R-MFE-TCN: A correlation prediction model between body surface and tumor during respiratory movement.

BACKGROUND: 2D CT image-guided radiofrequency ablation (RFA) is an exciting minimally invasive treatment that can destroy liver tumors without removing them. However, CT images can only provide limited static information, and the tumor will move with the patient's respiratory movement. Therefore, how to accurately locate tumors under free conditions is an urgent problem to be solved at present. PURPOSE: The purpose of this study is to propose a respiratory correlation prediction model for mixed reality surgical assistance system, Riemannian and Multivariate Feature Enhanced Temporal Convolutional Network (R-MFE-TCN), and to achieve accurate respiratory correlation prediction. METHODS: The model adopts a respiration-oriented Riemannian information enhancement strategy to expand the diversity of the dataset. A new Multivariate Feature Enhancement module (MFE) is proposed to retain respiratory data information, so that the network can fully explore the correlation of internal and external data information, the dual-channel is used to retain multivariate respiratory feature, and the Multi-headed Self-attention obtains respiratory peak-to-valley value periodic information. This information significantly improves the prediction performance of the network. At the same time, the PSO algorithm is used for hyperparameter optimization. In the experiment, a total of seven patients' internal and external respiratory motion trajectories were obtained from the dataset, and the first six patients were selected as the training set. The respiratory signal collection frequency was 21 Hz. RESULTS: A large number of experiments on the dataset prove the good performance of this method, which improves the prediction accuracy while also having strong robustness. This method can reduce the delay deviation under long window prediction and achieve good performance. In the case of 400 ms, the average RMSE and MAE are 0.0453  and 0.0361 mm, respectively, which is better than other research methods. CONCLUSION: The R-MFE-TCN can be extended to respiratory correlation prediction in different clinical situations, meeting the accuracy requirements for respiratory delay prediction in surgical assistance.

Differentiating HCC from ICC and prediction of ICC grade based on MRI deep-radiomics: Using lesions and their extended regions.

PURPOSE: This study aimed to evaluate the ability of MRI-based intratumoral and peritumoral radiomics features of liver tumors to differentiate between hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (ICC) and to predict ICC differentiation. METHODS: This study retrospectively collected 87 HCC patients and 75 ICC patients who were confirmed pathologically. The standard region of interest (ROI) of the lesion drawn by the radiologist manually shrank inward and expanded outward to form multiple ROI extended regions. A three-step feature selection method was used to select important radiomics features and convolution features from extended regions. The predictive performance of several machine learning classifiers on dominant feature sets was compared. The extended region performance was assessed by area under the curve (AUC), specificity, sensitivity, F1-score and accuracy. RESULTS: The performance of the model is further improved by incorporating convolution features. Compared with the standard ROI, the extended region obtained better prediction performance, among which 6 mm extended region had the best prediction ability (Classification: AUC = 0.96, F1-score = 0.94, Accuracy: 0.94; Grading: AUC = 0.94, F1-score = 0.93, Accuracy = 0.89). CONCLUSION: Larger extended region and fusion features can improve tumor predictive performance and have potential value in tumor radiology.

A radiomics model fusing clinical features to predict microsatellite status preoperatively in colorectal cancer liver metastasis.

PURPOSE: To study the combined model of radiomic features and clinical features based on enhanced CT images for noninvasive evaluation of microsatellite instability (MSI) status in colorectal liver metastasis (CRLM) before surgery. METHODS: The study included 104 patients retrospectively and collected CT images of patients. We adjusted the region of interest to increase the number of MSI-H images. Radiomic features were extracted from these CT images. The logistic models of simple clinical features, simple radiomic features, and radiomic features with clinical features were constructed from the original image data and the expanded data, respectively. The six models were evaluated in the validation set. A nomogram was made to conveniently show the probability of the patient having a high MSI (MSI-H). RESULTS: The model including radiomic features and clinical features in the expanded data worked best in the validation group. CONCLUSION: A logistic regression prediction model based on enhanced CT images combining clinical features and radiomic features after increasing the number of MSI-H images can effectively identify patients with CRLM with MSI-H and low-frequency microsatellite instability (MSI-L), and provide effective guidance for clinical immunotherapy of CRLM patients with unknown MSI status.

