Rethinking Multiple Instance Learning for Whole Slide Image Classification: A Bag-Level Classifier is a Good Instance-Level Teacher.

Multiple Instance Learning (MIL) has demonstrated promise in Whole Slide Image (WSI) classification. However, a major challenge persists due to the high computational cost associated with processing these gigapixel images. Existing methods generally adopt a two-stage approach, comprising a non-learnable feature embedding stage and a classifier training stage. Though it can greatly reduce memory consumption by using a fixed feature embedder pre-trained on other domains, such a scheme also results in a disparity between the two stages, leading to suboptimal classification accuracy. To address this issue, we propose that a bag-level classifier can be a good instance-level teacher. Based on this idea, we design Iteratively Coupled Multiple Instance Learning (ICMIL) to couple the embedder and the bag classifier at a low cost. ICMIL initially fixes the patch embedder to train the bag classifier, followed by fixing the bag classifier to fine-tune the patch embedder. The refined embedder can then generate better representations in return, leading to a more accurate classifier for the next iteration. To realize more flexible and more effective embedder fine-tuning, we also introduce a teacher-student framework to efficiently distill the category knowledge in the bag classifier to help the instance-level embedder fine-tuning. Intensive experiments were conducted on four distinct datasets to validate the effectiveness of ICMIL. The experimental results consistently demonstrated that our method significantly improves the performance of existing MIL backbones, achieving state-of-the-art results. The code and the organized datasets can be accessed by: https://github.com/Dootmaan/ICMIL/tree/confidence_based.

Transcranial volumetric imaging using a conformal ultrasound patch.

Accurate and continuous monitoring of cerebral blood flow is valuable for clinical neurocritical care and fundamental neurovascular research. Transcranial Doppler (TCD) ultrasonography is a widely used non-invasive method for evaluating cerebral blood flow1, but the conventional rigid design severely limits the measurement accuracy of the complex three-dimensional (3D) vascular networks and the practicality for prolonged recording2. Here we report a conformal ultrasound patch for hands-free volumetric imaging and continuous monitoring of cerebral blood flow. The 2 MHz ultrasound waves reduce the attenuation and phase aberration caused by the skull, and the copper mesh shielding layer provides conformal contact to the skin while improving the signal-to-noise ratio by 5 dB. Ultrafast ultrasound imaging based on diverging waves can accurately render the circle of Willis in 3D and minimize human errors during examinations. Focused ultrasound waves allow the recording of blood flow spectra at selected locations continuously. The high accuracy of the conformal ultrasound patch was confirmed in comparison with a conventional TCD probe on 36 participants, showing a mean difference and standard deviation of difference as -1.51 ± 4.34 cm s-1, -0.84 ± 3.06 cm s-1 and -0.50 ± 2.55 cm s-1 for peak systolic velocity, mean flow velocity, and end diastolic velocity, respectively. The measurement success rate was 70.6%, compared with 75.3% for a conventional TCD probe. Furthermore, we demonstrate continuous blood flow spectra during different interventions and identify cascades of intracranial B waves during drowsiness within 4 h of recording.

Segmentation Guided Crossing Dual Decoding Generative Adversarial Network for Synthesizing Contrast-Enhanced Computed Tomography Images.

Although contrast-enhanced computed tomography (CE-CT) images significantly improve the accuracy of diagnosing focal liver lesions (FLLs), the administration of contrast agents imposes a considerable physical burden on patients. The utilization of generative models to synthesize CE-CT images from non-contrasted CT images offers a promising solution. However, existing image synthesis models tend to overlook the importance of critical regions, inevitably reducing their effectiveness in downstream tasks. To overcome this challenge, we propose an innovative CE-CT image synthesis model called Segmentation Guided Crossing Dual Decoding Generative Adversarial Network (SGCDD-GAN). Specifically, the SGCDD-GAN involves a crossing dual decoding generator including an attention decoder and an improved transformation decoder. The attention decoder is designed to highlight some critical regions within the abdominal cavity, while the improved transformation decoder is responsible for synthesizing CE-CT images. These two decoders are interconnected using a crossing technique to enhance each other's capabilities. Furthermore, we employ a multi-task learning strategy to guide the generator to focus more on the lesion area. To evaluate the performance of proposed SGCDD-GAN, we test it on an in-house CE-CT dataset. In both CE-CT image synthesis tasks-namely, synthesizing ART images and synthesizing PV images-the proposed SGCDD-GAN demonstrates superior performance metrics across the entire image and liver region, including SSIM, PSNR, MSE, and PCC scores. Furthermore, CE-CT images synthetized from our SGCDD-GAN achieve remarkable accuracy rates of 82.68%, 94.11%, and 94.11% in a deep learning-based FLLs classification task, along with a pilot assessment conducted by two radiologists.

