Technical and clinical considerations of a physical liver phantom for CT radiomics analysis.

OBJECTIVE: This study identifies key characteristics to help build a physical liver computed tomography (CT) phantom for radiomics harmonization; particularly, the higher-order texture metrics. MATERIALS AND METHODS: CT scans of a radiomics phantom comprising of 18 novel 3D printed inserts with varying size, shape, and material combinations were acquired on a 64-slice CT scanner (Brilliance 64, Philips Healthcare). The images were acquired at 120 kV, 250 mAs, CTDIvol of 16.36 mGy, 2 mm slice thickness, and iterative noise-reduction reconstruction (iDose, Philips Healthcare, Andover, MA). Radiomics analysis was performed using the Cancer Imaging Phenomics Toolkit (CaPTk), following automated segmentation of 3D regions of interest (ROI) of the 18 inserts. The findings were compared to three additional ROI obtained of an anthropomorphic liver phantom, a patient liver CT scan, and a water phantom, at comparable imaging settings. Percentage difference in radiomic metrics values between phantom and tissue was used to assess the biological equivalency and <10% was used to claim equivalent. RESULTS: The HU for all 18 ROI from the phantom ranged from -30 to 120 which is within clinically observed HU range of the liver, showing that our phantom material (T3-6B) is representative of biological CT tissue densities (liver) with >50% radiomic features having <10% difference from liver tissue. Based on the assessment of the Neighborhood Gray Tone Difference Matrix (NGTDM) metrics it is evident that the water phantom ROI show extreme values compared to the ROIs from the phantom. This result may further reinforce the difference between a structureless quantity such as water HU values and tissue HU values found in liver. CONCLUSION: The 3-D printed patterns of the constructed radiomics phantom cover a wide span of liver tissue textures seen in CT images. Using our results, texture metrics can be selectively harmonized to establish clinically relevant and reliable radiomics panels.

Conditional generative learning for medical image imputation.

Image imputation refers to the task of generating a type of medical image given images of another type. This task becomes challenging when the difference between the available images, and the image to be imputed is large. In this manuscript, one such application is considered. It is derived from the dynamic contrast enhanced computed tomography (CECT) imaging of the kidneys: given an incomplete sequence of three CECT images, we are required to impute the missing image. This task is posed as one of probabilistic inference and a generative algorithm to generate samples of the imputed image, conditioned on the available images, is developed, trained, and tested. The output of this algorithm is the "best guess" of the imputed image, and a pixel-wise image of variance in the imputation. It is demonstrated that this best guess is more accurate than those generated by other, deterministic deep-learning based algorithms, including ones which utilize additional information and more complex loss terms. It is also shown that the pixel-wise variance image, which quantifies the confidence in the reconstruction, can be used to determine whether the result of the imputation meets a specified accuracy threshold and is therefore appropriate for a downstream task.

Radiomics Correlation to CD68+ Tumor-Associated Macrophages in Clear Cell Renal Cell Carcinoma.

INTRODUCTION: Renal cell carcinoma (RCC) is the ninth most common cancer worldwide, with clear cell RCC (ccRCC) being the most frequent histological subtype. The tumor immune microenvironment (TIME) of ccRCC is an important factor to guide treatment, but current assessments are tissue-based, which can be time-consuming and resource-intensive. In this study, we used radiomics extracted from clinically performed computed tomography (CT) as a noninvasive surrogate for CD68 tumor-associated macrophages (TAMs), a significant component of ccRCC TIME. METHODS: TAM population was measured by CD68+/PanCK+ ratio and tumor-TAM clustering was measured by normalized K function calculated from multiplex immunofluorescence (mIF). A total of 1,076 regions on mIF slides from 78 patients were included. Radiomic features were extracted from multiphase CT of the ccRCC tumor. Statistical machine learning models, including random forest, Adaptive Boosting, and ElasticNet, were used to predict TAM population and tumor-TAM clustering. RESULTS: The best models achieved an area under the ROC curve of 0.81 (95% CI: [0.69, 0.92]) for TAM population and 0.77 (95% CI: [0.66, 0.88]) for tumor-TAM clustering, respectively. CONCLUSION: Our study demonstrates the potential of using CT radiomics-derived imaging markers as a surrogate for assessment of TAM in ccRCC for real-time treatment response monitoring and patient selection for targeted therapies and immunotherapies.

