Predictive [18F]-FDG PET/CT-Based Radiogenomics Modelling of Driver Gene Mutations in Non-small Cell Lung Cancer.

RATIONALE AND OBJECTIVES: To investigate whether [18F]-FDG PET/CT-derived radiomics may correlate with driver gene mutations in non-small cell lung cancer (NSCLC) patients. MATERIALS AND METHODS: In this IRB-approved retrospective study, 203 patients with surgically treated NSCLC who underwent subsequent genomic analysis of the primary tumour at our institution between December 2004 and January 2014 were identified. Of those, 128 patients (mean age 62.4 ± 10.8 years; range: 35-84) received preoperative [18F]-FDG PET/CT as part of their initial staging and thus were included in the study. PET and CT image segmentation and feature extraction were performed semi-automatically with an open-source software platform (LIFEx, Version 6.30, lifexsoft.org). Molecular profiles using different next-generation sequencing (NGS) panels were collected from a web-based resource (cBioPortal.ca for Cancer genomics). Two statistical models were then built to evaluate the predictive ability of [18F]-FDG PET/CT-derived radiomics features for driver gene mutations in NSCLC. RESULTS: More than half (68/128, 53%) of all tumour samples harboured three or more gene mutations. Overall, 55% of tumour samples demonstrated a mutation in TP53, 26% of samples had alterations in KRAS and 17% in EGFR. Extensive statistical analysis resulted in moderate to good predictive ability. The highest Youden Index for TP53 was achieved using combined PET/CT features (0.70), for KRAS using PET features only (0.57) and for EGFR using CT features only (0.60). CONCLUSION: Our study demonstrated a moderate to good correlation between radiomics features and driver gene mutations in NSCLC, indicating increased predictive ability of genomic profiles using combined [18F]-FDG PET/CT-derived radiomics features.

Gastro-Esophageal Cancer: Can Radiomic Parameters from Baseline 18F-FDG-PET/CT Predict the Development of Distant Metastatic Disease?

We aimed to determine if clinical parameters and radiomics combined with sarcopenia status derived from baseline 18F-FDG-PET/CT could predict developing metastatic disease and overall survival (OS) in gastroesophageal cancer (GEC). Patients referred for primary staging who underwent 18F-FDG-PET/CT from 2008 to 2019 were evaluated retrospectively. Overall, 243 GEC patients (mean age = 64) were enrolled. Clinical, histopathology, and sarcopenia data were obtained, and primary tumor radiomics features were extracted. For classification (early-stage vs. advanced disease), the association of the studied parameters was evaluated. Various clinical and radiomics models were developed and assessed. Accuracy and area under the curve (AUC) were calculated. For OS prediction, univariable and multivariable Cox analyses were performed. The best model included PET/CT radiomics features, clinical data, and sarcopenia score (accuracy = 80%; AUC = 88%). For OS prediction, various clinical, CT, and PET features entered the multivariable analysis. Three clinical factors (advanced disease, age ≥ 70 and ECOG ≥ 2), along with one CT-derived and one PET-derived radiomics feature, retained their significance. Overall, 18F-FDG PET/CT radiomics seems to have a potential added value in identifying GEC patients with advanced disease and may enhance the performance of baseline clinical parameters. These features may also have a prognostic value for OS, improving the decision-making for GEC patients.

The [18F]F-FDG PET/CT Radiomics Classifier of Histologic Subtypes and Anatomical Disease Origins across Various Malignancies: A Proof-of-Principle Study.

We aimed to investigate whether [18F]F-FDG-PET/CT-derived radiomics can classify histologic subtypes and determine the anatomical origin of various malignancies. In this IRB-approved retrospective study, 391 patients (age = 66.7 ± 11.2) with pulmonary (n = 142), gastroesophageal (n = 128) and head and neck (n = 121) malignancies were included. Image segmentation and feature extraction were performed semi-automatically. Two models (all possible subset regression [APS] and recursive partitioning) were employed to predict histology (squamous cell carcinoma [SCC; n = 219] vs. adenocarcinoma [AC; n = 172]), the anatomical origin, and histology plus anatomical origin. The recursive partitioning algorithm outperformed APS to determine histology (sensitivity 0.90 vs. 0.73; specificity 0.77 vs. 0.65). The recursive partitioning algorithm also revealed good predictive ability regarding anatomical origin. Particularly, pulmonary malignancies were identified with high accuracy (sensitivity 0.93; specificity 0.98). Finally, a model for the synchronous prediction of histology and anatomical disease origin resulted in high accuracy in determining gastroesophageal AC (sensitivity 0.88; specificity 0.92), pulmonary AC (sensitivity 0.89; specificity 0.88) and head and neck SCC (sensitivity 0.91; specificity 0.92). Adding PET-features was associated with marginal incremental value for both the prediction of histology and origin in the APS model. Overall, our study demonstrated a good predictive ability to determine patients' histology and anatomical origin using [18F]F-FDG-PET/CT-derived radiomics features, mainly from CT.