Radiomics model based on intratumoral and peritumoral features for predicting major pathological response in non-small cell lung cancer receiving neoadjuvant immunochemotherapy.

Objective: To establish a radiomics model based on intratumoral and peritumoral features extracted from pre-treatment CT to predict the major pathological response (MPR) in patients with non-small cell lung cancer (NSCLC) receiving neoadjuvant immunochemotherapy. Methods: A total of 148 NSCLC patients who underwent neoadjuvant immunochemotherapy from two centers (SRRSH and ZCH) were retrospectively included. The SRRSH dataset (n=105) was used as the training and internal validation cohort. Radiomics features of intratumoral (T) and peritumoral regions (P1 = 0-5mm, P2 = 5-10mm, and P3 = 10-15mm) were extracted from pre-treatment CT. Intra- and inter- class correlation coefficients and least absolute shrinkage and selection operator were used to feature selection. Four single ROI models mentioned above and a combined radiomics (CR: T+P1+P2+P3) model were established by using machine learning algorithms. Clinical factors were selected to construct the combined radiomics-clinical (CRC) model, which was validated in the external center ZCH (n=43). The performance of the models was assessed by DeLong test, calibration curve and decision curve analysis. Results: Histopathological type was the only independent clinical risk factor. The model CR with eight selected radiomics features demonstrated a good predictive performance in the internal validation (AUC=0.810) and significantly improved than the model T (AUC=0.810 vs 0.619, p<0.05). The model CRC yielded the best predictive capability (AUC=0.814) and obtained satisfactory performance in the independent external test set (AUC=0.768, 95% CI: 0.62-0.91). Conclusion: We established a CRC model that incorporates intratumoral and peritumoral features and histopathological type, providing an effective approach for selecting NSCLC patients suitable for neoadjuvant immunochemotherapy.

Mulberry leaf polysaccharide improves cyclophosphamide-induced growth inhibition and intestinal damage in chicks by modulating intestinal flora, enhancing immune regulation and antioxidant capacity.

Polysaccharides are generally considered to have immune enhancing functions, and mulberry leaf polysaccharide is the main active substance in mulberry leaves, while there are few studies on whether mulberry leaf polysaccharide (MLP) has an effect on immunosuppression and intestinal damage caused by cyclophosphamide (CTX), we investigated whether MLP has an ameliorative effect on intestinal damage caused by CTX. A total of 210 1-day-old Mahuang cocks were selected for this experiment. Were equally divided into six groups and used to evaluate the immune effect of MLP. Our results showed that MLP significantly enhanced the growth performance of chicks and significantly elevated the secretion of cytokines (IL-1ß, IL-10, IL-6, TNF-α, and IFN-γ), immunoglobulins and antioxidant enzymes in the serum of immunosuppressed chicks. It attenuated jejunal damage and elevated the expression of jejunal tight junction proteins Claudin1, Zo-1 and MUC2, which protected intestinal health. MLP activated TLR4-MyD88-NF-κB pathway and enhanced the expression of TLR4, MyD88 and NF-κB, which served to protect the intestine. 16S rDNA gene high-throughput sequencing showed that MLP increased species richness, restored CTX-induced gut microbiome imbalance, and enhanced the abundance of probiotic bacteria in the gut. MLP improves cyclophosphamide-induced growth inhibition and intestinal damage in chicks by modulating intestinal flora and enhancing immune regulation and antioxidant capacity. In conclusion, this study provides a scientific basis for MLP as an immune enhancer to regulate chick intestinal flora and protect chick intestinal mucosal damage.

