Image Biomarker Standardization Initiative Research Articles

Radiomics Studies on Ischemic Stroke and Carotid Atherosclerotic Disease: A Reporting Quality Assessment.

Objective: To assess the reporting quality of radiomics studies on ischemic stroke, intracranial and carotid atherosclerotic disease using the Image Biomarker Standardization Initiative (IBSI) reporting guidelines with the aim of finding avenues of improvement for future publications. Method: PubMed database was searched to identify relevant radiomics studies. Of 560 articles, 41 original research articles were included in this analysis. Based on IBSI radiomics reporting guidelines, checklists for CT-based and MRI-based studies were created to allow a structured and comprehensive evaluation of each study's adherence to these guidelines. Results: The main topics covered by the included radiomics studies were ischemic stroke, intracranial artery disease, and carotid atherosclerotic disease. The reporting checklist median score was 17/40 for the 20 CT-based radiomics studies and 22.5/50 for the 20 MRI-based studies. Basic items like imaging modality, region of interest, and image biomarker set utilized were included in all studies. However, details regarding image acquisition and reconstruction, post-acquisition image processing, and image biomarkers computation were inconsistently detailed across studies. Conclusion: The overall reporting quality of the included radiomics studies was suboptimal. These findings underscore a pressing need for improved reporting practices in radiomics research, to ensure validation and reproducibility of results. Our study provides insights into current reporting standards and highlights specific areas where adherence to IBSI guidelines could be significantly improved.

The Image Biomarker Standardization Initiative: Standardized Convolutional Filters for Reproducible Radiomics and Enhanced Clinical Insights.

Filters are commonly used to enhance specific structures and patterns in images, such as vessels or peritumoral regions, to enable clinical insights beyond the visible image using radiomics. However, their lack of standardization restricts reproducibility and clinical translation of radiomics decision support tools. In this special report, teams of researchers who developed radiomics software participated in a three-phase study (September 2020 to December 2022) to establish a standardized set of filters. The first two phases focused on finding reference filtered images and reference feature values for commonly used convolutional filters: mean, Laplacian of Gaussian, Laws and Gabor kernels, separable and nonseparable wavelets (including decomposed forms), and Riesz transformations. In the first phase, 15 teams used digital phantoms to establish 33 reference filtered images of 36 filter configurations. In phase 2, 11 teams used a chest CT image to derive reference values for 323 of 396 features computed from filtered images using 22 filter and image processing configurations. Reference filtered images and feature values for Riesz transformations were not established. Reproducibility of standardized convolutional filters was validated on a public data set of multimodal imaging (CT, fluorodeoxyglucose PET, and T1-weighted MRI) in 51 patients with soft-tissue sarcoma. At validation, reproducibility of 486 features computed from filtered images using nine configurations × three imaging modalities was assessed using the lower bounds of 95% CIs of intraclass correlation coefficients. Out of 486 features, 458 were found to be reproducible across nine teams with lower bounds of 95% CIs of intraclass correlation coefficients greater than 0.75. In conclusion, eight filter types were standardized with reference filtered images and reference feature values for verifying and calibrating radiomics software packages. A web-based tool is available for compliance checking.

Advancing noninvasive glioma classification with diffusion radiomics: Exploring the impact of signal intensity normalization.

This study investigates the influence of diffusion-weighted Magnetic Resonance Imaging (DWI-MRI) on radiomic-based prediction of glioma types according to molecular status and assesses the impact of DWI intensity normalization on model generalizability. Radiomic features, compliant with image biomarker standardization initiative standards, were extracted from preoperative MRI of 549 patients with diffuse glioma, known IDH, and 1p19q-status. Anatomical sequences (T1, T1c, T2, FLAIR) underwent N4-Bias Field Correction (N4) and WhiteStripe normalization (N4/WS). Apparent diffusion coefficient (ADC) maps were normalized using N4 or N4/z-score. Nine machine-learning algorithms were trained for multiclass prediction of glioma types (IDH-mutant 1p/19q codeleted, IDH-mutant 1p/19q non-codeleted, IDH-wild type). Four approaches were compared: Anatomical, anatomical + ADC naive, anatomical + ADC N4, and anatomical + ADC N4/z-score. The University of California San Francisco (UCSF)-glioma dataset (n = 409) was used for external validation. Naïve-Bayes algorithms yielded overall the best performance on the internal test set. Adding ADC radiomics significantly improved AUC from 0.79 to 0.86 (P = .011) for the IDH-wild-type subgroup, but not for the other 2 glioma subgroups (P > .05). In the external UCSF dataset, the addition of ADC radiomics yielded a significantly higher AUC for the IDH-wild-type subgroup (P ≤ .001): 0.80 (N4/WS anatomical alone), 0.81 (anatomical + ADC naive), 0.81 (anatomical + ADC N4), and 0.88 (anatomical + ADC N4/z-score) as well as for the IDH-mutant 1p/19q non-codeleted subgroup (P < .012 each). ADC radiomics can enhance the performance of conventional MRI-based radiomic models, particularly for IDH-wild-type glioma. The benefit of intensity normalization of ADC maps depends on the type and context of the used data.