Comparison of 68Ga-DOTATATE Positron Emmited Tomography/Computed Tomography and Gadoxetic Acid-Enhanced Magnetic Resonance Imaging for the Detection of Liver Metastases from Well-Differentiated Neuroendocrine Tumors.

This study aimed to compare the detection of neuroendocrine tumor liver metastases (NLMs) in hepatobiliary-specific contrast-enhanced MRI (pMR) versus 68Ga-DOTATATE PET/CT (DT-PET). This retrospective study cohort included 30 patients with well-differentiated neuroendocrine tumors who underwent both DT-PET and pMR. Two readers independently assessed NLMs count, SUVmax on DT-PET, and signal characteristics on pMR. A consensus review by two additional readers resolved discrepancies between the modalities. Results showed concordance between DT-PET and pMR NLM count in 14/30 patients (47%). pMR identified more NLMs in 12/30 patients (40%), of which 4 patients showed multiple deposits on pMR but only 0-1 lesions on DT-PET. DT-PET detected more in 4/30 patients (13%). Overall, pMR detected more metastases than DT-PET (p = 0.01). Excluding the four outliers, there was excellent agreement between the two methods (ICC: 0.945, 95%CI: 0.930, 0.958). Notably, pMR had a higher NLM detection rate than DT-PET, with correlations found between lesion size on pMR and DT-PET detectability, as well as diffusion restriction on pMR and SUVmax on DT-PET. In conclusion, in consecutive patients with well-differentiated NETs, the detection rate of NLM is higher with pMR than with DT-PET. However, when excluding patients whose tumors do not overexpress somatostatin receptors (13% of the cohort), high concordance in the detection of NLM is observed between DT PET and pMR.

Diagnostic performance of whole-body [18F]FDG PET/MR in cancer M staging: A systematic review and meta-analysis.

OBJECTIVES: To calculate the pooled diagnostic performances of whole-body [18F]FDG PET/MR in M staging of [18F]FDG-avid cancer entities. METHODS: A diagnostic meta-analysis was conducted on the [18F]FDG PET/MR in M staging, including studies: (1) evaluated [18F]FDG PET/MR in detecting distant metastasis; (2) compared[ 18F]FDG PET/MR with histopathology, follow-up, or asynchronous multimodality imaging as the reference standard; (3) provided data for the whole-body evaluation; (4) provided adequate data to calculate the meta-analytic performances. Pooled performances were calculated with their confidence interval. In addition, forest plots, SROC curves, and likelihood ratio scatterplots were drawn. All analyses were performed using STATA 16. RESULTS: From 52 eligible studies, 2289 patients and 2072 metastases were entered in the meta-analysis. The whole-body pooled sensitivities were 0.95 (95%CI: 0.91-0.97) and 0.97 (95%CI: 0.91-0.99) at the patient and lesion levels, respectively. The pooled specificities were 0.99 (95%CI: 0.97-1.00) and 0.97 (95%CI: 0.90-0.99), respectively. Additionally, subgroup analyses were performed. The calculated pooled sensitivities for lung, gastrointestinal, breast, and gynecological cancers were 0.90, 0.93, 1.00, and 0.97, respectively. The pooled specificities were 1.00, 0.98, 0.97, and 1.00, respectively. Furthermore, the pooled sensitivities for non-small cell lung, colorectal, and cervical cancers were 0.92, 0.96, and 0.86, respectively. The pooled specificities were 1.00, 0.95, and 1.00, respectively. CONCLUSION: [18F]FDG PET/MR was a highly accurate modality in M staging in the reported [18F]FDG-avid malignancies. The results showed high sensitivity and specificity in each reviewed malignancy type. Thus, our findings may help clinicians and patients to be confident about the performance of [18F]FDG PET/MR in the clinic. CLINICAL RELEVANCE STATEMENT: Although [18F]FDG PET/MR is not a routine imaging technique in current guidelines, mostly due to its availability and logistic issues, our findings might add to the limited evidence regarding its performance, showing a sensitivity of 0.95 and specificity of 0.97. KEY POINTS: • The whole-body [18F]FDG PET/MR showed high accuracy in detecting distant metastases at both patient and lesion levels. • The pooled sensitivities were 95% and 97% and pooled specificities were 99% and 97% at patient and lesion levels, respectively. • The results suggested that 18F-FDG PET/MR was a strong modality in the exclusion and confirmation of distant metastases.

