A Transfer Learning-Based Framework for Classifying Lymph Node Metastasis in Prostate Cancer Patients.

Background: Prostate cancer is the second most common new cancer diagnosis in the United States. It is usually slow-growing, and when it is low-grade and confined to the prostate gland, it can be treated either conservatively (through active surveillance) or with surgery. However, if the cancer has spread beyond the prostate, such as to the lymph nodes, then that indicates a more aggressive cancer, and surgery may not be adequate. Methods: The challenge is that it is often difficult for radiologists reading prostate-specific imaging such as magnetic resonance images (MRIs) to differentiate malignant lymph nodes from non-malignant ones. An emerging field is the development of artificial intelligence (AI) models, including machine learning and deep learning, for medical imaging to assist in diagnostic tasks. Earlier research focused on implementing texture algorithms to extract imaging features used in classification models. More recently, researchers began studying the use of deep learning for both stand-alone feature extraction and end-to-end classification tasks. In order to tackle the challenges inherent in small datasets, this study was designed as a scalable hybrid framework utilizing pre-trained ResNet-18, a deep learning model, to extract features that were subsequently fed into a machine learning classifier to automatically identify malignant lymph nodes in patients with prostate cancer. For comparison, two texture algorithms were implemented, namely the gray-level co-occurrence matrix (GLCM) and Gabor. Results: Using an institutional prostate lymph node dataset (42 positives, 84 negatives), the proposed framework achieved an accuracy of 76.19%, a sensitivity of 79.76%, and a specificity of 69.05%. Using GLCM features, the classification achieved an accuracy of 61.90%, a sensitivity of 74.07%, and a specificity of 42.86%. Using Gabor features, the classification achieved an accuracy of 65.08%, a sensitivity of 73.47%, and a specificity of 52.50%. Conclusions: Our results demonstrate that a hybrid approach, i.e., using a pre-trainined deep learning model for feature extraction, followed by a machine learning classifier, is a viable solution. This hybrid approach is especially useful in medical-imaging-based applications with small datasets.

Natural language processing pipeline to extract prostate cancer-related information from clinical notes.

OBJECTIVES: To develop an automated pipeline for extracting prostate cancer-related information from clinical notes. MATERIALS AND METHODS: This retrospective study included 23,225 patients who underwent prostate MRI between 2017 and 2022. Cancer risk factors (family history of cancer and digital rectal exam findings), pre-MRI prostate pathology, and treatment history of prostate cancer were extracted from free-text clinical notes in English as binary or multi-class classification tasks. Any sentence containing pre-defined keywords was extracted from clinical notes within one year before the MRI. After manually creating sentence-level datasets with ground truth, Bidirectional Encoder Representations from Transformers (BERT)-based sentence-level models were fine-tuned using the extracted sentence as input and the category as output. The patient-level output was determined by compilation of multiple sentence-level outputs using tree-based models. Sentence-level classification performance was evaluated using the area under the receiver operating characteristic curve (AUC) on 15% of the sentence-level dataset (sentence-level test set). The patient-level classification performance was evaluated on the patient-level test set created by radiologists by reviewing the clinical notes of 603 patients. Accuracy and sensitivity were compared between the pipeline and radiologists. RESULTS: Sentence-level AUCs were ≥ 0.94. The pipeline showed higher patient-level sensitivity for extracting cancer risk factors (e.g., family history of prostate cancer, 96.5% vs. 77.9%, p < 0.001), but lower accuracy in classifying pre-MRI prostate pathology (92.5% vs. 95.9%, p = 0.002) and treatment history of prostate cancer (95.5% vs. 97.7%, p = 0.03) than radiologists, respectively. CONCLUSION: The proposed pipeline showed promising performance, especially for extracting cancer risk factors from patient's clinical notes. CLINICAL RELEVANCE STATEMENT: The natural language processing pipeline showed a higher sensitivity for extracting prostate cancer risk factors than radiologists and may help efficiently gather relevant text information when interpreting prostate MRI. KEY POINTS: When interpreting prostate MRI, it is necessary to extract prostate cancer-related information from clinical notes. This pipeline extracted the presence of prostate cancer risk factors with higher sensitivity than radiologists. Natural language processing may help radiologists efficiently gather relevant prostate cancer-related text information.

