Search

PurposeTo develop and interpret optimal predictive models to identify epidermal growth factor receptor (EGFR) mutation status and subtypes in patients with lung adenocarcinoma based on multicentric 18F-FDG PET/CT data, and further construct a prognostic model to predict their clinical outcome.MethodsThe 18F-FDG PET/CT imaging and clinical characters of 767 patients with lung adenocarcinoma from 4 cohorts were collected. Seventy-six radiomics candidates using cross-combination method to identity EGFR mutation status and subtypes were built. Further, Shapley additive explanations and local interpretable model-agnostic explanations were used for optimal models’ interpretation. Moreover, in order to predict the overall survival, a multivariate Cox proportional hazard model based on handcrafted radiomics features and clinical characteristics was constructed. The predictive performance and clinical net benefit of the models were evaluated via area under receiver operating characteristic (AUC), C-index and decision curve analysis. ResultsAmong the 76 radiomics candidates, light gradient boosting machine classifier (LGBM) combined with recursive feature elimination wrapped LGBM feature selection method achieved best performance in predicting EGFR mutation status (AUC reached 0.80, 0.61, 0.71 in the internal test cohort and two external test cohorts, respectively). And extreme gradient boosting classifier combined with support vector machine feature selection method achieved best performance in predicting EGFR subtypes (AUC reached 0.76, 0.63, 0.61 in the internal test cohort and two external test cohorts, respectively). The C-index of the Cox proportional hazard model achieved 0.863.ConclusionsThe integration of cross-combination method and the external validation from multi-center data achieved a good prediction and generalization performance in predicting EGFR mutation status and its subtypes. The combination of handcrafted radiomics features and clinical factors achieved good performance in predicting prognosis. With the urgent needs of multicentric 18F-FDG PET/CT trails, robust and explainable radiomics models have great potential in decision making and prognosis prediction of lung adenocarcinoma.

ObjectiveDeep learning-based radiomics (DLR) has achieved great success in medical image analysis and has been considered a replacement for conventional radiomics that relies on handcrafted features. In this study, we aimed to explore the capability of DLR for the prediction of 5-year progression-free survival (PFS) in advanced nasopharyngeal carcinoma (NPC) using pretreatment PET/CT images.MethodsA total of 257 patients (170/87 patients in internal/external cohorts) with advanced NPC (TNM stage III or IVa) were enrolled. We developed an end-to-end multi-modality DLR model, in which a 3D convolutional neural network was optimized to extract deep features from pretreatment PET/CT images and predict the probability of 5-year PFS. The TNM stage, as a high-level clinical feature, could be integrated into our DLR model to further improve the prognostic performance. For a comparison between conventional radiomics and DLR, 1,456 handcrafted features were extracted, and optimal conventional radiomics methods were selected from 54 cross-combinations of six feature selection methods and nine classification methods. In addition, risk group stratification was performed with clinical signature, conventional radiomics signature, and DLR signature.ResultsOur multi-modality DLR model using both PET and CT achieved higher prognostic performance (area under the receiver operating characteristic curve (AUC) = 0.842 ± 0.034 and 0.823 ± 0.012 for the internal and external cohorts) than the optimal conventional radiomics method (AUC = 0.796 ± 0.033 and 0.782 ± 0.012). Furthermore, the multi-modality DLR model outperformed single-modality DLR models using only PET (AUC = 0.818 ± 0.029 and 0.796 ± 0.009) or only CT (AUC = 0.657 ± 0.055 and 0.645 ± 0.021). For risk group stratification, the conventional radiomics signature and DLR signature enabled significant difference between the high- and low-risk patient groups in both the internal and external cohorts (p < 0.001), while the clinical signature failed in the external cohort (p = 0.177).ConclusionOur study identified potential prognostic tools for survival prediction in advanced NPC, which suggests that DLR could provide complementary values to the current TNM staging.