Disparity and Diversity in NSCLC Imaging and Genomics: Evaluation of a Mature, Multicenter Database.

Lung cancer remains the leading cancer-related death across North America. Imaging is fundamental. Recently, healthcare disparities came into research focus. Our aim was to explore disparity from an imaging, genetic, and outcome perspective. We utilized the AACR Project GENIE Biopharma Consortium (BPC) dataset v 1.1 to build a collated NSCLC dataset. Descriptive and analytical statistics were applied according to data characteristics. From 1849 patients, mean age was 64.4 y (±10.5), 58% (n = 1065) were female, 23% (n = 419) never smoked, 84% (n = 1545) were of white race, and 57% (n = 1052) were < stage III. No difference (p > 0.05) was found for baseline imaging by race. White race showed higher 3-month surveillance imaging (p = 0.048) and a baseline stage < IV (OR 0.61). KRAS (33.3 vs. 17.9%), STK11 (14.8 vs. 7.3%), and KEAP1 (13.3 vs. 5.3%) mutations were predominant among white patients while EGFR mutation (19.2 vs. 44.1%) was less predominant. Mutations in TP53 or KEAP1 had worse PFS and OS. The latter was also reduced in STK11, KRAS + STK11, and KRAS + KEAP1 mutations. Meanwhile, EGFR mutation had increased OS. Multivariate analysis showed that progression on imaging at 3 or 6 months (HR 1.69 and 1.43, respectively), TP53 (HR 1.37) and KRAS (HR 1.26) had lower OS while EGFR and LRP1B (HR 0.69 and 0.39, respectively) had higher OS. No racial disparity at baseline imaging was observed. Higher initial stages among non-white patients might reflect inequalities in accessing healthcare. However, race wasn't associated to OS. Finally, progression in imaging at 3 or 6 months showed the higher hazard ratios for death.

Prognostic Value of Sarcopenia and Metabolic Parameters of 18F-FDG-PET/CT in Patients with Advanced Gastroesophageal Cancer.

We investigated the prognostic value of sarcopenia measurements and metabolic parameters of primary tumors derived from 18F-FDG-PET/CT among patients with primary, metastatic esophageal and gastroesophageal cancer. A total of 128 patients (26 females; 102 males; mean age 63.5 ± 11.7 years; age range: 29-91 years) with advanced metastatic gastroesophageal cancer who underwent 18F-FDG-PET/CT as part of their initial staging between November 2008 and December 2019 were included. Mean and maximum standardized uptake value (SUV) and SUV normalized by lean body mass (SUL) were measured. Skeletal muscle index (SMI) was measured at the level of L3 on the CT component of the 18F-FDG-PET/CT. Sarcopenia was defined as SMI < 34.4 cm2/m2 in women and <45.4 cm2/m2 in men. A total of 60/128 patients (47%) had sarcopenia on baseline 18F-FDG-PET/CT. Mean SMI in patients with sarcopenia was 29.7 cm2/m2 in females and 37.5 cm2/m2 in males. In a univariable analysis, ECOG (<0.001), bone metastases (p = 0.028), SMI (p = 0.0075) and dichotomized sarcopenia score (p = 0.033) were significant prognostic factors for overall survival (OS) and progression-free survival (PFS). Age was a poor prognostic factor for OS (p = 0.017). Standard metabolic parameters were not statistically significant in the univariable analysis and thus were not evaluated further. In a multivariable analysis, ECOG (p < 0.001) and bone metastases (p = 0.019) remained significant poor prognostic factors for OS and PFS. The final model demonstrated improved OS and PFS prognostication when combining clinical parameters with imaging-derived sarcopenia measurements but not metabolic tumor parameters. In summary, the combination of clinical parameters and sarcopenia status, but not standard metabolic values from 18F-FDG-PET/CT, may improve survival prognostication in patients with advanced, metastatic gastroesophageal cancer.

Inter-observer variability of expert-derived morphologic risk predictors in aortic dissection.