Liver Fibrosis, Fat, and Iron Evaluation with MRI and Fibrosis and Fat Evaluation with US: A Practical Guide for Radiologists.

Quantitative imaging biomarkers of liver disease measured by using MRI and US are emerging as important clinical tools in the management of patients with chronic liver disease (CLD). Because of their high accuracy and noninvasive nature, in many cases, these techniques have replaced liver biopsy for the diagnosis, quantitative staging, and treatment monitoring of patients with CLD. The most commonly evaluated imaging biomarkers are surrogates for liver fibrosis, fat, and iron. MR elastography is now routinely performed to evaluate for liver fibrosis and typically combined with MRI-based liver fat and iron quantification to exclude or grade hepatic steatosis and iron overload, respectively. US elastography is also widely performed to evaluate for liver fibrosis and has the advantage of lower equipment cost and greater availability compared with those of MRI. Emerging US fat quantification methods can be performed along with US elastography. The author group, consisting of members of the Society of Abdominal Radiology (SAR) Liver Fibrosis Disease-Focused Panel (DFP), the SAR Hepatic Iron Overload DFP, and the European Society of Radiology, review the basics of liver fibrosis, fat, and iron quantification with MRI and liver fibrosis and fat quantification with US. The authors cover technical requirements, typical case display, quality control and proper measurement technique and case interpretation guidelines, pitfalls, and confounding factors. The authors aim to provide a practical guide for radiologists interpreting these examinations. © RSNA, 2023 See the invited commentary by Ronot in this issue. Quiz questions for this article are available in the supplemental material.

Performing Automatic Identification and Staging of Urothelial Carcinoma in Bladder Cancer Patients Using a Hybrid Deep-Machine Learning Approach.

Accurate clinical staging of bladder cancer aids in optimizing the process of clinical decision-making, thereby tailoring the effective treatment and management of patients. While several radiomics approaches have been developed to facilitate the process of clinical diagnosis and staging of bladder cancer using grayscale computed tomography (CT) scans, the performances of these models have been low, with little validation and no clear consensus on specific imaging signatures. We propose a hybrid framework comprising pre-trained deep neural networks for feature extraction, in combination with statistical machine learning techniques for classification, which is capable of performing the following classification tasks: (1) bladder cancer tissue vs. normal tissue, (2) muscle-invasive bladder cancer (MIBC) vs. non-muscle-invasive bladder cancer (NMIBC), and (3) post-treatment changes (PTC) vs. MIBC.

Long-term outcomes of prostate intensity-modulated radiation therapy incorporating a simultaneous intra-prostatic MRI-directed boost.

Purpose/objectives: This retrospective study demonstrates the long-term outcomes of treating prostate cancer using intensity modulated (IMRT) with incorporation of MRI-directed boost. Materials/methods: From February 2009 to February 2013, 78 men received image-guided IMRT delivering 77.4 Gy in 44 fractions with simultaneously integrated boost to 81-83 Gy to an MRI-identified lesion. Patients with intermediate-risk or high-risk prostate cancer were recommended to receive 6 and 24-36 months of adjuvant hormonal therapy, respectively. Results: Median follow-up was 113 months (11-147). There were 18 low-risk, 43 intermediate-risk, and 17 high-risk patients per NCCN risk stratification included in this study. Adjuvant hormonal therapy was utilized in 32 patients (41%). The 10-year biochemical control rate for all patients was 77%. The 10-year biochemical control rates for low-risk, intermediate-risk, and high-risk diseases were 94%, 81%, and 88%, respectively (p = 0.35). The 10-year rates of local control, distant control, and survival were 99%, 88%, and 66%, respectively. Of 25 patients who died, only four (5%) died of prostate cancer. On univariate analysis, T-category and pretreatment PSA level were associated with distant failure rate (p = 0.02). There was no grade =3 genitourinary and gastrointestinal toxicities that persisted at the last follow-up. Conclusions: This study demonstrated the long-term efficacy of using MRI to define an intra-prostatic lesion for SIB to 81-83Gy while treating the entire prostate gland to 77.4 Gy with IMRT. Our study confirms that modern MRI can be used to locally intensify dose to prostate tumors providing high long-term disease control while maintaining favorable long-term toxicity.

