Non-invasive decision support for NSCLC treatment using PET/CT radiomics.
Ontology highlight
ABSTRACT:
SUBMITTER: Mu W
PROVIDER: S-EPMC7567795 | biostudies-literature | 2020 Oct
REPOSITORIES: biostudies-literature
Publications
Non-invasive decision support for NSCLC treatment using PET/CT radiomics.
Mu Wei W Jiang Lei L Zhang JianYuan J Shi Yu Y Gray Jhanelle E JE Tunali Ilke I Gao Chao C Sun Yingying Y Tian Jie J Zhao Xinming X Sun Xilin X Gillies Robert J RJ Schabath Matthew B MB
Nature communications 20201016 1
Two major treatment strategies employed in non-small cell lung cancer, NSCLC, are tyrosine kinase inhibitors, TKIs, and immune checkpoint inhibitors, ICIs. The choice of strategy is based on heterogeneous biomarkers that can dynamically change during therapy. Thus, there is a compelling need to identify comprehensive biomarkers that can be used longitudinally to help guide therapy choice. Herein, we report a <sup>18</sup>F-FDG-PET/CT-based deep learning model, which demonstrates high accuracy in ...[more]
Similar Datasets
Project description:BackgroundPrognostic models based on individual patient characteristics can improve treatment decisions and outcome in the future. In many (radiomic) studies, small size and heterogeneity of datasets is a challenge that often limits performance and potential clinical applicability of these models. The current study is example of a retrospective multi-centric study with challenges and caveats. To highlight common issues and emphasize potential pitfalls, we aimed for an extensive analysis of these multi-center pre-treatment datasets, with an additional 18F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) scan acquired during treatment.MethodsThe dataset consisted of 138 stage II-IV non-small cell lung cancer (NSCLC) patients from four different cohorts acquired from three different institutes. The differences between the cohorts were compared in terms of clinical characteristics and using the so-called 'cohort differences model' approach. Moreover, the potential prognostic performances for overall survival of radiomic features extracted from CT or FDG-PET, or relative or absolute differences between the scans at the two time points, were assessed using the LASSO regression method. Furthermore, the performances of five different classifiers were evaluated for all image sets.ResultsThe individual cohorts substantially differed in terms of patient characteristics. Moreover, the cohort differences model indicated statistically significant differences between the cohorts. Neither LASSO nor any of the tested classifiers resulted in a clinical relevant prognostic model that could be validated on the available datasets.ConclusionThe results imply that the study might have been influenced by a limited sample size, heterogeneous patient characteristics, and inconsistent imaging parameters. No prognostic performance of FDG-PET or CT based radiomics models can be reported. This study highlights the necessity of extensive evaluations of cohorts and of validation datasets, especially in retrospective multi-centric datasets.
| S-EPMC6546238 | biostudies-literature
Project description:Purpose: This study aimed to compare the performance of radiomics and deep learning in predicting EGFR mutation status in patients with lung cancer based on PET/CT images, and tried to explore a model with excellent prediction performance to accurately predict EGFR mutation status in patients with non-small cell lung cancer (NSCLC). Method: PET/CT images of 194 NSCLC patients from Xijing Hospital were collected and divided into a training set and a validation set according to the ratio of 7:3. Statistics were made on patients' clinical characteristics, and a large number of features were extracted based on their PET/CT images (4306 radiomics features and 2048 deep learning features per person) with the pyradiomics toolkit and 3D convolutional neural network. Then a radiomics model (RM), a deep learning model (DLM), and a hybrid model (HM) were established. The performance of the three models was compared by receiver operating characteristic (ROC) curves, sensitivity, specificity, accuracy, calibration curves, and decision curves. In addition, a nomogram based on a deep learning score (DS) and the most significant clinical characteristic was plotted. Result: In the training set composed of 138 patients (64 with EGFR mutation and 74 without EGFR mutation), the area under the ROC curve (AUC) of HM (0.91, 95% CI: 0.86-0.96) was higher than that of RM (0.82, 95% CI: 0.75-0.89) and DLM (0.90, 95% CI: 0.85-0.95). In the validation set composed of 57 patients (32 with EGFR mutation and 25 without EGFR mutation), the AUC of HM (0.85, 95% CI: 0.77-0.93) was also higher than that of RM (0.68, 95% CI: 0.52-0.84) and DLM (0.79, 95% CI: 0.67-0.91). In all, HM achieved better diagnostic performance in predicting EGFR mutation status in NSCLC patients than two other models. Conclusion: Our study showed that the deep learning model based on PET/CT images had better performance than radiomics model in diagnosing EGFR mutation status of NSCLC patients based on PET/CT images. Combined with the most statistically significant clinical characteristic (smoking) and deep learning features, our hybrid model had better performance in predicting EGFR mutation types of patients than two other models, which could enable NSCLC patients to choose more personalized treatment schemes.
