CroMAM: A Cross-Magnification Attention Feature Fusion Model for Predicting Genetic Status and Survival of Gliomas using Histological Images.

Predicting the gene mutation status in whole slide images (WSI) is crucial for the clinical treatment, cancer management, and research of gliomas. With advancements in CNN and Transformer algorithms, several promising models have been proposed. However, existing studies have paid little attention on fusing multi-magnification information, and the model requires processing all patches from a whole slide image. In this paper, we propose a cross-magnification attention model called CroMAM for predicting the genetic status and survival of gliomas. The CroMAM first utilizes a systematic patch extraction module to sample a subset of representative patches for downstream analysis. Next, the CroMAM applies Swin Transformer to extract local and global features from patches at different magnifications, followed by acquiring high-level features and dependencies among single-magnification patches through the application of a Vision Transformer. Subsequently, the CroMAM exchanges the integrated feature representations of different magnifications and encourage the integrated feature representations to learn the discriminative information from other magnification. Additionally, we design a cross-magnification attention analysis method to examine the effect of cross-magnification attention quantitatively and qualitatively which increases the model's explainability. To validate the performance of the model, we compare the proposed model with other multi-magnification feature fusion models on three tasks in two datasets. Extensive experiments demonstrate that the proposed model achieves state-of-the-art performance in predicting the genetic status and survival of gliomas. The implementation of the CroMAM will be publicly available upon the acceptance of this manuscript at https://github.com/GuoJisen/CroMAM.

Differentiation of Hepatocellular Carcinoma from Intrahepatic Cholangiocarcinoma through MRI Radiomics.

The purpose of this study was to investigate the efficacy of magnetic resonance imaging (MRI) radiomics in differentiating hepatocellular carcinoma (HCC) from intrahepatic cholangiocarcinoma (ICC). The clinical and MRI data of 129 pathologically confirmed HCC patients and 48 ICC patients treated at the Affiliated Hospital of North Sichuan Medical College between April 2016 and December 2021 were retrospectively analyzed. The patients were randomly divided at a ratio of 7:3 into a training group of 124 patients (90 with HCC and 34 with ICC) and a validation group of 53 patients (39 with HCC and 14 with ICC). Radiomic features were extracted from axial fat suppression T2-weighted imaging (FS-T2WI) and axial arterial-phase (AP) and portal-venous-phase (PVP) dynamic-contrast-enhanced MRI (DCE-MRI) sequences, and the corresponding datasets were generated. The least absolute shrinkage and selection operator (LASSO) method was used to select the best radiomic features. Logistic regression was used to establish radiomic models for each sequence (FS-T2WI, AP and PVP models), a clinical model for optimal clinical variables (C model) and a joint radiomics model (JR model) integrating the radiomics features of all the sequences as well as a radiomics-clinical model combining optimal radiomic features and clinical risk factors (RC model). The performance of each model was evaluated using the area under the receiver operating characteristic curve (AUC). The AUCs of the FS-T2WI, AP, PVP, JR, C and RC models for distinguishing HCC from ICC were 0.693, 0.863, 0.818, 0.914, 0.936 and 0.977 in the training group and 0.690, 0.784, 0.727, 0.802, 0.860 and 0.877 in the validation group, respectively. The results of this study suggest that MRI-based radiomics may help noninvasively differentiate HCC from ICC. The model integrating the radiomics features and clinical risk factors showed a further improvement in performance.

DCE-MRI-based radiomics in predicting angiopoietin-2 expression in hepatocellular carcinoma.