Multitask deep learning for prediction of microvascular invasion and recurrence-free survival in hepatocellular carcinoma based on MRI images.

BACKGROUND AND AIMS: Accurate preoperative prediction of microvascular invasion (MVI) and recurrence-free survival (RFS) is vital for personalised hepatocellular carcinoma (HCC) management. We developed a multitask deep learning model to predict MVI and RFS using preoperative MRI scans. METHODS: Utilising a retrospective dataset of 725 HCC patients from seven institutions, we developed and validated a multitask deep learning model focused on predicting MVI and RFS. The model employs a transformer architecture to extract critical features from preoperative MRI scans. It was trained on a set of 234 patients and internally validated on a set of 58 patients. External validation was performed using three independent sets (n = 212, 111, 110). RESULTS: The multitask deep learning model yielded high MVI prediction accuracy, with AUC values of 0.918 for the training set and 0.800 for the internal test set. In external test sets, AUC values were 0.837, 0.815 and 0.800. Radiologists' sensitivity and inter-rater agreement for MVI prediction improved significantly when integrated with the model. For RFS, the model achieved C-index values of 0.763 in the training set and ranged between 0.628 and 0.728 in external test sets. Notably, PA-TACE improved RFS only in patients predicted to have high MVI risk and low survival scores (p < .001). CONCLUSIONS: Our deep learning model allows accurate MVI and survival prediction in HCC patients. Prospective studies are warranted to assess the clinical utility of this model in guiding personalised treatment in conjunction with clinical criteria.

Gadolinium deposition in the liver and brain in a rat model with liver fibrosis after intravenous administration of gadoxetate disodium.

Objectives: To investigate gadolinium deposition in the liver and brain in a rat model with liver fibrosis (LF) after intravenous administration of gadoxetate disodium (GD) and the histological effects of gadolinium deposition in the liver and brain. Methods: Adult male Sprague-Dawley rats were randomly assigned to one of the three groups: 1) LF group received intraperitoneal injection of carbon tetrachloride (CCl4) for 9 weeks alone; 2) LF&GD group received CCl4 and intravenous administration of GD (for 5 consecutive days); 3) GD group received olive oil and GD. Seven days after the final injection of GD, the deep cerebellar nuclei (DCN) and liver were excised to determine gadolinium concentrations via inductively coupled plasma mass spectrometry, and histologic staining was performed. Bonferroni's post-hoc test and Wilcoxon rank sum test were used to compare the differences between the three groups. Results: The concentrations of retained gadolinium in the liver in the LF&GD group (2.18 ± 0.44 µg/g) were significantly greater compared to the LF group (0.02 ± 0.01 µg/g, P < 0.001) and GD group (0.37 ± 0.11 µg/g, P < 0.001). Also, the concentrations of retained gadolinium in DCN were increased in the LF&GD group (0.13 ± 0.06 µg/g) compared to the LF group (0.01 ± 0.00 µg/g, P < 0.001) and GD group (0.06 ± 0.02 µg/g, P = 0.019). No histopathological alterations were detected in the liver and DCN between LF&GD group and LF group. Conclusions: LF aggravated gadolinium deposition in the liver and DCN after administration of GD. However, no significant acute histological alterations were observed due to gadolinium deposition.

Assessment of Right Atrial Function Measured with Cardiac MRI Feature Tracking for Predicting Outcomes in Patients with Dilated Cardiomyopathy.