Preoperative prediction of the stage, size, grade, and necrosis score in clear cell renal cell carcinoma using MRI-based radiomics.

PURPOSE: Clear cell renal cell carcinoma (ccRCC) is the most common subtype of renal cell carcinoma. Currently, there is a lack of noninvasive methods to stratify ccRCC prognosis prior to any invasive therapies. The purpose of this study was to preoperatively predict the tumor stage, size, grade, and necrosis (SSIGN) score of ccRCC using MRI-based radiomics. METHODS: A multicenter cohort of 364 histopathologically confirmed ccRCC patients (272 low [< 4] and 92 high [≥ 4] SSIGN score) with preoperative T2-weighted and T1-contrast-enhanced MRI were retrospectively identified and divided into training (254 patients) and testing sets (110 patients). The performance of a manually optimized radiomics model was assessed by measuring accuracy, sensitivity, specificity, area under receiver operating characteristic curve (AUROC), and area under precision-recall curve (AUPRC) on an independent test set, which was not included in model training. Lastly, its performance was compared to that of a machine learning pipeline, Tree-Based Pipeline Optimization Tool (TPOT). RESULTS: The manually optimized radiomics model using Random Forest classification and Analysis of Variance feature selection methods achieved an AUROC of 0.89, AUPRC of 0.81, accuracy of 0.89 (95% CI 0.816-0.937), specificity of 0.95 (95% CI 0.875-0.984), and sensitivity of 0.72 (95% CI 0.537-0.852) on the test set. The TPOT using Extra Trees Classifier achieved an AUROC of 0.94, AUPRC of 0.83, accuracy of 0.89 (95% CI 0.816-0.937), specificity of 0.95 (95% CI 0.875-0.984), and sensitivity of 0.72 (95% CI 0.537-0.852) on the test set. CONCLUSION: Preoperative MR radiomics can accurately predict SSIGN score of ccRCC, suggesting its promise as a prognostic tool that can be used in conjunction with diagnostic markers.

Deep Learning Based on MRI for Differentiation of Low- and High-Grade in Low-Stage Renal Cell Carcinoma.

Pretreatment determination of renal cell carcinoma aggressiveness may help to guide clinical decision-making. PURPOSE: To evaluate the efficacy of residual convolutional neural network using routine MRI in differentiating low-grade (grade I-II) from high-grade (grade III-IV) in stage I and II renal cell carcinoma. STUDY TYPE: Retrospective. POPULATION: In all, 376 patients with 430 renal cell carcinoma lesions from 2008-2019 in a multicenter cohort were acquired. The 353 Fuhrman-graded renal cell carcinomas were divided into a training, validation, and test set with a 7:2:1 split. The 77 WHO/ISUP graded renal cell carcinomas were used as a separate WHO/ISUP test set. FIELD STRENGTH/SEQUENCE: 1.5T and 3.0T/T2 -weighted and T1 contrast-enhanced sequences. ASSESSMENT: The accuracy, sensitivity, and specificity of the final model were assessed. The receiver operating characteristic (ROC) curve and precision-recall curve were plotted to measure the performance of the binary classifier. A confusion matrix was drawn to show the true positive, true negative, false positive, and false negative of the model. STATISTICAL TESTS: Mann-Whitney U-test for continuous data and the chi-square test or Fisher's exact test for categorical data were used to compare the difference of clinicopathologic characteristics between the low- and high-grade groups. The adjusted Wald method was used to calculate the 95% confidence interval (CI) of accuracy, sensitivity, and specificity. RESULTS: The final deep-learning model achieved a test accuracy of 0.88 (95% CI: 0.73-0.96), sensitivity of 0.89 (95% CI: 0.74-0.96), and specificity of 0.88 (95% CI: 0.73-0.96) in the Fuhrman test set and a test accuracy of 0.83 (95% CI: 0.73-0.90), sensitivity of 0.92 (95% CI: 0.84-0.97), and specificity of 0.78 (95% CI: 0.68-0.86) in the WHO/ISUP test set. DATA CONCLUSION: Deep learning can noninvasively predict the histological grade of stage I and II renal cell carcinoma using conventional MRI in a multiinstitutional dataset with high accuracy. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY STAGE: 2.