BACKGROUND: Hepatocellular carcinoma (HCC) is the sixth most common cancer, and the third leading cause of cancer death worldwide. Studies have shown that increased angiopoietin-2 (Ang-2) expression relative to Ang-1 expression in tumors is associated with a poor prognosis.The purpose of this study was to investigate the efficacy of predicting Ang-2 expression in HCC by preoperative dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI)-based radiomics. METHODS: The data of 52 patients with HCC who underwent surgical resection in our hospital were retrospectively analyzed. Ang-2 expression in HCC was analyzed by immunohistochemistry. All patients underwent preoperative upper abdominal DCE-MRI and intravoxel incoherent motion diffusion-weighted imaging scans. Radiomics features were extracted from the early and late arterial and portal phases of axial DCE-MRI. Univariate analysis and least absolute shrinkage and selection operator (LASSO) was performed to select the optimal radiomics features for analysis. A logistic regression analysis was performed to establish a DCE-MRI radiomics model, clinic-radiologic (CR) model and combined model integrating the radiomics score with CR factors. The stability of each model was verified by 10-fold cross-validation. Receiver operating characteristic (ROC) curve analysis, calibration curve analysis and decision curve analysis (DCA) were employed to evaluate these models. RESULTS: Among the 52 HCC patients, high Ang-2 expression was found in 30, and low Ang-2 expression was found in 22. The areas under the ROC curve (AUCs) for the radiomics model, CR model and combined model for predicting Ang-2 expression were 0.800, 0.874, and 0.933, respectively. The DeLong test showed that there was no significant difference in the AUC between the radiomics model and the CR model (p > 0.05) but that the AUC for the combined model was significantly greater than those for the other 2 models (p < 0.05). The DCA results showed that the combined model outperformed the other 2 models and had the highest net benefit. CONCLUSION: The DCE-MRI-based radiomics model has the potential to predict Ang-2 expression in HCC patients; the combined model integrating the radiomics score with CR factors can further improve the prediction performance.

Radiomics models based on multisequence MRI for predicting PD-1/PD-L1 expression in hepatocellular carcinoma.

The purpose of this study was to explore the effectiveness of radiomics based on multisequence MRI in predicting the expression of PD-1/PD-L1 in hepatocellular carcinoma (HCC). One hundred and eight patients with HCC who underwent contrast-enhanced MRI 2 weeks before surgical resection were enrolled in this retrospective study. Corresponding paraffin sections were collected for immunohistochemistry to detect the expression of PD-1 and PD-L1. All patients were randomly divided into a training cohort and a validation cohort at a ratio of 7:3. Univariate and multivariate analyses were used to select potential clinical characteristics related to PD-1 and PD-L1 expression. Radiomics features were extracted from the axial fat-suppression T2-weighted imaging (FS-T2WI) images and the arterial phase and portal venous phase images from the axial dynamic contrast-enhanced MRI, and the corresponding feature sets were generated. The least absolute shrinkage and selection operator (LASSO) was used to select the optimal radiomics features for analysis. Logistic regression analysis was performed to construct single-sequence and multisequence radiomics and radiomic-clinical models. The predictive performance was judged by the area under the receiver operating characteristic curve (AUC) in the training and validation cohorts. In the whole cohort, PD-1 expression was positive in 43 patients, and PD-L1 expression was positive in 34 patients. The presence of satellite nodules served as an independent predictor of PD-L1 expression. The AUC values of the FS-T2WI, arterial phase, portal venous phase and multisequence models in predicting the expression of PD-1 were 0.696, 0.843, 0.863, and 0.946 in the training group and 0.669, 0.792, 0.800 and 0.815 in the validation group, respectively. The AUC values of the FS-T2WI, arterial phase, portal venous phase, multisequence and radiomic-clinical models in predicting PD-L1 expression were 0.731, 0.800, 0.800, 0.831 and 0.898 in the training group and 0.621, 0.743, 0.771, 0.810 and 0.779 in the validation group, respectively. The combined models showed better predictive performance. The results of this study suggest that a radiomics model based on multisequence MRI has the potential to predict the preoperative expression of PD-1 and PD-L1 in HCC, which could become an imaging biomarker for immune checkpoint inhibitor (ICI)-based treatment.

