TPA: Two-stage progressive attention segmentation framework for hepatocellular carcinoma on multi-modality MRI.

BACKGROUND: Dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) plays a crucial role in the diagnosis and measurement of hepatocellular carcinoma (HCC). The multi-modality information contained in the multi-phase images of DCE-MRI is important for improving segmentation. However, this remains a challenging task due to the heterogeneity of HCC, which may cause one HCC lesion to have varied imaging appearance in each phase of DCE-MRI. In particular, some phases exhibit inconsistent sizes and boundaries will result in a lack of correlation between modalities, and it may pose inaccurate segmentation results. PURPOSE: We aim to design a multi-modality segmentation model that can learn meaningful inter-phase correlation for achieving HCC segmentation. METHODS: In this study, we propose a two-stage progressive attention segmentation framework (TPA) for HCC based on the transformer and the decision-making process of radiologists. Specifically, the first stage aims to fuse features from multi-phase images to identify HCC and provide localization region. In the second stage, a multi-modality attention transformer module (MAT) is designed to focus on the features that can represent the actual size. RESULTS: We conduct training, validation, and test in a single-center dataset (386 cases), followed by external test on a batch of multi-center datasets (83 cases). Furthermore, we analyze a subgroup of data with weak inter-phase correlation in the test set. The proposed model achieves Dice coefficient of 0.822 and 0.772 in the internal and external test sets, respectively, and 0.829, 0.791 in the subgroup. The experimental results demonstrate that our model outperforms state-of-the-art models, particularly within subgroup. CONCLUSIONS: The proposed TPA provides best segmentation results, and utilizing clinical prior knowledge for network design is practical and feasible.

Diagnostic performance of MRI for residual or recurrent hepatocellular carcinoma after locoregional treatment according to contrast agent type: a systematic review and meta­analysis.

PURPOSE: The ideal contrast agent for imaging patients with hepatocellular carcinoma (HCC) following locoregional therapies (LRT) remains uncertain. We conducted a meta-analysis to assess the diagnostic performance of magnetic resonance imaging with extracellular contrast agent (ECA-MRI) and hepatobiliary agent (EOB-MRI) in detecting residual or recurrence HCC following LRT. METHODS: Original studies comparing the diagnostic performance of ECA-MRI and EOB-MRI were systematically identified through comprehensive searches in PubMed, EMBASE, Cochrane Library and Web of Science databases. The pooled sensitivity and specificity of ECA-MRI and EOB-MRI were calculated using a bivariate-random-effects model. Subgroup-analyses were conducted to compare the diagnostic performance of ECA-MRI and EOB-MRI according to different variables. Meta-regression analysis was employed to explore potential sources of study heterogeneity. RESULTS: A total of 15 eligible studies encompassing 803 patients and 1018 lesions were included. Comparative analysis revealed no significant difference between ECA-MRI and EOB-MRI in the overall pooled sensitivity (87% vs. 79%) and specificity (92% vs. 96%) for the detection of residual or recurrent HCC after LRT (P = 0.41), with comparable areas under the HSROC of 0.95 and 0.92. Subgroup analyses indicated no significant diagnostic performance differences between ECA-MRI and EOB-MRI according to study design, type of LRT, most common etiology of liver disease, baseline lesion size, time of post-treated examination and MRI field strength (All P > 0.05). CONCLUSION: ECA-MRI exhibited overall comparable diagnostic performance to EOB-MRI in assessing residual or recurrent HCC after LRT.

Effects of Low-Osmolar Contrast Media on Long-Term Renal Impairment After Coronary Angiography: Iohexol Versus Iopromide.

To investigate the long-term effects of 2 commonly used low-osmolar contrast media, iohexol and iopromide, on renal function and survival in patients who underwent coronary angiography. A total of 14,141 cardiology patients from 2006 to 2013 were recruited, of whom 1,793 patients (679 patients on iohexol and 1,114 on iopromide) were evaluated for long-term renal impairment and 5,410 patients (1,679 patients on iohexol and 3,731 on iopromide) were admitted for survival analyses spanning as long as 15 years. Univariate and multivariate logistic regression were used to explore the risk factors for long-term renal impairment. Cox proportional hazard regression was used to investigate the risk factors affecting survival. Propensity score matching and inverse probability of treatment weighting were applied to balance the baseline clinical characteristics. Patients receiving iohexol demonstrated a greater occurrence of renal impairment compared with those who received iopromide. Such difference remained consistent both before and after propensity score matching or inverse probability of treatment weighting, with a statistical significance of p <0.05. Among clinical variables, receiving contrast-enhanced contrast tomography/magnetic resonance imaging during follow-up, antihypertensive medication usage, presence of proteinuria, and anemia were identified as risk factors for long-term renal impairment (p = 0.041, 0.049, 0.006, and 0.029, respectively). During survival analyses, the difference was insignificant after propensity score matching and inverse probability of treatment weighting. In conclusion, administration of iohexol was more likely to induce long-term renal impairment than iopromide, particularly among patients diagnosed with anemia and proteinuria and those taking antihypertensive medication and with additional contrast exposure. The all-cause mortality, however, showed no significant difference between iohexol and iopromide administration.

Predicting Microvascular Invasion in Hepatocellular Carcinoma Using CT-based Radiomics Model.