OBJECTIVES: Establishing the reproducibility of expert-derived measurements on CTA exams of aortic dissection is clinically important and paramount for ground-truth determination for machine learning. METHODS: Four independent observers retrospectively evaluated CTA exams of 72 patients with uncomplicated Stanford type B aortic dissection and assessed the reproducibility of a recently proposed combination of four morphologic risk predictors (maximum aortic diameter, false lumen circumferential angle, false lumen outflow, and intercostal arteries). For the first inter-observer variability assessment, 47 CTA scans from one aortic center were evaluated by expert-observer 1 in an unconstrained clinical assessment without a standardized workflow and compared to a composite of three expert-observers (observers 2-4) using a standardized workflow. A second inter-observer variability assessment on 30 out of the 47 CTA scans compared observers 3 and 4 with a constrained, standardized workflow. A third inter-observer variability assessment was done after specialized training and tested between observers 3 and 4 in an external population of 25 CTA scans. Inter-observer agreement was assessed with intraclass correlation coefficients (ICCs) and Bland-Altman plots. RESULTS: Pre-training ICCs of the four morphologic features ranged from 0.04 (-0.05 to 0.13) to 0.68 (0.49-0.81) between observer 1 and observers 2-4 and from 0.50 (0.32-0.69) to 0.89 (0.78-0.95) between observers 3 and 4. ICCs improved after training ranging from 0.69 (0.52-0.87) to 0.97 (0.94-0.99), and Bland-Altman analysis showed decreased bias and limits of agreement. CONCLUSIONS: Manual morphologic feature measurements on CTA images can be optimized resulting in improved inter-observer reliability. This is essential for robust ground-truth determination for machine learning models. KEY POINTS: • Clinical fashion manual measurements of aortic CTA imaging features showed poor inter-observer reproducibility. • A standardized workflow with standardized training resulted in substantial improvements with excellent inter-observer reproducibility. • Robust ground truth labels obtained manually with excellent inter-observer reproducibility are key to develop reliable machine learning models.

CT Radiomics and Whole Genome Sequencing in Patients with Pancreatic Ductal Adenocarcinoma: Predictive Radiogenomics Modeling.

We investigate whether computed tomography (CT) derived radiomics may correlate with driver gene mutations in patients with pancreatic ductal adenocarcinoma (PDAC). In this retrospective study, 47 patients (mean age 64 ± 11 years; range: 42-86 years) with PDAC, who were treated surgically and who underwent preoperative CT imaging at our institution were included in the study. Image segmentation and feature extraction was performed semi-automatically with a commonly used open-source software platform. Genomic data from whole genome sequencing (WGS) were collected from our institution's web-based resource. Two statistical models were then built, in order to evaluate the predictive ability of CT-derived radiomics feature for driver gene mutations in PDAC. 30/47 of all tumor samples harbored 2 or more gene mutations. Overall, 81% of tumor samples demonstrated mutations in KRAS, 68% of samples had alterations in TP53, 26% in SMAD4 and 19% in CDKN2A. Extended statistical analysis revealed acceptable predictive ability for KRAS and TP53 (Youden Index 0.56 and 0.67, respectively) and mild to acceptable predictive signal for SMAD4 and CDKN2A (Youden Index 0.5, respectively). Our study establishes acceptable correlation of radiomics features and driver gene mutations in PDAC, indicating an acceptable prognostication of genomic profiles using CT-derived radiomics. A larger and more homogenous cohort may further enhance the predictive ability.

Prognostic value of PET/CT and MR-based baseline radiomics among patients with non-metastatic nasopharyngeal carcinoma.

Purpose: Radiomics is an emerging imaging assessment technique that has shown promise in predicting survival among nasopharyngeal carcinoma (NPC) patients. Studies so far have focused on PET or MR-based radiomics independently. The aim of our study was to evaluate the prognostic value of clinical and radiomic parameters derived from both PET/CT and MR. Methods: Retrospective evaluation of 124 NPC patients with PET/CT and radiotherapy planning MR (RP-MR). Primary tumors were segmented using dedicated software (LIFEx version 6.1) from PET, CT, contrast-enhanced T1-weighted (T1-w), and T2-weighted (T2-w) MR sequences with 376 radiomic features extracted. Summary statistics describe patient, disease, and treatment characteristics. The Kaplan-Meier (KM) method estimates overall survival (OS) and progression-free survival (PFS). Clinical factors selected based on univariable analysis and the multivariable Cox model were subsequently constructed with radiomic features added. Results: The final models comparing clinical, clinical + RP-MR, clinical + PET/CT and clinical + RP-MR + PET/CT for OS and PFS demonstrated that combined radiomic signatures were significantly associated with improved survival prognostication (AUC 0.62 vs 0.81 vs 0.75 vs 0.86 at 21 months for PFS and 0.56 vs 0.85 vs 0.79 vs 0.96 at 24 months for OS). Clinical + RP-MR features initially outperform clinical + PET/CT for both OS and PFS (<18 months), and later in the clinical course for PFS (>42 months). Conclusion: Our study demonstrated that PET/CT-based radiomic features may improve survival prognostication among NPC patients when combined with baseline clinical and MR-based radiomic features.

