets: Application to PET-based prediction of lung cancer subtypes

Shiri²,

Yousefirizi

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Purpose To evaluate the impact of harmonization and oversampling methods on multi-center imbalanced datasets, with specific application to PET-based radiomics modeling for histologic subtype prediction in non-small cell lung cancer (NSCLC). Methods The study included 245 patients with adenocarcinoma (ADC) and 78 patients with squamous cell carcinoma (SCC) from 4 centers. Utilizing 1502 radiomics features per patient, we trained, validated, and externally tested 4 machine-learning classifiers, to investigate the effect of no harmonization (NoH) or 4 harmonization methods, paired with no oversampling (NoO) or 5 oversampling methods on subtype prediction. Model performance was evaluated using the average area under the ROC curve (AUROC) and G-mean via 5 times 5-fold cross-validations. Statistical comparisons of the combined models against baseline (NoH+NoO) were performed for each fold of cross-validation using the DeLong test. Results The number of cross-combinations with both AUROC and G-mean outperforming baseline in internal validation and external testing was 15, 4, 2, and 7 (out of 29) for random forest (RF), linear discriminant analysis (LDA), logistic regression (LR), and support vector machine (SVM), respectively. ComBat harmonization combined with oversampling (SMOTE) via RF yielded better performance than baseline (AUROC and G-mean of internal validation: 0.725 vs. 0.608 and 0.625 vs. 0.398; external testing: 0.637 vs. 0.567 and 0.363 vs. 0.234), though statistical significances were not observed. Conclusion Applying harmonization and oversampling methods in multi-center imbalanced datasets can improve NSCLC-subtype prediction, but varies widely across classifiers. We have created open-source comparisons of harmonization and oversampling on different classifiers for comprehensive evaluations in different studies.

show abstract

[18F]FDG-PET/CT Radiomics and Artificial Intelligence in Lung Cancer: Technical Aspects and Potential Clinical Applications

Cited by 43 publications

References 229 publications

Machine Learning and Texture Analysis of [18F]FDG PET/CT Images for the Prediction of Distant Metastases in Non-Small-Cell Lung Cancer Patients

Machine Learning and Texture Analysis of [18F]FDG PET/CT Images for the Prediction of Distant Metastases in Non-Small-Cell Lung Cancer Patients

Lung Cancer Staging: Imaging and Potential Pitfalls

Impact of harmonization and oversampling methods on radiomics analysis of multi-center imbalanced datasets: Application to PET-based prediction of lung cancer subtypes

Contact Info

Product

Resources

About