Investigating the role of imaging factors in the variability of CT-based texture analysis metrics.

OBJECTIVE: This study assesses the robustness of first-order radiomic texture features namely interquartile range (IQR), coefficient of variation (CV) and standard deviation (SD) derived from computed tomography (CT) images by varying dose, reconstruction algorithms and slice thickness using scans of a uniform water phantom, a commercial anthropomorphic liver phantom, and a human liver in-vivo. MATERIALS AND METHODS: Scans were acquired on a 16 cm detector GE Revolution Apex Edition CT scanner with variations across three different nominal slice thicknesses: 0.625, 1.25, and 2.5 mm, three different dose levels: CTDIvol of 13.86 mGy for the standard dose, 40% reduced dose and 60% reduced dose and two different reconstruction algorithms: a deep learning image reconstruction (DLIR-high) algorithm and a hybrid iterative reconstruction (IR) algorithm ASiR-V50% (AV50) were explored, varying one at a time. To assess the effect of non-linear modifications of images by AV50 and DLIR-high, images of the water phantom were also reconstructed using filtered back projection (FBP). Quantitative measures of IQR, CV and SD were extracted from twelve pre-selected, circular (1 cm diameter) regions of interest (ROIs) capturing different texture patterns across all scans. RESULTS: Across all scans, imaging, and reconstruction settings, CV, IQR and SD were observed to increase with reduction in dose and slice thickness. An exception to this observation was found when using FBP reconstruction. Lower values of CV, IQR and SD were observed in DLIR-high reconstructions compared to AV50 and FBP. The Poisson statistics were more stringently noted in FBP than DLIR-high and AV50, due to the non-linear nature of the latter two algorithms. CONCLUSION: Variation in image noise due to dose reduction algorithms, tube current, and slice thickness show a consistent trend across phantom and patient scans. Prospective evaluation across multiple centers, scanners and imaging protocols is needed for establishing quality assurance standards of radiomics.

A cross-sectional study to test equivalence of low- versus intermediate-flip angle dynamic susceptibility contrast MRI measures of relative cerebral blood volume in patients with high-grade gliomas at 1.5 Tesla field strength.

Introduction: 1.5 Tesla (1.5T) remain a significant field strength for brain imaging worldwide. Recent computer simulations and clinical studies at 3T MRI have suggested that dynamic susceptibility contrast (DSC) MRI using a 30° flip angle ("low-FA") with model-based leakage correction and no gadolinium-based contrast agent (GBCA) preload provides equivalent relative cerebral blood volume (rCBV) measurements to the reference-standard acquisition using a single-dose GBCA preload with a 60° flip angle ("intermediate-FA") and model-based leakage correction. However, it remains unclear whether this holds true at 1.5T. The purpose of this study was to test this at 1.5T in human high-grade glioma (HGG) patients. Methods: This was a single-institution cross-sectional study of patients who had undergone 1.5T MRI for HGG. DSC-MRI consisted of gradient-echo echo-planar imaging (GRE-EPI) with a low-FA without preload (30°/P-); this then subsequently served as a preload for the standard intermediate-FA acquisition (60°/P+). Both normalized (nrCBV) and standardized relative cerebral blood volumes (srCBV) were calculated using model-based leakage correction (C+) with IBNeuro™ software. Whole-enhancing lesion mean and median nrCBV and srCBV from the low- and intermediate-FA methods were compared using the Pearson's, Spearman's and intraclass correlation coefficients (ICC). Results: Twenty-three HGG patients composing a total of 31 scans were analyzed. The Pearson and Spearman correlations and ICCs between the 30°/P-/C+ and 60°/P+/C+ acquisitions demonstrated high correlations for both mean and median nrCBV and srCBV. Conclusion: Our study provides preliminary evidence that for HGG patients at 1.5T MRI, a low FA, no preload DSC-MRI acquisition can be an appealing alternative to the reference standard higher FA acquisition that utilizes a preload.