A correlative study between IVIM-DWI parameters and VEGF and MMPs expression in hepatocellular carcinoma.

Background: Hepatocellular carcinoma (HCC) is the fourth most common cause of cancer-related death worldwide. Angiogenic factors may be valuable indices of tumor recurrence and treatment and potentially useful markers for predicting the response to antiangiogenesis therapy. Vascular endothelial growth factor (VEGF) and matrix metalloproteinases (MMPs) are major drivers of tumor angiogenesis. Preoperatively predicting the expression of VEGF and MMPs is crucial for treating HCC. Intravoxel incoherent motion (IVIM) diffusion-weighted imaging (DWI) has been successfully used in the differential diagnosis of HCC, pathological grading, and treatment response evaluation. However, the correlations between IVIM-DWI parameters and VEGF and MMP expression have not been reported. This study provides a preliminary analysis of the correlation between IVIM-DWI parameters and the expression of VEGF, MMP-2, and MMP-9 to investigate the value of IVIM-DWI in the noninvasive evaluation of angiogenesis in HCC. Methods: IVIM-DWI was performed in 61 patients with HCC 1 week before they underwent surgical resection. VEGF, MMP-2, and MMP-9 expression was detected using immunohistochemistry staining. Spearman correlation analysis was used to analyze the correlations between the IVIM-DWI parameters and VEGF, MMP-2, and MMP-9 expression in HCC. Results: The fast apparent diffusion coefficient fraction (f) value was positively correlated with the expression of VEGF (P<0.001), MMP-2 (P=0.002), and MMP-9 (P<0.001). The fast apparent diffusion coefficient (D*) was positively correlated with VEGF (P<0.001) and MMP-9 (P<0.001) expression but was not correlated with MMP-2 (P=0.659) expression. The apparent diffusion coefficient (ADC) and slow apparent diffusion coefficient (D) values were not significantly correlated with the expression of VEGF (P=0.103 and P=0.543, respectively), MMP-2 (P=0.596 and P=0.338, respectively), or MMP-9 (P=0.102 and P=0.660, respectively). Conclusions: IVIM-DWI can be used to noninvasively evaluate angiogenesis in HCC.

Radiomic Analysis Based on Magnetic Resonance Imaging for Predicting PD-L2 Expression in Hepatocellular Carcinoma.

Hepatocellular carcinoma (HCC) is the sixth most common malignant tumour and the third leading cause of cancer death in the world. The emerging field of radiomics involves extracting many clinical image features that cannot be recognized by the human eye to provide information for precise treatment decision making. Radiomics has shown its importance in HCC identification, histological grading, microvascular invasion (MVI) status, treatment response, and prognosis, but there is no report on the preoperative prediction of programmed death ligand-2 (PD-L2) expression in HCC. The purpose of this study was to investigate the value of MRI radiomic features for the non-invasive prediction of immunotherapy target PD-L2 expression in hepatocellular carcinoma (HCC). A total of 108 patients with HCC confirmed by pathology were retrospectively analysed. Immunohistochemical analysis was used to evaluate the expression level of PD-L2. 3D-Slicer software was used to manually delineate volumes of interest (VOIs) and extract radiomic features on preoperative T2-weighted, arterial-phase, and portal venous-phase MR images. Least absolute shrinkage and selection operator (LASSO) was performed to find the best radiomic features. Multivariable logistic regression models were constructed and validated using fivefold cross-validation. The area under the receiver characteristic curve (AUC) was used to evaluate the predictive performance of each model. The results show that among the 108 cases of HCC, 50 cases had high PD-L2 expression, and 58 cases had low PD-L2 expression. Radiomic features correlated with PD-L2 expression. The T2-weighted, arterial-phase, and portal venous-phase and combined MRI radiomics models showed AUCs of 0.789 (95% CI: 0.702-0.875), 0.727 (95% CI: 0.632-0.823), 0.770 (95% CI: 0.682-0.875), and 0.871 (95% CI: 0.803-0.939), respectively. The combined model showed the best performance. The results of this study suggest that prediction based on the radiomic characteristics of MRI could noninvasively predict the expression of PD-L2 in HCC before surgery and provide a reference for the selection of immune checkpoint blockade therapy.

