External validation of a radiomic signature to predict p16 (HPV) status from standard CT images of anal cancer patients.

The paper deals with the evaluation of the performance of an existing and previously validated CT based radiomic signature, developed in oropharyngeal cancer to predict human papillomavirus (HPV) status, in the context of anal cancer. For the validation in anal cancer, a dataset of 59 patients coming from two different centers was collected. The primary endpoint was HPV status according to p16 immunohistochemistry. Predefined statistical tests were performed to evaluate the performance of the model. The AUC obtained here in anal cancer is 0.68 [95% CI (0.32-1.00)] with F1 score of 0.78. This signature is TRIPOD level 4 (57%) with an RQS of 61%. This study provides proof of concept that this radiomic signature has the potential to identify a clinically relevant molecular phenotype (i.e., the HPV-ness) across multiple cancers and demonstrates potential for this radiomic signature as a CT imaging biomarker of p16 status.

Exploring Hypoxia in Prostate Cancer With T2-weighted Magnetic Resonance Imaging Radiomics and Pimonidazole Scoring.

BACKGROUND/AIM: Radiomics involves high throughput extraction of mineable precise quantitative imaging features that serve as non-invasive prognostic or predictive biomarkers. High levels of hypoxia are associated with a poorer prognosis in prostate cancer and limit radiation therapy efficacy. Most patients with prostate cancer undergo magnetic resonance imaging (MRI) as a part of their diagnostics, and T2 imaging is the most utilised imaging method. The aim of this study was to determine whether hypoxia in prostate tumors could be identified using a radiomics model extracted from T2-weighted MR images. MATERIALS AND METHODS: Eighty eight intermediate or high-risk prostate cancer patients were evaluated. Prior to radical prostatectomy, all patients received pimonidazole (PIMO). PIMO hypoxic scores were assigned in whole-mount sections from prostatectomy specimens by an experienced pathologist who was blinded to MRI. The region of interest used for radiomics analysis included the prostatic index tumor. Radiomics extraction yielded 165 features using a special evaluation version of RadiomiX [RadiomiX Research Toolbox version 20180831 (OncoRadiomics SA, Liège, Belgium)] for non-clinical use. Multivariable logistic regression with Elastic Net regularization was utilised using 10 times repeated 10-fold cross-validation to select the best model hyperparameters, optimizing for area under the receiver operating characteristic curve (AUC). RESULTS: The average (out of sample) performance based on the repeated cross validation using the ONESE model yielded an AUC of 0.60±0.2. Shape-based features were the most prominent in the model. CONCLUSION: The development of a radiomics hypoxia model using T2 weighted MR images, standard in the staging of prostate cancer, is possible.

Static FET PET radiomics for the differentiation of treatment-related changes from glioma progression.

PURPOSE: To investigate the potential of radiomics applied to static clinical PET data using the tracer O-(2-[18F]fluoroethyl)-L-tyrosine (FET) to differentiate treatment-related changes (TRC) from tumor progression (TP) in patients with gliomas. PATIENTS AND METHODS: One hundred fifty-one (151) patients with histologically confirmed gliomas and post-therapeutic progressive MRI findings according to the response assessment in neuro-oncology criteria underwent a dynamic amino acid PET scan using the tracer O-(2-[18F]fluoroethyl)-L-tyrosine (FET). Thereof, 124 patients were investigated on a stand-alone PET scanner (data used for model development and validation), and 27 patients on a hybrid PET/MRI scanner (data used for model testing). Mean and maximum tumor to brain ratios (TBRmean, TBRmax) were calculated using the PET data from 20 to 40 min after tracer injection. Logistic regression models were evaluated for the FET PET parameters TBRmean, TBRmax, and for radiomics features of the tumor areas as well as combinations thereof to differentiate between TP and TRC. The best performing models in the validation dataset were finally applied to the test dataset. The diagnostic performance was assessed by receiver operating characteristic analysis. RESULTS: Thirty-seven patients (25%) were diagnosed with TRC, and 114 (75%) with TP. The logistic regression model comprising the conventional FET PET parameters TBRmean and TBRmax resulted in an AUC of 0.78 in both the validation (sensitivity, 64%; specificity, 80%) and the test dataset (sensitivity, 64%; specificity, 80%). The model combining the conventional FET PET parameters and two radiomics features yielded the best diagnostic performance in the validation dataset (AUC, 0.92; sensitivity, 91%; specificity, 80%) and demonstrated its generalizability in the independent test dataset (AUC, 0.85; sensitivity, 81%; specificity, 70%). CONCLUSION: The developed radiomics classifier allows the differentiation between TRC and TP in pretreated gliomas based on routinely acquired static FET PET scans with a high diagnostic accuracy.