Deep Learning to Distinguish Benign from Malignant Renal Lesions Based on Routine MR Imaging.

PURPOSE: With increasing incidence of renal mass, it is important to make a pretreatment differentiation between benign renal mass and malignant tumor. We aimed to develop a deep learning model that distinguishes benign renal tumors from renal cell carcinoma (RCC) by applying a residual convolutional neural network (ResNet) on routine MR imaging. EXPERIMENTAL DESIGN: Preoperative MR images (T2-weighted and T1-postcontrast sequences) of 1,162 renal lesions definitely diagnosed on pathology or imaging in a multicenter cohort were divided into training, validation, and test sets (70:20:10 split). An ensemble model based on ResNet was built combining clinical variables and T1C and T2WI MR images using a bagging classifier to predict renal tumor pathology. Final model performance was compared with expert interpretation and the most optimized radiomics model. RESULTS: Among the 1,162 renal lesions, 655 were malignant and 507 were benign. Compared with a baseline zero rule algorithm, the ensemble deep learning model had a statistically significant higher test accuracy (0.70 vs. 0.56, P = 0.004). Compared with all experts averaged, the ensemble deep learning model had higher test accuracy (0.70 vs. 0.60, P = 0.053), sensitivity (0.92 vs. 0.80, P = 0.017), and specificity (0.41 vs. 0.35, P = 0.450). Compared with the radiomics model, the ensemble deep learning model had higher test accuracy (0.70 vs. 0.62, P = 0.081), sensitivity (0.92 vs. 0.79, P = 0.012), and specificity (0.41 vs. 0.39, P = 0.770). CONCLUSIONS: Deep learning can noninvasively distinguish benign renal tumors from RCC using conventional MR imaging in a multi-institutional dataset with good accuracy, sensitivity, and specificity comparable with experts and radiomics.

MRI - ultrasound fusion guided biopsy of the prostate: lesion volume as a predictor of cancer in patients with repeat biopsies.

INTRODUCTION: The objective was to analyze the diagnostic value of multiparametric magnetic resonance imaging (MRI) prostate lesion volume (PLV) and its correlation with the subsequent MRI-ultrasound (MRI-US) fusion biopsy results. MATERIALS AND METHODS: Between March 2014 and July 2016, 150 men underwent MRI-US fusion biopsies at our institution. All suspicious prostate lesions were graded according to the Prostate Imaging Reporting and Data System (PIRADS) and their volumes were measured. These lesions were subsequently biopsied. All data were prospectively collected and retrospectively analyzed. The PLV of all suspicious lesions was correlated with the presence of cancer on the final MRI-US fusion biopsy. The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated. RESULTS: There were 206 suspicious lesions identified in 150 men. The overall cancer detection rate was 102/206 (49.5%). The mean PLV for benign lesions was 0.63 ± 0.94 cm3 versus 1.44 ± 1.76 cm3 for cancerous lesions (P < 0.01). There was a statistically significant difference between the PLV of PIRADS 5 lesions when compared to PIRADS 4, 3, and 2 lesions (P < 0.0001, < 0.0001, and 0.006, respectively). The area under the curve for volume in predicting prostate cancer (PCa) was 0.66. The optimal volume for predicting PCa was 0.26 cm3 with a sensitivity, specificity, PPV, and NPV of 80.7%, 42.7%, 41.2%, and 74.6%, respectively. CONCLUSION: PLV may serve as a useful measure to triage patients prior to MRI-US fusion biopsy and help better understand the limits of this technology for individual patients.

Pearls and pitfalls of response evaluation criteria in solid tumors (RECIST) v1.1 non-target lesion assessment.

