ObjectiveTo investigate the application value of a multimodal model integrating radiomics features， deep learning features， and clinical structured data in predicting severe acute pancreatitis （SAP）， and to provide more accurate tools for the early identification of SAP in clinical practice. MethodsThe patients with acute pancreatitis （AP） who attended The First Affiliated Hospital of Soochow University， Jintan Hospital Affiliated to Jiangsu University， and Suzhou Yongding Hospital from January 1， 2017 to December 31， 2023 were included. Related data were collected， including demographic information， previous medical history， etiology， laboratory test data， and systemic inflammatory response syndrome （SIRS） within 24 hours after admission， as well as imaging data within 72 hours after admission， while related scores were calculated， including Ranson score， modified CT severity index （MCTSI）， bedside index for severity in acute pancreatitis （BISAP）， and systemic inflammatory response syndrome， albumin， blood urea nitrogen and pleural effusion （SABP） score. The model was constructed in the following process： （1） three-dimensional CT images were used to extract and identify radiomics features， and a radiomics classification model was established based on the extreme gradient Boost （XGBoost） algorithm； （2） U-Net is used to perform semantic segmentation of three-dimensional CT images， and then the results of segmentation were imported into 3D ResNet50 to construct a deep learning classification model； （3） the predicted values of the above two models were integrated with clinical structured data to establish a multimodal model based on the XGBoost algorithm. The variable importance plot and local interpretability plot were used to perform visual interpretation of the model. The independent samples t-test was used for comparison of normally distributed continuous data between groups， and the Mann-Whitney U test was used for comparison of non-normally distributed continuous data between groups； the chi-square test or Fisher’s exact test was used for comparison of categorical data between groups. The receiver operating characteristic （ROC） curve was plotted for each model and existing scoring systems， and the area under the ROC curve （AUC） was calculated to assess their performance； the Delong test was used for comparison of AUC. ResultsA total of 609 patients who met the criteria were included， among whom 114 （18.7%） developed SAP. In this study， the data of 426 patients from The First Affiliated Hospital of Soochow University was used as the training set， and the data of 183 patients from Jintan Hospital Affiliated to Jiangsu University and Suzhou Yongding Hospital were used as the independent test set. The multimodal model had an AUC of 0.914 in the test set， which was significantly higher than the AUC of traditional scoring systems such as MCTSI （AUC=0.827）， Ranson score （AUC=0.675）， BISAP （AUC=0.791）， and SABP score （AUC=0.648）； in addition， the multimodal model showed a significant improvement in performance compared with the radiomics classification model （AUC=0.739） and the deep learning classification model （AUC=0.685） （the Delong test： Z=-3.23， -4.83， -3.48， -4.92， -4.31， and -4.59， all P <0.01）. The top 10 variables in terms of importance in the multimodal model were pleural effusion， predicted value of the deep learning model， predicted value of the radiomics model， triglycerides， calcium ions， SIRS， white blood cell count， age， platelets， and C-reactive protein， suggesting that the above variables had significant contributions to the performance of the model in predicting SAP. ConclusionBased on structured data， radiomic features， and deep learning features， this study constructs a multicenter prediction model for SAP based on the XGBoost algorithm， which has a better predictive performance than existing traditional scoring systems and unimodal models.

