Clinically Applicable AI System for Accurate Diagnosis, Quantitative Measurements, and Prognosis of COVID-19 Pneumonia Using Computed Tomography.

Many COVID-19 patients infected by SARS-CoV-2 virus develop pneumonia (called novel coronavirus pneumonia, NCP) and rapidly progress to respiratory failure. However, rapid diagnosis and identification of high-risk patients for early intervention are challenging. Using a large computed tomography (CT) database from 3,777 patients, we developed an AI system that can diagnose NCP and differentiate it from other common pneumonia and normal controls. The AI system can assist radiologists and physicians in performing a quick diagnosis especially when the health system is overloaded. Significantly, our AI system identified important clinical markers that correlated with the NCP lesion properties. Together with the clinical data, our AI system was able to provide accurate clinical prognosis that can aid clinicians to consider appropriate early clinical management and allocate resources appropriately. We have made this AI system available globally to assist the clinicians to combat COVID-19.

Prenatal Diagnosis of Placenta Accreta Spectrum Disorders: Deep Learning Radiomics of Pelvic MRI.

BACKGROUND: Diagnostic performance of placenta accreta spectrum (PAS) by prenatal MRI is unsatisfactory. Deep learning radiomics (DLR) has the potential to quantify the MRI features of PAS. PURPOSE: To explore whether DLR from MRI can be used to identify pregnancies with PAS. STUDY TYPE: Retrospective. POPULATION: 324 pregnant women (mean age, 33.3 years) suspected PAS (170 training and 72 validation from institution 1, 82 external validation from institution 2) with clinicopathologically proved PAS (206 PAS, 118 non-PAS). FIELD STRENGTH/SEQUENCE: 3-T, turbo spin-echo T2-weighted images. ASSESSMENT: The DLR features were extracted using the MedicalNet. An MRI-based DLR model incorporating DLR signature, clinical model (different clinical characteristics between PAS and non-PAS groups), and MRI morphologic model (radiologists' binary assessment for the PAS diagnosis) was developed. These models were constructed in the training dataset and then validated in the validation datasets. STATISTICAL TESTS: The Student t-test or Mann-Whitney U, χ2 or Fisher exact test, Kappa, dice similarity coefficient, intraclass correlation coefficients, least absolute shrinkage and selection operator logistic regression, multivariate logistic regression, receiver operating characteristic (ROC) curve, DeLong test, net reclassification improvement (NRI) and integrated discrimination improvement (IDI), calibration curve with Hosmer-Lemeshow test, decision curve analysis (DCA). P < 0.05 indicated a significant difference. RESULTS: The MRI-based DLR model had a higher area under the curve than the clinical model in three datasets (0.880 vs. 0.741, 0.861 vs. 0.772, 0.852 vs. 0.675, respectively) or MRI morphologic model in training and independent validation datasets (0.880 vs. 0.760, 0.861, vs. 0.781, respectively). The NRI and IDI were 0.123 and 0.104, respectively. The Hosmer-Lemeshow test had nonsignificant statistics (P = 0.296 to 0.590). The DCA offered a net benefit at any threshold probability. DATA CONCLUSION: An MRI-based DLR model may show better performance in diagnosing PAS than a clinical or MRI morphologic model. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY STAGE: 2.

Discrimination between HER2-overexpressing, -low-expressing, and -zero-expressing statuses in breast cancer using multiparametric MRI-based radiomics.

OBJECTIVES: To explore the performance of multiparametric MRI-based radiomics in discriminating different human epidermal growth factor receptor 2 (HER2) expressing statuses (i.e., HER2-overexpressing, HER2-low-expressing, and HER2-zero-expressing) in breast cancer. METHODS: A total of 771 breast cancer patients from two institutions were retrospectively studied. Five-hundred-eighty-one patients from Institution I were divided into a training dataset (n1 = 407) and an independent validation dataset (n1 = 174); 190 patients from Institution II formed the external validation dataset. All patients were categorized into HER2-overexpressing, HER2-low-expressing, and HER2-zero-expressing groups based on pathologic examination. Multiparametric (including T2-weighted imaging with fat suppression [T2WI-FS], diffusion-weighted imaging [DWI], apparent diffusion coefficient [ADC], and dynamic contrast-enhanced [DCE]) MRI-based radiomics features were extracted and then selected from the training dataset using the least absolute shrinkage and selection operator (LASSO) regression. Three predictive models to discriminate HER2-overexpressing vs. others, HER2-low expressing vs. others, and HER2-zero-expressing vs. others were developed based on the selected features. The model performance was evaluated using the area under the receiver operating characteristic curve (AUC). RESULTS: Eleven radiomics features from DWI, ADC, and DCE; one radiomics feature from DWI; and 17 radiomics features from DWI, ADC, and DCE were selected to build three predictive models, respectively. In training, independent validation, and external validation datasets, radiomics models achieved AUCs of 0.809, 0.737, and 0.725 in differentiating HER2-overexpressing from others; 0.779, 0.778, and 0.782 in differentiating HER2-low-expressing from others; and 0.889, 0.867, and 0.813 in differentiating HER2-zero-expressing from others, respectively. CONCLUSIONS: Multiparametric MRI-based radiomics model may preoperatively predict HER2 statuses in breast cancer patients. CLINICAL RELEVANCE STATEMENT: The MRI-based radiomics models could be used to noninvasively identify the new three-classification of HER2 expressing status in breast cancer, which is helpful to the decision-making for HER2-target therapies. KEY POINTS: • Detecting HER2-overexpressing, HER2-low-expressing, and HER2-zero-expressing status in breast cancer patients is crucial for determining candidates for anti-HER2 therapy. • Radiomics features from multiparametric MRI significantly differed among HER2-overexpressing, HER2-low expressing, and HER2-zero-expressing breast cancers. • Multiparametric MRI-based radiomics could preoperatively evaluate three different HER2-expressing statuses and help to determine potential candidates for anti-HER2 therapy in breast cancer patients.