Achieving imaging and computational reproducibility on multiparametric MRI radiomics features in brain tumor diagnosis: phantom and clinical validation.

The Image Biomarker Standardization Initiative has helped improve the computational reproducibility of MRI radiomics features. Nonetheless, the MRI sequences and features with high imaging reproducibility are yet to be established. To determine reproducible multiparametric MRI radiomics features across test-retest, multi-scanner, and computational reproducibility comparisons, and to evaluate their clinical value in brain tumor diagnosis. To assess reproducibility, T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), and diffusion-weighted imaging (DWI) were acquired from three 3-T MRI scanners using standardized phantom, and radiomics features were extracted using two computational algorithms. Reproducible radiomics features were selected when the concordance correlation coefficient value above 0.9 across multiple sessions, scanners, and computational algorithms. Random forest classifiers were trained with reproducible features (n = 117) and validated in a clinical cohort (n = 50) to evaluate whether features with high reproducibility improved the differentiation of glioblastoma from primary central nervous system lymphomas (PCNSLs). Radiomics features from T2WI demonstrated higher repeatability (65-94%) than those from DWI (38-48%) or T1WI (2-92%). Across test-retest, multi-scanner, and computational comparisons, T2WI provided 41 reproducible features, DWI provided six, and T1WI provided two. The performance of the classification model with reproducible features was higher than that using non-reproducible features in both training set (AUC, 0.916 vs. 0.877) and validation set (AUC, 0.957 vs. 0.869). Radiomics features with high reproducibility across multiple sessions, scanners, and computational algorithms were identified, and they showed higher diagnostic performance than non-reproducible radiomics features in the differentiation of glioblastoma from PCNSL. By identifying the radiomics features showing higher multi-machine reproducibility, our results also demonstrated higher radiomics diagnostic performance in the differentiation of glioblastoma from PCNSL, paving the way for further research designs and clinical application in neuro-oncology. • Highly reproducible radiomics features across multiple sessions, scanners, and computational algorithms were identified using phantom and applied to clinical diagnosis. • Radiomics features from T2-weighted imaging were more reproducible than those from T1-weighted and diffusion-weighted imaging. • Radiomics features with good reproducibility had better diagnostic performance for brain tumors than features with poor reproducibility.

Standardized Radiomics Analysis of Clinical Myocardial Perfusion Stress SPECT Images to Identify Coronary Artery Calcification.

Myocardial perfusion (MP) stress single-photon emission computed tomography (SPECT) is an established diagnostic test for patients suspected of coronary artery disease (CAD). Meanwhile, coronary artery calcification (CAC) scoring obtained from diagnostic CT is a highly sensitive test, offering incremental diagnostic information in identifying patients with significant CAD yet normal MP stress SPECT (MPSS) scans. However, after decades of wide utilization of MPSS, CAC is not commonly reimbursed (e.g. by the CMS), nor widely deployed in community settings. We studied the potential of complementary information deduced from the radiomics analysis of normal MPSS scans in predicting the CAC score. We collected data from 428 patients with normal (non-ischemic) MPSS (99mTc-sestamibi; consensus reading). A nuclear medicine physician verified iteratively reconstructed images (attenuation-corrected) to be free from fixed perfusion defects and artifactual attenuation. Three-dimensional images were automatically segmented into four regions of interest (ROIs), including myocardium and three vascular segments (left anterior descending [LAD]-left circumference [LCX]-right coronary artery [RCA]). We used our software package, standardized environment for radiomics analysis (SERA), to extract 487 radiomic features in compliance with the image biomarker standardization initiative (IBSI). Isotropic cubic voxels were discretized using fixed bin-number discretization (eight schemes). We first performed blind-to-outcome feature selection focusing on a priori usefulness, dynamic range, and redundancy of features. Subsequently, we performed univariate and multivariate machine learning analyses to predict CAC scores from i) selected radiomic features, ii) 10 clinical features, and iii) combined radiomics + clinical features. Univariate analysis invoked Spearman correlation with Benjamini-Hotchberg false-discovery correction. The multivariate analysis incorporated stepwise linear regression, where we randomly selected a 15% test set and divided the other 85% of data into 70% training and 30% validation sets. Training started from a constant (intercept) model, iteratively adding/removing features (stepwise regression), invoking the Akaike information criterion (AIC) to discourage overfitting. Validation was run similarly, except that the training output model was used as the initial model. We randomized training/validation sets 20 times, selecting the best model using log-likelihood for evaluation in the test set. Assessment in the test set was performed thoroughly by running the entire operation 50 times, subsequently employing Fisher's method to verify the significance of independent tests. Unsupervised feature selection significantly reduced 8×487 features to 56. In univariate analysis, no feature survived the false-discovery rate (FDR) to directly correlate with CAC scores. Applying Fisher's method to the multivariate regression results demonstrated combining radiomics with the clinical features to enhance the significance of the prediction model across all cardiac segments. Conclusions: Our standardized and statistically robust multivariate analysis demonstrated significant prediction of the CAC score for all cardiac segments when combining MPSS radiomic features with clinical features, suggesting radiomics analysis can add diagnostic or prognostic value to standard MPSS for wide clinical usage.

