Current role of magnetic resonance imaging on assessing and monitoring the efficacy of phototherapy.

Phototherapy, also known as photobiological therapy, is a non-invasive and highly effective physical treatment method. Its broad use in clinics has led to significant therapeutic results. Phototherapy parameters, such as intensity, wavelength, and duration, can be adjusted to create specific therapeutic effects for various medical conditions. Meanwhile, Magnetic Resonance Imaging (MRI), with its diverse imaging sequences and excellent soft-tissue contrast, provides a valuable tool to understand the therapeutic effects and mechanisms of phototherapy. This review explores the clinical applications of commonly used phototherapy techniques, gives a brief overview of how phototherapy impacts different diseases, and examines MRI's role in various phototherapeutic scenarios. We argue that MRI is crucial for precise targeting, treatment monitoring, and prognosis assessment in phototherapy. Future research and applications will focus on personalized diagnosis and monitoring of phototherapy, expanding its applications in treatment and exploring multimodal imaging technology to enhance diagnostic and therapeutic precision and effectiveness.

Microfluidics-enabled fluorinated assembly of EGCG-ligands-siTOX nanoparticles for synergetic tumor cells and exhausted t cells regulation in cancer immunotherapy.

Immune checkpoint inhibitor (ICI)-derived evolution offers a versatile means of developing novel immunotherapies that targets programmed death-ligand 1 (PD-L1)/programmed death-1 (PD-1) axis. However, one major challenge is T cell exhaustion, which contributes to low response rates in "cold" tumors. Herein, we introduce a fluorinated assembly system of LFNPs/siTOX complexes consisting of fluorinated EGCG (FEGCG), fluorinated aminolauric acid (LA), and fluorinated polyethylene glycol (PEG) to efficiently deliver small interfering RNA anti-TOX (thymus high mobility group box protein, TOX) for synergistic tumor cells and exhausted T cells regulation. Using a microfluidic approach, a library of LFNPs/siTOX complexes were prepared by altering the placement of the hydrophobe (LA), the surface PEGylation density, and the siTOX ratio. Among the different formulations tested, the lead formulation, LFNPs3-3/siTOX complexes, demonstrated enhanced siRNA complexation, sensitive drug release, improved stability and delivery efficacy, and acceptable biosafety. Upon administration by the intravenous injection, this formulation was able to evoke a robust immune response by inhibiting PD-L1 expression and mitigating T cell exhaustion. Overall, this study provides valuable insights into the fluorinated assembly and concomitant optimization of the EGCG-based delivery system. Furthermore, it offers a promising strategy for cancer immunotherapy, highlighting its potential in improving response rates in ''cold'' tumors.

The Use of Cyclodextrin Inclusion Complexes to Increase the Solubility and Pharmacokinetic Profile of Albendazole.

Albendazole is the preferred deworming drug and has strong insecticidal effects on human and animal helminth parasites, showing remarkable activity against hepatocellular carcinoma and colorectal cancer cells. However, it is classified as being in class II in the Biopharmaceutics Classification System due to its poor water solubility (0.2 mg/L) and high permeability, which make the clinical application of albendazole impractical. Through complexation with methyl-ß-cyclodextrin, as the best result so far, albendazole's water solubility was increased by 150,000 times, and albendazole could be 90% released during the first 10 min. In an in vivo pharmacokinetic study, the Cmax and Tmax of the active metabolized sulfoxide were changed from 2.81 µg/mL at 3 h to 10.2 µg/mL at 6 h and the AUC0-48 was increased from 50.72 h⁎µg/mL to 119.95 h⁎µg/mL, indicating that the inclusion complex obtained can be used as a new oral therapeutic anti-anthelmintic and anti-tumor agent formulation.

Inhibitory role of bone marrow mesenchymal stem cells-derived exosome in non-small-cell lung cancer: microRNA-30b-5p, EZH2 and PI3K/AKT pathway.