Platelet factor 4 (PF4) induces cluster of differentiation 40 (CD40) expression in human aortic endothelial cells (HAECs) through the SIRT1/NF-κB/p65 signaling pathway.

PF4 is a pro-atherosclerotic molecule. Endothelial CD40, upon binding to its ligand CD40L, induces endothelial cell (EC) activation, which is a vital pathophysiological process in the initiation and progression of atherosclerosis. However, the relationship between PF4 and endothelial CD40 remains elusive. This study aims to investigate whether and how PF4 affects endothelial CD40 expression using primary HAECs. PF4 treatment down-regulated sirtuin 1 (SIRT1) expression but upregulated the expression of acetylated NF-κB p65 (Ac-p65) and CD40 in HAECs in a concentration- and time-dependent manner. Pretreatment with SIRT1 agonist (SRT1720 or RSV) or SIRT1-overexpressing lentivirus attenuated PF4-induced Ac-p65 and CD40 expression in HAECs, whereas preincubation with SIRT1 antagonist (NAM or EX527) or SIRT1 shRNA had the opposite effect. To investigate whether NF-κB/p65 signaling pathway modulates CD40 expression in PF4-treated HAECs, PDTC, a NF-κB inhibitor, and p65-shRNA were introduced. PDTC or p65-shRNA treatment down-regulated Ac-p65 expression in HAECs. PDTC or p65-shRNA preincubation suppressed CD40 expression in HAECs after PF4 treatment. To better determine whether SIRT1 regulates CD40 expression in PF4-treated HAECs via the NF-κB/p65 signaling pathway, p65-knockdown HAECs were preincubated with SIRT1 agonists before PF4 treatment. SIRT1 agonist preincubation further decreased CD40 expression in p65-knockdown HAECs treated with PF4. Moreover, PF4 treatment promoted p65 nuclear translocation in HAECs. The results of dual luciferase assay demonstrated that four NF-κB binding sites in the promoter of human CD40 gene were activated in PF4-treated HAECs. In conclusion, our findings suggest that PF4 treatment facilitates CD40 expression in HAECs through the SIRT1/NF-κB/p65 pathway.

Effectiveness of iliac vein stenting combined with endovenous laser treatment of recurrent varicose veins associated with iliac vein compression.

Background: Iliac vein compression syndrome (IVCS) is an underlying cause of varicose vein (VV) recurrence after venous surgery. However, the management of recurrent varicose veins (RVVs) combined with IVCS has rarely been reported. This study aimed to investigate the outcomes of a one-stop procedure to correct outflow obstruction and superficial reflux for patients with RVVs and IVCS. Methods: A retrospective analysis was conducted of 102 consecutive patients diagnosed with RVVs. Computed tomography venography (CTV) was performed to confirm IVCS. The cases were divided into 2 groups: the IRVVs group, including patients with RVVs and IVCS (n=48), and the RVVs group, including patients with RVVs only (n=54). The characteristics, vein reflux, and clinical, etiological, anatomical, and pathophysiological (CEAP) distribution were investigated. Then, the IRVVs group patients who underwent endovenous laser ablation (EVLA) (n=39) were divided into a further 2 groups: the EVLA + S group (n=19), who received EVLA and stenting of iliac vein, and the EVLA group (n=20), who received EVLA treatment alone. The great/small saphenous vein (GSV/SSV) trunk occlusion, VV recurrence, visual analogue scale (VAS), and venous clinical severity score (VCSS) were investigated. Results: The prevalence rate of femoral vein reflux was 81.2% in IRVVs group and 50% in RVVs group (P<0.05). In the IRVVs group, 72.9% of patients manifested as CEAP clinical class >3, which was higher than that in RVVs group (48.1%) (P<0.05). The 12-month GSV/SSV occlusion rate in the EVLA + S and EVLA groups were 94.7% and 90.0%, respectively. Totals of 9 patients in EVLA + S group and 6 patients in EVLA group had active venous ulcers, and the ulcer healing time in EVLA + S group was significantly shorter (27.22±7.12 vs. 46.67±9.83 days, P<0.05). The reductions in the VAS and VCSS values between baseline, 1 month, and 12 months in the EVLA + S group were more obvious than those in EVLA group (P<0.05). Conclusions: The one-stop combination treatment of iliac venous stenting and EVLA in patients with RVVs and IVCS is safe and effective and provides prominent symptom relief, improved quality of life, and a more satisfactory ulcer healing than EVLA alone.