Cervical aortic arch with aneurysm formation and an anomalous right subclavian artery and left vertebral artery: A case report.

BACKGROUND: A cervical aortic arch (CAA) refers to a high-riding aortic arch (AA) that often extends above the level of the clavicle. This condition is very rare, with an incidence of less than 1/10000. CASE SUMMARY: A 29-year-old woman was admitted to the otolaryngology department of our hospital for repeated bilateral purulent nasal discharge for the prior 3 mo. The patient was diagnosed with chronic sinusitis and chronic rhinitis at admission. A preoperative noncontrast chest computed tomography scan showed a high-riding, tortuous AA extending to the mid-upper level of the first thoracic vertebra with local cystic dilatation. A further computed tomography angiography examination showed that the brachiocephalic trunk, left common carotid artery, left vertebral artery (LVA) (slender), and left subclavian artery sequentially branched off of the aorta from the proximal end to the distal end of the AA. The proximal end of the right subclavian artery (RSCA) was tortuous and dilated. The AA showed tumor-like local expansion, with a maximum diameter of approximately 4 cm. After consultation with the department of cardiac macrovascular surgery, the patient was diagnosed with left CAA with aneurysm formation and an anomalous RSCA and LVA and was transferred to that department. The patient underwent AA aneurysm resection and artificial blood vessel replacement under general anesthesia and cardiopulmonary bypass. No abnormality was found during the 2-mo follow-up after discharge. CONCLUSION: A CAA is a rare congenital anomaly of vascular development. The present unique case of CAA with aneurysm formation and an anomalous RSCA and LVA enriches existing CAA data.

Hidden Markov Modeling Reveals Prolonged "Baseline" State and Shortened Antagonistic State across the Adult Lifespan.

The brain networks undergo functional reorganization across the whole lifespan, but the dynamic patterns behind the reorganization remain largely unclear. This study models the dynamics of spontaneous activity of large-scale networks using hidden Markov model (HMM), and investigates how it changes with age on two adult lifespan datasets of 176/157 subjects (aged 20-80 years). Results for both datasets showed that 1) older adults tended to spend less time on a state where default mode network (DMN) and attentional networks show antagonistic activity, 2) older adults spent more time on a "baseline" state with moderate-level activation of all networks, accompanied with lower transition probabilities from this state to the others and higher transition probabilities from the others to this state, and 3) HMM exhibited higher sensitivity in uncovering the age effects compared with temporal clustering method. Our results suggest that the aging brain is characterized by the shortening of the antagonistic instances between DMN and attention systems, as well as the prolongation of the inactive period of all networks, which might reflect the shift of the dynamical working point near criticality in older adults.

Progress of MRI Radiomics in Hepatocellular Carcinoma.

BACKGROUND: Hepatocellular carcinoma (HCC) is the sixth most common cancer in the world and the third leading cause of cancer-related death. Although the diagnostic scheme of HCC is currently undergoing refinement, the prognosis of HCC is still not satisfactory. In addition to certain factors, such as tumor size and number and vascular invasion displayed on traditional imaging, some histopathological features and gene expression parameters are also important for the prognosis of HCC patients. However, most parameters are based on postoperative pathological examinations, which cannot help with preoperative decision-making. As a new field, radiomics extracts high-throughput imaging data from different types of images to build models and predict clinical outcomes noninvasively before surgery, rendering it a powerful aid for making personalized treatment decisions preoperatively. OBJECTIVE: This study reviewed the workflow of radiomics and the research progress on magnetic resonance imaging (MRI) radiomics in the diagnosis and treatment of HCC. METHODS: A literature review was conducted by searching PubMed for search of relevant peer-reviewed articles published from May 2017 to June 2021.The search keywords included HCC, MRI, radiomics, deep learning, artificial intelligence, machine learning, neural network, texture analysis, diagnosis, histopathology, microvascular invasion, surgical resection, radiofrequency, recurrence, relapse, transarterial chemoembolization, targeted therapy, immunotherapy, therapeutic response, and prognosis. RESULTS: Radiomics features on MRI can be used as biomarkers to determine the differential diagnosis, histological grade, microvascular invasion status, gene expression status, local and systemic therapeutic responses, and prognosis of HCC patients. CONCLUSION: Radiomics is a promising new imaging method. MRI radiomics has high application value in the diagnosis and treatment of HCC.