Prognostic Value of [18F]-FDG PET/CT Radiomics Combined with Sarcopenia Status among Patients with Advanced Gastroesophageal Cancer.

We investigated, whether 18[18F]-FDG PET/CT-derived radiomics combined with sarcopenia measurements improves survival prognostication among patients with advanced, metastatic gastroesophageal cancer. In our study, 128 consecutive patients with advanced, metastatic esophageal and gastroesophageal cancer (n = 128; 26 females; 102 males; mean age 63.5 ± 11.7 years; age range: 29−91 years) undergoing 18[18F]-FDG PET/CT for staging between November 2008 and December 2019 were included. Segmentation of the primary tumor and radiomics analysis derived from PET and CT images was performed semi-automatically with a commonly used open-source software platform (LIFEX, Version 6.30, lifexsoft.org). Patients' nutritional status was determined by measuring the skeletal muscle index (SMI) at the level of L3 on the CT component. Univariable and multivariable analyses were performed to establish a survival prediction model including radiomics, clinical data, and SMI score. Univariable Cox proportional hazards model revealed ECOG (<0.001) and bone metastasis (p = 0.028) to be significant clinical parameters for overall survival (OS) and progression free survival (PFS). Age (p = 0.017) was an additional prognostic factor for OS. Multivariable analysis showed improved prognostication for overall and progression free survival when adding sarcopenic status, PET and CT radiomics to the model with clinical parameters only. PET and CT radiomics derived from hybrid 18[18F]-FDG PET/CT combined with sarcopenia measurements and clinical parameters may improve survival prediction among patients with advanced, metastatic gastroesophageal cancer.

Diagnostic performance of [18F]-FDG PET/MR in evaluating colorectal cancer: a systematic review and meta-analysis.

PURPOSE: To calculate the diagnostic performance of [18F]-FDG PET/MR in colorectal cancer (CRC). METHODS: This study was designed following the PRISMA-DTA guidelines. To be included, published original articles (until December 31, 2021) that met the following criteria were considered eligible: (1) evaluated [18F]-FDG PET/MR as the diagnostic method to detect CRC; (2) compared [18F]-FDG PET/MR with histopathology as the reference standard, or clinical/imaging composite follow-up when pathology was not available; (3) provided adequate crude data for meta-analysis. The diagnostic pooled measurements were calculated at patient and lesion levels. Regarding sub-group analysis, diagnostic measurements were calculated in "TNM staging," "T staging," "N staging," "M staging," and "liver metastasis" sub-groups. Additionally, we calculated the pooled performances in "rectal cancer: patient-level" and "rectal cancer: lesion-level" sub-groups. A hierarchical method was used to pool the performances. The bivariate model was conducted to find the summary points. Analyses were performed using STATA 16. RESULTS: A total of 1534 patients from 18 studies were entered. The pooled sensitivities in CRC lesion detection (tumor, lymph nodes, and metastases) were 0.94 (95%CI: 0.89-0.97) and 0.93 (95%CI: 0.82-0.98) at patient-level and lesion-level, respectively. The pooled specificities were 0.89 (95%CI: 0.84-0.93) and 0.95 (95%CI: 0.90-0.98) at patient-level and lesion-level, respectively. In sub-groups, the highest sensitivity (0.97, 95%CI: 0.86-0.99) and specificity (0.99, 95%CI: 0.84-1.00) were calculated for "M staging" and "rectal cancer: lesion-level," respectively. The lowest sensitivity (0.81, 95%CI: 0.65-0.91) and specificity (0.79, 95%CI: 0.52-0.93) were calculated for "N staging" and "T staging," respectively. CONCLUSION: This meta-analysis showed an overall high diagnostic performance for [18F]-FDG PET/MR in detecting CRC lesions/metastases. Thus, this modality can play a significant role in several clinical scenarios in CRC staging and restaging. Specifically, one of the main strengths of this modality is ruling out the existence of CRC lesions/metastases. Finally, the overall diagnostic performance was not found to be affected in the post-treatment setting.

