Use of MRI-based deep learning radiomics to diagnose sacroiliitis related to axial spondyloarthritis.

OBJECTIVES: This study aimed to evaluate the performance of a deep learning radiomics (DLR) model, which integrates multimodal MRI features and clinical information, in diagnosing sacroiliitis related to axial spondyloarthritis (axSpA). MATERIAL & METHODS: A total of 485 patients diagnosed with sacroiliitis related to axSpA (n = 288) or non-sacroiliitis (n = 197) by sacroiliac joint (SIJ) MRI between May 2018 and October 2022 were retrospectively included in this study. The patients were randomly divided into training (n = 388) and testing (n = 97) cohorts. Data were collected using three MRI scanners. We applied a convolutional neural network (CNN) called 3D U-Net for automated SIJ segmentation. Additionally, three CNNs (ResNet50, ResNet101, and DenseNet121) were used to diagnose axSpA-related sacroiliitis using a single modality. The prediction results of all the CNN models across different modalities were integrated using a stacking method based on different algorithms to construct ensemble models, and the optimal ensemble model was used as DLR signature. A combined model incorporating DLR signature with clinical factors was developed using multivariable logistic regression. The performance of the models was evaluated using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). RESULTS: Automated deep learning-based segmentation and manual delineation showed good correlation. ResNet50, as the optimal basic model, achieved an area under the curve (AUC) and accuracy of 0.839 and 0.804, respectively. The combined model yielded the highest performance in diagnosing axSpA-related sacroiliitis (AUC: 0.910; accuracy: 0.856) and outperformed the best ensemble model (AUC: 0.868; accuracy: 0.825) (all P < 0.05). Moreover, the DCA showed good clinical utility in the combined model. CONCLUSION: We developed a diagnostic model for axSpA-related sacroiliitis by combining the DLR signature with clinical factors, which resulted in excellent diagnostic performance.

Automatic Image Segmentation and Grading Diagnosis of Sacroiliitis Associated with AS Using a Deep Convolutional Neural Network on CT Images.

Ankylosing spondylitis (AS) is a chronic inflammatory disease that causes inflammatory low back pain and may even limit activity. The grading diagnosis of sacroiliitis on imaging plays a central role in diagnosing AS. However, the grading diagnosis of sacroiliitis on computed tomography (CT) images is viewer-dependent and may vary between radiologists and medical institutions. In this study, we aimed to develop a fully automatic method to segment sacroiliac joint (SIJ) and further grading diagnose sacroiliitis associated with AS on CT. We studied 435 CT examinations from patients with AS and control at two hospitals. No-new-UNet (nnU-Net) was used to segment the SIJ, and a 3D convolutional neural network (CNN) was used to grade sacroiliitis with a three-class method, using the grading results of three veteran musculoskeletal radiologists as the ground truth. We defined grades 0-I as class 0, grade II as class 1, and grades III-IV as class 2 according to modified New York criteria. nnU-Net segmentation of SIJ achieved Dice, Jaccard, and relative volume difference (RVD) coefficients of 0.915, 0.851, and 0.040 with the validation set, respectively, and 0.889, 0.812, and 0.098 with the test set, respectively. The areas under the curves (AUCs) of classes 0, 1, and 2 using the 3D CNN were 0.91, 0.80, and 0.96 with the validation set, respectively, and 0.94, 0.82, and 0.93 with the test set, respectively. 3D CNN was superior to the junior and senior radiologists in the grading of class 1 for the validation set and inferior to expert for the test set (P < 0.05). The fully automatic method constructed in this study based on a convolutional neural network could be used for SIJ segmentation and then accurately grading and diagnosis of sacroiliitis associated with AS on CT images, especially for class 0 and class 2. The method for class 1 was less effective but still more accurate than that of the senior radiologist.

Performance of adding hepatobiliary phase image in magnetic resonance imaging for detection of hepatocellular carcinoma: a meta-analysis.