Discrimination between human epidermal growth factor receptor 2 (HER2)-low-expressing and HER2-overexpressing breast cancers: a comparative study of four MRI diffusion models.

OBJECTIVES: To determine the value of conventional DWI, continuous-time random walk (CTRW), fractional order calculus (FROC), and stretched exponential model (SEM) in discriminating human epidermal growth factor receptor 2 (HER2) status of breast cancer (BC). METHODS: This prospective study included 158 women who underwent DWI, CTRW, FROC, and SEM and were pathologically categorized into the HER2-zero-expressing group (n = 10), HER2-low-expressing group (n = 86), and HER2-overexpressing group (n = 62). Nine diffusion parameters, namely ADC, αCTRW, ßCTRW, DCTRW, ßFROC, DFROC, µFROC, αSEM, and DDCSEM of the primary tumor, were derived from four diffusion models. These diffusion metrics and clinicopathologic features were compared between groups. Logistic regression was used to determine the optimal diffusion metrics and clinicopathologic variables for classifying the HER2-expressing statuses. Receiver operating characteristic (ROC) curves were used to evaluate their discriminative ability. RESULTS: The estrogen receptor (ER) status, progesterone receptor (PR) status, and tumor size differed between HER2-low-expressing and HER2-overexpressing groups (p < 0.001 to p = 0.009). The αCTRW, DCTRW, ßFROC, DFROC, µFROC, αSEM, and DDCSEM were significantly lower in HER2-low-expressing BCs than those in HER2-overexpressing BCs (p < 0.001 to p = 0.01). Further multivariable logistic regression analysis showed that the αCTRW was the single best discriminative metric, with an area under the curve (AUC) being higher than that of ADC (0.802 vs. 0.610, p < 0.05); the addition of ER status, PR status, and tumor size to the αCTRW improved the AUC to 0.877. CONCLUSIONS: The αCTRW could help discriminate the HER2-low-expressing and HER2-overexpressing BCs. CLINICAL RELEVANCE STATEMENT: Human epidermal growth factor receptor 2 (HER2)-low-expressing breast cancer (BC) might also benefit from the HER2-targeted therapy. Prediction of HER2-low-expressing BC or HER2-overexpressing BC is crucial for appropriate management. Advanced continuous-time random walk diffusion MRI offers a solution to this clinical issue. KEY POINTS: • Human epidermal receptor 2 (HER2)-low-expressing BC had lower αCTRW, DCTRW, ßFROC, DFROC, µFROC, αSEM, and DDCSEM values compared with HER2-overexpressing breast cancer. • The αCTRW was the single best diffusion metric (AUC = 0.802) for discrimination between the HER2-low-expressing and HER2-overexpressing breast cancers. • The addition of αCTRW to the clinicopathologic features (estrogen receptor status, progesterone receptor status, and tumor size) further improved the discriminative ability.

Development and Validation of MRI Radiomics Models to Differentiate HER2-Zero, -Low, and -Positive Breast Cancer.

BACKGROUND. Breast cancer HER2 expression has been redefined using a three-tiered system, with HER2-zero cancers considered ineligible for HER2-targeted therapy, HER2-low cancers considered candidates for novel HER2-targeted drugs, and HER2-positive cancers treated with traditional HER2-targeted medications. OBJECTIVE. The purpose of this study was to assess MRI radiomics models for a three-tiered classification of HER2 expression of breast cancer. METHODS. This retrospective study included 592 patients with pathologically confirmed breast cancer (mean age, 47.0 ± 18.0 [SD] years) who underwent breast MRI at either of a health system's two hospitals from April 2016 through June 2022. Three-tiered HER2 status was pathologically determined. Radiologists assessed the conventional MRI features of tumors and manually segmented the tumors on multiparametric sequences (T2-weighted images, DWI, ADC maps, and T1-weighted delayed contrast-enhanced images) to extract radiomics features. Least absolute shrinkage and selection operator analysis was used to develop two radiomics signatures, to differentiate HER2-zero cancers from HER2-low or HER2-positive cancers (task 1) as well as to differentiate HER2-low cancers from HER2-positive cancers (task 2). Patients from hospital 1 were randomly assigned to a discovery set (task 1: n = 376; task 2: n = 335) or an internal validation set (task 1: n = 161; task 2: n = 143); patients from hospital 2 formed an external validation set (task 1: n = 55; task 2: n = 50). Multivariable logistic regression analysis was used to create nomograms combining radiomics signatures with clinicopathologic and conventional MRI features. RESULTS. AUC, sensitivity, and specificity in the discovery, internal validation, and external validation sets were as follows: for task 1, 0.89, 99.4%, and 69.0%; 0.86, 98.6%, and 76.5%; and 0.78, 100.0%, and 0.0%, respectively; for task 2, 0.77, 93.8%, and 32.3%; 0.75, 92.9%, and 6.8%; and 0.77, 97.0%, and 29.4%, respectively. For task 1, no nomogram was created because no clinicopathologic or conventional MRI feature was associated with HER2 status independent of the MRI radiomics signature. For task 2, a nomogram including an MRI radiomics signature and three pathologic features (histologic grade of III, high Ki-67 index, and positive progesterone receptor status) that were independently associated with HER2-low expression had an AUC of 0.87, 0.83, and 0.80 in the three sets. CONCLUSION. MRI radiomics features were used to differentiate HER2-zero from HER2-low cancers or HER2-positives cancers as well as to differentiate HER2-low cancers from HER2-positive cancers. CLINICAL IMPACT. MRI radiomics may help select patients for novel or traditional HER2-targeted therapies, particularly those patients with ambiguous results of immunohistochemical staining results or limited access to fluorescence in situ hybridization.

