Search

Background: Accurate, noninvasive, and reliable assessment of epidermal growth factor receptor (EGFR) mutation status and EGFR molecular subtypes is essential for treatment plan selection and individualized therapy in lung adenocarcinoma (LUAD). Radiomics models based on 18F‐FDG PET/CT have great potential in identifying EGFR mutation status and EGFR subtypes in patients with LUAD. The validation of multi‐center data, model visualization, and interpretation are significantly important for the management, application and trust of machine learning predictive models. However, few EGFR‐related research involved model visualization and interpretation, and multi‐center trial. Purpose: To develop explainable optimal predictive models based on handcrafted radiomics features (HRFs) extracted from multi‐center 18F‐FDG PET/CT to predict EGFR mutation status and molecular subtypes in LUAD. Methods: Baseline 18F‐FDG PET/CT images of 383 LUAD patients from three hospitals and one public data set were collected. Further, 1808 HRFs were extracted from the primary tumor regions using Pyradiomics. Predictive models were built based on cross‐combination of seven feature selection methods and seven machine learning algorithms. Yellowbrick and explainable artificial intelligence technology were used for model visualization and interpretation. Receiver operating characteristic curve, classification report and confusion matrix were used for model performance evaluation. Clinical applicability of the optimal models was assessed by decision curve analysis. Results: STACK feature selection method combined with light gradient boosting machine (LGBM) reached optimal performance in identifying EGFR mutation status ([area under the curve] AUC = 0.81 in the internal test cohort; AUC = 0.62 in the external test cohort). Random forest feature selection method combined with LGBM reached optimal performance in predicting EGFR mutation molecular subtypes (AUC = 0.89 in the internal test cohort; AUC = 0.61 in the external test cohort). Conclusions: Explainable machine learning models combined with radiomics features extracted from multi‐center/scanner 18F‐FDG PET/CT have certain potential to identify EGFR mutation status and subtypes in LUAD, which might be helpful to the treatment of LUAD. [ABSTRACT FROM AUTHOR]

Purpose: Our study intended to explore the correlation between HER2 alterations and 18F-FDG PET/CT metabolic parameters and their prognostic value in EGFR-negative non-small-cell lung cancer (NSCLC) patients detected by next-generation sequencing (NGS). Methods: NGS assay was performed in 1737 NSCLC patients, a total of 88 HER2 alterations and 176 negative HER2 with EGFR-negative patients were randomly selected for this study. Results: When the HER2 status with EGFR-negative group was analyzed, multivariate analysis showed that smoking status, primary tumor SUVmax (pSUVmax) < 13.03 and stage were the independent deterministic factors of HER2 alterations. Multivariate cox regression analysis revealed that HER2 status, age, smoking status and stage were independent risk factors for overall survival (OS) in EGFR-negative NSCLC patients with different HER2 status. When the HER2 alterations group was separately analyzed, multivariate analysis demonstrated that low pSUVmax < 15.32 and histology were the independent deterministic factors of HER2 mutation. Multivariate cox regression analysis revealed that pSUVmax, smoking status, nodal involvement and treatment methods were independent risk factors for OS in EGFR-negative NSCLC patients with HER2 alterations. Conclusion: The study revealed that low pSUVmax was associated with HER2 alterations in EGFR-negative NSCLC patients, moreover HER2 mutation and HER2 amplification exhibited distinct 18F-FDG metabolic and clinical characteristics. Furthermore, it explored the prognostic value of HER2 alterations and 18F-FDG PET/CT metabolic parameters of pSUVmax in EGFR-negative NSCLC patients. [ABSTRACT FROM AUTHOR]

Background: Accurate, noninvasive, and reliable assessment of epidermal growth factor receptor (EGFR) mutation status and EGFR molecular subtypes is essential for treatment plan selection and individualized therapy in lung adenocarcinoma (LUAD). Radiomics models based on 18 F-FDG PET/CT have great potential in identifying EGFR mutation status and EGFR subtypes in patients with LUAD. The validation of multi-center data, model visualization, and interpretation are significantly important for the management, application and trust of machine learning predictive models. However, few EGFR-related research involved model visualization and interpretation, and multi-center trial., Purpose: To develop explainable optimal predictive models based on handcrafted radiomics features (HRFs) extracted from multi-center 18 F-FDG PET/CT to predict EGFR mutation status and molecular subtypes in LUAD., Methods: Baseline 18 F-FDG PET/CT images of 383 LUAD patients from three hospitals and one public data set were collected. Further, 1808 HRFs were extracted from the primary tumor regions using Pyradiomics. Predictive models were built based on cross-combination of seven feature selection methods and seven machine learning algorithms. Yellowbrick and explainable artificial intelligence technology were used for model visualization and interpretation. Receiver operating characteristic curve, classification report and confusion matrix were used for model performance evaluation. Clinical applicability of the optimal models was assessed by decision curve analysis., Results: STACK feature selection method combined with light gradient boosting machine (LGBM) reached optimal performance in identifying EGFR mutation status ([area under the curve] AUC = 0.81 in the internal test cohort; AUC = 0.62 in the external test cohort). Random forest feature selection method combined with LGBM reached optimal performance in predicting EGFR mutation molecular subtypes (AUC = 0.89 in the internal test cohort; AUC = 0.61 in the external test cohort)., Conclusions: Explainable machine learning models combined with radiomics features extracted from multi-center/scanner 18 F-FDG PET/CT have certain potential to identify EGFR mutation status and subtypes in LUAD, which might be helpful to the treatment of LUAD., (© 2024 American Association of Physicists in Medicine.)