Impact of titanium-coated polypropylene mesh on functional outcome and quality of life after inguinal hernia repair.

Objective: This study aims to compare the clinical outcomes of complications, quality of life, and chronic pain between titanium-coated polypropylene mesh and polypropylene mesh after Lichtenstein or TAPP surgery. Methods: A retrospective cohort study was conducted, involving patients who underwent inguinal hernia repair using Timesh light®, Optilene LP®, or 3DMax™ meshes between January 2020 and May 2022. Based on the surgical method, patients were divided into Lichtenstein and TAPP groups, and further categorized according to the type of mesh used. The primary endpoints assessed postoperative complications, postoperative pain, and postoperative quality of life. Secondary endpoints included postoperative sensation in the surgical area and postoperative recurrence rate. Results: A total of 180 Lichtenstein procedures and 478 TAPP procedures were included in the analysis after propensity score matching. The findings revealed that patients with titanium-coated polypropylene mesh did not exhibit significant advantages in perioperative data. Within three months to one year after TAPP surgery, patients with the titanium-coated polypropylene mesh reported improved foreign body sensation during activities (P = 0.002) and a lower incidence of chronic pain (P = 0.008). However, after one year, these advantages of titanium-coated polypropylene mesh were no longer significant during activity or at rest. In the TAPP group, the titanium-coated polypropylene mesh depicted advantages in the single score of the SF-36 questionnaire. Conclusions: The utilization of titanium-coated polypropylene mesh resulted in reduced foreign body sensation and chronic pain in activity within one year after TAPP surgery, significantly enhancing certain aspects of the patient's quality of life compared to polypropylene mesh.

Central Venous Catheter as a Novel Approach to Postoperative Thrombolysis in Patients with Acute Iliofemoral Deep Venous Thrombosis.

BACKGROUND AND AIMS: Percutaneous mechanical thrombectomy (PMT) along with postoperative thrombolysis (POT) has been the standard treatment for acute iliofemoral deep venous thrombosis (IFDVT). However, commonly used catheter directed thrombolysis (CDT) approaches for POT carry certain disadvantages, including the need for a sheath, inferior comfortability, and catheter-related complications. Therefore, we propose a new simplified method of POT using a central venous catheter (CVC). METHODS: The retrospective study analyzed patients with IFDVT who underwent POT using CVC from January 2020 to August 2021. The treatment modalities included filter placement, thrombus removal, iliac vein obstruction release, postoperative CVC thrombolysis, filter retrieval, and adequate full course anticoagulation. RESULTS: A total of 39 patients were included in this retrospective study. All patients underwent PMT surgery with a procedure success rate of 100%. In the post-PMT CVC thrombolysis, the puncture sites were located in the below-knee vein, including 58.97% in the peroneal vein. The mean duration of CVC-directed thrombolysis was 3.69 ± 1.08 days, and the total urokinase dose was 2.27 ± 0.71 MIU. A total of 37 patients (94.87%) had successful thrombolysis with a length of hospital stay of 5.82 ± 2.21 days. During CVC-directed thrombolysis, only four minor bleeding complications occurred, two of which were indwelling catheter-related. During the 12-month follow-up period, the patency rate and post-thrombotic syndrome incidences were 97.44% and 2.56%, respectively. CONCLUSION: Thrombolysis through a CVC is a feasible, safe, and effective POT method, and could be an alternative to the conventional CDT approach for patients with IFDVT.