BackgroundBreast cancer is a heterogeneous disease, and the human epidermal growth factor receptor 2 (HER2) expression may vary considerably between primary and metastatic lesions, or even within a single lesion. Repeated biopsies cannot always be performed. In this feasibility trial, we assessed whether a novel 68Ga-NOTA-MAL-MZHER2 (68Ga-HER2) affibody PET/CT could determine the HER2 status of each lesion if there was a clinical need for it.Methods68Ga-HER2 affibody PET/CT was performed in breast cancer patients if HER2 status remained unclear after standard examinations (including bone scan, 18F-FDG PET/CT, CT, and feasible biopsy). All available images for each patient were evaluated through an independent review of two committee-certified radiologists with nuclear medicine expertise. In case of discrepancy, adjudication by a third radiologist was performed as needed. All radiologists were blinded to the clinical information.ResultsTwenty-four patients were enrolled. 68Ga-HER2 affibody PET/CT was requested by physicians due to the following reasons: 6 with multiple primary cancers, 13 with metastases not amenable to biopsy or repeated biopsy, 6 with inconsistent HER2 status between primary and metastatic lesions, and 4 with different HER2 status within different metastases. The final PET report revealed that the 68Ga-HER2 affibody tumor uptake was considered positive in 16 patients, negative in 7 patients, and equivocal in one patient. The heterogeneity of 68Ga-HER2 affibody uptake was observed, with a maximal 8.5-fold difference within one patient and a maximal 11-fold difference between patients. 68Ga-HER2 affibody PET/CT demonstrated a high diagnostic accuracy in differentiating HER2-enriched breast cancer, with a sensitivity of 91.7% and a specificity of 84.6%, regardless of prior lines of anti-HER2 therapies.Conclusion68Ga-HER2 affibody PET/CT imaging could provide valuable information on HER2 expression of each tumor in the body of patients, which may help in personalized clinical decision-making. Its value is now under systemic assessment.

ObjectivesMantle cell lymphoma (MCL) represents a group of highly heterogeneous tumors, leading to a poor prognosis. Early prognosis prediction may guide the choice of therapeutic regimen. Thus, the purpose of this study was to investigate the potential application value of heterogeneity index (HI) in predicting the prognosis of MCL.MethodsA total of 83 patients with histologically proven MCL who underwent baseline fluorine-18-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) were retrospectively enrolled. The clinicopathologic index and PET/CT metabolic parameters containing maximum and mean standard uptake value (SUVmax and SUVmean), metabolic tumor volume (MTV), total lesion glycolysis (TLG), and HI were evaluated. Receiver operating characteristic (ROC) curve analyses were performed to determine the optimal cutoff values of the parameters for progression-free survival (PFS) and overall survival (OS). Univariate and multivariate Cox regression were used to assess relationships between risk factors and recurrence. Kaplan–Meier plots were applied for survival analyses.ResultsIn univariate analyses, age [HR = 2.51, 95% CI = 1.20–5.24, p = 0.041 for body weight (BW)] and HI-BW (HR = 4.17, 95% CI = 1.00–17.38, p = 0.050) were significantly correlated with PFS. In multivariate analyses, age (HR = 2.61, 95% CI = 1.25–5.47, p = 0.011 for BW) and HI-BW (HR = 4.41, 95% CI = 1.06–18.41, p = 0.042) were independent predictors for PFS, but not for OS. B symptoms (HR = 5.00, 95% CI = 1.16–21.65, p = 0.031 for BW) were an independent prognostic factor for OS, but not for PFS. The other clinicopathologic index and PET/CT metabolic parameters were not related to outcome survival in MCL.ConclusionThe age and HI derived from baseline PET/CT parameters were significantly correlated with PFS in MCL patients.

BackgroundThe accurate definition of gross tumor volume (GTV) of esophageal squamous cell carcinoma (ESCC) can promote precise irradiation field determination, and further achieve the radiotherapy curative effect. This retrospective study is intended to assess the applicability of leveraging deep learning-based method to automatically define the GTV from 3D 18F-FDG PET/CT images of patients diagnosed with ESCC.MethodsWe perform experiments on a clinical cohort with 164 18F-FDG PET/CT scans. The state-of-the-art esophageal GTV segmentation deep neural net is first employed to delineate the lesion area on PET/CT images. Afterwards, we propose a novel equivalent truncated elliptical cone integral method (ETECIM) to estimate the GTV value. Indexes of Dice similarity coefficient (DSC), Hausdorff distance (HD), and mean surface distance (MSD) are used to evaluate the segmentation performance. Conformity index (CI), degree of inclusion (DI), and motion vector (MV) are used to assess the differences between predicted and ground truth tumors. Statistical differences in the GTV, DI, and position are also determined.ResultsWe perform 4-fold cross-validation for evaluation, reporting the values of DSC, HD, and MSD as 0.72 ± 0.02, 11.87 ± 4.20 mm, and 2.43 ± 0.60 mm (mean ± standard deviation), respectively. Pearson correlations (R2) achieve 0.8434, 0.8004, 0.9239, and 0.7119 for each fold cross-validation, and there is no significant difference (t = 1.193, p = 0.235) between the predicted and ground truth GTVs. For DI, a significant difference is found (t = −2.263, p = 0.009). For position assessment, there is no significant difference (left-right in x direction: t = 0.102, p = 0.919, anterior–posterior in y direction: t = 0.221, p = 0.826, and cranial–caudal in z direction: t = 0.569, p = 0.570) between the predicted and ground truth GTVs. The median of CI is 0.63, and the gotten MV is small.ConclusionsThe predicted tumors correspond well with the manual ground truth. The proposed GTV estimation approach ETECIM is more precise than the most commonly used voxel volume summation method. The ground truth GTVs can be solved out due to the good linear correlation with the predicted results. Deep learning-based method shows its promising in GTV definition and clinical radiotherapy application.