A Narrative Review of the Use of Artificial Intelligence in Breast, Lung, and Prostate Cancer.

Artificial intelligence (AI) has been an important topic within radiology. Currently, AI is used clinically to assist with the detection of lesions through detection systems. However, a number of recent studies have demonstrated the increased value of neural networks in radiology. With an increasing number of screening requirements for cancers, this review aims to study the accuracy of the numerous AI models used in the detection and diagnosis of breast, lung, and prostate cancers. This study summarizes pertinent findings from reviewed articles and provides analysis on the relevancy to clinical radiology. This study found that whereas AI is showing continual improvement in radiology, AI alone does not surpass the effectiveness of a radiologist. Additionally, it was found that there are multiple variations on how AI should be integrated with a radiologist's workflow.

Spatial assessments in texture analysis: what the radiologist needs to know.

To date, studies investigating radiomics-based predictive models have tended to err on the side of data-driven or exploratory analysis of many thousands of extracted features. In particular, spatial assessments of texture have proven to be especially adept at assessing for features of intratumoral heterogeneity in oncologic imaging, which likewise may correspond with tumor biology and behavior. These spatial assessments can be generally classified as spatial filters, which detect areas of rapid change within the grayscale in order to enhance edges and/or textures within an image, or neighborhood-based methods, which quantify gray-level differences of neighboring pixels/voxels within a set distance. Given the high dimensionality of radiomics datasets, data dimensionality reduction methods have been proposed in an attempt to optimize model performance in machine learning studies; however, it should be noted that these approaches should only be applied to training data in order to avoid information leakage and model overfitting. While area under the curve of the receiver operating characteristic is perhaps the most commonly reported assessment of model performance, it is prone to overestimation when output classifications are unbalanced. In such cases, confusion matrices may be additionally reported, whereby diagnostic cut points for model predicted probability may hold more clinical significance to clinical colleagues with respect to related forms of diagnostic testing.

Sarcopenia and body fat change as risk factors for radiologic incisional hernia following robotic nephrectomy.

OBJECTIVE: To assess the effect of body muscle and fat metrics on the development of radiologic incisional hernia (IH) following robotic nephrectomy. MATERIALS AND METHODS: We retrospectively reviewed the records of patients who underwent robotic nephrectomy for kidney tumors between 2011 and 2017. All pre- and postoperative CTs were re-reviewed by experienced radiologists for detection of radiologic IH and calculation of the following metrics using Synapse 3D software: cross-sectional psoas muscle mass at the level of L3 and L4 as well as subcutaneous and visceral fat areas. Sarcopenia was defined as psoas muscle index below the lowest quartile. Cox proportional hazard model was constructed to examine the association between muscle and fat metrics and the risk of developing radiologic IH. RESULTS: A total of 236 patients with a median (IQR) age of 64 (54-70) years were included in this study. In a median (IQR) follow-up of 23 (14-38) months, 62 (26%) patients developed radiologic IH. On Cox proportional hazard model, we were unable to detect an association between sarcopenia and risk of IH development. In terms of subcutaneous fat change from pre-op, both lower and higher values were associated with IH development (HR (95% CI) 2.1 (1.2-3.4), p = 0.01 and 2.4 (1.4-4.1), p < 0.01 for < Q1 and ≥ Q3, respectively). Similar trend was found for visceral fat area changes from pre-op with a HR of 2.8 for < Q1 and 1.8 for ≥ Q3. CONCLUSION: Both excessive body fat gain and loss are associated with development of radiologic IH in patients undergoing robotic nephrectomy.

Radiogenomic Associations Clear Cell Renal Cell Carcinoma: An Exploratory Study.

