Multi­parameter quantitative magnetic resonance imaging in the early assessment of radiation­induced parotid damage in patients with nasopharyngeal carcinoma following intensity­modulated radiotherapy.

The present study aimed to investigate the value of intravoxel incoherent motion imaging (IVIM) and three-dimensional pulsed continuous arterial spin labeling (ASL) in assessing dynamic changes of the parotid gland in patients with nasopharyngeal carcinoma (NPC) following radiotherapy (RT). A total of 18 patients with NPC who underwent intensity-modulated RT were enrolled in the present study. All patients underwent conventional magnetic resonance imaging, plus IVIM and ASL imaging of the bilateral parotid glands within 2 weeks prior to RT, and 1 week (1W) and 3 months (3M) following RT. Pure diffusion coefficient (D), pseudo-diffusion coefficient (D*), perfusion fraction (F) and blood flow (BF) were analyzed. D and BF values were significantly increased from pre-RT to 1W post-RT [change rate: Median (IQR), ΔD1W%: 39.28% (38.23%) and ΔBF1W%: 60.84% (54.88%)] and continued to increase from 1W post-RT to 3M post-RT [55.44% (40.56%) and ΔBF%: 120.39% (128.74%)]. In addition, the F value was significantly increased from pre-RT to 1W post-RT, [change rate: Median (IQR), ΔF1W%: 28.13% (44.66%)], and this decreased significantly from 1W post-RT to 3M post-RT. However, no significant differences were observed between pre-RT and 3M post-RT. Results of the present study also demonstrated that the D* value was significantly decreased from pre-RT to 1W post-RT and 3M post-RT [change rate: Median (IQR), ΔD*1w%: -41.86% (51.71%) and ΔD*3M: -29.11% (42.67%)]. No significant difference was observed between the different time intervals post-RT. There was a significant positive correlation between percentage change in ΔBF1W and radiation dose (ρ=0.548, P=0.001). Thus, IVIM-diffusion-weighted imaging and ASL may aid in the detection and prediction of radiation-induced parotid damage in the early stages following RT. They may contribute to further understanding the potential association between damage to the parotid glands and patient-/treatment-related variables, through the assessment of individual microcapillary perfusion and tissue diffusivity.

Evaluating magnetic resonance imaging characteristics and risk factors for hemifacial spasm.

PURPOSE: The specific neurovascular compression (NVC) event responsible for the symptomatic manifestation of hemifacial spasm (HFS) remains difficult to assess accurately using magnetic resonance imaging (MRI). We aim to evaluate the MRI characteristics of HFS. METHOD: We retrospectively included patients with HFS and divided them into a test group (n = 186) and a validation group (n = 28). The presence, severity, and offending vessel type of NVC in each portion, and the orientation of the offending vessel around the facial nerve, were recorded. Conditional logistic regression analyses were performed to evaluate correlations using test group. The validation group was used to verify whether our findings improved diagnostic performance. RESULTS: Deformity in the proximal cisternal segment was significantly correlated with HFS occurrence (odds ratio [OR]: 256.58, p = .002), whereas contact was not (p = .233). Both contact and deformity in the root detachment point (OR: 19.98 and 37.22, p < .001 and p = .013, respectively) or attached segment (OR: 4.99 and 252.52, p = .001 and p < .001, respectively) were significantly correlated with HFS occurrence. Our findings improved specificity, positive predictive value, and accuracy of diagnosis than conventional diagnostic methods. The vertebral artery predominantly compress the facial nerve in the inferior-anterior position, the anterior inferior cerebellar artery predominantly in the inferior position, the posterior inferior cerebellar artery predominantly in the inferior position, vein predominantly in the posterior-superior position. CONCLUSIONS: This study further demonstrates that within the susceptible portion of facial nerve, different portions of the nerve respond differently to NVC. Each offending vessel has its own preferred conflict orientation. Our study offers reference for neurosurgeons in diagnosis and treatment.

Radiological characteristics predicting early poor drug response in patients with hemifacial spasm.