CT-Based Radiomics Models for Differentiation of Benign and Malignant Thyroid Nodules: A Multicenter Development and Validation Study.

BACKGROUND. CT is increasingly detecting thyroid nodules. Prior studies indicated a potential role of CT-based radiomics models in characterizing thyroid nodules, although these studies lacked external validation. OBJECTIVE. The purpose of this study was to develop and validate a CT-based radiomics model for the differentiation of benign and malignant thyroid nodules. METHODS. This retrospective study included 378 patients (mean age, 46.3 ± 13.9 [SD] years; 86 men, 292 women) with 408 resected thyroid nodules (145 benign, 263 malignant) from two centers (center 1: 293 nodules, January 2018 to December 2022; center 2: 115 nodules, January 2020 to December 2022) who underwent preoperative multiphase neck CT (noncontrast, arterial, and venous phases). Nodules from center 1 were divided into training (n = 206) and internal validation (n = 87) sets; all nodules from center 2 formed an external validation set. Radiologists assessed nodules for morphologic CT features. Nodules were manually segmented on all phases, and radiomic features were extracted. Conventional (clinical and morphologic CT), noncontrast CT radiomics, arterial phase CT radiomics, venous phase CT radiomics, multiphase CT radiomics, and combined (clinical, morphologic CT, and multiphase CT radiomics) models were established using feature selection methods and evaluated by ROC curve analysis, calibration-curve analysis, and decision-curve analysis. RESULTS. The combined model included patient age, three morphologic features (cystic change, "edge interruption" sign, abnormal cervical lymph nodes), and 28 radiomic features (from all three phases). In the external validation set, the combined model had an AUC of 0.923, and, at an optimal threshold derived in the training set, sensitivity of 84.0%, specificity of 94.1%, and accuracy of 87.0%. In the external validation set, the AUC was significantly higher for the combined model than for the conventional model (0.827), noncontrast CT radiomics model (0.847), arterial phase CT radiomics model (0.826), venous phase CT radiomics model (0.773), and multiphase CT radiomics model (0.824) (all p < .05). In the external validation set, the calibration curves indicated the lowest (i.e., best) Brier score for the combined model; in the decision-curve analysis, the combined model had the highest net benefit for most of the range of threshold probabilities. CONCLUSION. A combined model incorporating clinical, morphologic CT, and multiphase CT radiomics features exhibited robust performance in differentiating benign and malignant thyroid nodules. CLINICAL IMPACT. The combined radiomics model may help guide further management for thyroid nodules detected on CT.

Detecting lesion-specific ischemia in patients with coronary artery disease with computed tomography fractional flow reserve measured at different sites.