An externally validated fully automated deep learning algorithm to classify COVID-19 and other pneumonias on chest computed tomography.

Purpose: In this study, we propose an artificial intelligence (AI) framework based on three-dimensional convolutional neural networks to classify computed tomography (CT) scans of patients with coronavirus disease 2019 (COVID-19), influenza/community-acquired pneumonia (CAP), and no infection, after automatic segmentation of the lungs and lung abnormalities. Methods: The AI classification model is based on inflated three-dimensional Inception architecture and was trained and validated on retrospective data of CT images of 667 adult patients (no infection n=188, COVID-19 n=230, influenza/CAP n=249) and 210 adult patients (no infection n=70, COVID-19 n=70, influenza/CAP n=70), respectively. The model's performance was independently evaluated on an internal test set of 273 adult patients (no infection n=55, COVID-19 n= 94, influenza/CAP n=124) and an external validation set from a different centre (305 adult patients: COVID-19 n=169, no infection n=76, influenza/CAP n=60). Results: The model showed excellent performance in the external validation set with area under the curve of 0.90, 0.92 and 0.92 for COVID-19, influenza/CAP and no infection, respectively. The selection of the input slices based on automatic segmentation of the abnormalities in the lung reduces analysis time (56 s per scan) and computational burden of the model. The Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) score of the proposed model is 47% (15 out of 32 TRIPOD items). Conclusion: This AI solution provides rapid and accurate diagnosis in patients suspected of COVID-19 infection and influenza.

A review in radiomics: Making personalized medicine a reality via routine imaging.

Radiomics is the quantitative analysis of standard-of-care medical imaging; the information obtained can be applied within clinical decision support systems to create diagnostic, prognostic, and/or predictive models. Radiomics analysis can be performed by extracting hand-crafted radiomics features or via deep learning algorithms. Radiomics has evolved tremendously in the last decade, becoming a bridge between imaging and precision medicine. Radiomics exploits sophisticated image analysis tools coupled with statistical elaboration to extract the wealth of information hidden inside medical images, such as computed tomography (CT), magnetic resonance (MR), and/or Positron emission tomography (PET) scans, routinely performed in the everyday clinical practice. Many efforts have been devoted in recent years to the standardization and validation of radiomics approaches, to demonstrate their usefulness and robustness beyond any reasonable doubts. However, the booming of publications and commercial applications of radiomics approaches warrant caution and proper understanding of all the factors involved to avoid "scientific pollution" and overly enthusiastic claims by researchers and clinicians alike. For these reasons the present review aims to be a guidebook of sorts, describing the process of radiomics, its pitfalls, challenges, and opportunities, along with its ability to improve clinical decision-making, from oncology and respiratory medicine to pharmacological and genotyping studies.

Privacy preserving distributed learning classifiers - Sequential learning with small sets of data.

BACKGROUND: Artificial intelligence (AI) typically requires a significant amount of high-quality data to build reliable models, where gathering enough data within a single institution can be particularly challenging. In this study we investigated the impact of using sequential learning to exploit very small, siloed sets of clinical and imaging data to train AI models. Furthermore, we evaluated the capacity of such models to achieve equivalent performance when compared to models trained with the same data over a single centralized database. METHODS: We propose a privacy preserving distributed learning framework, learning sequentially from each dataset. The framework is applied to three machine learning algorithms: Logistic Regression, Support Vector Machines (SVM), and Perceptron. The models were evaluated using four open-source datasets (Breast cancer, Indian liver, NSCLC-Radiomics dataset, and Stage III NSCLC). FINDINGS: The proposed framework ensured a comparable predictive performance against a centralized learning approach. Pairwise DeLong tests showed no significant difference between the compared pairs for each dataset. INTERPRETATION: Distributed learning contributes to preserve medical data privacy. We foresee this technology will increase the number of collaborative opportunities to develop robust AI, becoming the default solution in scenarios where collecting enough data from a single reliable source is logistically impossible. Distributed sequential learning provides privacy persevering means for institutions with small but clinically valuable datasets to collaboratively train predictive AI while preserving the privacy of their patients. Such models perform similarly to models that are built on a larger central dataset.