Kupffer cells (KCs), as residents and sentinels of the liver, are involved in the formation of hepatic fibrosis (HF). However, the biological functions of circular RNAs (circRNAs) in KCs to HF have not been determined. In this study, the expression levels of circRNAs, microRNAs, and messenger RNAs (mRNAs) in KCs from a mouse model of HF mice were investigated using microarray and circRNA-Seq analyses. circDcbld2 was identified as a candidate circRNA in HF, as evidenced by its up-regulation in KCs. Silver staining and mass spectrometry showed that Wtap and Igf2bp2 bind to cirDcbld2. The suppression of circDcbld2 expression decreased the KC inflammatory response and oxidative stress and inhibited hepatic stellate cell (HSCs) activation, attenuating mouse liver fibrogenesis. Mechanistically, Wtap mediated the N ⁶-methyladenosine (m6A) methylation of circDcbld2, and Igf2bp2 recognized m6A-modified circDcbld2 and increased its stability. circDcbld2 contributes to the occurrence of HF by binding miR-144-3p/Et-1 to regulate the inflammatory response and oxidative stress. These findings indicate that circDcbld2 functions via the m6A/circDcbld2/miR-144-3p/Et-1 axis and may act as a potential biomarker for HF treatment.

Human NAD(P)H: quinone oxidoreductase 1 (NQO1) is a flavoenzyme expressed at high levels in multiple solid tumors, making it an attractive target for anticancer drugs. Bioactivatable drugs targeting NQO1, such as β-lapachone (β-lap), are currently in clinical trials for the treatment of cancer. β-Lap selectively kills NQO1-positive (NQO1⁺) cancer cells by inducing reactive oxygen species (ROS) via catalytic activation of NQO1. In this study, we demonstrated that cryptotanshinone (CTS), a naturally occurring compound, induces NQO1-dependent necrosis without affecting NQO1 activity. CTS selectively kills NQO1⁺ cancer cells by inducing NQO1-dependent necrosis. Interestingly, CTS directly binds to NQO1 but does not activate its catalytic activity. In addition, CTS enables activation of JNK1/2 and PARP, accumulation of iron and Ca²⁺, and depletion of ATP and NAD⁺. Furthermore, CTS selectively suppressed tumor growth in the NQO1⁺ xenograft models, which was reversed by NQO1 inhibitor and NQO1 shRNA. In conclusion, CTS induces NQO1-dependent necrosis via the JNK1/2/iron/PARP/NAD⁺/Ca²⁺ signaling pathway. This study demonstrates the non-enzymatic function of NQO1 in inducing cell death and provides new avenues for the design and development of NQO1-targeted anticancer drugs.

Objective: To evaluate the feasibility of dynamic contrast-enhanced MRI (DCE-MRI) in differentiating tumor deposits (TDs) from metastatic lymph nodes (MLNs) in rectal cancer. Materials and Methods: A retrospective analysis was conducted on 70 patients with rectal cancer, including 168 lesions (70 TDs and 98 MLNs confirmed by histopathology), who underwent pretreatment MRI and subsequent surgery between March 2019 and December 2022. The morphological characteristics of TDs and MLNs, along with quantitative parameters derived from DCE-MRI (K trans , kep, and v e) and DWI (ADCmin, ADCmax, and ADCmean), were analyzed and compared between the two groups.Multivariable binary logistic regression and receiver operating characteristic (ROC) curve analyses were performed to assess the diagnostic performance of significant individual quantitative parameters and combined parameters in distinguishing TDs from MLNs. Results: All morphological features, including size, shape, border, and signal intensity, as well as all DCE-MRI parameters showed significant differences between TDs and MLNs (all P < 0.05). However, ADC values did not demonstrate significant differences (all P > 0.05). Among the single quantitative parameters, v e had the highest diagnostic accuracy, with an area under the ROC curve (AUC) of 0.772 for distinguishing TDs from MLNs. A multivariable logistic regression model incorporating short axis, border, v e, and ADC mean improved diagnostic performance, achieving an AUC of 0.833 (P = 0.027). Conclusion The combination of morphological features, DCE-MRI parameters, and ADC values can effectively aid in the preoperative differentiation of TDs from MLNs in rectal cancer.