| S-EPMC9092283 | biostudies-literature
Project description:Tumor blood flow (TBF) measurements in prostate cancer (PCa) provide an integrative index of tumor growth, which could be important for primary diagnosis and therapy response evaluation. 15O-water PET is the non-invasive gold standard but is technically demanding. The aim of this study was to compare the accuracy of three different non-invasive strategies with an invasively measured arterial input function (BSIF): Using image-derived input functions (IDIF) from either 1) a separate heart scan or 2) the pelvic scan or 3) a populations-based input function (PBIF). Nine patients with biopsy-verified PCa scheduled for prostatectomy were included. All patients were characterized with serum levels of PSA (s-PSA), multiparametric magnetic resonance imaging (mpMRI) and post-surgical histopathology Gleason Grade. Dynamic 15O-water was performed of the heart and the pelvic area 15 minutes apart. TBF estimated from both wash-in (K1) and wash-out (k2) constants was calculated using a one-compartmental model. Results: Mean (range) s-PSA was 12 (3-27) ng/mL, Gleason Grade Group was 2.9 (1-5), k2 was 0.44 (0.007-1.2), and K1 was 0.24 (0.07-0.55) mL/mL/min. k2 (BSIF) correlated with s-PSA (r=0.86, P<0.01) and Gleason Grade Group (rho=0.78, P=0.01). BSIF, heart-IDIF and PBIF provided near-identical k2 and K1 (r>0.95, P<0.001) with slopes near unity. The correlations of BSIF and pelvic-IDIF rate constants were good (r>0.95, P<0.001), but individual errors high. In conclusion, non-invasive protocols for 15O-water PET with IDIF or PBIF accurately measures perfusion in prostate cancer and might be useful for evaluation of tumor aggressiveness and treatment response.
| S-EPMC6261877 | biostudies-other
Project description:PurposeDetermination and development of an effective set of models leveraging Artificial Intelligence techniques to generate a system able to support clinical practitioners working with COVID-19 patients. It involves a pipeline including classification, lung and lesion segmentation, as well as lesion quantification of axial lung CT studies.ApproachA deep neural network architecture based on DenseNet is introduced for the classification of weakly-labeled, variable-sized (and possibly sparse) axial lung CT scans. The models are trained and tested on aggregated, publicly available data sets with over 10 categories. To further assess the models, a data set was collected from multiple medical institutions in Colombia, which includes healthy, COVID-19 and patients with other diseases. It is composed of 1,322 CT studies from a diverse set of CT machines and institutions that make over 550,000 slices. Each CT study was labeled based on a clinical test, and no per-slice annotation took place. This enabled a classification into Normal vs. Abnormal patients, and for those that were considered abnormal, an extra classification step into Abnormal (other diseases) vs. COVID-19. Additionally, the pipeline features a methodology to segment and quantify lesions of COVID-19 patients on the complete CT study, enabling easier localization and progress tracking. Moreover, multiple ablation studies were performed to appropriately assess the elements composing the classification pipeline.ResultsThe best performing lung CT study classification models achieved 0.83 accuracy, 0.79 sensitivity, 0.87 specificity, 0.82 F1 score and 0.85 precision for the Normal vs. Abnormal task. For the Abnormal vs COVID-19 task, the model obtained 0.86 accuracy, 0.81 sensitivity, 0.91 specificity, 0.84 F1 score and 0.88 precision. The ablation studies showed that using the complete CT study in the pipeline resulted in greater classification performance, restating that relevant COVID-19 patterns cannot be ignored towards the top and bottom of the lung volume.DiscussionThe lung CT classification architecture introduced has shown that it can handle weakly-labeled, variable-sized and possibly sparse axial lung studies, reducing the need for expert annotations at a per-slice level.ConclusionsThis work presents a working methodology that can guide the development of decision support systems for clinical reasoning in future interventionist or prospective studies.