OBJECTIVES: Patients with hemifacial spasm (HFS) often resort to botulinum toxin injections or microvascular decompression surgery when medication exhibits limited effectiveness. This study aimed to identify MRI and demographic factors associated with poor drug response at an early stage in patients with HFS. METHODS: We retrospectively included patients with HFS who underwent pre-therapeutic MRI examination. The presence, location, severity, and the offending vessels of neurovascular compression were blindly evaluated using MRI. Drug responses and clinical data were obtained from the medical notes or phone follow-ups. Logistic regression analysis was performed to identify potential factors. RESULTS: A total of 116 patients were included, with an average age at the time of first examination of 50.4 years and a median duration of onset of 18 months. Forty-nine (42.2%) patients reported no symptom relief. Thirty-seven (31.9%) patients reported poor symptom relief. Twenty-two (19.0%) patients reported partial symptom relief. Eight (6.9%) patients achieved complete symptom relief. The factors that were statistically significant associated with poor drug responses were contact in the attach segment of the facial nerve and aged 70 and above, with an odds ratio of 7.772 (p = 0.002) and 0.160 (p = 0.028), respectively. CONCLUSIONS: This study revealed that mild compression in the attach segment of the facial nerve in pre-therapeutic MRI increases the risk of poor drug responses in patients with HFS, while patients aged 70 and above showed a decreased risk. These findings may assist clinician to choose optimal treatment at an early stage.

Development and validation of a nomogram based on CT texture analysis for discriminating minimally invasive adenocarcinoma from glandular precursor lesions in sub­centimeter pulmonary ground glass nodules.

In a recent reclassification, adenocarcinoma in situ has been redefined as a glandular precursor lesion (GPL), alongside adenomatous hyperplasia. This updated classification necessitates corresponding adaptations in clinical diagnostic and therapeutic protocols. Consequently, the present study aimed to construct and validate a nomogram utilizing computed tomography (CT) texture features to effectively discriminate between minimally invasive adenocarcinoma (MIA) and GPL within sub-centimeter pulmonary ground glass nodules (GGNs). To achieve this objective, the present study employed rigorous statistical methodologies, including the Mann-Whitney U test and binary logistic regression analysis, to identify distinguishing features and establish predictive models. Subsequently, the diagnostic performance of these models underwent evaluation through receiver operating characteristic (ROC) curves. The area under the curve (AUC) in ROC curves was compared using DeLong's test. Additionally, the nomogram was constructed using R software and its diagnostic performance was validated through calibration curves. Within both the training and validation datasets, the AUCs were observed to be 0.992 [95% confidence interval (CI): 0.980-1.000] and 0.975 (95% CI: 0.935-1.000), respectively. DeLong's test revealed significant disparities in the AUCs between the nomogram and single-parameter models (P<0.001). Furthermore, calibration curves demonstrated concordance between the training and validation datasets. In conclusion, the application of a CT texture-based nomogram model has demonstrated aptitude in differentiating between MIA and GPL within sub-centimeter GGNs. This model streamlines the identification of optimal surgical interventions and enhances the sphere of clinical decision-making and management.

Artificial intelligence aided precise detection of local recurrence on MRI for nasopharyngeal carcinoma: a multicenter cohort study.

Background: MRI is the routine examination to surveil the recurrence of nasopharyngeal carcinoma, but it has relatively lower sensitivity than PET/CT. We aimed to find if artificial intelligence (AI) could be competent pre-inspector for MRI radiologists and whether AI-aided MRI could perform better or even equal to PET/CT. Methods: This multicenter study enrolled 6916 patients from five hospitals between September 2009 and October 2020. A 2.5D convolutional neural network diagnostic model and a nnU-Net contouring model were developed in the training and test cohorts and used to independently predict and visualize the recurrence of patients in the internal and external validation cohorts. We evaluated the area under the ROC curve (AUC) of AI and compared AI with MRI and PET/CT in sensitivity and specificity using the McNemar test. The prospective cohort was randomized into the AI and non-AI groups, and their sensitivity and specificity were compared using the Chi-square test. Findings: The AI model achieved AUCs of 0.92 and 0.88 in the internal and external validation cohorts, corresponding to the sensitivity of 79.5% and 74.3% and specificity of 91.0% and 92.8%. It had comparable sensitivity to MRI (e.g., 74.3% vs. 74.7%, P = 0.89) but lower sensitivity than PET/CT (77.9% vs. 92.0%, P < 0.0001) at the same individual-specificities. The AI model achieved moderate precision with a median dice similarity coefficient of 0.67. AI-aided MRI improved specificity (92.5% vs. 85.0%, P = 0.034), equaled PET/CT in the internal validation subcohort, and increased sensitivity (81.9% vs. 70.8%, P = 0.021) in the external validation subcohort. In the prospective cohort of 1248 patients, the AI group had higher sensitivity than the non-AI group (78.6% vs. 67.3%, P = 0.23), albeit nonsignificant. In future randomized controlled trials, a sample size of 3943 patients in each arm would be required to demonstrate the statistically significant difference. Interpretation: The AI model equaled MRI by expert radiologists, and AI-aided MRI by expert radiologists equaled PET/CT. A larger randomized controlled trial is warranted to demonstrate the AI's benefit sufficiently. Funding: The Sun Yat-sen University Clinical Research 5010 Program (2015020), Guangdong Basic and Applied Basic Research Foundation (2022A1515110356), and Guangzhou Science and Technology Program (2023A04J1788).