A Prospectively Validated Prognostic Model for Patients with Locally Advanced Squamous Cell Carcinoma of the Head and Neck Based on Radiomics of Computed Tomography Images.

BACKGROUND: Locoregionally advanced head and neck squamous cell carcinoma (HNSCC) patients have high relapse and mortality rates. Imaging-based decision support may improve outcomes by optimising personalised treatment, and support patient risk stratification. We propose a multifactorial prognostic model including radiomics features to improve risk stratification for advanced HNSCC, compared to TNM eighth edition, the gold standard. PATIENT AND METHODS: Data of 666 retrospective- and 143 prospective-stage III-IVA/B HNSCC patients were collected. A multivariable Cox proportional-hazards model was trained to predict overall survival (OS) using diagnostic CT-based radiomics features extracted from the primary tumour. Separate analyses were performed using TNM8, tumour volume, clinical and biological variables, and combinations thereof with radiomics features. Patient risk stratification in three groups was assessed through Kaplan-Meier (KM) curves. A log-rank test was performed for significance (p-value < 0.05). The prognostic accuracy was reported through the concordance index (CI). RESULTS: A model combining an 11-feature radiomics signature, clinical and biological variables, TNM8, and volume could significantly stratify the validation cohort into three risk groups (p < 0∙01, CI of 0.79 as validation). CONCLUSION: A combination of radiomics features with other predictors can predict OS very accurately for advanced HNSCC patients and improves on the current gold standard of TNM8.

Radiomics in Lung Diseases Imaging: State-of-the-Art for Clinicians.

Artificial intelligence (AI) has increasingly been serving the field of radiology over the last 50 years. As modern medicine is evolving towards precision medicine, offering personalized patient care and treatment, the requirement for robust imaging biomarkers has gradually increased. Radiomics, a specific method generating high-throughput extraction of a tremendous amount of quantitative imaging data using data-characterization algorithms, has shown great potential in individuating imaging biomarkers. Radiomic analysis can be implemented through the following two methods: hand-crafted radiomic features extraction or deep learning algorithm. Its application in lung diseases can be used in clinical decision support systems, regarding its ability to develop descriptive and predictive models in many respiratory pathologies. The aim of this article is to review the recent literature on the topic, and briefly summarize the interest of radiomics in chest Computed Tomography (CT) and its pertinence in the field of pulmonary diseases, from a clinician's perspective.

The application of a workflow integrating the variable reproducibility and harmonizability of radiomic features on a phantom dataset.

Radiomics-the high throughput extraction of quantitative features from medical images and their correlation with clinical and biological endpoints- is the subject of active and extensive research. Although the field shows promise, the generalizability of radiomic signatures is affected significantly by differences in scan acquisition and reconstruction settings. Previous studies reported on the sensitivity of radiomic features (RFs) to test-retest variability, inter-observer segmentation variability, and intra-scanner variability. A framework involving robust radiomics analysis and the application of a post-reconstruction feature harmonization method using ComBat was recently proposed to address these challenges. In this study, we investigated the reproducibility of RFs across different scanners and scanning parameters using this framework. We analysed thirteen scans of a ten-layer phantom that were acquired differently. Each layer was subdivided into sixteen regions of interest (ROIs), and the scans were compared in a pairwise manner, resulting in seventy-eight different scenarios. Ninety-one RFs were extracted from each ROI. As hypothesized, we demonstrate that the reproducibility of a given RF is not a constant but is dependent on the heterogeneity found in the data under analysis. The number (%) of reproducible RFs varied across the pairwise scenarios investigated, having a wide range between 8 (8.8%) and 78 (85.7%) RFs. Furthermore, in contrast to what has been previously reported, and as hypothesized in the robust radiomics analysis framework, our results demonstrate that ComBat cannot be applied to all RFs but rather on a percentage of those-the "ComBatable" RFs-which differed depending on the data being harmonized. The number (%) of reproducible RFs following ComBat harmonization varied across the pairwise scenarios investigated, ranging from 14 (15.4%) to 80 (87.9%) RFs, and was found to depend on the heterogeneity in the data. We conclude that the standardization of image acquisition protocols remains the cornerstone for improving the reproducibility of RFs, and the generalizability of the signatures developed. Our proposed approach helps identify the reproducible RFs across different datasets.