Exosomal microRNA (miRNA) exerts potential roles in non-small-cell lung cancer (NSCLC). The current study elucidated the role of miR-30b-5p shuttled by bone marrow mesenchymal stem cells (BMSCs)-derived exosomes in treating NSCLC. Bioinformatics analysis was performed with NSCLC-related miRNA microarray GSE169587 and mRNA data GSE74706 obtained for collection of the differentially expressed miRNAs and mRNAs. The relationship between miR-30b-5p and EZH2 was predicted and confirmed. Exosomes were isolated from BMSCs and identified. BMSCs-derived exosomes overexpressing miR-30b-5p were used to establish subcutaneous tumorigenesis models to study the effects of miR-30b-5p, EZH2 and PI3K/AKT signalling pathway on tumour growth. A total of 86 BMSC-exo-miRNAs were differentially expressed in NSCLC. Bioinfomatics analysis found that BMSC-exo-miR-30b-5p could regulate NSCLC progression by targeting EZH2, which was verified by in vitro cell experiments. Besides, the target genes of miR-30b-5p were enriched in PI3K/AKT signalling pathway. Animal experiments validated that BMSC-exo-miR-30b-5p promoted NSCLC cell apoptosis and prevented tumorigenesis in nude mice via EZH2/PI3K/AKT axis. Collectively, the inhibitory role of BMSC-derived exosomes-loaded miR-30b-5p in NSCLC was achieved through blocking the EZH2/PI3K/AKT axis.

A Clinic-Radiomics Model for Predicting the Incidence of Persistent Organ Failure in Patients with Acute Necrotizing Pancreatitis.

Background: Persistent organ failure (POF) is the leading cause of death in patients with acute necrotizing pancreatitis (ANP). Although several risk factors have been identified, there remains a lack of efficient instruments to accurately predict the incidence of POF in ANP. Methods: Retrospectively, the clinical and imaging data of 178 patients with ANP were collected from our database, and the patients were divided into training (n = 125) and validation (n = 53) cohorts. Through computed tomography image acquisition, the volume of interest segmentation, and feature extraction and selection, a pure radiomics model in terms of POF prediction was established. Then, a clinic-radiomics model integrating the pure radiomics model and clinical risk factors was constructed. Both primary and secondary endpoints were compared between the high- and low-risk groups stratified by the clinic-radiomics model. Results: According to the 547 selected radiomics features, four models were derived from features. A clinic-radiomics model in the training and validation sets showed better predictive performance than pure radiomics and clinical models. The clinic-radiomics model was evaluated by the ratios of intervention and mechanical ventilation, intensive care unit (ICU) stays, and hospital stays. The results showed that the high-risk group had significantly higher intervention rates, ICU stays, and hospital stays than the low-risk group, with the confidence interval of 90% (p < 0.1 for all). Conclusions: This clinic-radiomics model is a useful instrument for clinicians to evaluate the incidence of POF, facilitating patients' and their families' understanding of the ANP prognosis.

Evaluation of safety and efficacy of inhaled ambroxol in hospitalized adult patients with mucopurulent sputum and expectoration difficulty.

Background: Ambroxol is a widely used mucoactive drug in sputum clearance of respiratory diseases taken orally and by injection. However, there is a paucity of evidence for inhaled ambroxol in sputum clearance. Methods: This study performed a multicenter, randomized, double-blind, placebo-controlled, phase 3 trial at 19 centers in China. Hospitalized adult patients with mucopurulent sputum and expectoration difficulty were recruited. Patients were randomized by 1:1 to receive inhalation of either ambroxol hydrochloride solution 3 mL (22.5 mg) + 0.9% sodium chloride 3 mL or 0.9% sodium chloride 6 mL twice daily for 5 days, with an interval of more than 6 h. The primary efficacy endpoint was the absolute change in the sputum property score after treatment compared to the baseline in the intention-to-treat population. Results: Between 10 April 2018 and 23 November 2020, 316 patients were recruited and assessed for eligibility, of whom 138 who received inhaled ambroxol and 134 who received a placebo were included. Patients who received inhaled ambroxol had a significantly greater decrease in the sputum property score compared with patients who received inhalation of placebo (difference: -0.29; 95% CI: -0.53 to -0.05; p = 0.0215). Compared with the placebo, inhaled ambroxol also significantly reduced more expectoration volume in 24 h (difference: -0.18; 95% CI: -0.34 to -0.03; p = 0.0166). There was no significant difference in the proportion of adverse events between the two groups, and no deaths were reported. Discussion: In hospitalized adult patients with mucopurulent sputum and expectoration difficulty, inhaled ambroxol was safe and effective for sputum clearance compared with a placebo. Clinical trial registration: [https://www.chictr.org.cn/showproj.html?proj=184677], Chinese Clinical Trial Registry [ChiCTR2200066348].