Development of a magnetic resonance imaging-derived radiomics model to predict microvascular invasion in patients with hepatocellular carcinoma.

Background: Hepatocellular carcinoma (HCC) with microvascular invasion (MVI) has a poor prognosis, is prone to recurrence and metastasis, and requires more complex surgical techniques. Radiomics is expected to enhance the discriminative performance for identifying HCC, but the current radiomics models are becoming increasingly complex, tedious, and difficult to integrate into clinical practice. The purpose of this study was to investigate whether a simple prediction model using noncontrast-enhanced T2-weighted magnetic resonance imaging (MRI) could preoperatively predict MVI in HCC. Methods: A total of 104 patients with pathologically confirmed HCC (training cohort, n=72; test cohort, n=32; ratio, about 7:3) who underwent liver MRI within 2 months prior to surgery were retrospectively included. A total of 851 tumor-specific radiomic features were extracted on T2-weighted imaging (T2WI) for each patient using AK software (Artificial Intelligence Kit Version; V. 3.2.0R, GE Healthcare). Univariate logistic regression and least absolute shrinkage and selection operator (LASSO) regression were used in the training cohort for feature selection. The selected features were incorporated into a multivariate logistic regression model to predict MVI, which was validated in the test cohort. The model's effectiveness was evaluated using the receiver operating characteristic and calibration curves in the test cohort. Results: Eight radiomic features were identified to establish a prediction model. In the training cohort, the area under the curve, accuracy, specificity, sensitivity, and positive and negative predictive values of the model for predicting MVI were 0.867, 72.7%, 84.2%, 64.7%, 72.7%, and 78.6%, respectively; while in the test cohort, they were 0.820, 75%, 70.6%, 73.3%, 75%, and 68.8%, respectively. The calibration curves displayed good consistency between the prediction of MVI by the model and actual pathological results in both the training and validation cohorts. Conclusions: A prediction model using radiomic features from single T2WI can predict MVI in HCC. This model has the potential to be a simple and fast method to provide objective information for decision-making during clinical treatment.

Integrative Scoring System for Survival Prediction in Patients With Locally Advanced Nasopharyngeal Carcinoma: A Retrospective Multicenter Study.

PURPOSE: Tumor stage is crucial for prognostic evaluation and therapeutic decisions in locally advanced nasopharyngeal carcinoma (NPC) but is imprecise. We aimed to propose a new prognostic system by integrating quantitative imaging features and clinical factors. MATERIALS AND METHODS: This retrospective study included 1,319 patients with stage III-IVa NPC between April 1, 2010, and July 31, 2019, who underwent pretherapy magnetic resonance imaging (MRI) and received concurrent chemoradiotherapy with or without induction chemotherapy. The hand-crafted and deep-learned features were extracted from MRI for each patient. After feature selection, the clinical score, radiomic score, deep score, and integrative scores were constructed via Cox regression analysis. The scores were validated in two external cohorts. The predictive accuracy and discrimination were measured by the area under the curve (AUC) and risk group stratification. The end points were progression-free survival (PFS), overall survival (OS), and distant metastasis-free survival (DMFS). RESULTS: Both radiomics and deep learning were complementary to clinical variables (age, T stage, and N stage; all P < .05). The clinical-deep score was superior or equivalent to clinical-radiomic score, whereas it was noninferior to clinical-radiomic-deep score (all P > .05). These findings were also verified in the evaluation of OS and DMFS. The clinical-deep score yielded an AUC of 0.713 (95% CI, 0.697 to 0.729) and 0.712 (95% CI, 0.693 to 0.731) in the two external validation cohorts for predicting PFS with good calibration. This scoring system could stratify patients into high- and low-risk groups with distinct survivals (all P < .05). CONCLUSION: We established and validated a prognostic system integrating clinical data and deep learning to provide an individual prediction of survival for patients with locally advanced NPC, which might inform clinicians in treatment decision making.