Impact of plaque and luminal morphology in balloon angioplasty of the femoropopliteal artery: an intravascular ultrasound analysis.

Objective: To assess the effect of plaque and luminal morphologies in balloon angioplasty of femoropopliteal lesions using intravascular ultrasound (IVUS). Methods: This retrospective, observational study analyzed 836 cross-sectional images using IVUS, from 35 femoropopliteal arteries of patients who underwent endovascular treatment between September 2020 and February 2022. Pre- and post-balloon angioplasty images were matched per 5 mm. Post-balloon angioplasty images were grouped into successful (n = 345) and unsuccessful (n = 491) groups. Plaque and luminal morphologies (such as severity of calcification, vascular remodeling, and plaque eccentricity) were extracted before the balloon angioplasty procedure to identify the predictors of unsuccessful balloon angioplasty. Additionally, 103 images with severe dissection were analyzed using IVUS and angiography. Results: In univariate analyses, the predictive factors for unsuccessful balloon angioplasty were vascular remodeling (p < .001), plaque burden (p < .001), lumen eccentricity (p < .001), and balloon/vessel ratio (p = .01). Predictive factors for severe dissections were the guidewire route (p < .001) and balloon/vessel ratio (p = .04). In multivariate analysis, the predictive factors for unsuccessful balloon angioplasty included lumen eccentricity (odds ratio [OR]: 3.99, 95% confidence interval [CI]: 1.28-12.68, p = .02) and plaque burden (OR: 1.03, 95% CI: 1.02-1.04; p < .001). For severe dissections, the independent risk factor was an eccentric guidewire route (OR: 2.10, 95% CI: 1.22-3.65, p = .01). Conclusion: High plaque burden and luminal eccentricity were risk factors for failed femoropopliteal artery balloon angioplasty. Additionally, eccentric guidewire routes predicted severe dissection.

Comparison of angiography and ultrasound for femoropopliteal angioplasty: decision-making and 12-month outcomes.

BACKGROUND: This study aimed to investigate whether intravascular ultrasound (IVUS) combined with angiography during percutaneous transluminal angioplasty impacts treatment strategies and the 12-month patency of the femoropopliteal artery, compared to angiography alone. METHODS: This retrospective, single-center study enrolled 137 patients who underwent a femoropopliteal endovascular intervention between February 2020 and May 2021. Among these interventions, 43 were guided by IVUS combined with angiography and the remaining 94 were guided by angiography only. Treatment strategies and 12-month patency were analyzed in both groups. Multivariable analysis was performed to clarify the predictors of restenosis within 12 months. RESULTS: Primary patency at 12 months was significantly higher in the IVUS group than in the angiography group (56.4% vs. 76.7%, P=0.047). The reference diameter on IVUS images was greater than that on angiography images. Therefore, the IVUS group presented a higher balloon-to-vessel ratio [1.0 (0.97, 1.01) vs. 1.06 (1.0.1.25)]. More adjunctive stents were required in the angiography group. However, more dissections were performed in the IVUS group, with no difference in flow-limiting dissections between groups. Target disease length (odds ratio 1.02, P=0.021) and balloon-to-vessel ratio (odds ratio 0.01, P=0.021) were independent predictors of restenosis. CONCLUSIONS: Compared with angiography guidance alone, IVUS guidance for femoropopliteal artery-related treatment can significantly increase primary patency. This finding may be explained by the selection of larger balloons in IVUS and the resulting sufficient plaque compression and elastic membrane stretch. Moreover, IVUS was shown to detect more non-flow-limiting dissections than angiography.

Recognition of liver tumors by predicted hyperspectral features based on patient's computed tomography radiomics features.