OBJECTIVES: Whether a stenosis can cause hemodynamic lesion-specific ischemia is critical for the treatment decision in patients with coronary artery disease (CAD). Based on coronary computed tomography angiography (CCTA), CT fractional flow reserve (FFRCT) can be used to assess lesion-specific ischemia. The selection of an appropriate site along the coronary artery tree is vital for measuring FFRCT. However the optimal site to measure FFRCT for a target stenosis remains to be adequately determined. The purpose of this study was to determine the optimal site to measure FFRCT for a target lesion in detecting lesion-specific ischemia in CAD patients by evaluating the performance of FFRCT measured at different sites distal to the target lesion in detecting lesion-specific ischemia with FFR measured with invasive coronary angiography (ICA) as reference standard. METHODS: In this single-center retrospective cohort study, a total of 401 patients suspected of having CAD underwent invasive ICA and FFR between March 2017 and December 2021 were identified. 52 patients having both CCTA and invasive FFR within 90 days were enrolled. Patients with vessels 30%-90% diameter stenosis as determined by ICA were referred to invasive FFR evaluation, which was performed 2-3 cm distal to the stenosis under the condition of hyperemia. For each vessel with 30%-90% diameter stenosis, if only one stenosis was present, this stenosis was selected as the target lesion; if serial stenoses were present, the stenosis most distal to the vessel end was chosen as the target lesion. FFRCT was measured at four sites: 1 cm, 2 cm, and 3 cm distal to the lower border of the target lesion (FFRCT-1 cm, FFRCT-2 cm, FFRCT-3 cm), and the lowest FFRCT at the distal vessel tip (FFRCT-lowest). The normality of quantitative data was assessed using the Shapiro-Wilk test. Pearson's correlation analysis and Bland-Altman plots were used for assessing the correlation and difference between invasive FFR and FFRCT. Correlation coefficients derived from Chi-suqare test were used to assess the correlation between invasive FFR and the cominbaiton of FFRCT measred at four sites. The performances of significant obstruction stenosis (diameter stenosis ≥ 50%) at CCTA and FFRCT measured at the four sites and their combinations in diagnosing lesion-specific ischemia were evaluated by receiver-operating characteristic (ROC) curves using invasive FFR as the reference standard. The areas under ROC curves (AUCs) of CCTA and FFRCT were compared by the DeLong test. RESULTS: A total of 72 coronary arteries in 52 patients were included for analysis. Twenty-five vessels (34.7%) had lesion-specific ischemia detected by invasive FFR and 47 vesseles (65.3%) had no lesion-spefifice ischemia. Good correlation was found between invasive FFR and FFRCT-2 cm and FFRCT-3 cm (r = 0.80, 95% CI, 0.70 to 0.87, p < 0.001; r = 0.82, 95% CI, 0.72 to 0.88, p < 0.001). Moderate correlation was found between invasive FFR and FFRCT-1 cm and FFRCT-lowest (r = 0.77, 95% CI, 0.65 to 0.85, p < 0.001; r = 0.78, 95% CI, 0.67 to 0.86, p < 0.001). FFRCT-1 cm + FFRCT-2 cm, FFRCT-2 cm + FFRCT-3 cm, FFRCT-3 cm + FFRCT-lowest, FFRCT-1 cm + FFRCT-2 cm + FFRCT-3 cm, and FFRCT-2 cm + FFRCT-3 cm + FFRCT-lowest were correatled with invasive FFR (r = 0.722; 0.722; 0.701; 0.722; and 0.722, respectively; p < 0.001 for all). Bland-Altman plots revealed a mild difference between invasive FFR and the four FFRCT (invasive FFR vs. FFRCT-1 cm, mean difference -0.0158, 95% limits of agreement: -0.1475 to 0.1159; invasive FFR vs. FFRCT-2 cm, mean difference 0.0001, 95% limits of agreement: -0.1222 to 0.1220; invasive FFR vs. FFRCT-3 cm, mean difference 0.0117, 95% limits of agreement: -0.1085 to 0.1318; and invasive FFR vs. FFRCT-lowest, mean difference 0.0343, 95% limits of agreement: -0.1033 to 0.1720). AUCs of CCTA, FFRCT-1 cm, FFRCT-2 cm, FFRCT-3 cm, and FFRCT-lowest in detecting lesion-specific ischemia were 0.578, 0.768, 0.857, 0.856 and 0.770, respectively. All FFRCT had a higher AUC than CCTA (all p < 0.05), FFRCT-2 cm achieved the highest AUC at 0.857. The AUCs of FFRCT-2 cm and FFRCT-3 cm were comparable (p > 0.05). The AUCs were similar between FFRCT-1 cm + FFRCT-2 cm, FFRCT-3 cm + FFRCT-lowest and FFRCT-2 cm alone (AUC = 0.857, 0.857, 0.857, respectively; p > 0.05 for all). The AUCs of FFRCT-2 cm + FFRCT-3 cm, FFRCT-1 cm + FFRCT-2 cm + FFRCT-3 cm, FFRCT-and 2 cm + FFRCT-3 cm + FFRCT-lowest (0.871, 0.871, 0.872, respectively) were slightly higher than that of FFRCT-2 cm alone (0.857), but without significnacne differences (p > 0.05 for all). CONCLUSIONS: FFRCT measured at 2 cm distal to the lower border of the target lesion is the optimal measurement site for identifying lesion-specific ischemia in patients with CAD.

MRI-radiomics-clinical-based nomogram for prenatal prediction of the placenta accreta spectrum disorders.

OBJECTIVES: To investigate whether an MRI-radiomics-clinical-based nomogram can be used to prenatal predict the placenta accreta spectrum (PAS) disorders. METHODS: The pelvic MR images and clinical data of 156 pregnant women with pathologic-proved PAS (PAS group) and 115 pregnant women with no PAS (non-PAS group) identified by clinical and prenatal ultrasonic examination were retrospectively collected from two centers. These pregnancies were divided into a training (n = 133), an independent validation (n = 57), and an external validation (n = 81) cohort. Radiomic features were extracted from images of transverse oblique T2-weighted imaging. A radiomics signature was constructed. A nomogram, composed of MRI morphological findings, radiomic features, and prenatal clinical characteristics, was developed. The discrimination and calibration of the nomogram were conducted to assess its performance. RESULTS: A radiomics signature, including three PAS-related features, was associated with the presence of PAS in the three cohorts (p < 0.001 to p = 0.001). An MRI-radiomics-clinical nomogram incorporating radiomics signature, two prenatal clinical features, and two MRI morphological findings was developed, yielding a higher area under the curve (AUC) than that of the MRI morphological-determined PAS in the training cohort (0.89 vs. 0.78; p < 0.001) and external validation cohort (0.87 vs. 0.75; p = 0.003), while a comparable AUC value in the validation cohort (0.91 vs. 0.81; p = 0.09). The calibration was good. CONCLUSIONS: An MRI-radiomics-clinical nomogram had a robust performance in antenatal predicting the PAS in pregnancies. KEY POINTS: • An MRI-radiomics-clinical-based nomogram might serve as an adjunctive approach for the treatment decision-making in pregnancies suspicious of PAS. • The radiomic score provides a mathematical formula that predicts the possibility of PAS by using the MRI data, and pregnant women with PAS had higher radiomic scores than those without PAS.