With the emergence of deep learning techniques based on convolutional neural networks, artificial intelligence (AI) has driven transformative developments in the field of medical image analysis. Recently, large language models (LLMs) such as ChatGPT have also started to achieve distinction in this domain. Increasing research shows the undeniable role of AI in reshaping various aspects of medical image analysis, including processes such as image enhancement, segmentation, detection in image preprocessing, and postprocessing related to medical diagnosis and prognosis in clinical settings. However, despite the significant progress in AI research, studies investigating the recent advances in AI technology in the aforementioned aspects, the changes in research hotspot trajectories, and the performance of studies in addressing key clinical challenges in this field are limited. This article provides an overview of recent advances in AI for medical image analysis and discusses the methodological profiles, advantages, disadvantages, and future trends of AI technologies.
Artificial Intelligence ; Humans ; Image Processing, Computer-Assisted/methods* ; Neural Networks, Computer ; Deep Learning ; Diagnostic Imaging/methods*

Cardiovascular disease remains the leading cause of death in China, with its morbidity and mortality continue to rise. Ferroptosis, a unique form of iron-dependent cell death, plays a major role in many heart diseases. The classical mechanisms of ferroptosis include iron metabolism disorder, oxidative antioxidant imbalance and lipid peroxidation. Recent studies have found many additional mechanisms of ferroptosis, such as coenzyme Q10, ferritinophagy, lipid autophagy, mitochondrial metabolism disorder, and the regulation by nuclear factor erythroid 2-related factor 2 (NRF2). This article reviews recent advances in understanding the mechanisms of ferroptosis and its role in heart failure, myocardial ischemia/reperfusion injury, diabetic cardiomyopathy, myocardial toxicity of doxorubicin, septic cardiomyopathy, and arrhythmia. Furthermore, we discuss the potential of ferroptosis inhibitors/inducers as therapeutic targets for heart diseases, suggesting that ferroptosis may be an important intervention target of heart diseases.
Ferroptosis/physiology* ; Humans ; Heart Diseases/physiopathology* ; NF-E2-Related Factor 2/physiology* ; Animals ; Myocardial Reperfusion Injury/physiopathology* ; Lipid Peroxidation ; Heart Failure/physiopathology* ; Iron/metabolism* ; Diabetic Cardiomyopathies/physiopathology* ; Ubiquinone/analogs & derivatives*

Atherosclerosis (AS) is a prevalent clinical vascular condition and serves as a pivotal pathological foundation for cardiovascular diseases. Understanding the pathogenesis of AS has significant clinical and societal implications, aiding in the development of targeted drugs. Neutrophils, the most abundant leukocytes in circulation, assume a central role during inflammatory responses and closely interact with AS, which is a chronic inflammatory vascular disease. Neutrophil extracellular traps (NETs) are substantial reticular formations discharged by neutrophils that serve as an immune defense mechanism. These structures play a crucial role in inducing dysfunction of the vascular barrier following endothelial cell injury. Components released by NETs pose a threat to the integrity of vascular endothelium, which is essential as it acts as the primary barrier to maintain vascular wall integrity. Endothelial damage constitutes the initial stage in the onset of AS. Recent investigations have explored the intricate involvement of NETs in AS progression. The underlying structures of NETs and their active ingredients, including histone, myeloperoxidase (MPO), cathepsin G, neutrophil elastase (NE), matrix metalloproteinases (MMPs), antimicrobial peptide LL-37, alpha-defensin 1-3, and high mobility group protein B1 have diverse and complex effects on AS through various mechanisms. This review aims to comprehensively examine the interplay between NETs and AS while providing insights into their mechanistic underpinnings of NETs in this condition. By shedding light on this intricate relationship, this exploration paves the way for future investigations into NETs while guiding clinical translation efforts and charting new paths for therapeutic interventions.
Extracellular Traps/physiology* ; Humans ; Atherosclerosis/immunology* ; Neutrophils/physiology* ; Leukocyte Elastase/metabolism* ; Peroxidase/physiology* ; Matrix Metalloproteinases/physiology* ; Cathepsin G/metabolism* ; Cathelicidins ; HMGB1 Protein/physiology* ; Histones ; Animals ; Endothelium, Vascular