Screening and application of inhibitory aptamers for DNA repair protein apurinic/apyrimidinic endonuclease 1.

The base excision repair (BER) pathway is crucial for DNA repair, and apurinic/apyrimidinic endonuclease 1 (APE1) is a critical enzyme in this pathway. Overexpression of APE1 has been linked to multidrug resistance in various cancers, including lung cancer, colorectal cancer, and other malignant tumors. Therefore, reducing APE1 activity is desirable to improve cancer treatment. Inhibitory aptamers, which are versatile oligonucleotides for protein recognition and function restriction, are a promising tool for this purpose. In this study, we developed an inhibitory aptamer for APE1 using systematic evolution of ligands by exponential (SELEX) technology. We used carboxyl magnetic beads as the carrier and APE1 with a His-Tag as the positive screening target, while the His-Tag itself served as the negative screening target. The aptamer APT-D1 was selected based on its high binding affinity for APE1, with a dissociation constant (Kd) of 1.306 ± 0.1418 nM. Gel electrophoresis analysis showed that APT-D1 at a concentration of 1.6 µM could entirely inhibit APE1 with 21 nM. Our results suggest that these aptamers can be utilized for early cancer diagnosis and the treatment, and as an essential tool for studying the function of APE1.

Improvement of solubility and pharmacokinetic profile of hepatoprotector icariin through complexation with HP-γ-cyclodextrin.

Icariin as a hepatoprotector from Herba epimedii can expand the cardiovascular and cerebral blood vessels, promote hematopoietic functions, enhance the immune system and show anti-liver tumor activities. However, its low solubility (0.02 mg/mL) limits its clinical applications as food and medical supplements. Through complexation with HP-γ-cyclodextrin by using a trace amount of water-soluble polymer, the water solubility of icariin was increased by 654 times, which is the best result to date for the water solubility study of icariin. In an in vitro pharmacokinetic study, the complexation increased the dissolution rate of icariin by 80 times, and the icariin complex can be 100% released in the first few minutes. Through complexation, in an in vivo dog pharmacokinetic study, the C max of icariin was increased about 5 times, the AUC0-120 was increased about 20 times and the clearance of icariin was changed from 11.17 L/h/kg to 0.65 L/h/kg. The half-life time was changed from 0.68 h to 6.38 h and the relative bioavailability was increased by nearly 20 times, indicating that less drug is needed for the same therapeutic effect by using the icariin complex, and the complex can be used as a potential potent hepatoprotector or anti-liver cancer drug.

Upregulation of lncRNA PINK1-AS Predicts the Distant Metastasis of Patients with Small Cell Lung Cancer.