OBJECTIVES: To determine the performance of diagnostic algorithm of adding hepatobiliary phase (HBP) images in Gd-EOB-DTPA-enhanced MRI for the detection of hepatocellular carcinoma (HCC) measuring up to 3 cm in patients with chronic liver disease. METHODS: We searched multiple databases from inception to April 10, 2020, to identify studies on using Gd-EOB-DTPA-enhanced MRI for the diagnostic accuracy of HCC (≤ 3 cm) in patients with chronic liver disease. The diagnostic algorithm of Gd-EOB-DTPA-enhanced MRI with HBP for HCC was defined as a nodule showing hyperintensity during arterial phase and hypointensity during the portal venous, delayed, or hepatobiliary phases. For gadoxetic acid-enhanced MRI without HBP, the diagnostic criteria were a nodule showing arterial enhancement and hypointensity on the portal venous or delayed phases. The data were extracted to calculate summary estimates of sensitivity, specificity, diagnostic odds ratio, likelihood ratio, and summary receiver operating characteristic (sROC) by using a bivariate random-effects model. RESULTS: Twenty-nine studies with 2696 HCC lesions were included. Overall Gd-EOB-DTPA-enhanced MRI with HBP had a sensitivity of 87%, specificity of 92%, and the area under the sROC curve of 95%. The summary sensitivity of Gd-EOB-DTPA-enhanced MRI with HBP was significantly higher than that without HBP (84% vs 68%, p = 0.01). CONCLUSION: Gd-EOB-DTPA-enhanced MRI with HBP showed higher sensitivity than that without HBP and had comparable specificity for diagnosis of HCC in patients with chronic liver disease. KEY POINTS: • Hypointensity on HBP is a major feature for diagnosis of HCC. • Extending washout appearance to the transitional or hepatobiliary phase on Gd-EOB-DTPA provides favorable sensitivity and comparable specificity for diagnosis HCC. • The summary sensitivity of gadoxetic acid-enhanced MRI with HBP was significantly higher than that without HBP (84% vs 68%, p = 0.01) for diagnosis of HCC in patients with chronic liver disease.

Radiomics Nomograms Based on Non-enhanced MRI and Clinical Risk Factors for the Differentiation of Chondrosarcoma from Enchondroma.

BACKGROUND: Differentiating chondrosarcoma from enchondroma using conventional MRI remains challenging. An effective method for accurate preoperative diagnosis could affect the management and prognosis of patients. PURPOSE: To validate and evaluate radiomics nomograms based on non-enhanced MRI and clinical risk factors for the differentiation of chondrosarcoma from enchondroma. STUDY TYPE: Retrospective. POPULATION: A total of 103 patients with pathologically confirmed chondrosarcoma (n = 53) and enchondroma (n = 50) were randomly divided into training (n = 68) and validation (n = 35) groups. FIELD STRENGTH/SEQUENCE: Axial non-contrast-enhanced T1-weighted images (T1WI) and fat-suppressed T2-weighted images (T2WI-FS) were acquired at 3.0 T. ASSESSMENT: Clinical risk factors (sex, age, and tumor location) and diagnosis assessment based on morphologic MRI by three radiologists were recorded. Three radiomics signatures were established based on the T1WI, T2WI-FS, and T1WI + T2WI-FS sequences. Three clinical radiomics nomograms were developed based on the clinical risk factors and three radiomics signatures. STATISTICAL TESTS: The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of radiomics signatures and clinical radiomics nomograms. RESULTS: Tumor location was an important clinical risk factor (P < 0.05). The radiomics signature based on T1WI and T1WI + T2WI-FS features performed better than that based on T2WI-FS in the validation group (AUC in the validation group: 0.961, 0.938, and 0.833, respectively; P < 0.05). In the validation group, the three clinical radiomics nomograms (T1WI, T2WI-FS, and T1WI + T2WI-FS) achieved AUCs of 0.938, 0.935, and 0.954, respectively. In all patients, the clinical radiomics nomogram based on T2WI-FS (AUC = 0.967) performed better than that based on T2WI-FS (AUC = 0.901, P < 0.05). DATA CONCLUSION: The proposed clinical radiomics nomogram showed promising performance in differentiating chondrosarcoma from enchondroma. LEVEL OF EVIDENCE: 4 TECHNICAL EFFICACY: Stage 2.

[Radiomics models based on non-enhanced MRI can differentiate chondrosarcoma from enchondroma].