| S-EPMC9554434 | biostudies-literature
Project description:INTRODUCTION:Only a subgroup of non-small cell lung cancer (NSCLC) patients benefit from treatment using epidermal growth factor receptor (EGFR) tyrosine kinase inhibitors (TKI) such as afatinib. Tumour uptake of [18F]afatinib using positron emission tomography (PET) may identify those patients that respond to afatinib therapy. Therefore, the aim of this study was to find the optimal tracer kinetic model for quantification of [18F]afatinib uptake in NSCLC tumours. METHODS:[18F]Afatinib PET scans were performed in 10 NSCLC patients. The first patient was scanned for the purpose of dosimetry. Subsequent patients underwent a 20-min dynamic [15O]H2O PET scan (370 MBq) followed by a dynamic [18F]afatinib PET scan (342 ± 24 MBq) of 60 or 90 min. Using the Akaike information criterion (AIC), three pharmacokinetic plasma input models were evaluated with both metabolite-corrected sampler-based input and image-derived (IDIF) input functions in combination with discrete blood samples. Correlation analysis of arterial on-line sampling versus IDIF was performed. In addition, perfusion dependency and simplified measures were assessed. RESULTS:Ten patients were included. The injected activity of [18F]afatinib was 341 ± 37 MBq. Fifteen tumours could be identified in the field of view of the scanner. Based on AIC, tumour kinetics were best described using an irreversible two-tissue compartment model and a metabolite-corrected sampler-based input function (Akaike 50%). Correlation of plasma-based input functions with metabolite-corrected IDIF was very strong (r2 = 0.93). The preferred simplified uptake parameter was the tumour-to-blood ratio over the 60- to 90-min time interval (TBR60-90). Tumour uptake of [18F]afatinib was independent of perfusion. CONCLUSION:The preferred pharmacokinetic model for quantifying [18F]afatinib uptake in NSCLC tumours was the 2T3K_vb model. TBR60-90 showed excellent correlation with this model and is the best candidate simplified method. TRIAL REGISTRATION:https://eudract.ema.europa.eu/ nr 2012-002849-38.
| S-EPMC7431492 | biostudies-literature
Project description:Cross-sectional X-ray imaging has become the standard for staging most solid organ malignancies. However, for some malignancies such as urinary bladder cancer, the ability to accurately assess local extent of the disease and understand response to systemic chemotherapy is limited with current imaging approaches. In this study, we explored the feasibility that radiomics-based predictive models using pre- and post-treatment computed tomography (CT) images might be able to distinguish between bladder cancers with and without complete chemotherapy responses. We assessed three unique radiomics-based predictive models, each of which employed different fundamental design principles ranging from a pattern recognition method via deep-learning convolution neural network (DL-CNN), to a more deterministic radiomics feature-based approach and then a bridging method between the two, utilizing a system which extracts radiomics features from the image patterns. Our study indicates that the computerized assessment using radiomics information from the pre- and post-treatment CT of bladder cancer patients has the potential to assist in assessment of treatment response.