Combination of Quantitative Susceptibility Mapping and Diffusion Kurtosis Imaging Provides Potential Biomarkers for Early-Stage Parkinson's Disease.

Purpose: This study aimed to detect changes in iron deposition and neural microstructure in the substantia nigra (SN), red nucleus (RN), and basal ganglia of Parkinson's disease (PD) patients at different stages using quantitative susceptibility mapping and diffusion kurtosis imaging to identify potential indicators of early-stage PD. Methods: We enrolled 20 early-stage and 15 late-stage PD patients, as well as 20 age- and sex-matched controls. All participants underwent quantitative susceptibility mapping and diffusion kurtosis imaging to determine magnetic susceptibility (MS), fractional anisotropy (FA), mean diffusivity (MD), and mean kurtosis (MK) in several brain regions. Results: Compared with the control group, MS and MK values in the SN were significantly increased in the early- and late-stage PD group, whereas MS values in the red nucleus (RN), globus pallidus (GP), and caudate nucleus (CN), FA value in the CN and GP, and MK value in the CN and putamen (PU) were significantly increased in the late-stage PD group. There were positive correlations between MS and MK values in the CN and MS and FA values in the GP. Furthermore, the combination of MS and MK values in the SN provided high accuracy for distinguishing early-stage PD patients from controls. Conclusions: This study identified MS and MK in the SN as potential indicators of early-stage PD.

Add-on individualizing prediction of nasopharyngeal carcinoma using deep-learning based on MRI: A multicentre, validation study.

In nasopharyngeal carcinoma, deep-learning extracted signatures on MR images might be correlated with survival. In this study, we sought to develop an individualizing model using deep-learning MRI signatures and clinical data to predict survival and to estimate the benefit of induction chemotherapy on survivals of patients with nasopharyngeal carcinoma. Two thousand ninety-seven patients from three independent hospitals were identified and randomly assigned. When the deep-learning signatures of the primary tumor and clinically involved gross cervical lymph nodes extracted from MR images were added to the clinical data and TNM staging for the progression-free survival prediction model, the combined model achieved better prediction performance. Its application is among patients deciding on treatment regimens. Under the same conditions, with the increasing MRI signatures, the survival benefits achieved by induction chemotherapy are increased. In nasopharyngeal carcinoma, these prediction models are the first to provide an individualized estimation of survivals and model the benefit of induction chemotherapy on survivals.

MRI Radiogenomics in Precision Oncology: New Diagnosis and Treatment Method.

Precision medicine for cancer affords a new way for the most accurate and effective treatment to each individual cancer. Given the high time-evolving intertumor and intratumor heterogeneity features of personal medicine, there are still several obstacles hindering its diagnosis and treatment in clinical practice regardless of extensive exploration on it over the past years. This paper is to investigate radiogenomics methods in the literature for precision medicine for cancer focusing on the heterogeneity analysis of tumors. Based on integrative analysis of multimodal (parametric) imaging and molecular data in bulk tumors, a comprehensive analysis and discussion involving the characterization of tumor heterogeneity in imaging and molecular expression are conducted. These investigations are intended to (i) fully excavate the multidimensional spatial, temporal, and semantic related information regarding high-dimensional breast magnetic resonance imaging data, with integration of the highly specific structured data of genomics and combination of the diagnosis and cognitive process of doctors, and (ii) establish a radiogenomics data representation model based on multidimensional consistency analysis with multilevel spatial-temporal correlations.

A Joint Framework for Denoising and Estimating Diffusion Kurtosis Tensors Using Multiple Prior Information.