Oncologic imaging is an important facet of abdominal imaging that radiologists encounter nearly every day. Many oncology clinical trials utilize response evaluation criteria in solid tumors (RECIST) version 1.1 which divides tumor sites into target and non-target lesions. Although RECIST v1.1 provides clear instructions regarding the use of imaging in clinical trials, errors in response assessment still occur using these criteria. This is especially true of response assessment with regards to non-target lesions which involve rules which are less well-defined and somewhat subjective. This pictorial essay will review RECIST v1.1 guidelines and common non-target lesion errors which can occur at baseline and follow-up response assessment.

Needle-shaped ultrathin piezoelectric microsystem for guided tissue targeting via mechanical sensing.

Needles for percutaneous biopsies of tumour tissue can be guided by ultrasound or computed tomography. However, despite best imaging practices and operator experience, high rates of inadequate tissue sampling, especially for small lesions, are common. Here, we introduce a needle-shaped ultrathin piezoelectric microsystem that can be injected or mounted directly onto conventional biopsy needles and used to distinguish abnormal tissue during the capture of biopsy samples, through quantitative real-time measurements of variations in tissue modulus. Using well-characterized synthetic soft materials, explanted tissues and animal models, we establish experimentally and theoretically the fundamental operating principles of the microsystem, as well as key considerations in materials choices and device designs. Through systematic tests on human livers with cancerous lesions, we demonstrate that the piezoelectric microsystem provides quantitative agreement with magnetic resonance elastography, the clinical gold standard for the measurement of tissue modulus. The piezoelectric microsystem provides a foundation for the design of tools for the rapid, modulus-based characterization of tissues.

Rapid kV-switching single-source dual-energy CT ex vivo renal calculi characterization using a multiparametric approach: refining parameters on an expanded dataset.

PURPOSE: We aimed to determine the best algorithms for renal stone composition characterization using rapid kV-switching single-source dual-energy computed tomography (rsDECT) and a multiparametric approach after dataset expansion and refinement of variables. METHODS: rsDECT scans (80 and 140 kVp) were performed on 38 ex vivo 5- to 10-mm renal stones composed of uric acid (UA; n = 21), struvite (STR; n = 5), cystine (CYS; n = 5), and calcium oxalate monohydrate (COM; n = 7). Measurements were obtained for 17 variables: mean Hounsfield units (HU) at 11 monochromatic keV levels, effective Z, 2 iodine-water material basis pairs, and 3 mean monochromatic keV ratios (40/140, 70/120, 70/140). Analysis included using 5 multiparametric algorithms: Support Vector Machine, RandomTree, Artificial Neural Network, Naïve Bayes Tree, and Decision Tree (C4.5). RESULTS: Separating UA from non-UA stones was 100% accurate using multiple methods. For non-UA stones, using a 70-keV mean cutoff value of 694 HU had 100% accuracy for distinguishing COM from non-COM (CYS, STR) stones. The best result for distinguishing all 3 non-UA subtypes was obtained using RandomTree (15/17, 88%). CONCLUSIONS: For stones 5 mm or larger, multiple methods can distinguish UA from non-UA and COM from non-COM stones with 100% accuracy. Thus, the choice for analysis is per the user's preference. The best model for separating all three non-UA subtypes was 88% accurate, although with considerable individual overlap between CYS and STR stones. Larger, more diverse datasets, including in vivo data and technical improvements in material separation, may offer more guidance in distinguishing non-UA stone subtypes in the clinical setting.

Magnetic resonance elastography: beyond liver fibrosis-a case-based pictorial review.

Magnetic resonance elastography (MRE) has been introduced for clinical evaluation of liver fibrosis for nearly a decade. MRE has proven to be a robust and accurate technique for diagnosis and staging of liver fibrosis. As clinical experience with MRE grows, the possible role in evaluation of other diffuse and focal disorders of liver is emerging. Stiffness maps provide an opportunity to evaluate mechanical properties within a large volume of liver tissue. This enables appreciation of spatial heterogeneity of stiffness. Stiffness maps may reveal characteristic and differentiating features of chronic liver diseases and focal liver lesions and therefore provide useful information for clinical management. The objective of this pictorial review is to recapture the essentials of MRE technique and illustrate with examples, the utility of stiffness maps in other chronic liver disorders and focal liver lesions.