BACKGROUND: Primary liver tumors can be a serious threat to life and health. Early diagnosis may be life saving. Therefore, enhancing the accuracy of non-invasive early detection of liver tumors is imperative. METHODS: Firstly, image enhancement was applied to augment the dataset, resulting in a total of 464 samples after employing seven data augmentation methods. Subsequently, the XGBoost model was utilized to construct and learn the mapping relationship between Computed Tomography (CT) and corresponding hyperspectral imaging (HSI) data. This model enables the prediction of HSI features corresponding to CT features, thereby enriching CT with more comprehensive hyperspectral information. RESULTS: Four classifiers were employed to discern the presence of tumors in patients. The results demonstrated exceptional performance, with a classification accuracy exceeding 90%. CONCLUSIONS: This study proposes an artificial intelligence-based methodology that utilizes early CT radiomics features to predict HSI features. Subsequently, the results are utilized for non-invasive tumor prediction and early screening, thereby enhancing the accuracy of non-invasive liver tumor detection.

Classification of metastatic hepatic carcinoma and hepatocellular carcinoma lesions using contrast-enhanced CT based on EI-CNNet.

BACKGROUND: For hepatocellular carcinoma and metastatic hepatic carcinoma, imaging is one of the main diagnostic methods. In clinical practice, diagnosis mainly relied on experienced imaging physicians, which was inefficient and cannot met the demand for rapid and accurate diagnosis. Therefore, how to efficiently and accurately classify the two types of liver cancer based on imaging is an urgent problem to be solved at present. PURPOSE: The purpose of this study was to use the deep learning classification model to help radiologists classify the single metastatic hepatic carcinoma and hepatocellular carcinoma based on the enhanced features of enhanced CT (Computer Tomography) portal phase images of the liver site. METHODS: In this retrospective study, 52 patients with metastatic hepatic carcinoma and 50 patients with hepatocellular carcinoma were among the patients who underwent preoperative enhanced CT examinations from 2017-2020. A total of 565 CT slices from these patients were used to train and validate the classification network (EI-CNNet, training/validation: 452/113). First, the EI block was used to extract edge information from CT slices to enrich fine-grained information and classify them. Then, ROC (Receiver Operating Characteristic) curve was used to evaluate the performance, accuracy, and recall of the EI-CNNet. Finally, the classification results of EI-CNNet were compared with popular classification models. RESULTS: By utilizing 80% data for model training and 20% data for model validation, the average accuracy of this experiment was 98.2% ± 0.62 (mean ± standard deviation (SD)), the recall rate was 97.23% ± 2.77, the precision rate was 98.02% ± 2.07, the network parameters were 11.83 MB, and the validation time was 9.83 s/sample. The classification accuracy was improved by 20.98% compared to the base CNN network and the validation time was 10.38 s/sample. Compared with other classification networks, the InceptionV3 network showed improved classification results, but the number of parameters was increased and the validation time was 33 s/sample, and the classification accuracy was improved by 6.51% using this method. CONCLUSION: EI-CNNet demonstrated promised diagnostic performance and has potential to reduce the workload of radiologists and may help distinguish whether the tumor is primary or metastatic in time; otherwise, it may be missed or misjudged.

Oscillatory shear stress promotes vein graft intimal hyperplasia via NADPH oxidase-related pathways.