Background Right atrial (RA) function strain is increasingly acknowledged as an important predictor of adverse events in patients with diverse cardiovascular conditions. However, the prognostic value of RA strain in patients with dilated cardiomyopathy (DCM) remains uncertain. Purpose To evaluate the prognostic value of RA strain derived from cardiac MRI (CMR) feature tracking (FT) in patients with DCM. Materials and Methods This multicenter, retrospective study included consecutive adult patients with DCM who underwent CMR between June 2010 and May 2022. RA strain parameters were obtained using CMR FT. The primary end points were sudden or cardiac death or heart transplant. Cox regression analysis was used to determine the association of variables with outcomes. Incremental prognostic value was evaluated using C indexes and likelihood ratio tests. Results A total of 526 patients with DCM (mean age, 51 years ± 15 [SD]; 381 male) were included. During a median follow-up of 41 months, 79 patients with DCM reached the primary end points. At univariable analysis, RA conduit strain was associated with the primary end points (hazard ratio [HR], 0.82 [95% CI: 0.76, 0.87]; P < .001). In multivariable Cox analysis, RA conduit strain was an independent predictor for the primary end points (HR, 0.83 [95% CI: 0.77, 0.90]; P < .001). A model combining RA conduit strain with other clinical and conventional imaging risk factors (C statistic, 0.80; likelihood ratio, 92.54) showed improved discrimination and calibration for the primary end points compared with models with clinical variables (C statistic, 0.71; likelihood ratio, 37.12; both P < .001) or clinical and imaging variables (C statistic, 0.75; likelihood ratio, 64.69; both P < .001). Conclusion CMR FT-derived RA conduit strain was an independent predictor of adverse outcomes among patients with DCM, providing incremental prognostic value when combined in a model with clinical and conventional CMR risk factors. Published under a CC BY 4.0 license. Supplemental material is available for this article.

OA-GAN: organ-aware generative adversarial network for synthesizing contrast-enhanced medical images.

Contrast-enhanced computed tomography (CE-CT) images are vital for clinical diagnosis of focal liver lesions (FLLs). However, the use of CE-CT images imposes a significant burden on patients due to the injection of contrast agents and extended shooting. Deep learning-based image synthesis models offer a promising solution that synthesizes CE-CT images from non-contrasted CT (NC-CT) images. Unlike natural images, medical image synthesis requires a specific focus on certain organs or localized regions to ensure accurate diagnosis. Determining how to effectively emphasize target organs poses a challenging issue in medical image synthesis. To solve this challenge, we present a novel CE-CT image synthesis model called, Organ-Aware Generative Adversarial Network (OA-GAN). The OA-GAN comprises an organ-aware (OA) network and a dual decoder-based generator. First, the OA network learns the most discriminative spatial features about the target organ (i.e. liver) by utilizing the ground truth organ mask as localization cues. Subsequently, NC-CT image and captured feature are fed into the dual decoder-based generator, which employs a local and global decoder network to simultaneously synthesize the organ and entire CECT image. Moreover, the semantic information extracted from the local decoder is transferred to the global decoder to facilitate better reconstruction of the organ in entire CE-CT image. The qualitative and quantitative evaluation on a CE-CT dataset demonstrates that the OA-GAN outperforms state-of-the-art approaches for synthesizing two types of CE-CT images such as arterial phase and portal venous phase. Additionally, subjective evaluations by expert radiologists and a deep learning-based FLLs classification also affirm that CE-CT images synthesized from the OA-GAN exhibit a remarkable resemblance to real CE-CT images.

Convolutional neural network applied to preoperative venous-phase CT images predicts risk category in patients with gastric gastrointestinal stromal tumors.

OBJECTIVE: The risk category of gastric gastrointestinal stromal tumors (GISTs) are closely related to the surgical method, the scope of resection, and the need for preoperative chemotherapy. We aimed to develop and validate convolutional neural network (CNN) models based on preoperative venous-phase CT images to predict the risk category of gastric GISTs. METHOD: A total of 425 patients pathologically diagnosed with gastric GISTs at the authors' medical centers between January 2012 and July 2021 were split into a training set (154, 84, and 59 with very low/low, intermediate, and high-risk, respectively) and a validation set (67, 35, and 26, respectively). Three CNN models were constructed by obtaining the upper and lower 1, 4, and 7 layers of the maximum tumour mask slice based on venous-phase CT Images and models of CNN_layer3, CNN_layer9, and CNN_layer15 established, respectively. The area under the receiver operating characteristics curve (AUROC) and the Obuchowski index were calculated to compare the diagnostic performance of the CNN models. RESULTS: In the validation set, CNN_layer3, CNN_layer9, and CNN_layer15 had AUROCs of 0.89, 0.90, and 0.90, respectively, for low-risk gastric GISTs; 0.82, 0.83, and 0.83 for intermediate-risk gastric GISTs; and 0.86, 0.86, and 0.85 for high-risk gastric GISTs. In the validation dataset, CNN_layer3 (Obuchowski index, 0.871) provided similar performance than CNN_layer9 and CNN_layer15 (Obuchowski index, 0.875 and 0.873, respectively) in prediction of the gastric GIST risk category (All P >.05). CONCLUSIONS: The CNN based on preoperative venous-phase CT images showed good performance for predicting the risk category of gastric GISTs.