| S-EPMC5562694 | biostudies-other
Project description:PurposeTo investigate the performance of pretreatment fluorine 18 (18F) fluorodeoxyglucose PET/CT radiomics in predicting severe immune-related adverse events (irSAEs) among patients with advanced non-small cell lung cancer (NSCLC) treated with immunotherapy, which is important in optimizing treatment plans and alleviating future complications with early interventions.Materials and methodsThe retrospective arm of this study included 146 patients with histologically confirmed stage IIIB-IV NSCLC who were treated with immune checkpoint blockade between June 2011 and December 2017 and who were split into training (n = 97) and test (n = 49) cohorts. A prospective validation arm enrolled 48 patients before initiation of immunotherapy between January 2018 and June 2019 as an independent test cohort. Radiomics features extracted from baseline (preimmunotherapy treatment) PET, CT, and PET/CT fusion images were used to generate a radiomics score (RS) to quantify patient risk for developing irSAEs by an improved least absolute shrinkage and selection operator method. Weighted multivariable logistic regression analysis was then used to develop a nomogram model to predict irSAEs, which was assessed by its calibration, discrimination, and clinical usefulness.ResultsThe radiomics nomogram, incorporating the RS, type of immune checkpoint blockade, and dosing schedule, was able to predict patients with and without irSAEs with area under the receiver operating characteristic curve of 0.92 (95% confidence interval [CI]: 0.86, 0.98), 0.92 (95% CI: 0.86, 0.99), and 0.88 (95% CI: 0.78, 0.97) in the training, test, and prospective validation cohorts, respectively. Decision curve analysis showed that the radiomics nomogram model had the highest overall net benefit.ConclusionA high RS is a significant risk factor for development of irSAEs, demonstrating the value of PET/CT images in predicting irSAEs. By the identification, at baseline, of patients with NSCLC most likely to have irSAEs, treatment plans can be optimized before initiation of immunotherapy.Supplemental material is available for this article.© RSNA, 2020See also the commentary by Yousefi.
| S-EPMC8074998 | biostudies-literature
Project description:ObjectivesTo develop and validate a PET/CT nomogram for preoperative estimation of lymph node (LN) staging in patients with non-small cell lung cancer (NSCLC).MethodsA total of 263 pathologically confirmed LNs from 124 patients with NCSLC were retrospectively analyzed. Positron-emission tomography/computed tomography (PET/CT) examination was performed before treatment according to the clinical schedule. In the training cohort (N = 185), malignancy-related features, such as SUVmax, short-axis diameter (SAD), and CT radiomics features, were extracted from the regions of LN based on the PET/CT scan. The Minimum-Redundancy Maximum-Relevance (mRMR) algorithm and the Least Absolute Shrinkage and Selection Operator (LASSO) regression model were used for feature selection and radiomics score building. The radiomics score (Rad-Score) and SUVmax were incorporated in a PET/CT nomogram using the multivariable logistic regression analysis. The performance of the proposed model was evaluated with discrimination, calibration, and clinical application in an independent testing cohort (N = 78).ResultsThe radiomics scores consisting of 14 selected features were significantly associated with LN status for both training cohort with AUC of 0.849 (95% confidence interval (CI), 0.796-0.903) and testing cohort with AUC of 0.828 (95% CI, 0.782-0.919). The PET/CT nomogram incorporating radiomics score and SUVmax showed moderate improvement of the efficiency with AUC of 0.881 (95% CI, 0.834-0.928) in the training cohort and AUC of 0.872 (95% CI, 0.797-0.946) in the testing cohort. The decision curve analysis indicated that the PET/CT nomogram was clinically useful.ConclusionThe PET/CT nomogram, which incorporates Rad-Score and SUVmax, can improve the diagnostic performance of LN metastasis.Key points• The PET/CT nomogram (Int-Score) based on lymph node (LN) PET/CT images can reliably predict LN status in NSCLC. • Int-Score is a relatively objective diagnostic method, which can play an auxiliary role in the process of clinicians making treatment decisions.