Diffusion kurtosis imaging (DKI) has been shown to be valuable in a wide range of neuroscientific and clinical applications. However, reliable estimation of DKI tensors is often compromised by noise, especially for the kurtosis tensor (KT). Here, we propose a joint denoising and estimating framework that integrates multiple sources of prior information, including nonlocal structural self-similarity (NSS), local spatial smoothness (LSS), physical relevance (PR) of the DKI model, and noise characteristics of magnitude diffusion MRI (dMRI) images for improved estimation of DKI tensors. The local and nonlocal spatial smoothing constraints are complementary to each other, making the proposed framework highly effective in reducing the noise fluctuations on DKI tensors, especially KT. As an additional refinement, we propose to impose a physically relevant constraint within our joint denoising and estimation framework. We further adopt the first-moment noise-corrected fitting model (M1NCM) to remove the noncentral χ -distribution noise bias. The effectiveness of integrating multiple sources of priors into the joint framework is verified by comparing the proposed M1NCM-NSS-LSS-PR method with various versions of M1NCM-based estimators and two state-of-the-art methods. Results show that the proposed method outperformed the compared methods in simulations and in-vivo dMRI datasets of both spatially stationary and nonstationary noise distributions. The in-vivo experiments also show that the proposed M1NCM-NSS-LSS-PR method was robust to the number of diffusion directions.

Renal epithelioid angiomyolipoma: computed tomography manifestation and radiologic-pathologic correlation depending on different epithelioid component percentages.

BACKGROUND: Renal epithelioid angiomyolipoma (EAML) is a rare and potentially malignant mesenchymal lesion mainly composed of epithelioid cells. Although some case reports or small case series have been published, the computed tomography (CT) manifestations and radiologic-pathologic correlation depending on different epithelioid component percentages have not been studied before. OBJECTIVE: To investigate the CT manifestation and radiologic-pathologic correlation between renal EAML and angiomyolipoma (AML) with epithelioid component. METHODS: The clinicopathologic and imaging data of 53 patients with an original diagnosis of EAML or AML with epithelioid component were retrospectively collected from three hospitals. All tissue specimens were re-sectioned and re-observed under the microscope. Samples were divided into an EAML group (≥ 80% epithelioid component, n = 25) and AML with epithelioid component group (5% ≤ epithelioid component < 80%, n = 28). Two radiologists reviewed the images in consensus, describing and comparing the CT manifestation, including the long diameter of the tumor, morphology, presence of necrosis or cystic change, hemorrhage, fat, calcification, enlarged blood vessels, and dynamic enhancement pattern according to the Hounsfield unit value of each CT phase between the two groups. The radiologic-pathologic correlation depending on the different percentages of epithelioid component were studied. RESULTS: The long diameter of the tumor, presence of necrosis or cystic change, fat, enhancement pattern, and tumor-to-cortex enhancement ratio of the cortical phase between the two groups were significantly different (z = - 2.932, P = 0.003; χ2 = 18.020, P < 0.001; χ2 = 16.377, P < 0.001; P = 0.020; and T = - 3.944, P < 0.001, respectively). In multivariate logistic regression analysis, the significant predictive factors of EAML included the presence of necrosis or cystic change [odds ratio (OR) 11.864, P = 0.001] and absence of fat (OR 0.095, P = 0.003). Correlation analysis found that the presence of necrosis or cystic change (r = 0.679, P < 0.001) and fat (r = - 0.603, P < 0.001) were both moderately related to the epithelioid component percentage. The combined model based on the presence of necrosis or cystic change and absence of fat yielded the best diagnostic performance in discriminating EAML and AML with epithelioid component with the highest area under the curve (0.887). CONCLUSION: EAML has characteristic CT signs; these characteristic CT signs are closely related to the epithelioid component percentage. The presence of necrosis or cystic change and the absence of fat were independent predictors of EAML.

The Effect of Individual Musculoskeletal Conditions on Depression: Updated Insights From an Irish Longitudinal Study on Aging.