A multicenter clinical AI system study for detection and diagnosis of focal liver lesions.

Early and accurate diagnosis of focal liver lesions is crucial for effective treatment and prognosis. We developed and validated a fully automated diagnostic system named Liver Artificial Intelligence Diagnosis System (LiAIDS) based on a diverse sample of 12,610 patients from 18 hospitals, both retrospectively and prospectively. In this study, LiAIDS achieved an F1-score of 0.940 for benign and 0.692 for malignant lesions, outperforming junior radiologists (benign: 0.830-0.890, malignant: 0.230-0.360) and being on par with senior radiologists (benign: 0.920-0.950, malignant: 0.550-0.650). Furthermore, with the assistance of LiAIDS, the diagnostic accuracy of all radiologists improved. For benign and malignant lesions, junior radiologists' F1-scores improved to 0.936-0.946 and 0.667-0.680 respectively, while seniors improved to 0.950-0.961 and 0.679-0.753. Additionally, in a triage study of 13,192 consecutive patients, LiAIDS automatically classified 76.46% of patients as low risk with a high NPV of 99.0%. The evidence suggests that LiAIDS can serve as a routine diagnostic tool and enhance the diagnostic capabilities of radiologists for liver lesions.

Radiomics analysis of contrast-enhanced computerized tomography for differentiation of gastric schwannomas from gastric gastrointestinal stromal tumors.

PURPOSE: To assess the performance of radiomics-based analysis of contrast-enhanced computerized tomography (CE-CT) images for distinguishing GS from gastric GIST. METHODS: Forty-nine patients with GS and two hundred fifty-three with GIST were enrolled in this retrospective study. CT features were evaluated by two associate chief radiologists. Radiomics features were extracted from portal venous phase images using Pyradiomics software. A non-radiomics dataset (combination of clinical characteristics and radiologist-determined CT features) and a radiomics dataset were used to build stepwise logistic regression and least absolute shrinkage and selection operator (LASSO) logistic regression models, respectively. Model performance was evaluated according to sensitivity, specificity, accuracy, and receiver operating characteristic (ROC) curve, and Delong's test was applied to compare the area under the curve (AUC) between different models. RESULTS: A total of 1223 radiomics features were extracted from portal venous phase images. After reducing dimensions by calculating Pearson correlation coefficients (PCCs), 20 radiomics features, 20 clinical characteristics + CT features were used to build the models, respectively. The AUC values for the models using radiomics features and those using clinical features were more than 0.900 for both the training and validation groups. There were no significant differences in predictive performance between the radiomic and clinical data models according to Delong's test. CONCLUSION: A radiomics-based model applied to CE-CT images showed comparable predictive performance to senior physicians in the differentiation of GS from GIST.

Nonlocal based FISTA network for noninvasive cardiac transmembrane potential imaging.

Objective. The primary aim of our study is to advance our understanding and diagnosis of cardiac diseases. We focus on the reconstruction of myocardial transmembrane potential (TMP) from body surface potential mapping.Approach. We introduce a novel methodology for the reconstruction of the dynamic distribution of TMP. This is achieved through the integration of convolutional neural networks with conventional optimization algorithms. Specifically, we utilize the subject-specific transfer matrix to describe the dynamic changes in TMP distribution and ECG observations at the body surface. To estimate the TMP distribution, we employ LNFISTA-Net, a learnable non-local regularized iterative shrinkage-thresholding network. The coupled estimation processes are iteratively repeated until convergence.Main results. Our experiments demonstrate the capabilities and benefits of this strategy. The results highlight the effectiveness of our approach in accurately estimating the TMP distribution, thereby providing a reliable method for the diagnosis of cardiac diseases.Significance. Our approach demonstrates promising results, highlighting its potential utility for a range of applications in the medical field. By providing a more accurate and dynamic reconstruction of TMP, our methodology could significantly improve the diagnosis and treatment of cardiac diseases, thereby contributing to advancements in healthcare.