An imaging-based machine learning model outperforms clinical risk scores for prognosis of cirrhotic variceal bleeding.

To develop and validate a machine learning model based on contrast-enhanced CT to predict the risk of occurrence of the composite clinical endpoint (hospital-based intervention or death) in cirrhotic patients with acute variceal bleeding (AVB). This retrospective study enrolled 330 cirrhotic patients with AVB between January 2017 and December 2020 from three clinical centers. Contrast-enhanced CT and clinical data were collected. Centers A and B were divided 7:3 into a training set and an internal test set, and center C served as a separate external test set. A well-trained deep learning model was applied to segment the liver and spleen. Then, we extracted 106 original features of the liver and spleen separately based on the Image Biomarker Standardization Initiative (IBSI). We constructed the Liver-Spleen (LS) model based on the selected radiomics features. The performance of LS model was evaluated by receiver operating characteristics and calibration curves. The clinical utility of models was analyzed using decision curve analyses (DCA). The LS model demonstrated the best diagnostic performance in predicting the composite clinical endpoint of AVB in patients with cirrhosis, with an AUC of 0.782 (95% CI 0.650-0.882) and 0.789 (95% CI 0.674-0.878) in the internal test and external test groups, respectively. Calibration curves and DCA indicated the LS model had better performance than traditional clinical scores. A novel machine learning model outperforms previously known clinical risk scores in assessing the prognosis of cirrhotic patients with AVB CLINICAL RELEVANCE STATEMENT: The Liver-Spleen model based on contrast-enhanced CT has proven to be a promising tool to predict the prognosis of cirrhotic patients with acute variceal bleeding, which can facilitate decision-making and personalized therapy in clinical practice. • The Liver-Spleen machine learning model (LS model) showed good performance in assessing the clinical composite endpoint of cirrhotic patients with AVB (AUC ≥ 0.782, sensitivity ≥ 80%). • The LS model outperformed the clinical scores (AUC ≤ 0.730, sensitivity ≤ 70%) in both internal and external test cohorts.

Limited impact of discretization/interpolation parameters on the predictive power of CT radiomic features in a surgical cohort of pancreatic cancer patients.

To explore the variation of the discriminative power of CT (Computed Tomography) radiomic features (RF) against image discretization/interpolation in predicting early distant relapses (EDR) after upfront surgery. Data of 144 patients with pre-surgical high contrast CT were processed consistently with IBSI (Image Biomarker Standardization Initiative) guidelines. Image interpolation/discretization parameters were intentionally changed, including cubic voxel size (0.21-27 mm3) and binning (32-128 grey levels) in a 15 parameter's sets. After excluding RF with poor inter-observer delineation agreement (ICC < 0.80) and not negligible inter-scanner variability, the variation of 80 RF against discretization/interpolation was first quantified. Then, their ability in classifying patients with early distant relapses (EDR, < 10months, previously assessed at the first quartile value of time-to-relapse) was investigated in terms of AUC (Area Under Curve) variation for those RF significantly associated to EDR. Despite RF variability against discretization/interpolation parameters was large and only 30/80 RF showed %COV < 20 (%COV = 100*STDEV/MEAN), AUC changes were relatively limited: for 30 RF significantly associated with EDR (AUC values around 0.60-0.70), the mean values of SD of AUC variability and AUC range were 0.02 and 0.05 respectively. AUC ranges were between 0.00 and 0.11, with values ≤ 0.05 in 16/30 RF. These variations were further reduced when excluding the extreme values of 32 and 128 for grey levels (Average AUC range 0.04, with values between 0.00 and 0.08). The discriminative power of CT RF in the prediction of EDR after upfront surgery for pancreatic cancer is relatively invariant against image interpolation/discretization within a large range of voxel sizes and binning.

Artificial intelligence aided diagnosis of pulmonary nodules segmentation and feature extraction

To develop a high-accuracy low-dose computed tomography (LDCT) lung nodule diagnosis system by combining artificial intelligence (AI) technology with the Lung CT Screening Reporting and Data System (Lung-RADS), which can be used in the future AI-aided diagnosis of pulmonary nodules. The study comprised the following steps: (1) the best deep-learning segmentation method for pulmonary nodules was compared and selected objectively; (2) the Image Biomarker Standardization Initiative (IBSI) was used for feature extraction and to determine the best feature reduction method; and (3) a principal component analysis (PCA) and three machine learning methods were used to analyse the extracted features, and the best method was determined. The Lung Nodule Analysis 16 dataset was applied to train and test the established system in this study. The competition performance metric (CPM) score of the nodule segmentation reached 0.83, the accuracy of nodule classification was 92%, the kappa coefficient with the ground truth was 0.68, and the overall diagnostic accuracy (calculated by the nodules) was 0.75. This paper summarises a more efficient AI-assisted diagnosis process of pulmonary nodules, and has better performance compared with the previous literature. In addition, this method will be validated in a future external clinical study.