Comparison of electrodiagnosis, neurosonography and MR neurography in localization of ulnar neuropathy at the elbow.

INTRODUCTION: In patients with ulnar neuropathy at the elbow (UNE) the precise determination of the site of lesion is important for subsequent differential diagnostic considerations and therapeutic management. Due to a paucity of comparable data, to better define the role of different diagnostic tests, we performed the first prospective study comparing the diagnostic accuracy of short segment nerve stimulation, nerve ultrasonography, MR neurography (MRN), and diffusion tensor imaging (DTI) in patients with UNE. METHODS: UNE was clinically diagnosed in 17 patients with 18 affected elbows. For all 18 affected elbows in patients and 20 elbows in 10 healthy volunteers, measurements of all different diagnostic tests were performed at six anatomical positions across the elbow with measuring points from distal (D4) to proximal (P6) in relation to the medial epicondyle (P0). Additional qualitative assessment regarding structural changes of surrounding nerve anatomy was conducted. RESULTS: The difference between affected arms of patients and healthy control arms were most frequently the largest at measure intervals D2 to P0 and P0 to P2 for electrophysiological testing, or measure points P0 and P2 for all other devices, respectively. At both levels P0 and at P2, T2 contrast-to-noise ratio (CNR) of MRN and mean diffusivity (MD) of DTI-based MRN showed best accuracies. DISCUSSION: This study revealed differences in diagnostic performance of tests concerning a specific location of UNE, with better results for T2 contrast to noise ratio (CNR) in MRN and mean diffusivity of DTI-based MRN. Additional testing with MRN and nerve ultrasonography is recommended to uncover anatomical changes.

Radiomics for detecting prostate cancer bone metastases invisible in CT: a proof-of-concept study.

OBJECTIVES: To investigate, in patients with metastatic prostate cancer, whether radiomics of computed tomography (CT) image data enables the differentiation of bone metastases not visible on CT from unaffected bone using 68 Ga-PSMA PET imaging as reference standard. METHODS: In this IRB-approved retrospective study, 67 patients (mean age 71 ± 7 years; range: 55-84 years) showing a total of 205 68 Ga-PSMA-positive prostate cancer bone metastases in the thoraco-lumbar spine and pelvic bone being invisible in CT were included. Metastases and 86 68 Ga-PSMA-negative bone volumes in the same body region were segmented and further post-processed. Intra- and inter-reader reproducibility was assessed, with ICCs < 0.90 being considered non-reproducible. To account for imbalances in the dataset, data augmentation was performed to achieve improved class balance and to avoid model overfitting. The dataset was split into training, test, and validation set. After a multi-step dimension reduction process and feature selection process, the 11 most important and independent features were selected for statistical analyses. RESULTS: A gradient-boosted tree was trained on the selected 11 radiomic features in order to classify patients' bones into bone metastasis and normal bone using the training dataset. This trained model achieved a classification accuracy of 0.85 (95% confidence interval [CI]: 0.76-0.92, p < .001) with 78% sensitivity and 93% specificity. The tuned model was applied on the original, non-augmented dataset resulting in a classification accuracy of 0.90 (95% CI: 0.82-0.98) with 91% sensitivity and 88% specificity. CONCLUSION: Our proof-of-concept study indicates that radiomics may accurately differentiate unaffected bone from metastatic bone, being invisible by the human eye on CT. KEY POINTS: • This proof-of-concept study showed that radiomics applied on CT images may accurately differentiate between bone metastases and metastatic-free bone in patients with prostate cancer. • Future promising applications include automatic bone segmentation, followed by a radiomics classifier, allowing for a screening-like approach in the detection of bone metastases.

Registry of Aortic Diseases to Model Adverse Events and Progression (ROADMAP) in Uncomplicated Type B Aortic Dissection: Study Design and Rationale.