A study of the correlations between IVIM-DWI parameters and the histologic differentiation of hepatocellular carcinoma.

The present study aimed to investigate the value of intravoxel incoherent motion diffusion weighted imaging (IVIM-DWI) in the preoperative prediction of the histologic differentiation of hepatocellular carcinoma (HCC). Seventy HCC patients were scanned with a 3.0 T magnetic resonance scanner. The values of apparent diffusion coefficient (ADC), slow apparent diffusion coefficient (D), fast apparent diffusion coefficient (D*), and the fraction of the fast apparent diffusion coefficient (f) were measured. Analysis of variance was used to compare the differences in parameters between groups with different degrees of histologic differentiation. p < 0.05 was considered statistically significant. Receiver operating characteristic (ROC) curves were used to analyse the efficacy of IVIM-DWI parameters for predicting the histologic differentiation of HCC. The ADC and D values for well, moderately and poorly differentiated HCC were 1.35 ± 0.17 × 10-3 mm2/s, 1.16 ± 0.17 × 10-3 mm2/s, 0.98 ± 0.21 × 10-3 mm2/s, and 1.06 ± 0.15 × 10-3 mm2/s, 0.88 ± 0.16 × 10-3 mm2/s, 0.76 ± 0.18 × 10-3 mm2/s, respectively, and all differences were significant. The D* and f values of the three groups were 32.87 ± 14.70 × 10-3 mm2/s, 41.68 ± 17.90 × 10-3 mm2/s, 34.54 ± 18.60 × 10-3 mm2/s and 0.22 ± 0.07, 0.23 ± 0.08, 0.18 ± 0.07, respectively, with no significant difference. When the cut-off values of ADC and D were 1.25 × 10-3 mm2/s and 0.97 × 10-3 mm2/s, respectively, their diagnostic sensitivities and specificities for distinguishing well differentiated HCC from moderately differentiated and poorly differentiated HCC were 73.3%, 85.5%, 86.7%, and 78.2%, and their areas under the ROC curve were 0.821 and 0.841, respectively. ADC and D values can be used preoperatively to predict the degree of histologic differentiation in HCC, and the D value has better diagnostic value.

Application of Diffusion Weighted Imaging in Prostate Cancer Bone Metastasis: Detection and Therapy Evaluation.

BACKGROUND: Bone metastasis is one of the most common complications of Prostate Cancer (PCa). The detection of distal bone metastasis at the time of initial PCa diagnosis is valuable for the determination of therapeutic methods and for the prognosis of PCa. Many current therapeutic methods target PCa bone metastasis, but no uniform evaluation standard for therapeutic efficacy has been established; in addition, traditional therapeutic evaluation standards that rely on changes in the measured tumor volume are quite controversial. In clinical practice, the volumes of some tumors often change nonsignificantly at the early stage of therapy (especially targeted therapy), while the volumes of other tumors, such as metastatic bone lesions, are difficult to measure. Diffusion-Weighted Imaging (DWI) not only reflects the diffusion characteristics of tissues but can also allow the analysis of microstructural and functional changes in tissues. Therefore, DWI is suitable for evaluations of early responses to tumor therapy. OBJECTIVE: This study mainly reviews the principle of DWI and its progress in the detection and therapy evaluation of PCa bone metastasis. METHODS: PubMed was searched to identify eligible articles up to December 26, 2020. The keywords of the analysis included DWI, PCa, bone metastasis, therapeutic response, targeted therapy, Bone Scintigraphy (BS), Positron Emission Tomography/Computed Tomography (PET/CT) and metastatic Castration-Resistant Prostate Cancer (mCRPC). RESULTS: This review based on collected articles achieved an imaging biomarker for detection and therapy evaluation of PCa bone metastasis. CONCLUSION: DWI is a promising imaging method for the detection and therapeutic evaluation of PCa bone metastases.