Phenotyping the Histopathological Subtypes of Non-Small-Cell Lung Carcinoma: How Beneficial Is Radiomics?

The aim of this study was to investigate the usefulness of radiomics in the absence of well-defined standard guidelines. Specifically, we extracted radiomics features from multicenter computed tomography (CT) images to differentiate between the four histopathological subtypes of non-small-cell lung carcinoma (NSCLC). In addition, the results that varied with the radiomics model were compared. We investigated the presence of the batch effects and the impact of feature harmonization on the models' performance. Moreover, the question on how the training dataset composition influenced the selected feature subsets and, consequently, the model's performance was also investigated. Therefore, through combining data from the two publicly available datasets, this study involves a total of 152 squamous cell carcinoma (SCC), 106 large cell carcinoma (LCC), 150 adenocarcinoma (ADC), and 58 no other specified (NOS). Through the matRadiomics tool, which is an example of Image Biomarker Standardization Initiative (IBSI) compliant software, 1781 radiomics features were extracted from each of the malignant lesions that were identified in CT images. After batch analysis and feature harmonization, which were based on the ComBat tool and were integrated in matRadiomics, the datasets (the harmonized and the non-harmonized) were given as an input to a machine learning modeling pipeline. The following steps were articulated: (i) training-set/test-set splitting (80/20); (ii) a Kruskal-Wallis analysis and LASSO linear regression for the feature selection; (iii) model training; (iv) a model validation and hyperparameter optimization; and (v) model testing. Model optimization consisted of a 5-fold cross-validated Bayesian optimization, repeated ten times (inner loop). The whole pipeline was repeated 10 times (outer loop) with six different machine learning classification algorithms. Moreover, the stability of the feature selection was evaluated. Results showed that the batch effects were present even if the voxels were resampled to an isotropic form and whether feature harmonization correctly removed them, even though the models' performances decreased. Moreover, the results showed that a low accuracy (61.41%) was reached when differentiating between the four subtypes, even though a high average area under curve (AUC) was reached (0.831). Further, a NOS subtype was classified as almost completely correct (true positive rate ~90%). The accuracy increased (77.25%) when only the SCC and ADC subtypes were considered, as well as when a high AUC (0.821) was obtained-although harmonization decreased the accuracy to 58%. Moreover, the features that contributed the most to models' performance were those extracted from wavelet decomposed and Laplacian of Gaussian (LoG) filtered images and they belonged to the texture feature class.. In conclusion, we showed that our multicenter data were affected by batch effects, that they could significantly alter the models' performance, and that feature harmonization correctly removed them. Although wavelet features seemed to be the most informative features, an absolute subset could not be identified since it changed depending on the training/testing splitting. Moreover, performance was influenced by the chosen dataset and by the machine learning methods, which could reach a high accuracy in binary classification tasks, but could underperform in multiclass problems. It is, therefore, essential that the scientific community propose a more systematic radiomics approach, focusing on multicenter studies, with clear and solid guidelines to facilitate the translation of radiomics to clinical practice.

Role of [68Ga]Ga-PSMA-11 PET radiomics to predict post-surgical ISUP grade in primary prostate cancer.

The aim of this study is to investigate the role of [68Ga]Ga-PSMA-11 PET radiomics for the prediction of post-surgical International Society of Urological Pathology (PSISUP) grade in primary prostate cancer (PCa). This retrospective study included 47 PCa patients who underwent [68Ga]Ga-PSMA-11 PET at IRCCS San Raffaele Scientific Institute before radical prostatectomy. The whole prostate was manually contoured on PET images and 103 image biomarker standardization initiative (IBSI)-compliant radiomic features (RFs) were extracted. Features were then selected using the minimum redundancy maximum relevance algorithm and a combination of the 4 most relevant RFs was used to train 12 radiomics machine learning models for the prediction of PSISUP grade: ISUP ≥ 4 vs ISUP < 4. Machine learning models were validated by means of fivefold repeated cross-validation, and two control models were generated to assess that our findings were not surrogates of spurious associations. Balanced accuracy (bACC) was collected for all generated models and compared with Kruskal-Wallis and Mann-Whitney tests. Sensitivity, specificity, and positive and negative predictive values were also reported to provide a complete overview of models' performance. The predictions of the best performing model were compared against ISUP grade at biopsy. ISUP grade at biopsy was upgraded in 9/47 patients after prostatectomy, resulting in a bACC = 85.9%, SN = 71.9%, SP = 100%, PPV = 100%, and NPV = 62.5%, while the best-performing radiomic model yielded a bACC = 87.6%, SN = 88.6%, SP = 86.7%, PPV = 94%, and NPV = 82.5%. All radiomic models trained with at least 2 RFs (GLSZM-Zone Entropy and Shape-Least Axis Length) outperformed the control models. Conversely, no significant differences were found for radiomic models trained with 2 or more RFs (Mann-Whitney p > 0.05). These findings support the role of [68Ga]Ga-PSMA-11 PET radiomics for the accurate and non-invasive prediction of PSISUP grade.