Few longitudinal studies have systematically investigated whether or how individual musculoskeletal conditions (IMCs) convey risks for negative psychological health outcomes, and approaches to assess such risk in the older population are lacking. In this Irish nationally representative longitudinal prospective study of 6,715 individuals aged 50 and above, machine learning algorithms and various models, including mediation models, were employed to elaborate the underlying mechanisms of IMCs leading to depression and to develop an IMC-induced negative psychological risk (IMCPR) classification approach. Resultantly, arthritis [odds ratio (95% confidence interval): 2.233 (1.700-2.927)], osteoporosis [1.681 (1.133-2.421)], and musculoskeletal chronic pain [MCP, 2.404 (1.838-3.151)] were found to increase the risk of depression after 2 years, while fracture and joint replacement did not. Interestingly, mediation models further demonstrated that arthritis per se did not increase the risk of depression; such risk was augmented only when arthritis-induced restrictions of activities (ARA) existed [proportion of mediation: 316.3% (ARA of usual), 213.3% (ARA of social and leisure), and 251.3% (ARA of sleep)]. The random forest algorithm attested that osteoarthritis, not rheumatoid arthritis, contributed the most to depressive symptoms. Moreover, bone mineral density was negatively associated with depressive symptoms. Systemic pain contributed the most to the increased risk of depression, followed by back, knee, hip, and foot pain (mean Gini-Index: 3.778, 2.442, 1.980, 1.438, and 0.879, respectively). Based on the aforementioned findings, the IMCPR classification approach was developed using an interpretable machine learning model, which stratifies participants into three grades. Among the IMCPR grades, patients with a grade of "severe" had higher odds of depression than those with a "mild" [odds ratio (95% confidence interval): 4.055 (2.907-5.498)] or "moderate" [3.584 (2.101-5.883)] grade. Females with a "severe" grade had higher odds of depression by 334.0% relative to those with a "mild" grade, while males had a relative risk of 258.4%. In conclusion, the present data provide systematic insights into the IMC-induced depression risk and updated the related clinical knowledge. Furthermore, the IMCPR classification approach could be used as an effective tool to evaluate this risk.

An interpretable machine learning prognostic system for locoregionally advanced nasopharyngeal carcinoma based on tumor burden features.

OBJECTIVES: We aimed to build a survival system by combining a highly-accurate machine learning (ML) model with explainable artificial intelligence (AI) techniques to predict distant metastasis in locoregionally advanced nasopharyngeal carcinoma (NPC) patients using magnetic resonance imaging (MRI)-based tumor burden features. MATERIALS AND METHODS: 1643 patients from three hospitals were enrolled according to set criteria. We employed ML to develop a survival model based on tumor burden signatures and all clinical factors. Shapley Additive exPlanations (SHAP) was utilized to explain prediction results and interpret the complex non-linear relationship among features and distant metastasis. We also constructed other models based on routinely used cancer stages, Epstein-Barr virus (EBV) DNA, or other clinical features for comparison. Concordance index (C-index), receiver operating curve (ROC) analysis and decision curve analysis (DCA) were executed to assess the effectiveness of the models. RESULTS: Our proposed system consistently demonstrated promising performance across independent cohorts. The concordance indexes were 0.773, 0.766 and 0.760 in the training, internal validation and external validation sets. SHAP provided personalized protective and risk factors for each NPC patient and uncovered some novel non-linear relationships between features and distant metastasis. Furthermore, high-risk patients who received induction chemotherapy (ICT) and concurrent chemoradiotherapy (CCRT) had better 5-year distant metastasis-free survival (DMFS) than those who only received CCRT, whereas ICT + CCRT and CCRT had similar DMFS in low-risk patients. CONCLUSIONS: The interpretable machine learning system demonstrated superior performance in predicting metastasis in locoregionally advanced NPC. High-risk patients might benefit from ICT.

Three-dimensional pulsed continuous arterial spin labeling and intravoxel incoherent motion imaging of nasopharyngeal carcinoma: correlations with Ki-67 proliferation status.