Hepatic Krüppel-like factor 16 (KLF16) targets PPARα to improve steatohepatitis and insulin resistance.

OBJECTIVE: Impaired hepatic fatty acids oxidation results in lipid accumulation and redox imbalance, promoting the development of fatty liver diseases and insulin resistance. However, the underlying pathogenic mechanism is poorly understood. Krüppel-like factor 16 (KLF16) is a transcription factor that abounds in liver. We explored whether and by what mechanisms KLF16 affects hepatic lipid catabolism to improve hepatosteatosis and insulin resistance. DESIGN: KLF16 expression was determined in patients with non-alcoholic fatty liver disease (NAFLD) and mice models. The role of KLF16 in the regulation of lipid metabolism was investigated using hepatocyte-specific KLF16-deficient mice fed a high-fat diet (HFD) or using an adenovirus/adeno-associated virus to alter KLF16 expression in mouse primary hepatocytes (MPHs) and in vivo livers. RNA-seq, luciferase reporter gene assay and ChIP analysis served to explore the molecular mechanisms involved. RESULTS: KLF16 expression was decreased in patients with NAFLD, mice models and oleic acid and palmitic acid (OA and PA) cochallenged hepatocytes. Hepatic KLF16 knockout impaired fatty acid oxidation, aggravated mitochondrial stress, ROS burden, advancing hepatic steatosis and insulin resistance. Conversely, KLF16 overexpression reduced lipid deposition and improved insulin resistance via directly binding the promoter of peroxisome proliferator-activated receptor α (PPARα) to accelerate fatty acids oxidation and attenuate mitochondrial stress, oxidative stress in db/db and HFD mice. PPARα deficiency diminished the KLF16-evoked protective effects against lipid deposition in MPHs. Hepatic-specific PPARα overexpression effectively rescued KLF16 deficiency-induced hepatic steatosis, altered redox balance and insulin resistance. CONCLUSIONS: These findings prove that a direct KLF16-PPARα pathway closely links hepatic lipid homeostasis and redox balance, whose dysfunction promotes insulin resistance and hepatic steatosis.

Radiomics model of dual-time 2-[18F]FDG PET/CT imaging to distinguish between pancreatic ductal adenocarcinoma and autoimmune pancreatitis.

OBJECTIVES: Pancreatic ductal adenocarcinoma (PDAC) and autoimmune pancreatitis (AIP) are diseases with a highly analogous visual presentation that are difficult to distinguish by imaging. The purpose of this research was to create a radiomics-based prediction model using dual-time PET/CT imaging for the noninvasive classification of PDAC and AIP lesions. METHODS: This retrospective study was performed on 112 patients (48 patients with AIP and 64 patients with PDAC). All cases were confirmed by imaging and clinical follow-up, and/or pathology. A total of 502 radiomics features were extracted from the dual-time PET/CT images to develop a radiomics decision model. An additional 12 maximum intensity projection (MIP) features were also calculated to further improve the radiomics model. The optimal radiomics feature set was selected by support vector machine recursive feature elimination (SVM-RFE), and the final classifier was built using a linear SVM. The performance of the proposed dual-time model was evaluated using nested cross-validation for accuracy, sensitivity, specificity, and area under the curve (AUC). RESULTS: The final prediction model was developed from a combination of the SVM-RFE and linear SVM with the required quantitative features. The multimodal and multidimensional features performed well for classification (average AUC: 0.9668, accuracy: 89.91%, sensitivity: 85.31%, specificity: 96.04%). CONCLUSIONS: The radiomics model based on 2-[18F]fluoro-2-deoxy-D-glucose (2-[18F]FDG) PET/CT dual-time images provided promising performance for discriminating between patients with benign AIP and malignant PDAC lesions, which shows its potential for use as a diagnostic tool for clinical decision-making. KEY POINTS: • The clinical symptoms and imaging visual presentations of PDAC and AIP are highly similar, and accurate differentiation of PDAC and AIP lesions is difficult. • Radiomics features provided a potential noninvasive method for differentiation of AIP from PDAC. • The diagnostic performance of the proposed radiomics model indicates its potential to assist doctors in making treatment decisions.

Preoperative prediction of axillary sentinel lymph node burden with multiparametric MRI-based radiomics nomogram in early-stage breast cancer.