The role of [18F]-DCFPyL PET/MRI radiomics for pathological grade group prediction in prostate cancer.

To evaluate the diagnostic accuracy of [18F]-DCFPyL PET/MRI radiomics for the prediction of pathological grade group in prostate cancer (PCa) in therapy-naïve patients. Patients with confirmed or suspected PCa, who underwent [18F]-DCFPyL PET/MRI (n = 105), were included in this retrospective analysis of two prospective clinical trials. Radiomic features were extracted from the segmented volumes following the image biomarker standardization initiative (IBSI) guidelines. Histopathology obtained from systematic and targeted biopsies of the PET/MRI-detected lesions was the reference standard. Histopathology patterns were dichotomized as ISUP GG 1-2 vs. ISUP GG ≥ 3 categories. Different single-modality models were defined for feature extraction, including PET- and MRI-derived radiomic features. The clinical model included age, PSA, and lesions' PROMISE classification. Single models, as well as different combinations of them, were generated to calculate their performances. A cross-validation approach was used to evaluate the internal validity of the models. All radiomic models outperformed the clinical models. The best model for grade group prediction was the combination of PET + ADC + T2w radiomic features, showing sensitivity, specificity, accuracy, and AUC of 0.85, 0.83, 0.84, and 0.85, respectively. The MRI-derived (ADC + T2w) features showed sensitivity, specificity, accuracy, and AUC of 0.88, 0.78, 0.83, and 0.84, respectively. PET-derived features showed 0.83, 0.68, 0.76, and 0.79, respectively. The baseline clinical model showed 0.73, 0.44, 0.60, and 0.58, respectively. The addition of the clinical model to the best radiomic model did not improve the diagnostic performance. The performances of MRI and PET/MRI radiomic models as per the cross-validation scheme yielded an accuracy of 0.80 (AUC = 0.79), whereas clinical models presented an accuracy of 0.60 (AUC = 0.60). The combined [18F]-DCFPyL PET/MRI radiomic model was the best-performing model and outperformed the clinical model for pathological grade group prediction, indicating a complementary value of the hybrid PET/MRI model for non-invasive risk stratification of PCa. Further prospective studies are required to confirm the reproducibility and clinical utility of this approach.

External validation of an 18F-FDG-PET radiomic model predicting survival after radiotherapy for oropharyngeal cancer.

The purpose of the study is to externally validate published 18F-FDG-PET radiomic models for outcome prediction in patients with oropharyngeal cancer treated with chemoradiotherapy. Outcome data and pre-radiotherapy PET images of 100 oropharyngeal cancer patients (stage IV:78) treated with concomitant chemotherapy to 66-69 Gy/30 fr were available. Tumors were segmented using a previously validated semi-automatic method; 450 radiomic features (RF) were extracted according to IBSI (Image Biomarker Standardization Initiative) guidelines. Only one model for cancer-specific survival (CSS) prediction was suitable to be independently tested, according to our criteria. This model, in addition to HPV status, SUVmean and SUVmax, included two independent meta-factors (Fi), resulting from combining selected RF clusters. In a subgroup of 66 patients with complete HPV information, the global risk score R was computed considering the original coefficients and was tested by Cox regression as predictive of CSS. Independently, only the radiomic risk score RF derived from Fi was tested on the same subgroup to learn about the radiomics contribution to the model. The metabolic tumor volume (MTV) was also tested as a single predictor and its prediction performances were compared to the global and radiomic models. Finally, the validation of MTV and the radiomic score RF were also tested on the entire dataset. Regarding the analysis of the subgroup with HPV information, with a median follow-up of 41.6 months, seven patients died due to cancer. R was confirmed to be associated to CSS (p value = 0.05) with a C-index equal 0.75 (95% CI=0.62-0.85). The best cut-off value (equal to 0.15) showed high ability in patient stratification (p=0.01, HR=7.4, 95% CI=1.6-11.4). The 5-year CSS for R were 97% (95% CI: 93-100%) vs 74% (56-92%) for low- and high-risk groups, respectively. RF and MTV alone were also significantly associated to CSS for the subgroup with an almost identical C-index. According to best cut-off value (RF>0.12 and MTV>15.5cc), the 5-year CSS were 96% (95% CI: 89-100%) vs 65% (36-94%) and 97% (95% CI: 88-100%) vs 77% (58-93%) for RF and MTV, respectively. Results regarding RF and MTV were confirmed in the overall group. A previously published PET radiomic model for CSS prediction was independently validated. Performances of the model were similar to the ones of using only the MTV, without improvement of prediction accuracy.