The Application of rs-fMRI in Vascular Cognitive Impairment.

The incidence of vascular cognitive impairment (VCI) has been increasing for years and has become a major disabling factor in middle-aged and elderly populations. The pathogenesis of VCI is unclear, and there are no standard diagnostic criteria. Resting-state functional magnetic resonance imaging (rs-fMRI) can be used to detect spontaneous brain functional activity in a resting state, which facilitates in-depth investigation of the pathogenesis of VCI and provides an objective reference for early diagnosis, differential diagnosis, and prognostic evaluation. This article mainly reviews the principle and analysis of rs-fMRI data, as well as the progress of its application for VCI diagnosis.

Progress of intravoxel incoherent motion diffusion-weighted imaging in liver diseases.

Traditional magnetic resonance (MR) diffusion-weighted imaging (DWI) uses a single exponential model to obtain the apparent diffusion coefficient to quantitatively reflect the diffusion motion of water molecules in living tissues, but it is affected by blood perfusion. Intravoxel incoherent motion (IVIM)-DWI utilizes a double-exponential model to obtain information on pure water molecule diffusion and microcirculatory perfusion-related diffusion, which compensates for the insufficiency of traditional DWI. In recent years, research on the application of IVIM-DWI in the diagnosis and treatment of hepatic diseases has gradually increased and has achieved considerable progress. This study mainly reviews the basic principles of IVIM-DWI and related research progress in the diagnosis and treatment of hepatic diseases.

Intravoxel incoherent motion diffusion-weighted imaging to differentiate hepatocellular carcinoma from intrahepatic cholangiocarcinoma.

The present study aimed to explore the value of intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) in differentiating hepatocellular carcinoma (HCC) from intrahepatic cholangiocarcinoma (ICC). This study included 65 patients with malignant hepatic nodules (55 with HCC, 10 with ICC), and 17 control patients with normal livers. All patients underwent IVIM-DWI scans on a 3.0 T magnetic resonance imaging (MRI) scanner. The standard apparent diffusion coefficient (ADC), pure diffusion coefficient (Dslow), pseudo-diffusion coefficient (Dfast), and perfusion fraction (f) were obtained. Differences in the parameters among the groups were analysed using one-way ANOVA, with p < 0.05 indicating statistical significance. Receiver operating characteristic (ROC) curve analysis was used to compare the efficacy of each parameter in differentiating HCC from ICC. ADC, Dslow, Dfast, f significantly differed among the three groups. ADC and Dslow were significantly lower in the HCC group than in the ICC group, while Dfast was significantly higher in the HCC group than in the ICC group; f did not significantly differ between the HCC and ICC groups. When the cut-off values of ADC, Dslow, and Dfast were 1.27 × 10-3 mm2/s, 0.81 × 10-3 mm2/s, and 26.04 × 10-3 mm2/s, respectively, their diagnostic sensitivities for differentiating HCC from ICC were 98.18%, 58.18%, and 94.55%, their diagnostic specificities were 50.00%, 80.00%, and 80.00%, and their areas under the ROC curve (AUCs) were 0.687, 0.721, and 0.896, respectively. Dfast displayed the largest AUC value. IVIM-DWI can be used to differentiate HCC from ICC.