INTRODUCTION: This study investigates how quantitative texture analysis can be used to non-invasively identify novel radiogenomic correlations with clear cell renal cell carcinoma (ccRCC) biomarkers. METHODS: The Cancer Genome Atlas-Kidney Renal Clear Cell Carcinoma open-source database was used to identify 190 sets of patient genomic data that had corresponding multiphase contrast-enhanced CT images in The Cancer Imaging Archive. 2,824 radiomic features spanning fifteen texture families were extracted from CT images using a custom-built MATLAB software package. Robust radiomic features with strong inter-scanner reproducibility were selected. Random forest, AdaBoost, and elastic net machine learning (ML) algorithms evaluated the ability of the selected radiomic features to predict the presence of 12 clinically relevant molecular biomarkers identified from the literature. ML analysis was repeated with cases stratified by stage (I/II vs. III/IV) and grade (1/2 vs. 3/4). 10-fold cross validation was used to evaluate model performance. RESULTS: Before stratification by tumor grade and stage, radiomics predicted the presence of several biomarkers with weak discrimination (AUC 0.60-0.68). Once stratified, radiomics predicted KDM5C, SETD2, PBRM1, and mTOR mutation status with acceptable to excellent predictive discrimination (AUC ranges from 0.70 to 0.86). CONCLUSIONS: Radiomic texture analysis can potentially identify a variety of clinically relevant biomarkers in patients with ccRCC and may have a prognostic implication.

Predicting Soft Tissue Sarcoma Response to Neoadjuvant Chemotherapy Using an MRI-Based Delta-Radiomics Approach.

OBJECTIVES: To evaluate the performance of machine learning-augmented MRI-based radiomics models for predicting response to neoadjuvant chemotherapy (NAC) in soft tissue sarcomas. METHODS: Forty-four subjects were identified retrospectively from patients who received NAC at our institution for pathologically proven soft tissue sarcomas. Only subjects who had both a baseline MRI prior to initiating chemotherapy and a post-treatment scan at least 2 months after initiating chemotherapy and prior to surgical resection were included. 3D ROIs were used to delineate whole-tumor volumes on pre- and post-treatment scans, from which 1708 radiomics features were extracted. Delta-radiomics features were calculated by subtraction of baseline from post-treatment values and used to distinguish treatment response through univariate analyses as well as machine learning-augmented radiomics analyses. RESULTS: Though only 4.74% of variables overall reached significance at p ≤ 0.05 in univariate analyses, Laws Texture Energy (LTE)-derived metrics represented 46.04% of all such features reaching statistical significance. ROC analyses similarly failed to predict NAC response, with AUCs of 0.40 (95% CI 0.22-0.58) and 0.44 (95% CI 0.26-0.62) for RF and AdaBoost, respectively. CONCLUSION: Overall, while our result was not able to separate NAC responders from non-responders, our analyses did identify a subset of LTE-derived metrics that show promise for further investigations. Future studies will likely benefit from larger sample size constructions so as to avoid the need for data filtering and feature selection techniques, which have the potential to significantly bias the machine learning procedures.

Empowering breast cancer diagnosis and radiology practice: advances in artificial intelligence for contrast-enhanced mammography.

Artificial intelligence (AI) applications in breast imaging span a wide range of tasks including decision support, risk assessment, patient management, quality assessment, treatment response assessment and image enhancement. However, their integration into the clinical workflow has been slow due to the lack of a consensus on data quality, benchmarked robust implementation, and consensus-based guidelines to ensure standardization and generalization. Contrast-enhanced mammography (CEM) has improved sensitivity and specificity compared to current standards of breast cancer diagnostic imaging i.e., mammography (MG) and/or conventional ultrasound (US), with comparable accuracy to MRI (current diagnostic imaging benchmark), but at a much lower cost and higher throughput. This makes CEM an excellent tool for widespread breast lesion characterization for all women, including underserved and minority women. Underlining the critical need for early detection and accurate diagnosis of breast cancer, this review examines the limitations of conventional approaches and reveals how AI can help overcome them. The Methodical approaches, such as image processing, feature extraction, quantitative analysis, lesion classification, lesion segmentation, integration with clinical data, early detection, and screening support have been carefully analysed in recent studies addressing breast cancer detection and diagnosis. Recent guidelines described by Checklist for Artificial Intelligence in Medical Imaging (CLAIM) to establish a robust framework for rigorous evaluation and surveying has inspired the current review criteria.