PINK1-AS has been shown to participate in gastric cancer, while its role in other tumors is unclear. This study was carried out to explore the participation of PINK1-AS in small cell lung cancer (SCLC). In this study, the expression of PINK1-AS in SCLC and paired non-cancer tissues from 60 SCLC patients and in plasma samples from 60 SCLC patients and 60 healthy controls was analyzed with RT-qPCR. Chi-squared t test was applied to analyze the associations between plasma expression levels of PINK1-AS and the clinical factors of the patients. Patients were followed up for 5 years to explore the role of PINK1-AS in the prognosis of SCLC. ROC curve analysis was applied to explore the role of PINK1-AS in the prediction of distant metastasis. Transwell assays were performed to evaluate the role of silencing and overexpression of PINK1-AS in the invasion and migration of SCLC cells. We found that PINK1-AS was upregulated in SCLC tissues compared to that in non-cancer tissues. Plasma expression levels of PINK1-AS were increased in SCLC patients compared to that in the controls. High plasma expression levels of PINK1-AS were closely associated with worse survival. Plasma expression of PINK1-AS was only closely correlated with distant tumor metastasis, but not other factors. High plasma expression levels of PINK1-AS effectively separated patients with distant metastasis from non-metastatic patients. Moreover, PINK1-AS positively regulated the migration and invasion of SCLC cells. Therefore, the upregulation of PINK1-AS predicts the distant metastasis of patients with SCLC.

Development and validation of a clinical-radiomics model to predict recurrence for patients with hepatocellular carcinoma after curative resection.

PURPOSE: Recurrence is the leading cause of death in hepatocellular carcinoma (HCC) patients with curative resection. In this study, we aimed to develop a preoperative predictive model based on high-throughput radiomics features and clinical factors for prediction of long- and short-term recurrence for these patients. METHODS: A total of 270 patients with HCC who were followed up for at least 5 years after curative hepatectomy between June 2014 and December 2017 were enrolled in this retrospective study. Regions of interest were manually delineated in preoperative T2-weighted images using ITK-SNAP software on each HCC tumor slice. A total of 1197 radiomics features were extracted, and the recursive feature elimination method based on logistic regression was used for radiomics signature building. Tenfold cross-validation was applied for model development. Nomograms were constructed and assessed by calibration plot, which compares nomogram-predicated probability with observed outcome. Receiver-operating characteristic was then generated to evaluate the predictive performance of the model in the development and test cohorts. RESULTS: The 10 most recurrence-free survival-related radiomics features were selected for the radiomics signatures. A multiparametric clinical-radiomics model combining albumin and radiomics score for recurrence prediction was further established. The integrated model demonstrated good calibration and satisfactory discrimination, with the area under the curve (AUC) of 0.864, 95% CI 0.842-0.903, sensitivity of 0.889, and specificity of 0.644 in the test set. Calibration curve showed good agreement concerning 5-year recurrence risk predicted by the nomogram. In addition, the AUC of 1-, 2-, 3-, and 4-year recurrence was 0.935 (95% CI 0.836-1.000), 0.861 (95% CI 0.723-0.999), 0.878 (95% CI 0.762-0.994), and 0.878 (95% CI 0.762-0.994) in the test set, respectively. CONCLUSIONS: The clinical-radiomics model integrating radiomics features and clinical factors can improve recurrence predictions beyond predictions made using clinical factors or radiomics features alone. Our clinical-radiomics model is a valid method to predict recurrence that should improve preoperative prognostic performance and allow more individualized treatment decisions.

Serum-derived extracellular vesicles promote the growth and metastasis of non-small cell lung cancer by delivering the m6A methylation regulator HNRNPC through the regulation of DLGAP5.

PURPOSE: Serum-derived extracellular vesicles (EVs) have been reported to play an important role in non-small cell lung cancer (NSCLC). The current study sought to explore the effect of serum-EVs delivering m6A methylation regulator heterogeneous nuclear ribonucleoprotein C (HNRNPC) on the development of NSCLC through the regulation of discs large-associated protein 5 (DLGAP5). METHODS: NSCLC-related RNA-Seq and clinical data were first obtained from the TCGA database to screen differentially expressed m6A-related regulators, which were intersected with the differential genes in NSCLC-related microarray GSE43458 obtained from the GEO database for survival analysis and clinical correlation analysis. Correlation between HNRNPC and DLGAP5 expression was evaluated. Serum-EVs were isolated and identified, and the uptake of EVs by A549 cells was visualized using fluorescence microscopy. In vivo xenograft tumor models and tumor metastasis models were constructed in nude mice to observe growth and metastasis of NSCLC cells. RESULTS: HNRNPC was associated with poor prognosis and metastasis of NSCLC, and further implicated in the regulation of DNA replication and cell cycle-related pathways. HNRNPC might promote the growth and metastasis of NSCLC by identifying m6A modification of DLGAP5 mRNA. Serum-EVs delivered HNRNPC to NSCLC cells in vitro. In vivo experimentation further confirmed that serum-EVs could deliver HNRNPC to promote the growth and metastasis of NSCLC cells in nude mice. CONCLUSIONS: Our findings highlight that serum-EVs can deliver HNRNPC to NSCLC cells, wherein HNRNPC recognizes the m6A modification of DLGAP5 mRNA, thus ultimately promoting NSCLC growth and metastasis.