Objectives: To investigate the potential of 2-deoxy-2( 18 F)fluoro-d-glucose ( 18 F-FDG) combined positron emission tomography and computed tomography (PET/CT) in predicting programmed cell death ligand-1 (PDL1) expression status in pulmonary lesions of advanced non-small-cell lung cancer (NSCLC)., Materials and Methods: This retrospective study includes 133 untreated stage IIIB-IV NSCLC patients who underwent pulmonary lesion biopsy for PDL1 immunochemistry 1-4 weeks after 18 F-FDG PET/CT scanning, randomly assigned to cohorts for modelling and validation of PDL1 expression predictors. Mean and maximum standard uptake values (pSUVmean and pSUVmax), metabolic tumour volume (pMTV), and total lesion glycolysis (pTLG) of primary lesions were determined. PDL1 expression in pulmonary lesions (pPDL1) was determined using tumour proportion score (TPS), and pPDL1 TPS < 1%, 1-49 %, and ≥ 50 % were considered as pPDL1-negative, pPDL1-moderate, and pPDL1-strong, respectively., Results: pSUVmean and pSUVmax values were increased with the increase of pPDL1 levels, whereas pMTV and pTLG values were not associated with pPDL1 levels. In the modelling cohort, we found that pSUVmax rather than pSUVmean was an independent predictor for pPDL1-negative, pPDL1-moderate, and pPDL1-strong, whereas pSUVmax < 14.4, 14.4-17.5, and > 17.5 were suggested as predictors for pPDL1-negative, pPDL1-moderate, and pPDL1-strong, respectively (odds ratio: 4.82, 3.92, and 4.45, respectively; P = 0.002, 0.021, and 0.020, respectively). In the validation cohort, pSUVmax < 14.4, 14.4-17.5, and > 17.5 showed significantly high probabilities of being pPDL1-negative, pPDL1-moderate, and pPDL1-strong, respectively (P = 0.006). The accuracies of pSUVmax < 14.4, 14.4-17.5, and > 17.5 predicting pPDL1-negative, pPDL1-moderate, and pPDL1-strong, respectively, in validation cohort, were 66.7 %, 75.8 %, and 84.8 %, respectively., Conclusion: pSUVmax on 18 F-FDG PET/CT is a potential biomarker for pPDL1 TPS < 1%, 1-49 %, and ≥ 50 % in untreated stage IIIB-IV NSCLC, and therefore may be helpful for determining immunotherapeutic strategy for advanced NSCLC., (Copyright © 2020 Elsevier B.V. All rights reserved.)

The quantitative relationship between iodine and glucose metabolism in metastases from differentiated thyroid cancer (DTC) remains unknown. Aim of the prospective study was to establish the value of 18 F-FDG PET/CT in predicting 131 I-avidity of metastases from DTC before the first radioiodine therapy. A total of 121 postoperative DTC patients with elevated stimulated serum thyroglobulin (ssTg) who underwent 131 I adjuvant therapy or therapy after 18 F-FDG PET/CT scan were enrolled. The Receiver operating characteristic curve was established to create an optimal cut-off point and evaluate the value of SUVmax for predicting 131 I-avidity. In our study, the median SUVmax in 131 I-nonavid metastatic target lesions was also significantly higher than that in 131 I-avid metastatic target lesions (5.37 vs. 3.30; P = 0.000). At a cut-off value of 4.0 in SUVmax, the area under curve was 0.62 with the sensitivity, specificity, positive predictive value and negative predictive value of 75.3%, 56.7%, 76.1%, and 54.8%, respectively. These results suggest that 18 F-FDG PET/CT may be of great value in identifying metastases in postoperative DTC patients with elevated ssTg before 131 I administration, leading to an improved management of disease. 18 F-FDG positive metastatic DTC with SUVmax of greater than 4.0 possesses higher probability of non-avidity to radioiodine.

Objective: Radioiodine ((131)I) is considered an effective and low-risk therapeutic radionuclide for differentiated thyroid carcinoma (DTC); however, dilemmas exist in the optimization of indications, pre-treatment thyroid stimulating hormone (TSH) stimulation, dose decision, as well as in the treatment of (131)I-refractory disease. Refined strategies on (131)I treatment for DTC based on late evidence and novel insights are greatly needed., Conclusion: The indications of (131)I ablation continue to be refined with a better understanding of the risks and benefits. For pre-treatment TSH stimulation, recombinant human thyrotropin presents a better choice as it improves the quality of life, but is indicated only for ablation of the thyroid remnant and follow-up. Decreased doses of (131)I seem to be more appropriate in patients without gross residual disease or metastases, but maximal doses are suggested in patients with advanced disease. Imaging procedures contributing to decision-making for patients with advanced DTC also continue to be modified. As for the (131)I-refractory disease, there is a trend to increase (131)I uptake and retention by using additional therapeutic agents like kinase inhibitors with encouraging results.