MIFE: An Easy-to-Use Web-Based Tool for Standardized Radiomics Features Extraction in Medical Images

In last decades, the advancement of technology has led medical imaging to become a fundamental component in medical sciences. Additionally, it has been detected that medical imaging has the potential to generate biomarkers. Given the increased interest in biomarkers in medical imaging, the emerging branch of science called ”Radiomics” has been given rise, which combines the area of radiological analysis and machine learning techniques. Nevertheless, radiomic studies face significant reproducibility challenges as a result of multiple factors. Therefore, several research centers have joined in an international collaboration in the project called Image Biomarker Standardization Initiative (IBSI), which main goal is to standardize the calculation of image biomarkers. Several technological tools have been developed for medical image manipulation and radiomic data extraction. However, it has been detected that several of these tools require a prolonged learning curve for users. Therefore, there is a need for the creation of new tools that are user-friendly and do not represent a complex task for users to handle. In this research, an easy-to-use Web-based tool for radiomic feature extraction is presented, which is capable of extract 134 standardized features based on IBSI guidelines, and a usability punctuation equal to 88.1 based on System Usability Scale.

A systematic review of radiomics in chondrosarcoma: assessment of study quality and clinical value needs handy tools.

To evaluate the study quality and clinical value of radiomics studies on chondrosarcoma. PubMed, Embase, Web of Science, China National Knowledge Infrastructure, and Wanfang Data were searched for articles on radiomics for evaluating chondrosarcoma as of January 31, 2022. The study quality was assessed according to Radiomics Quality Score (RQS), Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) checklist, Image Biomarker Standardization Initiative (IBSI) guideline, and modified Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool. The level of evidence supporting clinical use of radiomics on chondrosarcoma differential diagnosis was determined based on meta-analyses. Twelve articles were included. The median RQS was 10.5 (range, -3 to 15), with an adherence rate of 36%. The adherence rate was extremely low in domains of high-level evidence (0%), open science and data (17%), and imaging and segmentation (35%). The adherence rate of the TRIPOD checklist was 61%, and low for section of title and abstract (13%), introduction (42%), and results (56%). The reporting rate of pre-processing steps according to the IBSI guideline was 60%. The risk of bias and concern of application were mainly related to the index test. The meta-analysis on differential diagnosis of enchondromas vs. chondrosarcomas showed a diagnostic odds ratio of 43.90 (95% confidential interval, 25.33-76.10), which was rated as weak evidence. The current scientific and reporting quality of radiomics studies on chondrosarcoma was insufficient. Radiomics has potential in facilitating the optimization of operation decision-making in chondrosarcoma. • Among radiomics studies on chondrosarcoma, although differential diagnostic models showed promising performance, only pieces of weak level of evidence were reached with insufficient study quality. • Since the RQS rating, the TRIPOD checklist, and the IBSI guideline have largely overlapped with each other, it is necessary to establish one widely acceptable methodological and reporting guideline for radiomics research. • The TRIPOD model typing, the phase classification of image mining studies, and the level of evidence category are useful tools to assess the gap between academic research and clinical application, although their modifications for radiomics studies are needed.

A systematic review of radiomics in pancreatitis: applying the evidence level rating tool for promoting clinical transferability

BackgroundMultiple tools have been applied to radiomics evaluation, while evidence rating tools for this field are still lacking. This study aims to assess the quality of pancreatitis radiomics research and test the feasibility of the evidence level rating tool.ResultsThirty studies were included after a systematic search of pancreatitis radiomics studies until February 28, 2022, via five databases. Twenty-four studies employed radiomics for diagnostic purposes. The mean ± standard deviation of the adherence rate was 38.3 ± 13.3%, 61.3 ± 11.9%, and 37.1 ± 27.2% for the Radiomics Quality Score (RQS), the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) checklist, and the Image Biomarker Standardization Initiative (IBSI) guideline for preprocessing steps, respectively. The median (range) of RQS was 7.0 (− 3.0 to 18.0). The risk of bias and application concerns were mainly related to the index test according to the modified Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool. The meta-analysis on differential diagnosis of autoimmune pancreatitis versus pancreatic cancer by CT and mass-forming pancreatitis versus pancreatic cancer by MRI showed diagnostic odds ratios (95% confidence intervals) of, respectively, 189.63 (79.65–451.48) and 135.70 (36.17–509.13), both rated as weak evidence mainly due to the insufficient sample size.ConclusionsMore research on prognosis of acute pancreatitis is encouraged. The current pancreatitis radiomics studies have insufficient quality and share common scientific disadvantages. The evidence level rating is feasible and necessary for bringing the field of radiomics from preclinical research area to clinical stage.

Radiomics-Based Deep Learning Prediction of Overall Survival in Non-Small-Cell Lung Cancer Using Contrast-Enhanced Computed Tomography.