OBJECTIVES: To develop and validate a multiparametric MRI-based radiomics nomogram for pretreatment predicting the axillary sentinel lymph node (SLN) burden in early-stage breast cancer. METHODS: A total of 230 women with early-stage invasive breast cancer were retrospectively analyzed. A radiomics signature was constructed based on preoperative multiparametric MRI from the training dataset (n = 126) of center 1, then tested in the validation cohort (n = 42) from center 1 and an external test cohort (n = 62) from center 2. Multivariable logistic regression was applied to develop a radiomics nomogram incorporating radiomics signature and predictive clinical and radiological features. The radiomics nomogram's performance was evaluated by its discrimination, calibration, and clinical use and was compared with MRI-based descriptors of primary breast tumor. RESULTS: The constructed radiomics nomogram incorporating radiomics signature and MRI-determined axillary lymph node (ALN) burden showed a good calibration and outperformed the MRI-determined ALN burden alone for predicting SLN burden (area under the curve [AUC]: 0.82 vs. 0.68 [p < 0.001] in training cohort; 0.81 vs. 0.68 in validation cohort [p = 0.04]; and 0.81 vs. 0.58 [p = 0.001] in test cohort). Compared with the MRI-based breast tumor combined descriptors, the radiomics nomogram achieved a higher AUC in test cohort (0.81 vs. 0.58, p = 0.005) and a comparable AUC in training (0.82 vs. 0.73, p = 0.15) and validation (0.81 vs. 0.65, p = 0.31) cohorts. CONCLUSION: A multiparametric MRI-based radiomics nomogram can be used for preoperative prediction of the SLN burden in early-stage breast cancer. KEY POINTS: • Radiomics nomogram incorporating radiomics signature and MRI-determined ALN burden outperforms the MRI-determined ALN burden alone for predicting SLN burden in early-stage breast cancer. • Radiomics nomogram might have a better predictive ability than the MRI-based breast tumor combined descriptors. • Multiparametric MRI-based radiomics nomogram can be used as a non-invasive tool for preoperative predicting of SLN burden in patients with early-stage breast cancer.

Magnetic resonance imaging of enhanced nerve repair with mesenchymal stem cells combined with microenvironment immunomodulation in neurotmesis.

INTRODUCTION: The immuno-microenvironment of injured nerves adversely affects mesenchymal stem cell (MSC) therapy for neurotmesis. Magnetic resonance imaging (MRI) can be used noninvasively to monitor nerve degeneration and regeneration. The aim of this study was to investigate nerve repair after MSC transplantation combined with microenvironment immunomodulation in neurotmesis by using multiparametric MRI. METHODS: Rats with sciatic nerve transection and surgical coaptation were treated with MSCs combined with immunomodulation or MSCs alone. Serial multiparametric MRI examinations were performed over an 8-week period after surgery. RESULTS: Nerves treated with MSCs combined with immunomodulation showed better functional recovery, rapid recovery of nerve T2, fractional anisotropy and radial diffusivity values, and more rapid restoration of the fiber tracks than nerves treated with MSCs alone. DISCUSSION: Transplantation of MSCs in combination with immunomodulation can exert a synergistic repair effect on neurotmesis, which can be monitored by multiparametric MRI.

Three-dimensional culture and clinical drug responses of a highly metastatic human ovarian cancer HO-8910PM cells in nanofibrous microenvironments of three hydrogel biomaterials.

BACKGROUND: Ovarian cancer is a highly aggressive malignant disease in gynecologic cancer. It is an urgent task to develop three-dimensional (3D) cell models in vitro and dissect the cell progression-related drug resistance mechanisms in vivo. In the present study, RADA16-I peptide has the reticulated nanofiber scaffold networks in hydrogel, which is utilized to develop robust 3D cell culture of a high metastatic human ovarian cancer HO-8910PM cell line accompanied with the counterparts of Matrigel and collagen I. RESULTS: Consequently, HO-8910PM cells were successfully cultivated in three types of hydrogel biomaterials, such as RADA16-I hydrogel, Matrigel, and collagen I, according to 3D cell culture protocols. Designer RADA16-I peptide had well-defined nanofiber networks architecture in hydrogel, which provided nanofiber cell microenvironments analogous to Matrigel and collagen I. 3D-cultured HO-8910PM cells in RADA16-I hydrogel, Matrigel, and collagen I showed viable cell proliferation, proper cell growth, and diverse cell shapes in morphology at the desired time points. For a long 3D cell culture period, HO-8910PM cells showed distinct cell aggregate growth patterns in RADA16-I hydrogel, Matrigel, and collagen I, such as cell aggregates, cell colonies, cell clusters, cell strips, and multicellular tumor spheroids (MCTS). The cell distribution and alignment were described vigorously. Moreover, the molecular expression of integrin ß1, E-cadherin and N-cadherin were quantitatively analyzed in 3D-cultured MCTS of HO-8910PM cells by immunohistochemistry and western blotting assays. The chemosensitivity assay for clinical drug responses in 3D context indicated that HO-8910PM cells in three types of hydrogels showed significantly higher chemoresistance to cisplatin and paclitaxel compared to 2D flat cell culture, including IC50 values and inhibition rates. CONCLUSION: Based on these results, RADA16-I hydrogel is a highly competent, high-profile, and proactive nanofiber scaffold to maintain viable cell proliferation and high cell vitality in 3D cell models, which may be particularly utilized to develop useful clinical drug screening platform in vitro.

Quantitative dynamic contrast-enhanced MR imaging can be used to predict the pathologic stages of oral tongue squamous cell carcinoma.