Feasibility of using CT radiomic signatures for predicting CD8-T cell infiltration and PD-L1 expression in renal cell carcinoma.

Objectives: To identify computed tomography (CT)-based radiomic signatures of cluster of differentiation 8 (CD8)-T cell infiltration and programmed cell death ligand 1 (PD-L1) expression levels in patients with clear-cell renal cell carcinoma (ccRCC). Methods: Seventy-eight patients with pathologically confirmed localized ccRCC, preoperative multiphase CT and tumor resection specimens were enrolled in this retrospective study. Regions of interest (ROI) of the ccRCC volume were manually segmented from the CT images and processed using a radiomics panel comprising of 1708 metrics. The extracted metrics were used as inputs to three machine learning classifiers: Random Forest, AdaBoost, and ElasticNet to create radiomic signatures for CD8-T cell infiltration and PD-L1 expression, respectively. Results: Using a cut-off of 80 lymphocytes per high power field, 59 % were classified to CD8 highly infiltrated tumors and 41 % were CD8 non highly infiltrated tumors, respectively. An ElasticNet classifier discriminated between these two groups of CD8-T cells with an AUC of 0.68 (95 % CI, 0.55-0.80). In addition, based on tumor proportion score with a cut-off of > 1 % tumor cells expressing PD-L1, 76 % were PD-L1 positive and 24 % were PD-L1 negative. An Adaboost classifier discriminated between PD-L1 positive and PD-L1 negative tumors with an AUC of 0.8 95 % CI: (0.66, 0.95). 3D radiomics metrics of graylevel co-occurrence matrix (GLCM) and graylevel run-length matrix (GLRLM) metrics drove the performance for CD8-Tcell and PD-L1 classification, respectively. Conclusions: CT-radiomic signatures can differentiate tumors with high CD8-T cell infiltration with moderate accuracy and positive PD-L1 expression with good accuracy in ccRCC.

Radiomics quality score in renal masses: a systematic assessment on current literature.

OBJECTIVE: To perform a systematic assessment and analyze the quality of radiomics methodology in current literature in the evaluation of renal masses using the Radiomics Quality Score (RQS) approach. METHODS: We systematically reviewed recent radiomics literature in renal masses published in PubMed, EMBASE, Elsevier, and Web of Science. Two reviewers blinded by each other's scores evaluated the quality of radiomics methodology in studies published from 2015 to August 2021 using the RQS approach. Owing to the diversity in the imaging modalities and radiomics applications, a meta-analysis could not be performed. RESULTS: Based on our inclusion/exclusion criteria, a total of 87 published studies were included in our study. The highest RQS was noted in three categories: reporting of clinical utility, gold standard, and feature reduction. The average RQS of the two reviewers ranged from 5 ≤ RQS≤19, with the maximum attainable RQS being 36. Very few (7/87 i.e., 8%) studies received an average RQS that ranged from 17 < RQS≤19, which represents studies with the highest RQS in our study. Many (39/87 i.e., 45%) studies received an average RQS that ranged from 13 < RQS≤15. No significant interreviewer scoring differences were observed. CONCLUSIONS: We report that the overall scientific quality and reporting of radiomics studies in renal masses is suboptimal, and subsequent studies should bolster current deficiencies to improve reporting of radiomics methodologies. ADVANCES IN KNOWLEDGE: The RQS approach is a meaningful quantitative scoring system to assess radiomics methodology quality and supports a comprehensive evaluation of the radiomics approach before its incorporation into clinical practice.

An Extra Set of Intelligent Eyes: Application of Artificial Intelligence in Imaging of Abdominopelvic Pathologies in Emergency Radiology.