Objective: To evaluate the feasibility of dynamic contrast-enhanced MRI (DCE-MRI) in differentiating tumor deposits (TDs) from metastatic lymph nodes (MLNs) in rectal cancer. Materials and Methods: A retrospective analysis was conducted on 70 patients with rectal cancer, including 168 lesions (70 TDs and 98 MLNs confirmed by histopathology), who underwent pretreatment MRI and subsequent surgery between March 2019 and December 2022. The morphological characteristics of TDs and MLNs, along with quantitative parameters derived from DCE-MRI (K trans , kep, and v e) and DWI (ADCmin, ADCmax, and ADCmean), were analyzed and compared between the two groups.Multivariable binary logistic regression and receiver operating characteristic (ROC) curve analyses were performed to assess the diagnostic performance of significant individual quantitative parameters and combined parameters in distinguishing TDs from MLNs. Results: All morphological features, including size, shape, border, and signal intensity, as well as all DCE-MRI parameters showed significant differences between TDs and MLNs (all P < 0.05). However, ADC values did not demonstrate significant differences (all P > 0.05). Among the single quantitative parameters, v e had the highest diagnostic accuracy, with an area under the ROC curve (AUC) of 0.772 for distinguishing TDs from MLNs. A multivariable logistic regression model incorporating short axis, border, v e, and ADC mean improved diagnostic performance, achieving an AUC of 0.833 (P = 0.027). Conclusion The combination of morphological features, DCE-MRI parameters, and ADC values can effectively aid in the preoperative differentiation of TDs from MLNs in rectal cancer.

AIM: To investigate the effects of Conbercept on various optical coherence tomography(OCT)biomarkers in patients with retinal vein occlusion-related macular edema(RVO-ME), and to analyze the correlation of these biomarker changes with visual prognosis.METHODS: Retrospective study. A total of 57 patients(57 eyes)with RVO-ME, including 25 patients(25 eyes)with central retinal vein occlusion(CRVO)and 32 patients(32 eyes)with branch retinal vein occlusion(BRVO), were enrolled in this study. All the patients received intravitreal injection of conbercept once a month, three times in total. The preoperative and postoperative best-corrected visual acuity(BCVA), and changes in OCT biomarkers, including central macular thickness(CMT), the length of disorganization of the retinal inner layers(DRIL), the number of hyperreflective dots(HRD), the area of intraretinal fluid(IRF), the area of subretinal fluid(SRF), and the length of ellipsoid zone(EZ)disruption were compared. Furthermore, the relationship of these changes with BCVA was analyzed.RESULTS:Compared with the baseline, at 3 mo post-treatment, BCVA(LogMAR)was improved, CMT was decreased, the length of DRIL was shortened, the number of HRD was reduced, the area of IRF was decreased, the area of SRF was reduced, and the length of EZ disruption was shortened(all P<0.05). Spearman correlation analysis showed that there was no correlation between the changes in CMT, the length of DRIL, the number of HRD, the area of IRF, the area of SRF and the change in BCVA before and after treatment(P>0.05). However, the change in the length of EZ disruption was positively correlated with the change in BCVA(rs=0.34, P=0.011), and the R2 value of the fitting curve between the change in the length of EZ disruption and the change in BCVA was 0.113(P=0.011). When comparing the pre- and post-treatment changes in BCVA, the length of DRIL, the number of HRD, the area of IRF, the area of SRF, and the length of EZ disruption between patients in the CRVO group and BRVO group, no significant differences were observed(all P>0.05). In contrast, a significant difference was found in the change in CMT between the two groups(P=0.002).CONCLUSION:Conbercept effectively improves multiple OCT biomarkers in patients with RVO-ME. Repair of EZ disruption is a key driver of visual recovery, and its stability may serve as a novel indicator for personalized decision-making in anti-vascular endothelial growth factor therapy.