BACKGROUND: To investigate whether quantitative dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) pharmacokinetic parameters can be used to predict the pathologic stages of oral tongue squamous cell carcinoma (OTSCC). METHODS: For this prospective study, DCE-MRI was performed in participants with OTSCC from May 2016 to June 2017. The pharmacokinetic parameters, including Ktrans, Kep, Ve, and Vp, were derived from DCE-MRI by utilizing a two-compartment extended Tofts model and a three-dimensional volume of interest. The postoperative pathologic stage was determined in each patient based on the 8th AJCC cancer staging manual. The quantitative DCE-MRI parameters were compared between stage I-II and stage III-IV lesions. Logistic regression analysis was used to determine independent predictors of tumor stages, followed by receiver operating characteristic (ROC) analysis to evaluate the predictive performance. RESULTS: The mean Ktrans, Kep and Vp values were significantly lower in stage III-IV lesions compared with stage I-II lesions (p = 0.013, 0.005 and 0.011, respectively). Kep was an independent predictor for the advanced stages as determined by univariate and multivariate logistic analysis. ROC analysis showed that Kep had the highest predictive capability, with a sensitivity of 64.3%, a specificity of 82.6%, a positive predictive value of 81.8%, a negative predictive value of 65.5%, and an accuracy of 72.5%. CONCLUSION: The quantitative DCE-MRI parameter Kep can be used as a biomarker for predicting pathologic stages of OTSCC.

Differentiation between high-grade gliomas and solitary brain metastases: a comparison of five diffusion-weighted MRI models.

BACKGROUND: To compare the diagnostic performance of neurite orientation dispersion and density imaging (NODDI), mean apparent propagator magnetic resonance imaging (MAP-MRI), diffusion kurtosis imaging (DKI), diffusion tensor imaging (DTI) and diffusion-weighted imaging (DWI) in distinguishing high-grade gliomas (HGGs) from solitary brain metastases (SBMs). METHODS: Patients with previously untreated, histopathologically confirmed HGGs (n = 20) or SBMs (n = 21) appearing as a solitary and contrast-enhancing lesion on structural MRI were prospectively recruited to undergo diffusion-weighted MRI. DWI data were obtained using a q-space Cartesian grid sampling procedure and were processed to generate parametric maps by fitting the NODDI, MAP-MRI, DKI, DTI and DWI models. The diffusion metrics of the contrast-enhancing tumor and peritumoral edema were measured. Differences in the diffusion metrics were compared between HGGs and SBMs, followed by receiver operating characteristic (ROC) analysis and the Hanley and McNeill test to determine their diagnostic performances. RESULTS: NODDI-based isotropic volume fraction (Viso) and orientation dispersion index (ODI); MAP-MRI-based mean-squared displacement (MSD) and q-space inverse variance (QIV); DKI-generated radial, mean diffusivity and fractional anisotropy (RDk, MDk and FAk); and DTI-generated radial, mean diffusivity and fractional anisotropy (RD, MD and FA) of the contrast-enhancing tumor were significantly different between HGGs and SBMs (p < 0.05). The best single discriminative parameters of each model were Viso, MSD, RDk and RD for NODDI, MAP-MRI, DKI and DTI, respectively. The AUC of Viso (0.871) was significantly higher than that of MSD (0.736), RDk (0.760) and RD (0.733) (p < 0.05). CONCLUSION: NODDI outperforms MAP-MRI, DKI, DTI and DWI in differentiating between HGGs and SBMs. NODDI-based Viso has the highest performance.

Assessment of Cardiac Lead Perforation: Comparison Among Chest Radiography, Transthoracic Echocardiography and Electrocardiography-gated Contrast-enhanced Cardiac CT.

OBJECTIVES: Cardiac lead perforation is a rare but potentially life-threatening event. The purpose of this study was to investigate the diagnostic performances of chest radiography, transthoracic echocardiography (TTE) and electrocardiography (ECG)-gated contrast-enhanced cardiac CT in the assessment of cardiac lead perforation. METHODS: This retrospective study was approved by the ethics review board of Sun Yat-Sen Memorial Hospital at Sun Yat-Sen University (Guangzhou, China), and the need to obtain informed consent was waived. Between May 2010 and Oct 2017, 52 patients were clinically suspected to have a cardiac lead perforation and received chest radiography, TTE and ECG-gated contrast-enhanced cardiac CT. Among them, 13 patients were identified as having cardiac lead perforation. The diagnostic performances of these three modalities were evaluated by receiver-operating characteristic (ROC) curves using a composite reference standard of surgical and electrophysiological results and clinical follow-up. The areas under ROCs (AUROCs) were compared with the McNemar test. RESULTS: The accuracies of chest radiography, TTE and ECG-gated contrast-enhanced cardiac CT imaging for the diagnosis of cardiac lead perforation were 73.1%, 82.7% and 98.1%, respectively. ECG-gated contrast-enhanced cardiac CT had a higher AUROC than chest radiography (p < 0.001) and TTE (p < 0.001). CONCLUSIONS: ECG-gated contrast-enhanced cardiac CT is superior to both chest radiography and TTE imaging for the assessment of cardiac lead perforation. KEY POINTS: • ECG-gated contrast-enhanced cardiac CT has an accuracy of 98.1% in the diagnosis of cardiac lead perforation. • The AUROC of ECG-gated contrast-enhanced cardiac CT is higher than those of chest radiography and TTE imaging. • ECG-gated contrast-enhanced cardiac CT imaging has better diagnostic performance than both chest radiography and TTE imaging for the assessment of cardiac lead perforation.

Predictive value of pretreatment MRI texture analysis in patients with primary nasopharyngeal carcinoma.

