External validation of 18 F-FDG PET-based radiomic models on identification of residual oesophageal cancer after neoadjuvant chemoradiotherapy.

OBJECTIVES: Detection of residual oesophageal cancer after neoadjuvant chemoradiotherapy (nCRT) is important to guide treatment decisions regarding standard oesophagectomy or active surveillance. The aim was to validate previously developed 18 F-FDG PET-based radiomic models to detect residual local tumour and to repeat model development (i.e. 'model extension') in case of poor generalisability. METHODS: This was a retrospective cohort study in patients collected from a prospective multicentre study in four Dutch institutes. Patients underwent nCRT followed by oesophagectomy between 2013 and 2019. Outcome was tumour regression grade (TRG) 1 (0% tumour) versus TRG 2-3-4 (≥1% tumour). Scans were acquired according to standardised protocols. Discrimination and calibration were assessed for the published models with optimism-corrected AUCs >0.77. For model extension, the development and external validation cohorts were combined. RESULTS: Baseline characteristics of the 189 patients included [median age 66 years (interquartile range 60-71), 158/189 male (84%), 40/189 TRG 1 (21%) and 149/189 (79%) TRG 2-3-4] were comparable to the development cohort. The model including cT stage plus the feature 'sum entropy' had best discriminative performance in external validation (AUC 0.64, 95% confidence interval 0.55-0.73), with a calibration slope and intercept of 0.16 and 0.48 respectively. An extended bootstrapped LASSO model yielded an AUC of 0.65 for TRG 2-3-4 detection. CONCLUSION: The high predictive performance of the published radiomic models could not be replicated. The extended model had moderate discriminative ability. The investigated radiomic models appeared inaccurate to detect local residual oesophageal tumour and cannot be used as an adjunct tool for clinical decision-making in patients.

Prediction of Non-Response to Neoadjuvant Chemoradiotherapy in Esophageal Cancer Patients with 18F-FDG PET Radiomics Based Machine Learning Classification.

BACKGROUND: Approximately 26% of esophageal cancer (EC) patients do not respond to neoadjuvant chemoradiotherapy (nCRT), emphasizing the need for pre-treatment selection. The aim of this study was to predict non-response using a radiomic model on baseline 18F-FDG PET. METHODS: Retrospectively, 143 18F-FDG PET radiomic features were extracted from 199 EC patients (T1N1-3M0/T2-4aN0-3M0) treated between 2009 and 2019. Non-response (n = 57; 29%) was defined as Mandard Tumor Regression Grade 4-5 (n = 44; 22%) or interval progression (n = 13; 7%). Randomly, 139 patients (70%) were allocated to explore all combinations of 24 feature selection strategies and 6 classification methods towards the cross-validated average precision (AP). The predictive value of the best-performing model, i.e AP and area under the ROC curve analysis (AUC), was evaluated on an independent test subset of 60 patients (30%). RESULTS: The best performing model had an AP (mean ± SD) of 0.47 ± 0.06 on the training subset, achieved by a support vector machine classifier trained on five principal components of relevant clinical and radiomic features. The model was externally validated with an AP of 0.66 and an AUC of 0.67. CONCLUSION: In the present study, the best-performing model on pre-treatment 18F-FDG PET radiomics and clinical features had a small clinical benefit to identify non-responders to nCRT in EC.

Addition of HER2 and CD44 to 18F-FDG PET-based clinico-radiomic models enhances prediction of neoadjuvant chemoradiotherapy response in esophageal cancer.