Post-sepsis psychiatric disorder: Pathophysiology, prevention, and treatment.

Post-sepsis psychiatric disorder, encompassing anxiety, depression, post-traumatic stress disorder and delirium, is a highly prevalent complication secondary to sepsis, resulting in a marked increase in long-term mortality among affected patients. Regrettably, psychiatric impairment associated with sepsis is frequently disregarded by clinicians. This review aims to summarize recent advancements in the understanding of the pathophysiology, prevention, and treatment of post-sepsis mental disorder, including coronavirus disease 2019-related psychiatric impairment. The pathophysiology of post-sepsis psychiatric disorder is complex and is known to involve blood-brain barrier disruption, overactivation of the hypothalamic-pituitary-adrenal axis, neuroinflammation, oxidative stress, neurotransmitter dysfunction, programmed cell death, and impaired neuroplasticity. No unified diagnostic criteria for this disorder are currently available; however, screening scales are often applied in its assessment. Modifiable risk factors for psychiatric impairment post-sepsis include the number of experienced traumatic memories, the length of ICU stay, level of albumin, the use of vasopressors or inotropes, daily activity function after sepsis, and the cumulative dose of dobutamine. To contribute to the prevention of post-sepsis psychiatric disorder, it may be beneficial to implement targeted interventions for these modifiable risk factors. Specific therapies for this condition remain scarce. Nevertheless, non-pharmacological approaches, such as comprehensive nursing care, may provide a promising avenue for treating psychiatric disorder following sepsis. In addition, although several therapeutic drugs have shown preliminary efficacy in animal models, further confirmation of their potential is required through follow-up clinical studies.

Imaging Features of Biliary Adenofibroma With Malignant Transformation: A Case Report and Literature Review.

Biliary adenofibroma (BAF) is a rare benign tumor, but it has the potential for malignant transformation. The differentiation between benign and malignant forms of BAF before surgery is of great importance for clinical decision-making. We report a case of BAF with invasive carcinoma. The patient did not present any clinical symptoms but had a history of hepatitis B virus infection for more than twenty years. Magnetic resonance imaging (MRI) revealed a solid and cystic 4 cm mass in segment II of the liver exhibiting hypointense signals on T1-weighted images and intermediate-to-high intensity signals on T2-weighted images. Enhancement scanning revealed markedly rim-like enhancement on the arterial phase, with the left inter-hepatic artery as the tumor-feeding artery, and wash-out on the venous and delayed phases. To the best of our knowledge, BAF with invasive carcinoma is uncommon. Preoperative qualitative diagnosis based on imaging features can achieve the maximum benefit for patients.

Optimizing Clinical Cardiac MRI Workflow through Single Breath-Hold Compressed Sensing Cine: An Evaluation of Feasibility and Efficiency.

BACKGROUND: Although compressed sensing (CS) accelerated cine holds immense potential to replace conventional cardiovascular magnetic resonance (CMR) cine, how to use CS-based cine appropriately during clinical CMR examinations still needs exploring. METHODS: A total of 104 patients (46.5 ± 17.1 years) participated in this prospective study. For each participant, a balanced steady state free precession (bSSFP) cine was acquired as a reference, followed by two CS accelerated cine sequences with identical parameters before and after contrast injection. Lastly, a CS accelerated cine sequence with an increased flip angle was obtained. We subsequently compared scanning time, image quality, and biventricular function parameters between these sequences. RESULTS: All CS cine sequences demonstrated significantly shorter acquisition times compared to bSSFPref cine (p < 0.001). The bSSFPref cine showed higher left ventricular ejection fraction (LVEF) than all CS cine sequences (all p < 0.001), but no significant differences in LVEF were observed among the three CS cine sequences. Additionally, CS cine sequences displayed superior global image quality (p < 0.05) and fewer artifacts than bSSFPref cine (p < 0.005). Unenhanced CS cine and enhanced CS cine with increased flip angle showed higher global image quality than other cine sequences (p < 0.005). CONCLUSION: Single breath-hold CS cine delivers precise biventricular function parameters and offers a range of benefits including shorter scan time, better global image quality, and diminished motion artifacts. This innovative approach holds great promise in replacing conventional bSSFP cine and optimizing the CMR examination workflow.