Evaluation of hepatic fibrosis: a review from the society of abdominal radiology disease focus panel.

Hepatic fibrosis is potentially reversible; however early diagnosis is necessary for treatment in order to halt progression to cirrhosis and development of complications including portal hypertension and hepatocellular carcinoma. Morphologic signs of cirrhosis on ultrasound (US), computed tomography (CT), and magnetic resonance imaging (MRI) alone are unreliable and are seen with more advanced disease. Newer imaging techniques to diagnose liver fibrosis are reliable and accurate, and include magnetic resonance elastography and US elastography (one-dimensional transient elastography and point shear wave elastography or acoustic radiation force impulse imaging). Research is ongoing with multiple other techniques for the noninvasive diagnosis of hepatic fibrosis, including MRI with diffusion-weighted imaging, hepatobiliary contrast enhancement, and perfusion; CT using perfusion, fractional extracellular space techniques, and dual-energy, contrast-enhanced US, texture analysis in multiple modalities, quantitative mapping, and direct molecular imaging probes. Efforts to advance the noninvasive imaging assessment of hepatic fibrosis will facilitate earlier diagnosis and improve patient monitoring with the goal of preventing the progression to cirrhosis and its complications.

Natural Orifice Transluminal Endoscopic Partial Prostatectomy: A Real-time Image-guided Focal Extirpative Feasibility Study.

OBJECTIVE: To assess the feasibility of focal endoscopic excision of prostate cancer (PCa) under guidance of real-time magnetic resonance imaging (MRI) or magnetic ultrasound fusion (MUF). MATERIALS AND METHODS: Using a cadaveric model, multifocal PCa was simulated using 2 MRI-compatible fiducial markers. These were inserted transrectally and used to generate regions of interests (ROIs) on a 1.5-T surface-coil MRI. The first marker was placed in the right mid-peripheral zone (ROI 1), and the second marker was placed in the left seminal vesicle as a referent lesion for subsequent imaging. MRI of the specimen was then obtained. The radiologist created ROIs using fusion biopsy system at each marker. Two additional incidental ROIs were identified in the left transitional zone (ROI 2-suspicious for benign prostatic hyperplasia nodule) and in the right anterior peripheral zone (ROI 3-suspicious for PCa). Holmium laser enucleation of the transitional zone of the prostate was performed to gain access to the peripheral zone lesions. MUF was used during endoscopic laser excision to convey targeting accuracy. The cadaver was then reimaged to determine the adequacy of resection and examined for histopathologic correlation. RESULTS: Real-time MUF imaging identified the target lesions consistently at the locations designated as ROIs. Complete endoscopic resection of ROIs was possible. Repeated MUF imaging and the postprocedure MRI confirmed the completeness of resection. Pathologic examination demonstrated complete excision, intact neurovascular bundles, and posterior prostatic capsule. CONCLUSION: This approach may represent a new minimally invasive frontier for focal surgical resection of PCa, making histopathologic margin status determination possible.

Clinical Implementation of Integrated Genomic Profiling in Patients with Advanced Cancers.

DNA focused panel sequencing has been rapidly adopted to assess therapeutic targets in advanced/refractory cancer. Integrated Genomic Profiling (IGP) utilising DNA/RNA with tumour/normal comparisons in a Clinical Laboratory Improvement Amendments (CLIA) compliant setting enables a single assay to provide: therapeutic target prioritisation, novel target discovery/application and comprehensive germline assessment. A prospective study in 35 advanced/refractory cancer patients was conducted using CLIA-compliant IGP. Feasibility was assessed by estimating time to results (TTR), prioritising/assigning putative therapeutic targets, assessing drug access, ascertaining germline alterations, and assessing patient preferences/perspectives on data use/reporting. Therapeutic targets were identified using biointelligence/pathway analyses and interpreted by a Genomic Tumour Board. Seventy-five percent of cases harboured 1-3 therapeutically targetable mutations/case (median 79 mutations of potential functional significance/case). Median time to CLIA-validated results was 116 days with CLIA-validation of targets achieved in 21/22 patients. IGP directed treatment was instituted in 13 patients utilising on/off label FDA approved drugs (n = 9), clinical trials (n = 3) and single patient IND (n = 1). Preliminary clinical efficacy was noted in five patients (two partial response, three stable disease). Although barriers to broader application exist, including the need for wider availability of therapies, IGP in a CLIA-framework is feasible and valuable in selection/prioritisation of anti-cancer therapeutic targets.