Deciphering the glioblastoma phenotype by computed tomography radiomics.

INTRODUCTION: Glioblastoma (GBM) is the most common malignant primary brain tumour which has, despite extensive treatment, a median overall survival of 15 months. Radiomics is the high-throughput extraction of large amounts of image features from radiographic images, which allows capturing the tumour phenotype in 3D and in a non-invasive way. In this study we assess the prognostic value of CT radiomics for overall survival in patients with a GBM. MATERIALS AND METHODS: Clinical data and pre-treatment CT images were obtained from 218 patients diagnosed with a GBM via biopsy who underwent radiotherapy +/- temozolomide between 2004 and 2015 treated at three independent institutes (n = 93, 62 and 63). A clinical prognostic score (CPS), a simple radiomics model consisting of volume based score (VPS), a complex radiomics prognostic score (RPS) and a combined clinical and radiomics (C + R)PS model were developed. The population was divided into three risk groups for each prognostic score and respective Kaplan-Meier curves were generated. RESULTS: Patient characteristics were broadly comparable. Clinically significant differences were observed with regards to radiation dose, tumour volume and performance status between datasets. Image acquisition parameters differed between institutes. The cross-validated c-indices were moderately discriminative and for the CPS ranged from 0.63 to 0.65; the VPS c-indices ranged between 0.52 and 0.61; the RPS c-indices ranged from 0.57 to 0.64 and the combined clinical and radiomics model resulted in c-indices of 0.59-0.71. CONCLUSION: In this study clinical and CT radiomics features were used to predict OS in GBM. Discrimination between low-, middle- and high-risk patients based on the combined clinical and radiomics model was comparable to previous MRI-based models.

[18F]FDG PET radiomics to predict disease-free survival in cervical cancer: a multi-scanner/center study with external validation.

PURPOSE: To test the performances of native and tumour to liver ratio (TLR) radiomic features extracted from pre-treatment 2-[18F] fluoro-2-deoxy-D-glucose ([18F]FDG) PET/CT and combined with machine learning (ML) for predicting cancer recurrence in patients with locally advanced cervical cancer (LACC). METHODS: One hundred fifty-eight patients with LACC from multiple centers were retrospectively included in the study. Tumours were segmented using the Fuzzy Local Adaptive Bayesian (FLAB) algorithm. Radiomic features were extracted from the tumours and from regions drawn over the normal liver. Cox proportional hazard model was used to test statistical significance of clinical and radiomic features. Fivefold cross validation was used to tune the number of features. Seven different feature selection methods and four classifiers were tested. The models with the selected features were trained using bootstrapping and tested in data from each scanner independently. Reproducibility of radiomics features, clinical data added value and effect of ComBat-based harmonisation were evaluated across scanners. RESULTS: After a median follow-up of 23 months, 29% of the patients recurred. No individual radiomic or clinical features were significantly associated with cancer recurrence. The best model was obtained using 10 TLR features combined with clinical information. The area under the curve (AUC), F1-score, precision and recall were respectively 0.78 (0.67-0.88), 0.49 (0.25-0.67), 0.42 (0.25-0.60) and 0.63 (0.20-0.80). ComBat did not improve the predictive performance of the best models. Both the TLR and the native models performance varied across scanners used in the test set. CONCLUSION: [18F]FDG PET radiomic features combined with ML add relevant information to the standard clinical parameters in terms of LACC patient's outcome but remain subject to variability across PET/CT devices.

Deep learning for the fully automated segmentation of the inner ear on MRI.