Imaging in the emergent setting carries high stakes. With increased demand for dedicated on-site service, emergency radiologists face increasingly large image volumes that require rapid turnaround times. However, novel artificial intelligence (AI) algorithms may assist trauma and emergency radiologists with efficient and accurate medical image analysis, providing an opportunity to augment human decision making, including outcome prediction and treatment planning. While traditional radiology practice involves visual assessment of medical images for detection and characterization of pathologies, AI algorithms can automatically identify subtle disease states and provide quantitative characterization of disease severity based on morphologic image details, such as geometry and fluid flow. Taken together, the benefits provided by implementing AI in radiology have the potential to improve workflow efficiency, engender faster turnaround results for complex cases, and reduce heavy workloads. Although analysis of AI applications within abdominopelvic imaging has primarily focused on oncologic detection, localization, and treatment response, several promising algorithms have been developed for use in the emergency setting. This article aims to establish a general understanding of the AI algorithms used in emergent image-based tasks and to discuss the challenges associated with the implementation of AI into the clinical workflow.

Non-Invasive Profiling of Advanced Prostate Cancer via Multi-Parametric Liquid Biopsy and Radiomic Analysis.

Integrating liquid biopsies of circulating tumor cells (CTCs) and cell-free DNA (cfDNA) with other minimally invasive measures may yield more comprehensive disease profiles. We evaluated the feasibility of concurrent cellular and molecular analysis of CTCs and cfDNA combined with radiomic analysis of CT scans from patients with metastatic castration-resistant PC (mCRPC). CTCs from 22 patients were enumerated, stained for PC-relevant markers, and clustered based on morphometric and immunofluorescent features using machine learning. DNA from single CTCs, matched cfDNA, and buffy coats was sequenced using a targeted amplicon cancer hotspot panel. Radiomic analysis was performed on bone metastases identified on CT scans from the same patients. CTCs were detected in 77% of patients and clustered reproducibly. cfDNA sequencing had high sensitivity (98.8%) for germline variants compared to WBC. Shared and unique somatic variants in PC-related genes were detected in cfDNA in 45% of patients (MAF > 0.1%) and in CTCs in 92% of patients (MAF > 10%). Radiomic analysis identified a signature that strongly correlated with CTC count and plasma cfDNA level. Integration of cellular, molecular, and radiomic data in a multi-parametric approach is feasible, yielding complementary profiles that may enable more comprehensive non-invasive disease modeling and prediction.

Characterizing breast masses using an integrative framework of machine learning and CEUS-based radiomics.

AIMS: We evaluated the performance of contrast-enhanced ultrasound (CEUS) based on radiomics analysis to distinguish benign from malignant breast masses. METHODS: 131 women with suspicious breast masses (BI-RADS 4a, 4b, or 4c) who underwent CEUS examinations (using intravenous injection of perflutren lipid microsphere or sulfur hexafluoride lipid-type A microspheres) prior to ultrasound-guided biopsies were retrospectively identified. Post biopsy pathology showed 115 benign and 16 malignant masses. From the cine clip of the CEUS exams obtained using the built-in GE scanner software, breast masses and adjacent normal tissue were then manually segmented using the ImageJ software. One frame representing each of the four phases: precontrast, early, peak, and delay enhancement were selected post segmentation from each CEUS clip. 112 radiomic metrics were extracted from each segmented tissue normalized breast mass using custom Matlab® code. Linear and nonlinear machine learning (ML) methods were used to build the prediction model to distinguish benign from malignant masses. tenfold cross-validation evaluated model performance. Area under the curve (AUC) was used to quantify prediction accuracy. RESULTS: Univariate analysis found 35 (38.5%) radiomic variables with p < 0.05 in differentiating between benign from malignant masses. No feature selection was performed. Predictive models based on AdaBoost reported an AUC = 0.72 95% CI (0.56, 0.89), followed by Random Forest with an AUC = 0.71 95% CI (0.56, 0.87). CONCLUSIONS: CEUS based texture metrics can distinguish between benign and malignant breast masses, which can, in turn, lead to reduced unnecessary breast biopsies.

A Radiomic-based Machine Learning Algorithm to Reliably Differentiate Benign Renal Masses from Renal Cell Carcinoma.