Ex Vivo Renal Stone Characterization with Single-Source Dual-Energy Computed Tomography: A Multiparametric Approach.

RATIONALE AND OBJECTIVES: We aimed to investigate a multiparametric approach using single-source dual-energy computed tomography (ssDECT) for the characterization of renal stones. MATERIALS AND METHODS: ssDECT scans were performed at 80 and 140 kVp on 32 ex vivo kidney stones of 3-10 mm in a phantom. True composition was determined by infrared spectroscopy to be uric acid (UA; n = 14), struvite (n = 7), cystine (n = 7), or calcium oxalate monohydrate (n = 4). Measurements were obtained for up to 52 variables, including mean density at 11 monochromatic keV levels, effective Z, and multiple material basis pairs. The data were analyzed with five multiparametric algorithms. After omitting 8 stones smaller than 5 mm, the remaining 24-stone dataset was similarly analyzed. Both stone datasets were also analyzed with a subset of 14 commonly used variables in the same fashion. RESULTS: For the 32-stone dataset, the best method for distinguishing UA from non-UA stones was 97% accurate, and for distinguishing the non-UA subtypes was 72% accurate. For the 24-stone dataset, the best method for distinguishing UA from non-UA stones was 100% accurate, and for distinguishing the non-UA subtypes was 75% accurate. CONCLUSION: Multiparametric ssDECT methods can distinguish UA from non-UA stones of 5 mm or larger with 100% accuracy. The best model to distinguish the non-UA renal stone subtypes was 75% accurate. Further refinement of this multiparametric approach may increase the diagnostic accuracy of separating non-UA subtypes and assist in the development of a clinical paradigm for in vivo use.

Diagnostic accuracy of magnetic resonance elastography in liver transplant recipients: A pooled analysis.

BACKGROUND AND AIMS: We conducted an individual participant data (IPD) pooled analysis on the diagnostic accuracy of magnetic resonance elastography (MRE) to detect fibrosis stage in liver transplant recipients. MATERIAL AND METHODS: Through a systematic literature search, we identified studies on diagnostic performance of MRE for staging liver fibrosis, using liver biopsy as gold standard. We contacted study authors for published and unpublished IPD on age, sex, body mass index, liver stiffness, fibrosis stage, degree of inflammation and interval between MRE and biopsy; from these we limited analysis to patients who had undergone liver transplantation. Through pooled analysis using nonparametric two-stage receiver-operating curve (ROC) regression models, we calculated the cluster-adjusted AUROC, sensitivity and specificity of MRE for any (≥ stage 1), significant (≥ stage 2) and advanced fibrosis (≥ stage 3) and cirrhosis (stage 4). RESULTS: We included 6 cohorts (4 published and 2 unpublished series) reporting on 141 liver transplant recipients (mean age, 57 years; 75.2% male; mean BMI, 27.1 kg/m2). Fibrosis stage distribution stage 0, 1, 2, 3, or 4, was 37.6%, 23.4%, 24.8%, 12% and 2.2%, respectively. Mean AUROC values (and 95% confidence intervals) for diagnosis of any (≥ stage 1), significant (≥ stage 2), or advanced fibrosis (≥ stage 3) and cirrhosis were 0.73 (0.66-0.81), 0.69 (0.62-0.74), 0.83 (0.61-0.88) and 0.96 (0.93-0.98), respectively. Similar diagnostic performance was observed in stratified analysis based on sex, obesity and inflammation grade. CONCLUSIONS: In conclusion, MRE has high diagnostic accuracy for detection of advanced fibrosis and cirrhosis in liver transplant recipients, independent of BMI and degree of inflammation.