Simple SummaryThe five-year survival rate of non-small-cell lung cancer (NSCLC), which accounts for 85% of all lung cancer cases, is only 10–20%. A reliable prediction model of overall survival (OS) that integrates imaging and clinical data is required. Overall, 492 patients with NSCLC from two hospitals were enrolled in this study. The compensation method was applied to reduce the variation of imaging features among different hospitals. We constructed a deep learning prediction model, DeepSurv, based on computed tomography radiomics and key clinical features to generate a personalized survival curve for each patient. The results of DeepSurv showed a good performance in discriminating high and low risk of survival. Furthermore, the generated personalized survival curves could be intuitively applied for individual OS prediction in clinical practice. We concluded that the proposed prediction model could benefit physicians, patients, and caregivers in managing NSCLC and facilitate personalized medicine.Patient outcomes of non-small-cell lung cancer (NSCLC) vary because of tumor heterogeneity and treatment strategies. This study aimed to construct a deep learning model combining both radiomic and clinical features to predict the overall survival of patients with NSCLC. To improve the reliability of the proposed model, radiomic analysis complying with the Image Biomarker Standardization Initiative and the compensation approach to integrate multicenter datasets were performed on contrast-enhanced computed tomography (CECT) images. Pretreatment CECT images and the clinical data of 492 patients with NSCLC from two hospitals were collected. The deep neural network architecture, DeepSurv, with the input of radiomic and clinical features was employed. The performance of survival prediction model was assessed using the C-index and area under the curve (AUC) 8, 12, and 24 months after diagnosis. The performance of survival prediction that combined eight radiomic features and five clinical features outperformed that solely based on radiomic or clinical features. The C-index values of the combined model achieved 0.74, 0.75, and 0.75, respectively, and AUC values of 0.76, 0.74, and 0.73, respectively, 8, 12, and 24 months after diagnosis. In conclusion, combining the traits of pretreatment CECT images, lesion characteristics, and treatment strategies could effectively predict the survival of patients with NSCLC using a deep learning model.

3D convolutional neural network model from contrast-enhanced CT to predict spread through air spaces in non-small cell lung cancer

PurposeThe purpose of this study was to compare the efficacy of five non-invasive models, including three-dimensional (3D) convolutional neural network (CNN) model, to predict the spread through air spaces (STAS) status of non-small cell lung cancer (NSCLC), and to obtain the best prediction model to provide a basis for clinical surgery planning. Materials and methodsA total of 203 patients (112 men, 91 women; mean age, 60 years; age range 22–80 years) with NSCLC were retrospectively included. Of these, 153 were used for training cohort and 50 for validation cohort. According to the image biomarker standardization initiative reference manual, the image processing and feature extraction were standardized using PyRadiomics. The logistic regression classifier was used to build the model. Five models (clinicopathological/CT model, conventional radiomics model, computer vision (CV) model, 3D CNN model and combined model) were constructed to predict STAS by NSCLC. Area under the receiver operating characteristic curves (AUC) were used to validate the capability of the five models to predict STAS. ResultsFor predicting STAS, the 3D CNN model was superior to the clinicopathological/CT model, conventional radiomics model, CV model and combined model and achieved satisfactory discrimination performance, with an AUC of 0.93 (95% CI: 0.70–0.82) in the training cohort and 0.80 (95% CI: 0.65–0.86) in the validation cohort. Decision curve analysis indicated that, when the probability of the threshold was over 10%, the 3D CNN model was beneficial for predicting STAS status compared to either treating all or treating none of the patients within certain ranges of risk threshold ConclusionThe 3D CNN model can be used for the preoperative prediction of STAS in patients with NSCLC, and was superior to the other four models in predicting patients' risk of developing STAS.

Radiomics outperforms clinical factors in characterizing human papilloma virus (HPV) for patients with oropharyngeal squamous cell carcinomas