BACKGROUND: A substantial proportion of patients undergo treatment for renal masses where active surveillance or observation may be more appropriate. OBJECTIVE: To determine whether radiomic-based machine learning platforms can distinguish benign from malignant renal masses. DESIGN, SETTING, AND PARTICIPANTS: A prospectively maintained single-institutional renal mass registry was queried to identify patients with a computed tomography-proven clinically localized renal mass who underwent partial or radical nephrectomy. INTERVENTION: Radiomic analysis of preoperative scans was performed. Clinical and radiomic variables of importance were identified through decision tree analysis, which were incorporated into Random Forest and REAL Adaboost predictive models. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: The primary outcome was the degree of congruity between the virtual diagnosis and final pathology. Subanalyses were performed for small renal masses and patients who had percutaneous renal mass biopsies as part of their workup. Receiver operating characteristic curves were used to evaluate each model's discriminatory function. RESULTS AND LIMITATIONS: A total of 684 patients met the selection criteria. Of them, 76% had renal cell carcinoma; 57% had small renal masses, of which 73% were malignant. Predictive modeling differentiated benign pathology from malignant with an area under the curve (AUC) of 0.84 (95% confidence interval [CI] 0.79-0.9). In small renal masses, radiomic analysis yielded a discriminatory AUC of 0.77 (95% CI 0.69-0.85). When negative and nondiagnostic biopsies were supplemented with radiomic analysis, accuracy increased from 83.3% to 93.4%. CONCLUSIONS: Radiomic-based predictive modeling may distinguish benign from malignant renal masses. Clinical factors did not substantially improve the diagnostic accuracy of predictive models. Enhanced diagnostic predictability may improve patient selection before surgery and increase the utilization of active surveillance protocols. PATIENT SUMMARY: Not all kidney tumors are cancerous, and some can be watched. We evaluated a new method that uses radiographic features invisible to the naked eye to distinguish benign masses from true cancers and found that it can do so with acceptable accuracy.

CT-based radiomics stratification of tumor grade and TNM stage of clear cell renal cell carcinoma.

OBJECTIVES: To evaluate the utility of CT-based radiomics signatures in discriminating low-grade (grades 1-2) clear cell renal cell carcinomas (ccRCC) from high-grade (grades 3-4) and low TNM stage (stages I-II) ccRCC from high TNM stage (stages III-IV). METHODS: A total of 587 subjects (mean age 60.2 years ± 12.2; range 22-88.7 years) with ccRCC were included. A total of 255 tumors were high grade and 153 were high stage. For each subject, one dominant tumor was delineated as the region of interest (ROI). Our institutional radiomics pipeline was then used to extract 2824 radiomics features across 12 texture families from the manually segmented volumes of interest. Separate iterations of the machine learning models using all extracted features (full model) as well as only a subset of previously identified robust metrics (robust model) were developed. Variable of importance (VOI) analysis was performed using the out-of-bag Gini index to identify the top 10 radiomics metrics driving each classifier. Model performance was reported using area under the receiver operating curve (AUC). RESULTS: The highest AUC to distinguish between low- and high-grade ccRCC was 0.70 (95% CI 0.62-0.78) and the highest AUC to distinguish between low- and high-stage ccRCC was 0.80 (95% CI 0.74-0.86). Comparable AUCs of 0.73 (95% CI 0.65-0.8) and 0.77 (95% CI 0.7-0.84) were reported using the robust model for grade and stage classification, respectively. VOI analysis revealed the importance of neighborhood operation-based methods, including GLCM, GLDM, and GLRLM, in driving the performance of the robust models for both grade and stage classification. CONCLUSION: Post-validation, CT-based radiomics signatures may prove to be useful tools to assess ccRCC grade and stage and could potentially add to current prognostic models. Multiphase CT-based radiomics signatures have potential to serve as a non-invasive stratification schema for distinguishing between low- and high-grade as well as low- and high-stage ccRCC. KEY POINTS: • Radiomics signatures derived from clinical multiphase CT images were able to stratify low- from high-grade ccRCC, with an AUC of 0.70 (95% CI 0.62-0.78). • Radiomics signatures derived from multiphase CT images yielded discriminative power to stratify low from high TNM stage in ccRCC, with an AUC of 0.80 (95% CI 0.74-0.86). • Models created using only robust radiomics features achieved comparable AUCs of 0.73 (95% CI 0.65-0.80) and 0.77 (95% CI 0.70-0.84) to the model with all radiomics features in classifying ccRCC grade and stage, respectively.