Purpose: To describe the design and methodological approach of a multicenter, retrospective study to externally validate a clinical and imaging-based model for predicting the risk of late adverse events in patients with initially uncomplicated type B aortic dissection (uTBAD). Materials and Methods: The Registry of Aortic Diseases to Model Adverse Events and Progression (ROADMAP) is a collaboration between 10 academic aortic centers in North America and Europe. Two centers have previously developed and internally validated a recently developed risk prediction model. Clinical and imaging data from eight ROADMAP centers will be used for external validation. Patients with uTBAD who survived the initial hospitalization between January 1, 2001, and December 31, 2013, with follow-up until 2020, will be retrospectively identified. Clinical and imaging data from the index hospitalization and all follow-up encounters will be collected at each center and transferred to the coordinating center for analysis. Baseline and follow-up CT scans will be evaluated by cardiovascular imaging experts using a standardized technique. Results: The primary end point is the occurrence of late adverse events, defined as aneurysm formation (≥6 cm), rapid expansion of the aorta (≥1 cm/y), fatal or nonfatal aortic rupture, new refractory pain, uncontrollable hypertension, and organ or limb malperfusion. The previously derived multivariable model will be externally validated by using Cox proportional hazards regression modeling. Conclusion: This study will show whether a recent clinical and imaging-based risk prediction model for patients with uTBAD can be generalized to a larger population, which is an important step toward individualized risk stratification and therapy.Keywords: CT Angiography, Vascular, Aorta, Dissection, Outcomes Analysis, Aortic Dissection, MRI, TEVAR© RSNA, 2022See also the commentary by Rajiah in this issue.

Incremental Prognostic Value of Coronary Artery Calcium Score for Predicting All-Cause Mortality after Transcatheter Aortic Valve Replacement.

Background Current risk models show limited performances for predicting all-cause mortality after transcatheter aortic valve replacement (TAVR). Purpose To determine the prognostic value of coronary artery calcium (CAC) scoring for predicting 30-day and 1-year mortality in patients undergoing TAVR. Materials and Methods In this single-center institutional review board-approved secondary analysis of prospectively collected data (SwissTAVI Registry), the authors evaluated participants who, before TAVR, underwent CT that included a nonenhanced electrocardiography-gated cardiac scan between May 2008 and September 2019 and who had not undergone previous coronary revascularization. Clinical data, including the European System for Cardiac Operative Risk Evaluation (EuroSCORE II), were recorded. The CAC score was determined, and 30-day and 1-year all-cause mortality were assessed by using Cox regression analyses. Results In total, 309 participants (mean age ± standard deviation, 81 years ± 7; 175 women) were included, with a median CAC score of 334 (interquartile range, 104-987). Seventy-seven of the 309 participants (25%) had a CAC score greater than or equal to 1000. A CAC score of 1000 or greater served as an independent predictor of 30-day (hazard ratio [HR], 4.5 [95% CI: 1.5, 13.6] compared with a CAC score <1000; P = .007) and 1-year (HR, 4.3 [95% CI: 1.5, 12.7] compared with a CAC score of 0-99; P = .008) mortality after TAVR. Similar trends were observed for each point increase of the EuroSCORE II as an independent predictor of 30-day (HR, 1.22 [95% CI: 1.10, 1.36]; P < .001) and 1-year (HR, 1.16 [95% CI: 1.08, 1.25]; P < .001) mortality. Adding the CAC score to the EuroSCORE II provided incremental prognostic value for 1-year mortality after TAVR over the EuroSCORE II alone (concordance index, 0.76 vs 0.69; P = .04). Conclusion In participants without prior coronary revascularization, the coronary artery calcium score represented an independent predictor of 30-day and 1-year mortality after transcatheter aortic valve replacement. ClinicalTrials.gov identifier, NCT01368250 © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Almeida in this issue.

Machine learning-based CT fractional flow reserve assessment in acute chest pain: first experience.