BACKGROUND: Recurrence and distant metastasis are still the main problems affecting the long-term prognosis of nasopharyngeal carcinoma (NPC) patients, and may be related to the Ki-67 proliferation status. We therefore explored the potential correlation between Ki-67 proliferation status in NPC with the parameters derived from two imaging techniques: three-dimensional pulsed continuous arterial spin labeling (3D pCASL) and intravoxel incoherent motion (IVIM). METHODS: Thirty-six patients with pathologically confirmed NPC were included, and the Ki-67 labeling index (LI) was measured by immunohistochemistry. All patients underwent plain and contrast-enhanced magnetic resonance imaging (MRI), IVIM, and 3D pCASL examination. The mean, maximum, and minimum of blood flow (BF), minimum of apparent diffusion coefficient (ADC), pure diffusion coefficient (D), pseudodiffusion coefficient (D*), and perfusion fraction (f) parameters were all measured, and Spearman's correlation analysis was performed to evaluate the relationships between these parameters and the Ki-67 LI. According to the Ki-67 values, the patients were divided into two groups: high (>50%) and low (≤50%). The rank-sum test (Mann-Whitney U test) was then used to compare the differences in quantitative parameters between the high and low Ki-67 groups. RESULTS: Ki-67 LI was positively correlated with BFmean and BFmax (r=0.415 and 0.425). D*mean and D*min did have positive correlation with Ki-67, but this was not significant (P=0.082 and 0.072). BFmax was significantly different between the high and low Ki-67 groups (P=0.028). CONCLUSIONS: 3D pCASL and IVIM are noninvasive functional MR perfusion imaging techniques that can evaluate perfusion information and perfusion parameters. Our study suggests that 3D pCASL is more effective than IVIM for assessing the proliferation status of NPC, which is beneficial for evaluating the prognosis of patients. Furthermore, BFmax is the best biomarker for distinguishing high from low Ki-67 levels.

Novel multifunctional adenine-modified chitosan dressings for promoting wound healing.

Wound healing is a dynamic and intricate process, and newly dressings are urgently needed to promote wound healing over the multiple stages. Herein, two water-soluble adenine-modified chitosan (CS-A) derivatives were synthesized in aqueous solutions and freeze-dried to obtain porous sponge-like dressings. The novel derivatives displayed antibacterial activities against S. aureus and E. coli. Moreover, CS-A derivatives demonstrated excellent hemocompatibility and cytocompatibility, as well as promoted the proliferation of the wound cells by shortening the G1 phase and improving DNA duplication efficiency. The ability of CS-A sponges to promote wound healing was studied in a full-thickness skin defect model. The histological analysis and immunohistochemical staining showed that the wounds treated with CS-A sponges displayed fewer inflammatory cells, and faster regeneration of epithelial tissue, collagen deposition and neovascularization. Therefore, CS-A derivatives have potential application in wound dressings and provide new ideas for the design of multifunctional biomaterials.

Artificial Intelligence in Breast MRI Radiogenomics: Towards Accurate Prediction of Neoadjuvant Chemotherapy Responses.

Neoadjuvant Chemotherapy (NAC) in breast cancer patients has considerable prognostic and treatment potential and can be tailored to individual patients as part of precision medicine protocols. This work reviews recent advances in artificial intelligence so as to enable the use of radiogenomics for accurate NAC analysis and prediction. The work addresses a new problem in radiogenomics mining: How to combine structural radiomics information and non-structural genomics information for accurate NAC prediction. This requires the automated extraction of parameters from structural breast radiomics data, and finding non-structural feature vectors with diagnostic value, which then are combined with genomics data acquired from exocrine bodies in blood samples from a cohort of cancer patients to enable accurate NAC prediction. A self-attention-based deep learning approach, along with an effective multi-channel tumour image reconstruction algorithm of high dimensionality, is proposed. The aim was to generate non-structural feature vectors for accurate prediction of the NAC responses by combining imaging datasets with exocrine body related genomics analysis.

A Prognostic Predictive System Based on Deep Learning for Locoregionally Advanced Nasopharyngeal Carcinoma.

BACKGROUND: Images from magnetic resonance imaging (MRI) are crucial unstructured data for prognostic evaluation in nasopharyngeal carcinoma (NPC). We developed and validated a prognostic system based on the MRI features and clinical data of locoregionally advanced NPC (LA-NPC) patients to distinguish low-risk patients with LA-NPC for whom concurrent chemoradiotherapy (CCRT) is sufficient. METHODS: This multicenter, retrospective study included 3444 patients with LA-NPC from January 1, 2010, to January 31, 2017. A 3-dimensional convolutional neural network was used to learn the image features from pretreatment MRI images. An eXtreme Gradient Boosting model was trained with the MRI features and clinical data to assign an overall score to each patient. Comprehensive evaluations were implemented to assess the performance of the predictive system. We applied the overall score to distinguish high-risk patients from low-risk patients. The clinical benefit of induction chemotherapy (IC) was analyzed in each risk group by survival curves. RESULTS: We constructed a prognostic system displaying a concordance index of 0.776 (95% confidence interval [CI] = 0.746 to 0.806) for the internal validation cohort and 0.757 (95% CI = 0.695 to 0.819), 0.719 (95% CI = 0.650 to 0.789), and 0.746 (95% CI = 0.699 to 0.793) for the 3 external validation cohorts, which presented a statistically significant improvement compared with the conventional TNM staging system. In the high-risk group, patients who received induction chemotherapy plus CCRT had better outcomes than patients who received CCRT alone, whereas there was no statistically significant difference in the low-risk group. CONCLUSIONS: The proposed framework can capture more complex and heterogeneous information to predict the prognosis of patients with LA-NPC and potentially contribute to clinical decision making.