Predicting clinical outcomes in COVID-19 using radiomics on chest radiographs.

OBJECTIVES: For optimal utilization of healthcare resources, there is a critical need for early identification of COVID-19 patients at risk of poor prognosis as defined by the need for intensive unit care and mechanical ventilation. We tested the feasibility of chest X-ray (CXR)-based radiomics metrics to develop machine-learning algorithms for predicting patients with poor outcomes. METHODS: In this Institutional Review Board (IRB) approved, Health Insurance Portability and Accountability Act (HIPAA) compliant, retrospective study, we evaluated CXRs performed around the time of admission from 167 COVID-19 patients. Of the 167 patients, 68 (40.72%) required intensive care during their stay, 45 (26.95%) required intubation, and 25 (14.97%) died. Lung opacities were manually segmented using ITK-SNAP (open-source software). CaPTk (open-source software) was used to perform 2D radiomics analysis. RESULTS: Of all the algorithms considered, the AdaBoost classifier performed the best with AUC = 0.72 to predict the need for intubation, AUC = 0.71 to predict death, and AUC = 0.61 to predict the need for admission to the intensive care unit (ICU). AdaBoost had similar performance with ElasticNet in predicting the need for admission to ICU. Analysis of the key radiomic metrics that drive model prediction and performance showed the importance of first-order texture metrics compared to other radiomics panel metrics. Using a Venn-diagram analysis, two first-order texture metrics and one second-order texture metric that consistently played an important role in driving model performance in all three outcome predictions were identified. CONCLUSIONS: Considering the quantitative nature and reliability of radiomic metrics, they can be used prospectively as prognostic markers to individualize treatment plans for COVID-19 patients and also assist with healthcare resource management. ADVANCES IN KNOWLEDGE: We report on the performance of CXR-based imaging metrics extracted from RT-PCR positive COVID-19 patients at admission to develop machine-learning algorithms for predicting the need for ICU, the need for intubation, and mortality, respectively.

Benchmarking Various Radiomic Toolkit Features While Applying the Image Biomarker Standardization Initiative toward Clinical Translation of Radiomic Analysis.

The image biomarkers standardization initiative (IBSI) was formed to address the standardization of extraction of quantifiable imaging metrics. Despite its effort, there remains a lack of consensus or established guidelines regarding radiomic feature terminology, the underlying mathematics and their implementation across various software programs. This creates a scenario where features extracted using different toolboxes cannot be used to build or validate the same model leading to a non-generalization of radiomic results. In this study, IBSI-established phantom and benchmark values were used to compare the variation of the radiomic features while using 6 publicly available software programs and 1 in-house radiomics pipeline. All IBSI-standardized features (11 classes, 173 in total) were extracted. The relative differences between the extracted feature values from the different software programs and the IBSI benchmark values were calculated to measure the inter-software agreement. To better understand the variations, features are further grouped into 3 categories according to their properties: 1) morphology, 2) statistic/histogram and 3)texture features. While a good agreement was observed for a majority of radiomics features across the various tested programs, relatively poor agreement was observed for morphology features. Significant differences were also found in programs that use different gray-level discretization approaches. Since these software programs do not include all IBSI features, the level of quantitative assessment for each category was analyzed using Venn and UpSet diagrams and quantified using two ad hoc metrics. Morphology features earned lowest scores for both metrics, indicating that morphological features are not consistently evaluated among software programs. We conclude that radiomic features calculated using different software programs may not be interchangeable. Further studies are needed to standardize the workflow of radiomic feature extraction.