OBJECTIVES: To assess the complementary value of human epidermal growth factor receptor 2 (HER2)-related biological tumor markers to clinico-radiomic models in predicting complete response to neoadjuvant chemoradiotherapy (NCRT) in esophageal cancer patients. METHODS: Expression of HER2 was assessed by immunohistochemistry in pre-treatment tumor biopsies of 96 patients with locally advanced esophageal cancer. Five other potentially active HER2-related biological tumor markers in esophageal cancer were examined in a sub-analysis on 43 patients. Patients received at least four of the five cycles of chemotherapy and full radiotherapy regimen followed by esophagectomy. Three reference clinico-radiomic models based on 18F-FDG PET were constructed to predict pathologic response, which was categorized into complete versus incomplete (Mandard tumor regression grade 1 vs. 2-5). The complementary value of the biological tumor markers was evaluated by internal validation through bootstrapping. RESULTS: Pathologic examination revealed 21 (22%) complete and 75 (78%) incomplete responders. HER2 and cluster of differentiation 44 (CD44), analyzed in the sub-analysis, were univariably associated with pathologic response. Incorporation of HER2 and CD44 into the reference models improved the overall performance (R2s of 0.221, 0.270, and 0.225) and discrimination AUCs of 0.759, 0.857, and 0.816. All models exhibited moderate to good calibration. The remaining studied biological tumor markers did not yield model improvement. CONCLUSIONS: Incorporation of HER2 and CD44 into clinico-radiomic prediction models improved NCRT response prediction in esophageal cancer. These biological tumor markers are promising in initial response evaluation. KEY POINTS: • A multimodality approach, integrating independent genomic and radiomic information, is promising to improve prediction of γpCR in patients with esophageal cancer. • HER2 and CD44 are potential biological tumor markers in the initial work-up of patients with esophageal cancer. • Prediction models combining 18F-FDG PET radiomic features with HER2 and CD44 may be useful in the decision to omit surgery after neoadjuvant chemoradiotherapy in patients with esophageal cancer.

The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping.

Background Radiomic features may quantify characteristics present in medical imaging. However, the lack of standardized definitions and validated reference values have hampered clinical use. Purpose To standardize a set of 174 radiomic features. Materials and Methods Radiomic features were assessed in three phases. In phase I, 487 features were derived from the basic set of 174 features. Twenty-five research teams with unique radiomics software implementations computed feature values directly from a digital phantom, without any additional image processing. In phase II, 15 teams computed values for 1347 derived features using a CT image of a patient with lung cancer and predefined image processing configurations. In both phases, consensus among the teams on the validity of tentative reference values was measured through the frequency of the modal value and classified as follows: less than three matches, weak; three to five matches, moderate; six to nine matches, strong; 10 or more matches, very strong. In the final phase (phase III), a public data set of multimodality images (CT, fluorine 18 fluorodeoxyglucose PET, and T1-weighted MRI) from 51 patients with soft-tissue sarcoma was used to prospectively assess reproducibility of standardized features. Results Consensus on reference values was initially weak for 232 of 302 features (76.8%) at phase I and 703 of 1075 features (65.4%) at phase II. At the final iteration, weak consensus remained for only two of 487 features (0.4%) at phase I and 19 of 1347 features (1.4%) at phase II. Strong or better consensus was achieved for 463 of 487 features (95.1%) at phase I and 1220 of 1347 features (90.6%) at phase II. Overall, 169 of 174 features were standardized in the first two phases. In the final validation phase (phase III), most of the 169 standardized features could be excellently reproduced (166 with CT; 164 with PET; and 164 with MRI). Conclusion A set of 169 radiomics features was standardized, which enabled verification and calibration of different radiomics software. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Kuhl and Truhn in this issue.

Repeatability of 18 F-FDG PET radiomic features: A phantom study to explore sensitivity to image reconstruction settings, noise, and delineation method.