ObjectivesThe accurate assessment of lymph node metastases (LNMs) and the preoperative nodal (N) stage are critical for the precise treatment of patients with gastric cancer (GC). The diagnostic performance, however, of current imaging procedures used for this assessment is sub-optimal. Our aim was to investigate the value of preoperative 18F-FDG PET/CT radiomic features to predict LNMs and the N stage.MethodsWe retrospectively collected clinical and 18F-FDG PET/CT imaging data of 185 patients with GC who underwent total or partial radical gastrectomy. Patients were allocated to training and validation sets using the stratified method at a fixed ratio (8:2). There were 2,100 radiomic features extracted from the 18F-FDG PET/CT scans. After selecting radiomic features by the random forest, relevancy-based, and sequential forward selection methods, the BalancedBagging ensemble classifier was established for the preoperative prediction of LNMs, and the OneVsRest classifier for the N stage. The performance of the models was primarily evaluated by the AUC and accuracy, and validated by the independent validation methods. Analysis of the feature importance and the correlation were also conducted. We also compared the predictive performance of our radiomic models to that with the contrast-enhanced CT (CECT) and 18F-FDG PET/CT.ResultsThere were 185 patients—127 men, 58 women, with the median age of 62, and an age range of 22–86 years. One CT feature and one PET feature were selected to predict LNMs and achieved the best performance (AUC: 82.2%, accuracy: 85.2%). This radiomic model also detected some LNMs that were missed in CECT (19.6%) and 18F-FDG PET/CT (35.7%). For predicting the N stage, four CT features and one PET feature were selected (AUC: 73.7%, accuracy: 62.3%). Of note, a proportion of patients in the validation set whose LNMs were incorrectly staged by CECT (57.4%) and 18F-FDG PET/CT (55%) were diagnosed correctly by our radiomic model.ConclusionWe developed and validated two machine learning models based on the preoperative 18F-FDG PET/CT images that have a predictive value for LNMs and the N stage in GC. These predictive models show a promise to offer a potentially useful adjunct to current staging approaches for patients with GC.

ObjectivesMicrosatellite instability (MSI) status is an important hallmark for prognosis prediction and treatment recommendation of colorectal cancer (CRC). To address issues due to the invasiveness of clinical preoperative evaluation of microsatellite status, we investigated the value of preoperative 18F-FDG PET/CT radiomics with machine learning for predicting the microsatellite status of colorectal cancer patients.MethodsA total of 173 patients that underwent 18F-FDG PET/CT scans before operations were retrospectively analyzed in this study. The microsatellite status for each patient was identified as microsatellite instability-high (MSI-H) or microsatellite stable (MSS), according to the test for mismatch repair gene proteins with immunohistochemical staining methods. There were 2,492 radiomic features in total extracted from 18F-FDG PET/CT imaging. Then, radiomic features were selected through multivariate random forest selection and univariate relevancy tests after handling the imbalanced dataset through the random under-sampling method. Based on the selected features, we constructed a BalancedBagging model based on Adaboost classifiers to identify the MSI status in patients with CRC. The model performance was evaluated by the area under the curve (AUC), sensitivity, specificity, and accuracy on the validation dataset.ResultsThe ensemble model was constructed based on two radiomic features and achieved an 82.8% AUC for predicting the MSI status of colorectal cancer patients. The sensitivity, specificity, and accuracy were 83.3, 76.3, and 76.8%, respectively. The significant correlation of the selected two radiomic features with multiple effective clinical features was identified (p < 0.05).Conclusion18F-FDG PET/CT radiomics analysis with the machine learning model provided a quantitative, efficient, and non-invasive mechanism for identifying the microsatellite status of colorectal cancer patients, which optimized the treatment decision support.