BACKGROUND: Computed tomography (CT)-derived fractional flow reserve (FFRCT) enables the non-invasive functional assessment of coronary artery stenosis. We evaluated the feasibility and potential clinical role of FFRCT in patients presenting to the emergency department with acute chest pain who underwent chest-pain CT (CPCT). METHODS: For this retrospective IRB-approved study, we included 56 patients (median age: 62 years, 14 females) with acute chest pain who underwent CPCT and who had at least a mild (≥25% diameter) coronary artery stenosis. CPCT was evaluated for the presence of acute plaque rupture and vulnerable plaque features. FFRCT measurements were performed using a machine learning-based software. We assessed the agreement between the results from FFRCT and patient outcome (including results from invasive catheter angiography and from any non-invasive cardiac imaging test, final clinical diagnosis and revascularization) for a follow-up of 3 months. RESULTS: FFRCT was technically feasible in 38/56 patients (68%). Eleven of the 38 patients (29%) showed acute plaque rupture in CPCT; all of them underwent immediate coronary revascularization. Of the remaining 27 patients (71%), 16 patients showed vulnerable plaque features (59%), of whom 11 (69%) were diagnosed with acute coronary syndrome (ACS) and 10 (63%) underwent coronary revascularization. In patients with vulnerable plaque features in CPCT, FFRCT had an agreement with outcome in 12/16 patients (75%). In patients without vulnerable plaque features (n=11), one patient showed myocardial ischemia (9%). In these patients, FFRCT and patient outcome showed an agreement in 10/11 patients (91%). CONCLUSIONS: Our preliminary data show that FFRCT is feasible in patients with acute chest pain who undergo CPCT provided that image quality is sufficient. FFRCT has the potential to improve patient triage by reducing further downstream testing but appears of limited value in patients with CT signs of acute plaque rupture.

Radiation Dose to the Fetus From Computed Tomography of Pregnant Patients-Development and Validation of a Web-Based Tool.

OBJECTIVE: Estimations of radiation dose absorbed by the fetus from computed tomography (CT) in pregnant patients is mandatory, but currently available methods are not feasible in clinical routine. The aims of this study were to develop and validate a tool for assessment of fetal dose from CT of pregnant patients and to develop a user-friendly web interface for fast fetal dose calculations. METHODS: In the first study part, 750 Monte Carlo (MC) simulations were performed on phantoms representing pregnant patients at various gestational stages. The MC code simulating vendor-independent dose distributions was validated against CT dose index (CTDI) measurements performed on CT scanners of 2 vendors. The volume CTDI-normalized fetal dose values from MC simulations were used for developing the computational algorithm enabling fetal dose assessments from CT of various body regions at different exposure settings. In the institutional review board-approved second part, the algorithm was validated against patient-specific MC simulations performed on CT data of 29 pregnant patients (gestational ages 8-35 weeks) who underwent CT. Furthermore, the tool was compared with a commercially available software. A user-friendly web-based interface for fetal dose calculations was created. RESULTS: Weighted CTDI values obtained from MC simulations were in excellent agreement with measurements performed on the 2 CT systems (average error, 4%). The median fetal dose from abdominal CT in pregnant patients was 2.7 mGy, showing moderate correlation with maternal perimeter (r = 0.69). The algorithm provided accurate estimates of fetal doses (average error, 11%), being more accurate than the commercially available tool. The web-based interface (www.fetaldose.org) enabling vendor-independent calculations of fetal doses from CT requires the input of gestational age, volume CTDI, tube voltage, and scan region. CONCLUSIONS: A tool for fetal dose assessments from CT of pregnant patients was developed and validated being freely available on a user-friendly web interface.

Aortic valve calcification scoring with computed tomography: impact of iterative reconstruction techniques.

To investigate whether image reconstruction with iterative reconstruction (IR) affects aortic valve calcification (AVC) scoring and likelihood categorization of severe aortic stenosis (AS). In this IRB-approved retrospective study, we included 100 consecutive patients with AS (40 females; mean age 77 ± 10 years; age range: 36-99 years) undergoing CT prior to transcatheter aortic valve replacement. Non-enhanced, electrocardiography-gated CT of the heart was reconstructed with filtered back projection (FBP) and with advanced modeled IR at strength levels 1-5. AVC Agatston scores were calculated and gender-specific cut-off values for AS likelihood categorization were applied according to current European Society of Cardiology recommendations (from unlikely to very likely). Friedman test with post-hoc Bonferroni correction was applied to analyze interval- and ordinal-scaled data. Compared to FBP, each IR strength level produced significantly different AVC Agatston scores (p < 0.001-0.002). Median AVC Agatston score for image reconstruction with FBP was 2527 (IQR: 1711-3663) and decreased with increasing IR strength levels up to 2281 (IQR: 1471-3357) at strength level 5. Likelihood categorization of severe AS was significantly different among image reconstruction algorithms (p < 0.001). Image reconstruction with IR strength level 5 led to a downward shift of likelihood categorization in 28 patients (28%) compared to images reconstructed with FBP. IR significantly impacts AVC scoring with significantly decreasing AVC scores with increasing IR strength levels. This leads to relevant changes in likelihood categorization of patients with severe AS., leading to underestimation of severe AS.