| S-EPMC8270849 | biostudies-literature
Project description:IntroductionImmunotherapy has improved outcomes for patients with non-small cell lung cancer (NSCLC), yet durable clinical benefit (DCB) is experienced in only a fraction of patients. Here, we test the hypothesis that radiomics features from baseline pretreatment 18F-FDG PET/CT scans can predict clinical outcomes of NSCLC patients treated with checkpoint blockade immunotherapy.MethodsThis study included 194 patients with histologically confirmed stage IIIB-IV NSCLC with pretreatment PET/CT images. Radiomics features were extracted from PET, CT, and PET+CT fusion images based on minimum Kullback-Leibler divergence (KLD) criteria. The radiomics features from 99 retrospective patients were used to train a multiparametric radiomics signature (mpRS) to predict DCB using an improved least absolute shrinkage and selection operator (LASSO) method, which was subsequently validated in both retrospective (N = 47) and prospective test cohorts (N = 48). Using these cohorts, the mpRS was also used to predict progression-free survival (PFS) and overall survival (OS) by training nomogram models using multivariable Cox regression analyses with additional clinical characteristics incorporated.ResultsThe mpRS could predict patients who will receive DCB, with areas under receiver operating characteristic curves (AUCs) of 0.86 (95%CI 0.79-0.94), 0.83 (95%CI 0.71-0.94), and 0.81 (95%CI 0.68-0.92) in the training, retrospective test, and prospective test cohorts, respectively. In the same three cohorts, respectively, nomogram models achieved C-indices of 0.74 (95%CI 0.68-0.80), 0.74 (95%CI 0.66-0.82), and 0.77 (95%CI 0.69-0.84) to predict PFS and C-indices of 0.83 (95%CI 0.77-0.88), 0.83 (95%CI 0.71-0.94), and 0.80 (95%CI 0.69-0.91) to predict OS.ConclusionPET/CT-based signature can be used prior to initiation of immunotherapy to identify NSCLC patients most likely to benefit from immunotherapy. As such, these data may be leveraged to improve more precise and individualized decision support in the treatment of patients with advanced NSCLC.
| S-EPMC8663718 | biostudies-literature
Project description:Background: This study investigated the performance of ensemble learning holomic models for the detection of breast cancer, receptor status, proliferation rate, and molecular subtypes from [18F]FDG-PET/CT images with and without incorporating data pre-processing algorithms. Additionally, machine learning (ML) models were compared with conventional data analysis using standard uptake value lesion classification. Methods: A cohort of 170 patients with 173 breast cancer tumors (132 malignant, 38 benign) was examined with [18F]FDG-PET/CT. Breast tumors were segmented and radiomic features were extracted following the imaging biomarker standardization initiative (IBSI) guidelines combined with optimized feature extraction. Ensemble learning including five supervised ML algorithms was utilized in a 100-fold Monte Carlo (MC) cross-validation scheme. Data pre-processing methods were incorporated prior to machine learning, including outlier and borderline noisy sample detection, feature selection, and class imbalance correction. Feature importance in each model was assessed by calculating feature occurrence by the R-squared method across MC folds. Results: Cross validation demonstrated high performance of the cancer detection model (80% sensitivity, 78% specificity, 80% accuracy, 0.81 area under the curve (AUC)), and of the triple negative tumor identification model (85% sensitivity, 78% specificity, 82% accuracy, 0.82 AUC). The individual receptor status and luminal A/B subtype models yielded low performance (0.46-0.68 AUC). SUVmax model yielded 0.76 AUC in cancer detection and 0.70 AUC in predicting triple negative subtype. Conclusions: Predictive models based on [18F]FDG-PET/CT images in combination with advanced data pre-processing steps aid in breast cancer diagnosis and in ML-based prediction of the aggressive triple negative breast cancer subtype.
| S-EPMC8000810 | biostudies-literature