Background Prediction of microvascular invasion (MVI) may help determine treatment strategies for hepatocellular carcinoma (HCC). Purpose To develop a radiomics approach for predicting MVI status based on preoperative multiphase CT images and to identify MVI-associated differentially expressed genes. Materials and Methods Patients with pathologically proven HCC from May 2012 to September 2020 were retrospectively included from four medical centers. Radiomics features were extracted from tumors and peritumor regions on preoperative registration or subtraction CT images. In the training set, these features were used to build five radiomics models via logistic regression after feature reduction. The models were tested using internal and external test sets against a pathologic reference standard to calculate area under the receiver operating characteristic curve (AUC). The optimal AUC radiomics model and clinical-radiologic characteristics were combined to build the hybrid model. The log-rank test was used in the outcome cohort (Kunming center) to analyze early recurrence-free survival and overall survival based on high versus low model-derived score. RNA sequencing data from The Cancer Image Archive were used for gene expression analysis. Results A total of 773 patients (median age, 59 years; IQR, 49-64 years; 633 men) were divided into the training set (n = 334), internal test set (n = 142), external test set (n = 141), outcome cohort (n = 121), and RNA sequencing analysis set (n = 35). The AUCs from the radiomics and hybrid models, respectively, were 0.76 and 0.86 for the internal test set and 0.72 and 0.84 for the external test set. Early recurrence-free survival (P < .01) and overall survival (P < .007) can be categorized using the hybrid model. Differentially expressed genes in patients with findings positive for MVI were involved in glucose metabolism. Conclusion The hybrid model showed the best performance in prediction of MVI. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Summers in this issue.

Added value of chest CT images to a personalized prognostic model in acute respiratory distress syndrome: a retrospective study.

Background: Acute respiratory distress syndrome (ARDS) is a critical disease in the intensive care unit (ICU) with high morbidity and mortality. The accuracy for predicting ARDS patients' outcome with mechanical ventilation is limited, and most based on clinical information. Methods: The patients diagnosed with ARDS between January 2014 and June 2019 were retrospectively recruited. Radiomics features were extracted from the upper, middle, and lower levels of the lung, and were further analyzed with the primary outcome (28-day mortality after ARDS onset). The univariate and multivariate logistic regression analyses were applied to figure out risk factors. Various predictive models were constructed and compared. Results: Of 366 ARDS patients recruited in this study, 276 (median age, 64 years [interquartile range, 54-75 years]; 208 male) survive on the Day 28. Among all factors, the APACHE II Score (OR 2.607, 95% CI 1.896-3.584, P < 0.001), the Radiomics_Score of the middle lung (OR 2.230, 95% CI 1.387-3.583, P = 0.01), the Radiomics_Score of the lower lung (OR 1.633, 95% CI 1.143-2.333, P = 0.01) were associated with the 28-day mortality. The clinical_radiomics predictive model (AUC 0.813, 95% CI 0.767-0.850) show the best performance compared with the clinical model (AUC 0.758, 95% CI 0.710-0.802), the radiomics model (AUC 0.692, 95% CI 0.641-0.739) and the various ventilator parameter-based models (highest AUC 0.773, 95% CI 0.726-0.815). Conclusions: The radiomics features of chest CT images have incremental values in predicting the 28-day mortality in ARDS patients with mechanical ventilation. Supplementary Information: The online version contains supplementary material available at 10.1007/s42058-023-00116-x.

MicroRNA-30/Cx43 axis contributes to podocyte injury by regulating ER stress in diabetic nephropathy.

BACKGROUND: The microRNA-30 family plays a critical role in the pathogenesis of podocyte injury. Cx43 plays an essential role in intercellular communication, which is essential for coordinated kidney function. This study was conducted to explore the function of microRNA-30s/Cx43 in podocyte injury in diabetic nephropathy (DN), both in vivo and in vitro. METHODS: SD rats were given streptozotocin (STZ) injections to induce DN. Podocytes were incubated in the medium in the presence or absence of high glucose (HG). The effects of the microRNA-30/Cx43 axis on DN and its underlying mechanisms were investigated by TUNEL assay, PAS, immunohistochemical staining, immunofluorescence staining, Western blot, RT-qPCR, RNA interference, and luciferase reporter assay. Podocytes were transfected with microRNA-30 family mimics, microRNA-30 family inhibitors, Cx43 siRNA, and negative controls to detect the effect of the microRNA-30/Cx43 axis. MicroRNA-30 family mimic AAVs, and microRNA-30 family inhibitor AAVs applied to regulate microRNA-30 family expression in the kidneys of the STZ-induced DN model rats to reveal the underlying mechanisms of the microRNA-30/Cx43 axis in DN. RESULTS: MicroRNA-30 family member expression was downregulated in HG-treated podocytes and the glomeruli of STZ-induced DN rats. Luciferase reporter assays confirmed Cx43 is a directed target of microRNA-30s. The overexpression of microRNA-30 family members attenuated the HG-induced podocyte injury and protected against podocyte apoptosis and endoplasmic reticulum stress (ERS) both in vivo and in vitro. Also, silencing Cx43 expression eased podocyte apoptosis, injury, and ERS induced by a HG+microRNA-30 family inhibitor. Double-immunofluorescence staining assays proved the co-localization of caspase12 and Cx43. CONCLUSIONS: The overexpression of microRNA-30 family members prevents HG-induced podocyte injury and attenuates ERS by modulating Cx43 expression. The microRNA-30/Cx43/ERS axis might be a potential therapeutic target to treat DN.