Tilmicosin/γ-Cyclodextrin complexation through supercritical carbon dioxide assistance and its pharmacokinetic and antibacterial study.

Tilmicosin, as an effective broad-spectrum antibacterial drug, has incomplete absorption and low bioavailability due to its low water solubility, which limits its veterinary clinical applications. As a non-polymeric drug carrier, γ-cyclodextrin was complexed with tilmicosin through supercritical carbon dioxide assistance for the first time, and confirmed by FTIR, X-ray diffraction, proton NMR and scanning electron microscopy. The water solubility of tilmicosin was increased 57-fold through complexation with γ-cyclodextrin, and the release and bioavailability of tilmicosin in the complex were significantly improved. The tilmicosin in complex showed better anti-Streptococcus agalactiae activity than that of tilmicosin alone in MIC, MBC and drug susceptibility studies.

Incremental Value of Radiomics in 5-Year Overall Survival Prediction for Stage II-III Rectal Cancer.

Although rectal cancer comprises up to one-third of colorectal cancer cases and several prognosis nomograms have been established for colon cancer, statistical tools for predicting long-term survival in rectal cancer are lacking. In addition, previous prognostic studies did not include much imaging findings, qualitatively or quantitatively. Therefore, we include multiparametric MRI information from both radiologists' readings and quantitative radiomics signatures to construct a prognostic model that allows 5-year overall survival (OS) prediction for advance-staged rectal cancer patients. The result suggested that the model combined with quantitative imaging findings might outperform that of conventional TNM staging or other clinical prognostic factors. It was noteworthy that the identified radiomics signature consisted of three from dynamic contrast-enhanced (DCE)-MRI, four from anatomical MRI, and one from functional diffusion-weighted imaging (DWI). This highlighted the importance of multiparametric MRI to address the issue of long-term survival estimation in rectal cancer. Additionally, the constructed radiomics signature demonstrated value to the conventional prognostic factors in predicting 5-year OS for stage II-III rectal cancer. The presented nomogram also provides a practical example of individualized prognosis estimation and may potentially impact treatment strategies.

Immunomodulatory functions of the circ_001678/miRNA-326/ZEB1 axis in non-small cell lung cancer via the regulation of PD-1/PD-L1 pathway.

High-throughput circular RNA (circRNA) sequencing identified circRNA_001678 (circ_001678) as an upregulated circRNA in non-small cell lung cancer (NSCLC) tissues. Hence, the current study sought to investigate the function and the underlying mechanism of circRNA_001678 in immune escape of NSCLC. Briefly, commercially purchased NSCLC cell lines were adopted for in vitro experiment to evaluate the effects of circ_001678 over-expression or knockdown on cell biological functions, including proliferation, migration and invasive abilities. In addition, the effects of circ_001678 on the in vivo tumorigenicity ability were evaluated for verification. Accordingly, we uncovered that circ_001678 over-expression augmented NSCLC progression in vitro and enhanced tumorigenicity ability in vivo. The interaction between circ_001678 and miR-326 predicted online was verified by means of luciferase and RNA pull-down assays. Furthermore, circ_001678 could sponge miR-326 to up-regulate ZEB1. On the other hand, the tumor-promoting effects of circ_001678 could be inhibited by anti-PD-L1/PD-1 treatment. Mechanistically, circ_001678 led to the activation of the PD-1/PD-L1 pathway to promote CD8+ T cell apoptosis, thereby inducing NSCLC cell immune escape via regulation of the miR-326/ZEB1 axis. To conclude, our findings revealed that circ_001678 sponges miR-326 to up-regulate ZEB1 expression and induce the PD-1/PD-L1 pathway-dependent immune escape, thereby promoting the malignant progression of NSCLC.