Background: Uncontrolled intimal hyperplasia (IH) after autologous saphenous vein grafting triggers a high restenosis rate; however, its association with the activation of NADPH oxidase (NOX)-related pathways is unclear. Here, we investigated the effects and mechanism of oscillatory shear stress (OSS) on grafted vein IH. Methods: Thirty male New Zealand rabbits were randomly divided into control, high-OSS (HOSS), and low-OSS (LOSS) groups, and the vein grafts were harvested after 4 weeks. Hematoxylin and eosin staining and Masson staining assays were used to observe morphological and structural changes. Immunohistochemical staining was used to detect α-SMA, PCNA, MMP-2, and MMP-9 expression. Immunofluorescence staining was used to observe reactive oxygen species (ROS) production in the tissues. Western blotting was used to determine the expression levels of pathway-related proteins (NOX1, NOX2, AKT, p-AKT, and BIRC5), PCNA, BCL-2, BAX, and caspase-3/cleaved caspase-3 in tissues. Results: Blood flow velocity was lower in the LOSS group than in the HOSS group, while vessel diameter did not change significantly. Shear rate was elevated in both HOSS and LOSS groups but was higher in the HOSS group. Additionally, vessel diameter increased with time in the HOSS and LOSS groups, whereas flow velocity did not. Intimal hyperplasia was significantly lower in the LOSS group than in the HOSS group. IH was dominated by smooth muscle fibers in the grafted veins and collagen fibers in the media. OSS restriction significantly reduced the α-SMA, PCNA, MMP-2, and MMP-9 levels. Moreover, ROS production and the expression of NOX1, NOX2, p-AKT, BIRC5, PCNA, BCL-2, BAX, and cleaved caspase-3 were phase-reduced in LOSS compared to the levels in the HOSS group. Total AKT was not differentially expressed among the three groups. Conclusion: OSS promotes the proliferation, migration, and survival of subendothelial vascular smooth muscle cells in grafted veins, which may be related to the regulation of downstream p-AKT/BIRC5 levels through the increased production of ROS by NOX. Drugs inhibiting this pathway might be used to prolong vein graft survival time.

Hernia mesh infection treatment following the repair of abdominal wall hernias: A single-center experience.

Introduction: The mesh-based repair of abdominal wall hernias is a commonly employed approach as it is easy to implement and associated with low rates of hernia recurrence. However, the occurrence of hernia mesh infections following such repair can be extremely serious, and no clinical consensus regarding the optimal treatment of such infections has been established. This study was thus developed to review the management of hernia mesh infection cases treated at our center, summarizing the demographic and clinical characteristics of affected patients and summarizing our associated therapeutic experiences. Methods: Data pertaining to 64 cases of hernia mesh infections treated at our center were retrospectively reviewed. Data were obtained from patient medical records, including general situation, hernia type, prior hernia repair approaches, type of mesh, and postoperative condition. Other reviewed outcomes include bacteriological and imaging findings, as well as treatment outcomes. In cases where conservative management was not successful, the approach to mesh removal (laparoscopic vs. open) was made based on the primary surgical approach and the type of material used for the repair. Results: In total, 42 patients underwent primary open inguinal hernioplasty (including plug repair, preperitoneal mesh repair, and Lichtenstein repair), while 11 patients underwent laparoscopic repair (9 transabdominal preperitoneal, TAPP and 2 totally extraperitoneal,TEP), and 11 patients with incisional hernias underwent the intraperitoneal onlay mesh (IPOM) procedure. Six patients exhibited mesh erosion of the internal organs. Of these patients, 38 underwent mesh removal via open debridement, while 9 underwent laparoscopic exploration and open debridement, and 1 underwent laparoscopic mesh removal. No patients exhibited serious postoperative sequelae, serious complications, or mortality after the treatment of mesh infections.One patient experienced postoperative infection recurrence following partial mesh removal, with the appearance of a small fistula. Hernias recurred in 2 patients following mesh removal, and 1 patient underwent repair via laparoscopic IPOM. Conclusions: While conservative treatment can cure early mesh infections, there is nonetheless a risk that these infections will recur. In view of the variety of surgical intervention of abdominal wall hernias at present,treatment of mesh infection should be individualized. Our findings suggest that hernias repaired via the placement of mesh in the preperitoneal space can more readily contribute to internal organ erosion and late-onset infections, with open debridement often being unable to completely remove the mesh without causing collateral damage. Laparoscopic exploration is an effective and minimally invasive approach to detecting internal organ involvement and removing the infected hernia mesh from affected patients.

Correlation Analysis of Gene and Radiomic Features in Colorectal Cancer Liver Metastases.