The effects of flip angle and gadolinium contrast agent on single breath-hold compressed sensing cardiac magnetic resonance cine for biventricular global strain assessment.

Background: Due to its potential to significantly reduce scanning time while delivering accurate results for cardiac volume function, compressed sensing (CS) has gained traction in cardiovascular magnetic resonance (CMR) cine. However, further investigation is necessary to explore its feasibility and impact on myocardial strain results. Materials and methods: A total of 102 participants [75 men, 46.5 ± 17.1 (SD) years] were included in this study. Each patient underwent four consecutive cine sequences with the same slice localization, including the reference multi-breath-hold balanced steady-state free precession (bSSFPref) cine, the CS cine with the same flip angle as bSSFPref before (CS45) and after (eCS45) contrast enhancement, and the CS cine (eCS70) with a 70-degree flip angle after contrast enhancement. Biventricular strain parameters were derived from cine images. Two-tailed paired t-tests were used for data analysis. Results: Global radial strain (GRS), global circumferential strain (GCS), and global longitudinal strain (GLS) were observed to be significantly lower in comparison to those obtained from bSSFPref sequences for both the right and left ventricles (all p < 0.001). No significant difference was observed on biventricular GRS-LAX (long-axis) and GLS values derived from enhanced and unenhanced CS cine sequences with the same flip angle, but remarkable reductions were noted in GRS-SAX (short-axis) and GCS values (p < 0.001). After contrast injection, a larger flip angle caused a significant elevation in left ventricular strain results (p < 0.001) but did not affect the right ventricle. The increase in flip angle appeared to compensate for contrast agent affection on left ventricular GRS-SAX, GCS values, and right ventricular GRS-LAX, GLS values. Conclusion: Despite incorporating gadolinium contrast agents and applying larger flip angles, single breath-hold CS cine sequences consistently yielded diminished strain values for both ventricles when compared with conventional cine sequences. Prior to employing this single breath-hold CS cine sequence to refine the clinical CMR examination procedure, it is crucial to consider its impact on myocardial strain results.

Carboxymethylated Abrus cantoniensis polysaccharide prevents CTX-induced immunosuppression and intestinal damage by regulating intestinal flora and butyric acid content.

As a Chinese folk health product, Abrus cantoniensis exhibits good immunomodulatory activity because of its polysaccharide components (ACP), and carboxymethylation of polysaccharides can often further improve the biological activity of polysaccharides. In this study, we explored the impact of prophylactic administration of carboxymethylated Abrus cantoniensis polysaccharide (CM-ACP) on immunosuppression and intestinal damage induced by cyclophosphamide (CTX) in mice. Our findings demonstrated that CM-ACP exhibited a more potent immunomodulatory activity compared to ACP. Additionally, CM-ACP effectively enhanced the abundance of short-chain fatty acid (SCFA)-producing bacteria in immunosuppressed mice and regulated the gene expression of STAT6 and STAT3 mediated pathway signals. In order to further explore the relationship among polysaccharides, intestinal immunity and intestinal flora, we performed a pseudo-sterile mouse validation experiment and fecal microbiota transplantation (FMT) experiment. The findings suggest that CM-FMT and butyrate attenuate CTX-induced immunosuppression and intestinal injury. CM-FMT and butyrate show superior immunomodulatory ability, and may effectively regulate intestinal cell metabolism and repair the damaged intestine by activating STAT6 and STAT3-mediated pathways. These findings offer new insights into the mechanisms by which CM-ACP functions as functional food or drug, facilitating immune response regulation and maintaining intestinal health.