Evaluating the diagnostic value of using metagenomic next-generation sequencing on bronchoalveolar lavage fluid and tissue in infectious pathogens located in the peripheral lung field.

BACKGROUND: Metagenomic next-generation sequencing (mNGS) exerts a vital part in accurately diagnosing pulmonary infection. However, the diagnostic value of different samples obtained by virtual bronchoscopic navigation (VBN) combined with mNGS for pathogen detection in infections located in the peripheral lung field (PLF) is still unclear. METHODS: Patients infected from July 2018 to February of the following year were carefully analyzed and divided into two parts, namely, non-infectious disease group and the infectious disease group. Then bronchial expansion tests were performed for each subject, collected liquid specimens and tissue standards, and conducted regular mNGS and microbiological detection and analysis. The value of mNGS and culture in pathogen detection was compared, at the same time, the performance of tissue mNGS and bronchoalveolar lavage fluid (BALF) mNGS in the diagnosis process was compared. When discrete variables were processed, Pearson χ2 and Fisher's exact test could be used to perform categorical variables analysis. Continuous variables were analyzed and compared by Mann-Whitney U test. RESULTS: After mNGS diagnosis, Acinetobacter baumannii, Pseudomonas aeruginosa and Rothia mucilaginosa were the bacterial species showing the highest abundances. In addition, mNGS achieved the sensitivities in the detection of pathogens in tissues and BALF of 72.9% and 81.4%, respectively, and it is higher than conventional culture. Bacterial diagnostic sensitivity was significantly different between BALF and tissue using mNGS (95.0% vs. 62.5%, P=0.03). The sensitivity and specificity of BALF in detecting fungal infections were not significantly different from those of mNGS. A consistency test showed that these two methods had some degree of consistency (k=0.673, P=0.000). CONCLUSIONS: This study showed that the mNGS in BALF samples and the mNGS in tissue samples which could be used to test for pathogens in the lungs. The sensitivity will increase when mNGS is combined with culture. Also, mNGS of BALF and tissues had some degree of consistency to detect fungal infections, whereas mNGS of BALF had better sensitivity to detect bacterial infection than mNGS of tissues.

Challenge of evolving Klebsiella pneumoniae infection in patients on hemodialysis: from the classic strain to the carbapenem-resistant hypervirulent one.

Loss of renal function may render hemodialysis patients more susceptible to infectious diseases, which is the second of all-causes mortality in this population. In addition to infection caused by the classic Klebsiella pneumoniae (cKp), however, hemodialysis staffs are now facing new challenge with growing prevalence of the carbapenem-resistant Kp (CR-Kp) and hypervirulent Kp (hvKp) as they are respectively associated with increased drug-resistance and virulence. We therefore chose to share our recent experience in treating severe infections either caused (cKp, CR-Kp, hvKp) or complicated (CR-hvKp) by these strains in hemodialysis patients. Based upon yet beyond published works, we further came up with the detection of intracranial lesion, novel diagnostic approach using unique biomarkers followed by selection of appropriate antibiotics, management of metastasic abscesses and bracing for the most lethal scenario in the order of cKp, CR-Kp, hvKp and CR-hvKp, respectively. Since reports of complicated hvKp infection in hemodialysis patients were rare, we also discussed in details this clinical entity focusing on its epidemiology, mechanism of increased virulence and involvement of the arteriovenous fistula as insidious source of persistent septicemia. By covering the full spectrum of clinically relevant Kp stains specifically from the viewpoint of nephrology, our work had highlighted the importance of infection control in uremic state and vice versa. As such, it may greatly raise the awareness of dialysis staffs against the challenge of evolving Klebsiella pneumoniae infection in hemodialysis patients and expeditiously reach a higher degree of readiness which was proved to be the key determinant of ultimate survival.