BACKGROUND: 18 F-fluoro-2-deoxy-D-Glucose positron emission tomography (18 F-FDG PET) radiomics has the potential to guide the clinical decision making in cancer patients, but validation is required before radiomics can be implemented in the clinical setting. The aim of this study was to explore how feature space reduction and repeatability of 18 F-FDG PET radiomic features are affected by various sources of variation such as underlying data (e.g., object size and uptake), image reconstruction methods and settings, noise, discretization method, and delineation method. METHODS: The NEMA image quality phantom was scanned with various sphere-to-background ratios (SBR), simulating different activity uptakes, including spheres with low uptake, that is, SBR smaller than 1. Furthermore, images of a phantom containing 3D printed inserts reflecting realistic heterogeneity uptake patterns were acquired. Data were reconstructed using various matrix sizes, reconstruction algorithms, and scan durations (noise). For every specific reconstruction and noise level, ten statistically equal replicates were generated. The phantom inserts were delineated using CT and PET-based segmentation methods. A total of 246 radiomic features was extracted from each image dataset. Images were discretized with a fixed number of 64 bins (FBN) and a fixed bin width (FBW) of 0.25 for the high and a FBW of 0.05 for the low uptake data. In terms of feature reduction, we determined the impact of these factors on the composition of feature clusters, which were defined on the basis of Spearman's correlation matrices. To assess feature repeatability, the intraclass correlation coefficient was calculated over the ten replicates. RESULTS: In general, larger spheres with high uptake resulted in better repeatability compared to smaller low uptake spheres. In terms of repeatability, features extracted from heterogeneous phantom inserts were comparable to features extracted from bigger high uptake spheres. For example, for an EARL-compliant reconstruction, larger and smaller high uptake spheres yielded good repeatability for 32% and 30% of the features, while the heterogeneous inserts resulted in 34% repeatable features. For the low uptake spheres, this was the case for 22% and 20% of the features for bigger and smaller spheres, respectively. Images reconstructed with point-spread-function (PSF) resulted in the highest repeatability when compared with OSEM or time-of-flight, for example, 53%, 30%, and 32% of repeatable features, respectively (for unsmoothed data, discretized with FBN, 300 s scan duration). Reducing image noise (increasing scan duration and smoothing) and using CT-based segmentation for the low uptake spheres yielded improved repeatability. FBW discretization resulted in higher repeatability than FBN discretization, for example, 89% and 35% of the features, respectively (for the EARL-compliant reconstruction and larger high uptake spheres). CONCLUSION: Feature space reduction and repeatability of 18 F-FDG PET radiomic features depended on all studied factors. The high sensitivity of PET radiomic features to image quality suggests that a high level of image acquisition and preprocessing standardization is required to be used as clinical imaging biomarker.

Prediction of Response to Neoadjuvant Chemotherapy and Radiation Therapy with Baseline and Restaging 18F-FDG PET Imaging Biomarkers in Patients with Esophageal Cancer.

Purpose To assess the value of baseline and restaging fluorine 18 (18F) fluorodeoxyglucose (FDG) positron emission tomography (PET) radiomics in predicting pathologic complete response to neoadjuvant chemotherapy and radiation therapy (NCRT) in patients with locally advanced esophageal cancer. Materials and Methods In this retrospective study, 73 patients with histologic analysis-confirmed T1/N1-3/M0 or T2-4a/N0-3/M0 esophageal cancer were treated with NCRT followed by surgery (Chemoradiotherapy for Esophageal Cancer followed by Surgery Study regimen) between October 2014 and August 2017. Clinical variables and radiomic features from baseline and restaging 18F-FDG PET were selected by univariable logistic regression and least absolute shrinkage and selection operator. The selected variables were used to fit a multivariable logistic regression model, which was internally validated by using bootstrap resampling with 20 000 replicates. The performance of this model was compared with reference prediction models composed of maximum standardized uptake value metrics, clinical variables, and maximum standardized uptake value at baseline NCRT radiomic features. Outcome was defined as complete versus incomplete pathologic response (tumor regression grade 1 vs 2-5 according to the Mandard classification). Results Pathologic response was complete in 16 patients (21.9%) and incomplete in 57 patients (78.1%). A prediction model combining clinical T-stage and restaging NCRT (post-NCRT) joint maximum (quantifying image orderliness) yielded an optimism-corrected area under the receiver operating characteristics curve of 0.81. Post-NCRT joint maximum was replaceable with five other redundant post-NCRT radiomic features that provided equal model performance. All reference prediction models exhibited substantially lower discriminatory accuracy. Conclusion The combination of clinical T-staging and quantitative assessment of post-NCRT 18F-FDG PET orderliness (joint maximum) provided high discriminatory accuracy in predicting pathologic complete response in patients with esophageal cancer. © RSNA, 2018 Online supplemental material is available for this article.

