Artificial intelligence and machine learning applications for the imaging of bone and soft tissue tumors.

Recent advancements in artificial intelligence (AI) and machine learning offer numerous opportunities in musculoskeletal radiology to potentially bolster diagnostic accuracy, workflow efficiency, and predictive modeling. AI tools have the capability to assist radiologists in many tasks ranging from image segmentation, lesion detection, and more. In bone and soft tissue tumor imaging, radiomics and deep learning show promise for malignancy stratification, grading, prognostication, and treatment planning. However, challenges such as standardization, data integration, and ethical concerns regarding patient data need to be addressed ahead of clinical translation. In the realm of musculoskeletal oncology, AI also faces obstacles in robust algorithm development due to limited disease incidence. While many initiatives aim to develop multitasking AI systems, multidisciplinary collaboration is crucial for successful AI integration into clinical practice. Robust approaches addressing challenges and embodying ethical practices are warranted to fully realize AI's potential for enhancing diagnostic accuracy and advancing patient care.

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.

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.

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.

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.

Whole-tumor 3D volumetric MRI-based radiomics approach for distinguishing between benign and malignant soft tissue tumors.

OBJECTIVES: Our purpose was to differentiate between malignant from benign soft tissue neoplasms using a combination of MRI-based radiomics metrics and machine learning. METHODS: Our retrospective study identified 128 histologically diagnosed benign (n = 36) and malignant (n = 92) soft tissue lesions. 3D ROIs were manually drawn on 1 sequence of interest and co-registered to other sequences obtained during the same study. One thousand seven hundred eight radiomics features were extracted from each ROI. Univariate analyses with supportive ROC analyses were conducted to evaluate the discriminative power of predictive models constructed using Real Adaptive Boosting (Adaboost) and Random Forest (RF) machine learning approaches. RESULTS: Univariate analyses demonstrated that 36.89% of individual radiomics varied significantly between benign and malignant lesions at the p ≤ 0.05 level. Adaboost and RF performed similarly well, with AUCs of 0.77 (95% CI 0.68-0.85) and 0.72 (95% CI 0.63-0.81), respectively, after 10-fold cross-validation. Restricting the machine learning models to only sequences extracted from T2FS and STIR sequences maintained comparable performance, with AUCs of 0.73 (95% CI 0.64-0.82) and 0.75 (95% CI 0.65-0.84), respectively. CONCLUSION: Machine learning decision classifiers constructed from MRI-based radiomics features show promising ability to preoperatively discriminate between benign and malignant soft tissue masses. Our approach maintains applicability even when the dataset is restricted to T2FS and STIR fluid-sensitive sequences, which may bolster practicality in clinical application scenarios by eliminating the need for complex co-registrations for multisequence analysis. KEY POINTS: • Predictive models constructed from MRI-based radiomics data and machine learning-augmented approaches yielded good discriminative power to correctly classify benign and malignant lesions on preoperative scans, with AUCs of 0.77 (95% CI 0.68-0.85) and 0.72 (95% CI 0.63-0.81) for Real Adaptive Boosting (Adaboost) and Random Forest (RF), respectively. • Restricting the models to only use metrics extracted from T2 fat-saturated (T2FS) and Short-Tau Inversion Recovery (STIR) sequences yielded similar performance, with AUCs of 0.73 (95% CI 0.64-0.82) and 0.75 (95% CI 0.65-0.84) for Adaboost and RF, respectively. • Radiomics-based machine learning decision classifiers constructed from multicentric data more closely mimic the real-world practice environment and warrant additional validation ahead of prospective implementation into clinical workflows.

Shape and texture-based radiomics signature on CT effectively discriminates benign from malignant renal masses.