ALA-Net: Adaptive Lesion-Aware Attention Network for 3D Colorectal Tumor Segmentation.

Accurate and reliable segmentation of colorectal tumors and surrounding colorectal tissues on 3D magnetic resonance images has critical importance in preoperative prediction, staging, and radiotherapy. Previous works simply combine multilevel features without aggregating representative semantic information and without compensating for the loss of spatial information caused by down-sampling. Therefore, they are vulnerable to noise from complex backgrounds and suffer from misclassification and target incompleteness-related failures. In this paper, we address these limitations with a novel adaptive lesion-aware attention network (ALA-Net) which explicitly integrates useful contextual information with spatial details and captures richer feature dependencies based on 3D attention mechanisms. The model comprises two parallel encoding paths. One of these is designed to explore global contextual features and enlarge the receptive field using a recurrent strategy. The other captures sharper object boundaries and the details of small objects that are lost in repeated down-sampling layers. Our lesion-aware attention module adaptively captures long-range semantic dependencies and highlights the most discriminative features, improving semantic consistency and completeness. Furthermore, we introduce a prediction aggregation module to combine multiscale feature maps and to further filter out irrelevant information for precise voxel-wise prediction. Experimental results show that ALA-Net outperforms state-of-the-art methods and inherently generalizes well to other 3D medical images segmentation tasks, providing multiple benefits in terms of target completeness, reduction of false positives, and accurate detection of ambiguous lesion regions.

A clinical-radiomics model incorporating T2-weighted and diffusion-weighted magnetic resonance images predicts the existence of lymphovascular invasion / perineural invasion in patients with colorectal cancer.

PURPOSE: Lymphovascular invasion (LVI) and perineural invasion (PNI) are independent prognostic factors in patients with colorectal cancer (CRC). In this study, we aimed to develop and validate a preoperative predictive model based on high-throughput radiomic features and clinical factors for accurate prediction of LVI/PNI in these patients. METHODS: Two hundred and sixty-three patients who underwent colorectal resection for histologically confirmed CRC between 1 February 2011 and 30 June 2020 were retrospectively enrolled. Between 1 February 2011 and 30 September 2018, 213 patients were randomly divided into a training cohort (n = 149) and a validation cohort (n = 64) by a ratio of 7:3. We used a 10000-iteration bootstrap analysis to estimate the prediction error and confidence interval for two cohorts. The independent test cohort consisted of 50 patients between 1 October 2018 and 30 June 2020. Regions of interest (ROIs) were manually delineated in high-resolution T2-weighted and diffusion-weighted images using ITK-SNAP software on each CRC tumor slice. In total, 3356 radiomic features were extracted from each ROI. Next, we used the maximum relevance minimum redundancy and least absolute shrinkage and selection operator algorithms to select the strongest of these features to establish a clinical-radiomics model for predicting LVI/PNI. Receiver-operating characteristic and calibration curves were then plotted to evaluate the predictive performance of the model in the training, validation, and independent test cohorts. RESULTS: A multiparametric clinical-radiomics model combining MRI-reported extramural vascular invasion (EMVI) status and a Radiomics score for the LVI/PNI estimation was established. This model had significant predictive power in the training cohort (area under the curve [AUC] 0.91; 95% confidence interval [CI]: 0.85-0.97), validation cohort (AUC: 0.88; 95% CI: 0.79-89), and independent test cohorts (AUC 0.83, 95% CI 0.72-0.95). The model performed well in the independent test cohort with sensitivity of 0.818, specificity of 0.714, and accuracy of 0.760. Calibration curve and decision curve analysis demonstrated clinical benefits. CONCLUSION: Multiparametric clinical-radiomics models can accurately predict LVI/PNI in patients with CRC. Our model has predictive ability that should improve preoperative diagnostic performance and allow more individualized treatment decisions.