Colorectal cancer liver metastasis (CRLM) was one of the cancers with high mortality. Clinically, the target point was determined by invasive detection, which increased the suffering of patients and the cost of treatment. If the target point was found through the relationship between early radiomic information and genetic information, it was expected to assist doctors in diagnosing disease, formulating treatment plans, and reducing the pain and burden of patients. In this study, gene coexpression analysis and hub gene mining were first performed on the gene data; secondly, quantitative radiomic features were extracted from CT-enhanced radiomic data to obtain features highly correlated with CRLM; and finally, we analyzed the relationship between gene features and radiomic feature correlations by establishing a link between early radiomic features and gene sequencing and finding highly correlated expressions. This experiment demonstrated that radiomic features could be used to mine gene attributes. Based on the four previously identified genes (NRAS, KRAS, BRAF, and PIK3CA), we identified two novel genes, MAPK1 and STAT1, highly associated with CRLM. There were specific correlations between these 6 genes and radiomic features (shape_elongation, glcm, glszm, firstorder_10percentile, gradient, exponent_firstorder_Range, and gradient_glszm_SmallAreaLowGrayLevel). Therefore, this paper established the correlation between radiomic features and genes, and through radiomic features, we could find the genes associated with them, which was expected to achieve noninvasive prediction of liver metastasis.

MRI-based radiomics distinguish different pathological types of hepatocellular carcinoma.

OBJECT: To distinguish combined hepatocellular cholangiocarcinoma (cHCC-CC), hepatocellular carcinoma (HCC) and cholangiocarcinoma (CC) before operation using MRI radiomics. METHOD: This study retrospectively analyzed 196 liver cancers: 33 cHCC-CC, 88 HCC and 75 CC. They had confirmed by pathological analysis in the Affiliated Hospital of Hebei University. MRI lesions were manually segmented by a radiologist.1316 features were extracted from MRI lesions by Pyradiomics. Useful features were retained through two-level feature selection to establish a classification model. Receiver operating characteristic (ROC), area under curve (AUC) and F1-score were used to evaluate the performance of the model. RESULTS: Compared with low-order image features, the performance of the model based on high-order features was improved by about 10%. The model showed better performance in identifying HCC tumors during the delay phase (AUC = 0.91, sensitivity = 0.88, specificity = 0.89, accuracy = 0.89, F1-Score = 0.88). CONCLUSION: The classification ability of cHCC-CC, HCC and CC can be further improved by extracting MRI high-order features and using a two-level feature selection method.

Gabor Dictionary of Sparse Image Patches Selected in Prior Boundaries for 3D Liver Segmentation in CT Images.

The gray contrast between the liver and other soft tissues is low, and the boundary is not obvious. As a result, it is still a challenging task to accurately segment the liver from CT images. In recent years, methods of machine learning have become a research hotspot in the field of medical image segmentation because they can effectively use the "gold standard" personalized features of the liver from different data. However, machine learning usually requires a large number of data samples to train the model and improve the accuracy of medical image segmentation. This paper proposed a method for liver segmentation based on the Gabor dictionary of sparse image blocks with prior boundaries. This method reduced the number of samples by selecting the test sample set within the initial boundary area of the liver. The Gabor feature was extracted and the query dictionary was created, and the sparse coefficient was calculated to obtain the boundary information of the liver. By optimizing the reconstruction error and filling holes, a smooth liver boundary was obtained. The proposed method was tested on the MICCAI 2007 dataset and ISBI2017 dataset, and five measures were used to evaluate the results. The proposed method was compared with methods for liver segmentation proposed in recent years. The experimental results show that this method can improve the accuracy of liver segmentation and effectively repair the discontinuity and local overlap of segmentation results.

Hyperspectral-attention mechanism-based improvement of radiomics prediction method for primary liver cancer.