Predicting Response to Neoadjuvant Chemoradiotherapy in Esophageal Cancer with Textural Features Derived from Pretreatment 18F-FDG PET/CT Imaging.

Adequate prediction of tumor response to neoadjuvant chemoradiotherapy (nCRT) in esophageal cancer (EC) patients is important in a more personalized treatment. The current best clinical method to predict pathologic complete response is SUVmax in 18F-FDG PET/CT imaging. To improve the prediction of response, we constructed a model to predict complete response to nCRT in EC based on pretreatment clinical parameters and 18F-FDG PET/CT-derived textural features. Methods: From a prospectively maintained single-institution database, we reviewed 97 consecutive patients with locally advanced EC and a pretreatment 18F-FDG PET/CT scan between 2009 and 2015. All patients were treated with nCRT (carboplatin/paclitaxel/41.4 Gy) followed by esophagectomy. We analyzed clinical, geometric, and pretreatment textural features extracted from both 18F-FDG PET and CT. The current most accurate prediction model with SUVmax as a predictor variable was compared with 6 different response prediction models constructed using least absolute shrinkage and selection operator regularized logistic regression. Internal validation was performed to estimate the model's performances. Pathologic response was defined as complete versus incomplete response (Mandard tumor regression grade system 1 vs. 2-5). Results: Pathologic examination revealed 19 (19.6%) complete and 78 (80.4%) incomplete responders. Least absolute shrinkage and selection operator regularization selected the clinical parameters: histologic type and clinical T stage, the 18F-FDG PET-derived textural feature long run low gray level emphasis, and the CT-derived textural feature run percentage. Introducing these variables to a logistic regression analysis showed areas under the receiver-operating-characteristic curve (AUCs) of 0.78 compared with 0.58 in the SUVmax model. The discrimination slopes were 0.17 compared with 0.01, respectively. After internal validation, the AUCs decreased to 0.74 and 0.54, respectively. Conclusion: The predictive values of the constructed models were superior to the standard method (SUVmax). These results can be considered as an initial step in predicting tumor response to nCRT in locally advanced EC. Further research in refining the predictive value of these models is needed to justify omission of surgery.

CT image biomarkers to improve patient-specific prediction of radiation-induced xerostomia and sticky saliva.

BACKGROUND AND PURPOSE: Current models for the prediction of late patient-rated moderate-to-severe xerostomia (XER12m) and sticky saliva (STIC12m) after radiotherapy are based on dose-volume parameters and baseline xerostomia (XERbase) or sticky saliva (STICbase) scores. The purpose is to improve prediction of XER12m and STIC12m with patient-specific characteristics, based on CT image biomarkers (IBMs). METHODS: Planning CT-scans and patient-rated outcome measures were prospectively collected for 249 head and neck cancer patients treated with definitive radiotherapy with or without systemic treatment. The potential IBMs represent geometric, CT intensity and textural characteristics of the parotid and submandibular glands. Lasso regularisation was used to create multivariable logistic regression models, which were internally validated by bootstrapping. RESULTS: The prediction of XER12m could be improved significantly by adding the IBM "Short Run Emphasis" (SRE), which quantifies heterogeneity of parotid tissue, to a model with mean contra-lateral parotid gland dose and XERbase. For STIC12m, the IBM maximum CT intensity of the submandibular gland was selected in addition to STICbase and mean dose to submandibular glands. CONCLUSION: Prediction of XER12m and STIC12m was improved by including IBMs representing heterogeneity and density of the salivary glands, respectively. These IBMs could guide additional research to the patient-specific response of healthy tissue to radiation dose.