A deep learning model based on MRI for prediction of vessels encapsulating tumour clusters and prognosis in hepatocellular carcinoma.

PURPOSE: This study aimed to build and evaluate a deep learning (DL) model to predict vessels encapsulating tumor clusters (VETC) and prognosis preoperatively in patients with hepatocellular carcinoma (HCC). METHODS: 320 pathologically confirmed HCC patients (58 women and 262 men) from two hospitals were included in this retrospective study. Institution 1 (n = 219) and Institution 2 (n = 101) served as the training and external test cohorts, respectively. Tumors were evaluated three-dimensionally and regions of interest were segmented manually in the arterial, portal venous, and delayed phases (AP, PP, and DP). Three ResNet-34 DL models were developed, consisting of three models based on a single sequence. The fusion model was developed by inputting the prediction probability of the output from the three single-sequence models into logistic regression. The area under the receiver operating characteristic curve (AUC) was used to compare performance, and the Delong test was used to compare AUCs. Early recurrence (ER) was defined as recurrence within two years of surgery and early recurrence-free survival (ERFS) rate was evaluated by Kaplan-Meier survival analysis. RESULTS: Among the 320 HCC patients, 227 were VETC- and 93 were VETC+ . In the external test cohort, the fusion model showed an AUC of 0.772, a sensitivity of 0.80, and a specificity of 0.61. The fusion model-based prediction of VETC high-risk and low-risk categories exhibits a significant difference in ERFS rates, akin to the outcomes observed in VETC + and VETC- confirmed through pathological analyses (p < 0.05). CONCLUSIONS: A DL framework based on ResNet-34 has demonstrated potential in facilitating non-invasive prediction of VETC as well as patient prognosis.

CT-based whole lung radiomics nomogram: a tool for identifying the risk of cardiovascular disease in patients with chronic obstructive pulmonary disease.

OBJECTIVES: To evaluate the value of CT-based whole lung radiomics nomogram for identifying the risk of cardiovascular disease (CVD) in patients with chronic obstructive pulmonary disease (COPD). MATERIALS AND METHODS: A total of 974 patients with COPD were divided into a training cohort (n = 402), an internal validation cohort (n = 172), and an external validation cohort (n = 400) from three hospitals. Clinical data and CT findings were analyzed. Radiomics features of whole lung were extracted from the non-contrast chest CT images. A radiomics signature was constructed with algorithms. Combined with the radiomics score and independent clinical factors, multivariate logistic regression analysis was used to establish a radiomics nomogram. ROC curve was used to analyze the prediction performance of the model. RESULTS: Age, weight, and GOLD were the independent clinical factors. A total of 1218 features were extracted and reduced to 15 features to build the radiomics signature. In the training cohort, the combined model (area under the curve [AUC], 0.731) showed better discrimination capability (p < 0.001) than the clinical factors model (AUC, 0.605). In the internal validation cohort, the combined model (AUC, 0.727) performed better (p = 0.032) than the clinical factors model (AUC, 0.629). In the external validation cohort, the combined model (AUC, 0.725) performed better (p < 0.001) than the clinical factors model (AUC, 0.690). Decision curve analysis demonstrated the radiomics nomogram outperformed the clinical factors model. CONCLUSION: The CT-based whole lung radiomics nomogram has the potential to identify the risk of CVD in patients with COPD. CLINICAL RELEVANCE STATEMENT: This study helps to identify cardiovascular disease risk in patients with chronic obstructive pulmonary disease on chest CT scans. KEY POINTS: • To investigate the value of CT-based whole lung radiomics features in identifying the risk of cardiovascular disease in chronic obstructive pulmonary disease patients. • The radiomics nomogram showed better performance than the clinical factors model to identify the risk of cardiovascular disease in patients with chronic obstructive pulmonary disease. • The radiomics nomogram demonstrated excellent performance in the training, internal validation, and external validation cohort (AUC, 0.731; AUC, 0.727; AUC, 0.725).