OBJECTIVE: To improve the accuracy of the prediction of primary liver cancer by radiomics employing non invasive hyperspectral imaging technology. METHODS: This retrospective study was approved by the IRB committee of our institution, and the rule of informed consent was put forward. This paper analyzes the hyperspectral images (HSI) of patients with primary liver cancer and finds that the spectral reflectance curve of tumor and non-tumor locations are significantly different at different wavelengths. By using the ISODATA algorithm to predict tumor, it is found that the result is obvious. It is speculated that the use of HSI to select computed tomography (CT) images can improve the accuracy of radiomics in the prediction of primary liver cancer. Therefore, we employed HSI in combination with radiomic features to complete this task. We use the attention mechanism to concentrate computing resources into highly correlated features and use these features to predict tumor. RESULTS: Using the hyperspectral-attention mechanism feature selection method, we were able to achieve an AUC of 0.96. Our study shows that HSI and radiomic features could aid in the prediction of liver cancer.

The effect of stent compression on in-stent restenosis and clinical outcomes in iliac vein compression syndrome.

BACKGROUND: To evaluate the effect of stent compression on in-stent restenosis (ISR) and clinical outcomes in patients with iliac vein compression syndrome (IVCS) after iliac vein stenting. METHODS: Fifty patients with IVCS treated with iliac vein stenting (Smart Control, Cordis, USA) between March 2017 and October 2018 were consecutively enrolled in this study. Computed tomography venography (CTV) was performed to assess stent compression and ISR. Based on the degree of stent compression, patients were allocated to a significant stent compression (SSC) group and an insignificant stent compression (ISC) group. The incidence of ISR was analyzed between the SSC and ISC groups. Patients' venous clinical severity scores (VCSSs) and responses to the chronic venous insufficiency questionnaire (CIVIQ) one year after stenting were compared between the two groups to evaluate the clinical improvement of venous insufficiency. RESULTS: In total, 34% of patients had SSC. There were significant differences in the incidence of ISR (52.9% vs. 21.2%, P=0.023), and in each group, there was one case of stent occlusion (5.88% vs. 3.03%, P=0.999). Patients in the SSC group had a higher VCSS score (8.41±5.92 vs. 3.15±2.87, P=0.04) and a lower CIVIQ score (83.35±8.86 vs. 92.21±4.32, P=0.001). CONCLUSIONS: SSC has a significant effect on the incidence of ISR and the clinical outcomes of venous insufficiency. Thus, a dedicated iliac venous stent with sufficient radial resistive force, crush resistance, and outward radial force is needed to prevent the occurrence of stent compression.

Midterm outcome of pharmacomechanical catheter-directed thrombolysis combined with stenting for treatment of iliac vein compression syndrome with acute iliofemoral deep venous thrombosis.

OBJECTIVE: This study assessed the effectiveness and safety of percutaneous mechanical thrombectomy and catheter-directed thrombolysis combined with stent placement in the management of iliac vein compression syndrome with acute iliofemoral deep venous thrombosis (DVT). METHODS: From December 2014 to April 2016, there were 46 patients with DVT who underwent percutaneous mechanical thrombectomy and catheter-directed thrombolysis and stenting for acute proximal DVT with computed tomography-verified iliofemoral stenosis. The Venous Registry Index was used for evaluating the degree of patency after pharmacomechanical thrombolysis; the prevalence of post-thrombotic syndrome (PTS) in the follow-up was assessed according to the Villalta scale. For up to 24 months, conditions of the patients were assessed using periodic duplex ultrasound scans. RESULTS: For all patients, the technical success rate was 100%; no major bleeding or 30-day mortality was observed. Overall, the 6-, 12-, and 24-month primary patency rates were 97.8%, 95.7%, and 91.1%, respectively. There was a significant reduction in Venous Registry Index (9.82 ± 1.74 to 1.15 ± 1.02; P < .05) after the procedure. According to the Villalta score, only one patient developed mild PTS and none developed severe PTS. Symptomatic pulmonary embolism was not observed during the hospitalization. The mean hospital stay was 6.5 ± 1.7 days. CONCLUSIONS: This technique provides a safe and effective treatment option for patients with acute proximal DVT caused by vein compression syndrome.