OBJECTIVES: Using a radiomics framework to quantitatively analyze tumor shape and texture features in three dimensions, we tested its ability to objectively and robustly distinguish between benign and malignant renal masses. We assessed the relative contributions of shape and texture metrics separately and together in the prediction model. MATERIALS AND METHODS: Computed tomography (CT) images of 735 patients with 539 malignant and 196 benign masses were segmented in this retrospective study. Thirty-three shape and 760 texture metrics were calculated per tumor. Tumor classification models using shape, texture, and both metrics were built using random forest and AdaBoost with tenfold cross-validation. Sensitivity analyses on five sub-cohorts with respect to the acquisition phase were conducted. Additional sensitivity analyses after multiple imputation were also conducted. Model performance was assessed using AUC. RESULTS: Random forest classifier showed shape metrics featuring within the top 10% performing metrics regardless of phase, attaining the highest variable importance in the corticomedullary phase. Convex hull perimeter ratio is a consistently high-performing shape feature. Shape metrics alone achieved an AUC ranging 0.64-0.68 across multiple classifiers, compared with 0.67-0.75 and 0.68-0.75 achieved by texture-only and combined models, respectively. CONCLUSION: Shape metrics alone attain high prediction performance and high variable importance in the combined model, while being independent of the acquisition phase (unlike texture). Shape analysis therefore should not be overlooked in its potential to distinguish benign from malignant tumors, and future radiomics platforms powered by machine learning should harness both shape and texture metrics. KEY POINTS: • Current radiomics research is heavily weighted towards texture analysis, but quantitative shape metrics should not be ignored in their potential to distinguish benign from malignant renal tumors. • Shape metrics alone can attain high prediction performance and demonstrate high variable importance in the combined shape and texture radiomics model. • Any future radiomics platform powered by machine learning should harness both shape and texture metrics, especially since tumor shape (unlike texture) is independent of the acquisition phase and more robust from the imaging variations.

Deep learning based classification of solid lipid-poor contrast enhancing renal masses using contrast enhanced CT.

OBJECTIVE: Establish a workflow that utilizes convolutional neural nets (CNN) to classify solid, lipid-poor, contrast enhancing renal masses using multiphase contrast enhanced CT (CECT) images and to assess the performance of the resulting network. METHODS: In this institutional review board approved study of 143 patients with predominantly solid, lipid-poor, contrast enhancing renal lesions (46 benign and 97 malignant), patients with a pre-operative multiphase CECT of the abdomen and pelvis obtained between June 2009 and June 2015 were retrospectively queried. Benign renal masses included oncocytoma and lipid-poor angiomyolipoma and the malignant group included clear cell, papillary, and chromophobe carcinomas.Region of interests of whole tumor volumes were manually segmented, and CT phase images with the largest cross-section of the segmented tumor in the axial plane were used for assessment. Post-surgical pathological evaluation was used to establish diagnosis.The segmented images of renal masses were used as input to a CNN. The data were augmented and split into training (83.9%) and validation sets (16.1%) to determine the hyperparameters of the CNN. Thereafter. the performance of the resulting CNN was quantified using eightfold cross-validation. RESULTS: The CNN-based classifier demonstrated an overall accuracy of 78% (95% confidence interval: 76-80%), sensitivity of 70% (95% confidence interval: 66-74%), specificity of 81% (79-83%) and an area under the curve of 0.82. CONCLUSION: A CNN-based classifier to diagnose solid enhancing malignant renal masses based on multiphase CECT images was developed. ADVANCES IN KNOWLEDGE: It was established that a CNN-based classifier could be trained to accurately distinguish malignant renal lesions.

Quantitative magnetic resonance imaging (q-MRI) for the assessment of soft-tissue sarcoma treatment response: a narrative case review of technique development.

Soft-tissue sarcomas are a heterogeneous class of tumors that exhibit varying degrees of cellularity and cystic degeneration in response to neoadjuvant chemotherapy. This creates unique challenges in the radiographic assessment of treatment response when relying on conventional markers such as tumor diameter (RECIST criteria). In this case series, we provide a narrative discussion of technique development for whole tumor volume quantitative magnetic resonance imaging (q-MRI), highlighting cases from a small pilot study of 8 patients (9 tumors) pre- and post-neoadjuvant chemotherapy. One of the methods of q-MRI analysis (the "constant-cutoff" technique) was able to predict responders versus non-responders based on percent necrosis and viable tumor volume calculations (p = 0.05), respectively. Our results suggest that q-MRI of whole tumor volume contrast enhancement may have a role in tumor response assessment, although further validation is needed.