Segmentation of anatomical structures is valuable in a variety of tasks, including 3D visualization, surgical planning, and quantitative image analysis. Manual segmentation is time-consuming and deals with intra and inter-observer variability. To develop a deep-learning approach for the fully automated segmentation of the inner ear in MRI, a 3D U-net was trained on 944 MRI scans with manually segmented inner ears as reference standard. The model was validated on an independent, multicentric dataset consisting of 177 MRI scans from three different centers. The model was also evaluated on a clinical validation set containing eight MRI scans with severe changes in the morphology of the labyrinth. The 3D U-net model showed precise Dice Similarity Coefficient scores (mean DSC-0.8790) with a high True Positive Rate (91.5%) and low False Discovery Rate and False Negative Rates (14.8% and 8.49% respectively) across images from three different centers. The model proved to perform well with a DSC of 0.8768 on the clinical validation dataset. The proposed auto-segmentation model is equivalent to human readers and is a reliable, consistent, and efficient method for inner ear segmentation, which can be used in a variety of clinical applications such as surgical planning and quantitative image analysis.

Non-invasive imaging prediction of tumor hypoxia: A novel developed and externally validated CT and FDG-PET-based radiomic signatures.

BACKGROUND: Tumor hypoxia increases resistance to radiotherapy and systemic therapy. Our aim was to develop and validate a disease-agnostic and disease-specific CT (+FDG-PET) based radiomics hypoxia classification signature. MATERIAL AND METHODS: A total of 808 patients with imaging data were included: N = 100 training/N = 183 external validation cases for a disease-agnostic CT hypoxia classification signature, N = 76 training/N = 39 validation cases for the H&N CT signature and N = 62 training/N = 36 validation cases for the Lung CT signature. The primary gross tumor volumes (GTV) were manually defined by experts on CT. In order to dichotomize between hypoxic/well-oxygenated tumors a threshold of 20% was used for the [18F]-HX4-derived hypoxic fractions (HF). A random forest (RF)-based machine-learning classifier/regressor was trained to classify patients as hypoxia-positive/ negative based on radiomic features. RESULTS: A 11 feature "disease-agnostic CT model" reached AUC's of respectively 0.78 (95% confidence interval [CI], 0.62-0.94), 0.82 (95% CI, 0.67-0.96) and 0.78 (95% CI, 0.67-0.89) in three external validation datasets. A "disease-agnostic FDG-PET model" reached an AUC of 0.73 (0.95% CI, 0.49-0.97) in validation by combining 5 features. The highest "lung-specific CT model" reached an AUC of 0.80 (0.95% CI, 0.65-0.95) in validation with 4 CT features, while the "H&N-specific CT model" reached an AUC of 0.84 (0.95% CI, 0.64-1.00) in validation with 15 CT features. A tumor volume-alone model was unable to significantly classify patients as hypoxia-positive/ negative. A significant survival split (P = 0.037) was found between CT-classified hypoxia strata in an external H&N cohort (n = 517), while 117 significant hypoxia gene-CT signature feature associations were found in an external lung cohort (n = 80). CONCLUSION: The disease-specific radiomics signatures perform better than the disease agnostic ones. By identifying hypoxic patients our signatures have the potential to enrich interventional hypoxia-targeting trials.

Diagnosis of Invasive Lung Adenocarcinoma Based on Chest CT Radiomic Features of Part-Solid Pulmonary Nodules: A Multicenter Study.

Background Solid components of part-solid nodules (PSNs) at CT are reflective of invasive adenocarcinoma, but studies describing radiomic features of PSNs and the perinodular region are lacking. Purpose To develop and to validate radiomic signatures diagnosing invasive lung adenocarcinoma in PSNs compared with the Brock, clinical-semantic features, and volumetric models. Materials and Methods This retrospective multicenter study (https://ClinicalTrials.gov, NCT03872362) included 291 patients (median age, 60 years; interquartile range, 55-65 years; 191 women) from January 2013 to October 2017 with 297 PSN lung adenocarcinomas split into training (n = 229) and test (n = 68) data sets. Radiomic features were extracted from the different regions (gross tumor volume [GTV], solid, ground-glass, and perinodular). Random-forest models were trained using clinical-semantic, volumetric, and radiomic features, and an online nodule calculator was used to compute the Brock model. Performances of models were evaluated using standard metrics such as area under the curve (AUC), accuracy, and calibration. The integrated discrimination improvement was applied to assess model performance changes after the addition of perinodular features. Results The radiomics model based on ground-glass and solid features yielded an AUC of 0.98 (95% confidence interval [CI]: 0.96, 1.00) on the test data set, which was significantly higher than the Brock (AUC, 0.83 [95% CI: 0.72, 0.94]; P = .007), clinical-semantic (AUC, 0.90 [95% CI: 0.83, 0.98]; P = .03), volumetric GTV (AUC, 0.87 [95% CI: 0.78, 0.96]; P = .008), and radiomics GTV (AUC, 0.88 [95% CI: 0.80, 0.96]; P = .01) models. It also achieved the best accuracy (93% [95% CI: 84%, 98%]). Both this model and the model with added perinodular features showed good calibration, whereas adding perinodular features did not improve the performance (integrated discrimination improvement, -0.02; P = .56). Conclusion Separating ground-glass and solid CT radiomic features of part-solid nodules was useful in diagnosing the invasiveness of lung adenocarcinoma, yielding a better predictive performance than the Brock, clinical-semantic, volumetric, and radiomics gross tumor volume models. Online supplemental material is available for this article. See also the editorial by Nishino in this issue. Published under a CC BY 4.0 license.