Purpose. To utilize radiomic features extracted from CT images to characterize Human Papilloma Virus (HPV) for patients with oropharyngeal cancer squamous cell carcinoma (OPSCC). Methods. One hundred twenty-eight OPSCC patients with known HPV-status (60-HPV + and 68-HPV-, confirmed by immunohistochemistry-P16-protein testing) were retrospectively studied. Radiomic features (11 feature-categories) were extracted in 3D from contrast-enhanced (CE)-CT images of gross-tumor-volumes using ‘in-house’ software (‘ROdiomiX’) developed and validated following the image-biomarker-standardization-initiative (IBSI) guidelines. Six clinical factors were investigated: Age-at-Diagnosis, Gender, Total-Charlson, Alcohol-Use, Smoking-History, and T-Stage. A Least-Absolute-Shrinkage-and-Selection-Operation (Lasso) technique combined with a Generalized-Linear-Model (Lasso-GLM) were applied to perform regularization in the radiomic and clinical feature spaces to identify the ranking of optimal feature subsets with most representative information for prediction of HPV. Lasso-GLM models/classifiers based on clinical factors only, radiomics only, and combined clinical and radiomics (ensemble/integrated) were constructed using random-permutation-sampling. Tests of significance (One-way ANOVA), average Area-Under-Receiver-Operating-Characteristic (AUC), and Positive and Negative Predictive values (PPV and NPV) were computed to estimate the generalization-error and prediction performance of the classifiers. Results. Five clinical factors, including T-stage, smoking status, and age, and 14 radiomic features, including tumor morphology, and intensity contrast were found to be statistically significant discriminators between HPV positive and negative cohorts. Performances for prediction of HPV for the 3 classifiers were: Radiomics-Lasso-GLM: AUC/PPV/NPV = 0.789/0.755/0.805; Clinical-Lasso-GLM: 0.676/0.747/0.672, and Integrated/Ensemble-Lasso-GLM: 0.895/0.874/0.844. Results imply that the radiomics-based classifier enabled better characterization and performance prediction of HPV relative to clinical factors, and that the combination of both radiomics and clinical factors yields even higher accuracy characterization and predictive performance. Conclusion. Albeit subject to confirmation in a larger cohort, this pilot study presents encouraging results in support of the role of radiomic features towards characterization of HPV in patients with OPSCC.

MRI Radiogenomics of Pediatric Medulloblastoma: A Multicenter Study.

Background Radiogenomics of pediatric medulloblastoma (MB) offers an opportunity for MB risk stratification, which may aid therapeutic decision making, family counseling, and selection of patient groups suitable for targeted genetic analysis. Purpose To develop machine learning strategies that identify the four clinically significant MB molecular subgroups. Materials and Methods In this retrospective study, consecutive pediatric patients with newly diagnosed MB at MRI at 12 international pediatric sites between July 1997 and May 2020 were identified. There were 1800 features extracted from T2- and contrast-enhanced T1-weighted preoperative MRI scans. A two-stage sequential classifier was designed-one that first identifies non-wingless (WNT) and non-sonic hedgehog (SHH) MB and then differentiates therapeutically relevant WNT from SHH. Further, a classifier that distinguishes high-risk group 3 from group 4 MB was developed. An independent, binary subgroup analysis was conducted to uncover radiomics features unique to infantile versus childhood SHH subgroups. The best-performing models from six candidate classifiers were selected, and performance was measured on holdout test sets. CIs were obtained by bootstrapping the test sets for 2000 random samples. Model accuracy score was compared with the no-information rate using the Wald test. Results The study cohort comprised 263 patients (mean age ± SD at diagnosis, 87 months ± 60; 166 boys). A two-stage classifier outperformed a single-stage multiclass classifier. The combined, sequential classifier achieved a microaveraged F1 score of 88% and a binary F1 score of 95% specifically for WNT. A group 3 versus group 4 classifier achieved an area under the receiver operating characteristic curve of 98%. Of the Image Biomarker Standardization Initiative features, texture and first-order intensity features were most contributory across the molecular subgroups. Conclusion An MRI-based machine learning decision path allowed identification of the four clinically relevant molecular pediatric medulloblastoma subgroups. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Chaudhary and Bapuraj in this issue.

A Novel Benchmarking Approach to Assess the Agreement among Radiomic Tools.

Background The translation of radiomic models into clinical practice is hindered by the limited reproducibility of features across software and studies. Standardization is needed to accelerate this process and to bring radiomics closer to clinical deployment. Purpose To assess the standardization level of seven radiomic software programs and investigate software agreement as a function of built-in image preprocessing (eg, interpolation and discretization), feature aggregation methods, and the morphological characteristics (ie, volume and shape) of the region of interest (ROI). Materials and Methods The study was organized into two phases: In phase I, the two Image Biomarker Standardization Initiative (IBSI) phantoms were used to evaluate the IBSI compliance of seven software programs. In phase II, the reproducibility of all IBSI-standardized radiomic features across tools was assessed with two custom Italian multicenter Shared Understanding of Radiomic Extractors (ImSURE) digital phantoms that allowed, in conjunction with a systematic feature extraction, observations on whether and how feature matches between program pairs varied depending on the preprocessing steps, aggregation methods, and ROI characteristics. Results In phase I, the software programs showed different levels of completeness (ie, the number of computable IBSI benchmark values). However, the IBSI-compliance assessment revealed that they were all standardized in terms of feature implementation. When considering additional preprocessing steps, for each individual program, match percentages fell by up to 30%. In phase II, the ImSURE phantoms showed that software agreement was dependent on discretization and aggregation as well as on ROI shape and volume factors. Conclusion The agreement of radiomic software varied in relation to factors that had already been standardized (eg, interpolation and discretization methods) and factors that need standardization. Both dependences must be resolved to ensure the reproducibility of radiomic features and to pave the way toward the clinical adoption of radiomic models. Published under a CC BY 4.0 license. Online supplemental material is available for this article. See also the editorial by Steiger in this issue. An earlier incorrect version appeared online and in print. This article was corrected on March 2, 2022.