objectiveDespite the heterogeneous biology of pancreatic cancer, similar surveillance schemas have been used. Identifying the high recurrence risk population and conducting prompt intervention may improve prognosis and prolong overall survival.MethodsOne hundred fifty-six resectable pancreatic cancer patients who had undergone 18F-FDG PET/CT from January 2013 to December 2018 were retrospectively reviewed. The patients were categorized into a training cohort (n = 109) and a validation cohort (n = 47). LIFEx software was used to extract radiomic features from PET/CT. The risk stratification system was based on predictive factors for recurrence, and the index of prediction accuracy was used to reflect both the discrimination and calibration.ResultsOverall, seven risk factors comprising the rad-score and clinical variables that were significantly correlated with relapse were incorporated into the final risk stratification system. The 1-year recurrence-free survival differed significantly among the low-, intermediate-, and high-risk groups (85.5, 24.0, and 9.1%, respectively; p < 0.0001). The C-index of the risk stratification system in the development cohort was 0.890 (95% CI, 0.835–0.945).ConclusionThe 18F-FDG PET/CT-based radiomic features and clinicopathological factors demonstrated good performance in predicting recurrence after pancreatectomy in pancreatic cancer patients, providing a strong recommendation for an adequate adjuvant therapy course in all patients. The high-risk recurrence population should proceed with closer follow-up in a clinical setting.

ObjectiveThe purpose of this study was to employ dual tracers 16α-[18F]fluoro-17β-estradiol (18F-FES) and [18F]fluorodeoxyglucose (18F-FDG) as imaging biomarkers in predicting progression-free survival (PFS) in ER-positive metastatic breast cancer (MBC) patients receiving fulvestrant therapy.MethodsWe retrospectively analyzed 35 HR+HER2- MBC patients who underwent 18F-FES and 18F-FDG PET/CT scans prior to fulvestrant therapy in our center. The SUVmax across all metastatic lesions on the PET/CT were assessed. The heterogeneity of ER expression was assigned by the presence of any 18F-FES negative lesions for patients with entirely 18F-FES positive lesions categorized into two groups by the median ratio of FES/FDG SUVmax, low FES/FDG, and high FES/FDG. PFS were estimated by the Kaplan-Meier method and compared by the log-rank test. Univariate and multivariate analyses were performed using the Cox proportional hazard model.ResultsIn total, 12 patients had both 18F-FES negative and positive lesions, indicating the heterogeneity of ER expression in metastatic lesions. These patients had a low median PFS of 5.5 months (95% CI 2.3–8.7). Of patients with entirely 18F-FES positive lesions, 11 had a low FES/FDG, and 12 had a high FES/FDG. These groups had a median PFS of 29.4 months (95% CI 2.3–56.5) and 14.7 months (95% CI 10.9–18.5), respectively. The patients were stratified in three categories based on incorporating both 18F-FES and 18F-FDG imaging results that were significantly correlated with PFS by univariate analysis (P < 0.001) and multivariate analysis (P = 0.006).Conclusion18F-FES and 18F-FDG PET could serve as prognostic imaging biomarkers for ER-positive MBC patients treated with fulvestrant therapy.

Purpose: To develop and interpret optimal predictive models to identify epidermal growth factor receptor (EGFR) mutation status and subtypes in patients with lung adenocarcinoma based on multicentric 18F-FDG PET/CT data, and further construct a prognostic model to predict their clinical outcome. Methods: The 18F-FDG PET/CT imaging and clinical characters of 767 patients with lung adenocarcinoma from 4 cohorts were collected. Seventy-six radiomics candidates using cross-combination method to identity EGFR mutation status and subtypes were built. Further, Shapley additive explanations and local interpretable model-agnostic explanations were used for optimal models' interpretation. Moreover, in order to predict the overall survival, a multivariate Cox proportional hazard model based on handcrafted radiomics features and clinical characteristics was constructed. The predictive performance and clinical net benefit of the models were evaluated via area under receiver operating characteristic (AUC), C-index and decision curve analysis. Results: Among the 76 radiomics candidates, light gradient boosting machine classifier (LGBM) combined with recursive feature elimination wrapped LGBM feature selection method achieved best performance in predicting EGFR mutation status (AUC reached 0.80, 0.61, 0.71 in the internal test cohort and two external test cohorts, respectively). And extreme gradient boosting classifier combined with support vector machine feature selection method achieved best performance in predicting EGFR subtypes (AUC reached 0.76, 0.63, 0.61 in the internal test cohort and two external test cohorts, respectively). The C-index of the Cox proportional hazard model achieved 0.863. Conclusions: The integration of cross-combination method and the external validation from multi-center data achieved a good prediction and generalization performance in predicting EGFR mutation status and its subtypes. The combination of handcrafted radiomics features and clinical factors achieved good performance in predicting prognosis. With the urgent needs of multicentric 18F-FDG PET/CT trails, robust and explainable radiomics models have great potential in decision making and prognosis prediction of lung adenocarcinoma. [ABSTRACT FROM AUTHOR]