Correction: Computed tomography-derived radiomic signature of head and neck squamous cell carcinoma (peri)tumoral tissue for the prediction of locoregional recurrence and distant metastasis after concurrent chemo-radiotherapy.

[This corrects the article DOI: 10.1371/journal.pone.0232639.].

Computed tomography-derived radiomic signature of head and neck squamous cell carcinoma (peri)tumoral tissue for the prediction of locoregional recurrence and distant metastasis after concurrent chemo-radiotherapy.

INTRODUCTION: In this study, we investigate the role of radiomics for prediction of overall survival (OS), locoregional recurrence (LRR) and distant metastases (DM) in stage III and IV HNSCC patients treated by chemoradiotherapy. We hypothesize that radiomic analysis of (peri-)tumoral tissue may detect invasion of surrounding tissues indicating a higher chance of locoregional recurrence and distant metastasis. METHODS: Two comprehensive data sources were used: the Dutch Cancer Society Database (Alp 7072, DESIGN) and "Big Data To Decide" (BD2Decide). The gross tumor volumes (GTV) were delineated on contrast-enhanced CT. Radiomic features were extracted using the RadiomiX Discovery Toolbox (OncoRadiomics, Liege, Belgium). Clinical patient features such as age, gender, performance status etc. were collected. Two machine learning methods were chosen for their ability to handle censored data: Cox proportional hazards regression and random survival forest (RSF). Multivariable clinical and radiomic Cox/ RSF models were generated based on significance in univariable cox regression/ RSF analyses on the held out data in the training dataset. Features were selected according to a decreasing hazard ratio for Cox and relative importance for RSF. RESULTS: A total of 444 patients with radiotherapy planning CT-scans were included in this study: 301 head and neck squamous cell carcinoma (HNSCC) patients in the training cohort (DESIGN) and 143 patients in the validation cohort (BD2DECIDE). We found that the highest performing model was a clinical model that was able to predict distant metastasis in oropharyngeal cancer cases with an external validation C-index of 0.74 and 0.65 with the RSF and Cox models respectively. Peritumoral radiomics based prediction models performed poorly in the external validation, with C-index values ranging from 0.32 to 0.61 utilizing both feature selection and model generation methods. CONCLUSION: Our results suggest that radiomic features from the peritumoral regions are not useful for the prediction of time to OS, LR and DM.

Systematic Review of Privacy-Preserving Distributed Machine Learning From Federated Databases in Health Care.

Big data for health care is one of the potential solutions to deal with the numerous challenges of health care, such as rising cost, aging population, precision medicine, universal health coverage, and the increase of noncommunicable diseases. However, data centralization for big data raises privacy and regulatory concerns.Covered topics include (1) an introduction to privacy of patient data and distributed learning as a potential solution to preserving these data, a description of the legal context for patient data research, and a definition of machine/deep learning concepts; (2) a presentation of the adopted review protocol; (3) a presentation of the search results; and (4) a discussion of the findings, limitations of the review, and future perspectives.Distributed learning from federated databases makes data centralization unnecessary. Distributed algorithms iteratively analyze separate databases, essentially sharing research questions and answers between databases instead of sharing the data. In other words, one can learn from separate and isolated datasets without patient data ever leaving the individual clinical institutes.Distributed learning promises great potential to facilitate big data for medical application, in particular for international consortiums. Our purpose is to review the major implementations of distributed learning in health care.

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.