OBJECTIVE: To develop and validate radiomics models based on non-enhanced magnetic resonance (MR) imaging for differentiating chondrosarcoma from enchondroma. METHODS: We retrospectively evaluated a total of 68 patients (including 27 with chondrosarcoma and 41 with enchondroma), who were randomly divided into training group (n=46) and validation group (n=22). Radiomics features were extracted from T1WI and T2WI-FS sequences of the whole tumor by two radiologists independently and selected by Low Variance, Univariate feature selection, and least absolute shrinkage and selection operator (LASSO). Radiomics models were constructed by multivariate logistic regression analysis based on the features from T1WI and T2WI-FS sequences. The receiver-operating characteristics (ROC) curve and intraclass correlation coefficient (ICC) analyses of the radiomics models and conventional MR imaging were performed to determine their diagnostic accuracy. RESULTS: The ICC value for interreader agreement of the radiomics features ranged from 0.779 to 0.923, which indicated good agreement. Ten and 11 features were selected from the T1WI and T2WI-FS sequences to construct radiomics models, respectively. The areas under the curve (AUCs) of T1WI and T2WI-FS models were 0.990 and 0.925 in training group and 0.915 and 0.855 in the validation group, respectively, showing no significant differences between the two sequence-based models (P>0.05). In all the cases, the AUCs of the two radiomics models based on T1WI and T2WI-FS sequences and conventional MR imaging were 0.955, 0.901 and 0.569, respectively, demonstrating a significantly higher diagnostic accuracy of the two sequence-based radiomics models than conventional MR imaging (P<0.01). CONCLUSIONS: The radiomics models based on T1WI and T2WI-FS non-enhanced MR imaging can be used for the differentiation of chondrosarcoma from enchondroma.

Synthesis and in vitro experiments of carcinoma vascular endothelial targeting polymeric nano-micelles combining small particle size and supermagnetic sensitivity.

Objective: To construct carcinoma vascular endothelial-targeted polymeric nanomicelles with high magnetic resonance imaging (MRI) sensitivity and to evaluate their biological safety and in vitro tumor-targeting effect, and to monitor their feasibility using clinical MRI scanner. Method: Amphiphilic block copolymer, poly(ethylene glycol)-b-poly(ε-caprolactone) (PEG-PCL) was synthesized via the ring-opening polymerization of ε-caprolactone (CL) initiated by poly(ethylene glycol) (PEG), in which cyclic pentapeptide Arg-Gly-Asp (cRGD) was conjugated with the terminal of hydrophilic PEG block. During the self-assembly of PEG-PCL micelles, superparamagnetic γ-Fe2O3 nanoparticles (11 nm) was loaded into the hydrophobic core. The cRGD-terminated γ-Fe2O3-loaded polymeric micelles targeting to carcinoma vascular endothelial cells, were characterized in particle size, morphology, loading efficiency and so on, especially high MRI sensitivity in vitro. Normal hepatic vascular endothelial cells (ED25) were incubated with the resulting micelles for assessing their safety. Human hepatic carcinoma vascular endothelial cells (T3A) were cultured with the resulting micelles to assess the micelle uptake using Prussian blue staining and the cell signal intensity using MRI. Results: All the polymeric micelles exhibited ultra-small particle sizes with approximately 50 nm, high relaxation rate, and low toxicity even at high iron concentrations. More blue-stained iron particles were present in the targeting group than the non-targeting and competitive inhibition groups. In vitro MRI showed T2WI and T2 relaxation times were significantly lower in the targeting group than in the other two groups. Conclusion: γ-Fe2O3-loaded PEG-PCL micelles not only possess ultra-small size and high superparamagnetic sensitivity, also can be actively targeted to carcinoma vascular endothelial cells by tumor-targeted cRGD. It appears to be a promising contrast agent for tumor-targeted imaging.

Effect of the division between early and late reflections on intelligibility of ideal binary-masked speech.

The ideal binary mask (IBM) that was originally defined in anechoic conditions has been found to yield substantial improvements in speech intelligibility in noise. The IBM has recently been extended to reverberant conditions where the direct sound and early reflections of target speech are regarded as the desired signal. It is of great interest to know how the division between early and late reflections impacts on the intelligibility of the IBM-processed noisy reverberant speech. In this present study, the division between early and late reflections in three rooms was first determined by four typical estimation approaches and then used to compute the IBMs in reverberant conditions. The IBMs were then applied to the noisy reverberant mixture signal for segregating the desired signal, and the segregated signal was further presented to normal-hearing listeners for word recognition. Results showed that the IBMs with different divisions between early and late reflections provided substantial improvements in speech intelligibility over the unprocessed mixture signals in all conditions tested, and there were small, but statistically significant, differences in speech intelligibility between the different IBMs in some conditions tested.