OBJECTIVES: To determine the predictive value of pretreatment MRI texture analysis for progression-free survival (PFS) in patients with primary nasopharyngeal carcinoma (NPC). METHODS: Ethical approval by the institutional review board was obtained for this retrospective analysis. In 79 patients with primary NPC, texture analysis of the primary tumour was performed on pretreatment T2 and contrast-enhanced T1-weighted images (T2WIs and CE-T1WIs). The Cox proportional hazards model was used to determine the association of texture features, tumour volume and the tumour-node-metastasis (TNM) stage with PFS. Survival curves were plotted using the Kaplan-Meier method. The prognostic performance was evaluated with the receiver operating characteristic (ROC) analyses and C-index. RESULTS: Tumour volume (hazard ratio, 1.054; 95% confidence interval [CI], 1.016-1.093) and CE-T1WI-based uniformity (hazard ratio, 0; 95% CI, 0-0.001) were identified as independent predictors for PFS (p < 0.05). Kaplan-Meier analysis showed that smaller tumour volume (less than the cut-off value, 11.699 cm3) and higher CE-T1WI-based uniformity (greater than the cut-off value, 0.856) were associated with improved PFS (p < 0.05). The combination of CE-T1WI-based uniformity with tumour volume and the overall stage predicted PFS better (area under the curve [AUC], 0.825; Cindex, 0.794) than the tumour volume (AUC, 0.659; C-index, 0.616) or the overall stage (AUC, 0.636; C-index, 0.627) did (p < 0.05). CONCLUSIONS: A texture parameter of pretreatment CE-T1WI-based uniformity improves the prediction of PFS in NPC patients. KEY POINTS: • Higher CE-T1WI-based uniformity and smaller tumour volume are predictive of improved PFS in NPC patients. • The combination of CE-T1WI-based uniformity with tumour volume and the overall stage has a better predictive ability for PFS than the tumour volume or the overall stage alone. • Pretreatment MRI texture analysis has a prognostic value for NPC patients.

Preoperative Diagnosis of Regional Lymph Node Metastasis of Colorectal Cancer With Quantitative Parameters From Dual-Energy CT.

OBJECTIVE. The purpose of this study was to investigate the performance of quantitative parameters derived from dual-energy CT (DECT) in the preoperative diagnosis of regional metastatic lymph nodes (LNs) in patients with colorectal cancer. SUBJECTS AND METHODS. Triphasic contrast-enhanced DECT was performed for 178 patients with colon or high rectal cancer. The morphologic criteria, short-axis diameter, and quantitative DECT parameters of the largest regional LN were measured and compared between pathologically metastatic and nonmetastatic LNs. Univariate and multivariable logistic regression analyses were used to determine the independent DECT parameters for predicting LN metastasis. Diagnostic performance measures were assessed by ROC curve analysis and compared by McNemar test. RESULTS. A total of 178 largest LNs (72 metastatic, 106 nonmetastatic) were identified in 178 patients. The best single DECT parameter for differentiation between metastatic and nonmetastatic LNs was normalized effective atomic number (Zeff) in the portal venous phase (AUC, 0.871; accuracy, 84.8%). These values were higher than those of morphologic criteria (AUC, 0.505-0.624; accuracy, 47.8-62.4%) and short-axis diameter (AUC, 0.647; accuracy, 66.3%) (p < 0.05). The diagnostic accuracy of combined normalized iodine concentration in the arterial phase and normalized effective atomic number in the portal venous phase was further improved to 87.1% (AUC, 0.916). CONCLUSION. Quantitative parameters derived from DECT can be used to improve preoperative diagnostic accuracy in evaluation for regional metastatic LNs in patients with colorectal cancer.

Axillary Sentinel Lymph Nodes in Breast Cancer: Quantitative Evaluation at Dual-Energy CT.

Purpose To evaluate the diagnostic performance of quantitative parameters derived from dual-energy CT for the preoperative diagnosis of metastatic sentinel lymph nodes (SLNs) in participants with breast cancer. Materials and Methods For this prospective study, dual-phase contrast agent-enhanced CT was performed in female participants with breast cancer from June 2015 to December 2017. Quantitative dual-energy CT parameters and morphologic parameters were compared between metastatic and nonmetastatic SLNs. The quantitative parameters were fitted to univariable and multivariable logistic regression models. The diagnostic role of morphologic and quantitative parameters was analyzed by receiver operating characteristic curves and compared by using the McNemar test. Results This study included 193 female participants (mean age, 47.6 years ± 10.1; age range, 22-79 years). Quantitative dual-energy CT parameters including slope of the spectral Hounsfield unit curve (λHu) measured at both arterial and venous phases, normalized iodine concentration at both arterial and venous phase, and normalized effective atomic number at the venous phase were higher in metastatic than in nonmetastatic SLNs (P value range, ≤.001 to .031). Univariable and multivariable logistic regression analyses showed that venous phase λHu (in Hounsfield units per kiloelectron-volt) was the best single parameter for the detection of metastatic SLNs. The accuracy of the venous phase λHu for detecting metastatic SLNs was 90.5% on a per-lymph node basis and 87.0% on a per-patient basis. The accuracy and specificity at venous phase λHu was higher than their counterparts in the morphologic parameters (P < .001). Conclusion Dual-energy CT is a complementary means for the preoperative identification of sentinel lymph nodes metastases in participants with breast cancer. © RSNA, 2018 Online supplemental material is available for this article.