Exploration of the molecular characteristics of the tumor-immune interaction and the development of an individualized immune prognostic signature for neuroblastoma.

Neuroblastoma (NBL) exists in a complex tumor-immune microenvironment. Immune cell infiltration and tumor-immune molecules play a critical role in tumor development and significantly impact the prognosis of patients. However, the molecular characteristics describing the NBL-immune interaction and their prognostic potential have yet to be investigated systematically. We first employed multiple machine learning algorithms, such as Gene Sets Enrichment Analysis and cell type identification by estimating relative subsets of RNA transcripts, to identify immunophenotypes and immunological characteristics in NBL patient data from public databases and then investigated the prognostic potential and regulatory networks of identified immune-related genes involved in the NBL-immune interaction. The immunity signature combining nine immunity genes was confirmed as more effective for individual risk stratification and survival outcome prediction in NBL patients than common clinical characteristics (area under the curve [AUC] = 0.819, C-index = 0.718, p < .001). A mechanistic exploration revealed the regulatory network of molecules involved in the NBL-immune interaction. These immune molecules were also discovered to possess a significant correlation with plasma cell infiltration, MYCN status, and the level of chemokines and macrophage-related molecules (p < .001). A nomogram was constructed based on the immune signature and clinical characteristics, which showed high potential for prognosis prediction (AUC = 0.856, C-index = 0.755, p < .001). We systematically elucidated the complex regulatory mechanisms and characteristics of the molecules involved in the NBL-immune interaction and their prognostic potential, which may have important implications for further understanding the molecular mechanism of the NBL-immune interaction and identifying high-risk NBL patients to guide clinical treatment.

Prognostic and Treatment Guiding Significance of MRI-Based Tumor Burden Features and Nodal Necrosis in Nasopharyngeal Carcinoma.

We aimed to develop a nomogram integrating MRI-based tumor burden features (MTBF), nodal necrosis, and some clinical factors to forecast the distant metastasis-free survival (DMFS) of patients suffering from non-metastatic nasopharyngeal carcinoma (NPC). A total of 1640 patients treated at Sun Yat-sen University Cancer Center (Guangzhou, China) from 2011 to 2016 were enrolled, among which 1148 and 492 patients were randomized to a training cohort and an internal validation cohort, respectively. Additionally, 200 and 257 patients were enrolled in the Foshan and Dongguan validation cohorts, respectively, which served as independent external validation cohorts. The MTBF were developed from the stepwise regression of six multidimensional tumor burden variables, based on which we developed a nomogram also integrating nodal necrosis and clinical features. This model divided the patients into high- and low-risk groups by an optimal cutoff. Compared with those of patients in the low-risk group, the DMFS [hazard ratio (HR): 4.76, 95% confidence interval (CI): 3.39-6.69; p < 0.0001], and progression-free survival (PFS; HR: 4.11, 95% CI: 3.13-5.39; p < 0.0001) of patients in the high-risk group were relatively poor. Furthermore, in the training cohort, the 3-year DMFS of high-risk patients who received induction chemotherapy (ICT) combined with concurrent chemoradiotherapy (CCRT) was better than that of those who were treated with CCRT alone (p = 0.0340), whereas low-risk patients who received ICT + CCRT had a similar DMFS to those who only received CCRT. The outcomes we obtained were all verified in the three validation cohorts. The survival model can be used as a reliable prognostic tool for NPC patients and is helpful to determine patients who will benefit from ICT.