The positive role of transforming growth factor-ß1 in ischemic stroke.

Ischemic stroke is one of the most disabling and fatal diseases around the world. The damaged brain tissues will undergo excessive autophagy, vascular endothelial cells injury, blood-brain barrier (BBB) impairment and neuroinflammation after ischemic stroke. However, there is no unified viewpoint on the underlying mechanism of brain damage. Transforming growth factor-ß1 (TGF-ß1), as a multi-functional cytokine, plays a crucial role in the intricate pathological processes and helps maintain the physiological homeostasis of brain tissues through various signaling pathways after ischemic stroke. In this review, we summarize the protective role of TGF-ß1 in autophagic flux, BBB, vascular remodeling, neuroinflammation and other aspects after ischemic stroke. Based on the review, we believe that TGF-ß1 could serve as a key target for treating ischemic stroke.

Eco-friendly shrink-resist finishing of wool through synergistic effect of disulfide bond reducing agent and papain.

The environmental benefits of utilizing protease as a biocatalyst for wool shrink-resist finishing have been widely recognized. However, the efficacy of individual protease treatment is unsatisfactory due to its incapability towards the outermost cuticle layer of wool fibers that contains hydrophobic fatty acids. In order to weaken the structural integrity of the highly cross-linked scales and promote the enzymatic anti-felting, sodium sulfite and tris (2-carboxyethyl) phosphine hydrochloride (TCEP) were employed in combination with papain, respectively, aiming at obtaining a low shrinkage without unacceptable fiber damages. Based on the synergistic effect of papain and TCEP, the edges of wool scales were slightly destroyed by the reduction of disulfide bonds, accompanied by enzymatic hydrolysis of the keratin component. Through the controlled reduction and hydrolysis of wool scales, satisfactory anti-felting result was achieved without causing severe damage to the fiber interiors. In the presence of 0.25 g/L TCEP and 25 U/mL papain, the area shrinkage of wool fabric decreased to approximately 6 %, with a low strength loss of less than 8 %. Meanwhile, the dyeing behavior of the wool fabric under low-temperature conditions was dramatically improved, leading to decreased energy consumption during production. The present work provides an alternative for eco-friendly finishing of wool fabrics, which can be applied commercially.

Dual-domain Collaborative Diffusion Sampling for Multi-Source Stationary Computed Tomography Reconstruction.

The multi-source stationary CT, where both the detector and X-ray source are fixed, represents a novel imaging system with high temporal resolution that has garnered significant interest. Limited space within the system restricts the number of X-ray sources, leading to sparse-view CT imaging challenges. Recent diffusion models for reconstructing sparse-view CT have generally focused separately on sinogram or image domains. Sinogram-centric models effectively estimate missing projections but may introduce artifacts, lacking mechanisms to ensure image correctness. Conversely, image-domain models, while capturing detailed image features, often struggle with complex data distribution, leading to inaccuracies in projections. Addressing these issues, the Dual-domain Collaborative Diffusion Sampling (DCDS) model integrates sinogram and image domain diffusion processes for enhanced sparse-view reconstruction. This model combines the strengths of both domains in an optimized mathematical framework. A collaborative diffusion mechanism underpins this model, improving sinogram recovery and image generative capabilities. This mechanism facilitates feedback-driven image generation from the sinogram domain and uses image domain results to complete missing projections. Optimization of the DCDS model is further achieved through the alternative direction iteration method, focusing on data consistency updates. Extensive testing, including numerical simulations, real phantoms, and clinical cardiac datasets, demonstrates the DCDS model's effectiveness. It consistently outperforms various state-of-the-art benchmarks, delivering exceptional reconstruction quality and precise sinogram.

Time-reversion Fast-sampling Score-based Model for Limited-angle CT Reconstruction.

The score-based generative model (SGM) has received significant attention in the field of medical imaging, particularly in the context of limited-angle computed tomography (LACT). Traditional SGM approaches achieved robust reconstruction performance by incorporating a substantial number of sampling steps during the inference phase. However, these established SGM-based methods require large computational cost to reconstruct one case. The main challenge lies in achieving high-quality images with rapid sampling while preserving sharp edges and small features. In this study, we propose an innovative rapid-sampling strategy for SGM, which we have aptly named the time-reversion fast-sampling (TIFA) score-based model for LACT reconstruction. The entire sampling procedure adheres steadfastly to the principles of robust optimization theory and is firmly grounded in a comprehensive mathematical model. TIFA's rapid-sampling mechanism comprises several essential components, including jump sampling, time-reversion with re-sampling, and compressed sampling. In the initial jump sampling stage, multiple sampling steps are bypassed to expedite the attainment of preliminary results. Subsequently, during the time-reversion process, the initial results undergo controlled corruption by introducing small-scale noise. The re-sampling process then diligently refines the initially corrupted results. Finally, compressed sampling fine-tunes the refinement outcomes by imposing regularization term. Quantitative and qualitative assessments conducted on numerical simulations, real physical phantom, and clinical cardiac datasets, unequivocally demonstrate that TIFA method (using 200 steps) outperforms other state-of-the-art methods (using 2000 steps) from available [0°, 90°] and [0°, 60°]. Furthermore, experimental results underscore that our TIFA method continues to reconstruct high-quality images even with 10 steps. Our code at https://github.com/tianzhijiaoziA/TIFADiffusion.

A nomogram for predicting the probability of femoral head collapse in convalescent SARS patients with glucocorticoid-induced osteonecrosis of the femoral head: an 18-year population-based retrospective cohort study.

Background: This study aimed to develop a nomogram capable of predicting the probability of femoral head collapse based on an 18-year follow-up cohort of convalescent severe acute respiratory syndrome (SARS) patients with glucocorticoid-induced osteonecrosis of the femoral head (ONFH). Methods: Data on the natural history of 120 patients (205 hips) who underwent glucocorticoid-induced ONFH at China-Japan Friendship Hospital (CJFH) in 2003 were retrospectively collected. Follow-up was conducted from June 2003 to October 2021. A nomogram was developed in a training cohort and validated in another cohort. Results: A total of 205 hips were included for analysis, with 143 hips in the training cohorts and 62 hips in the validation cohorts. After 18 years of follow-up, 53 femoral heads collapsed, while 152 femoral heads spontaneously repaired to some extent (necrotic areas reduced or vanished). Following multivariate regression analysis, the Association Research Circulation Osseous (ARCO) staging, necrosis index (NI), and CJFH Classification were entered into the nomogram. The nomogram showed robust discrimination, with an AUC of 0.907 (95% CI: 0.85-0.96). The calibration curves showed an agreement between the probability as predicted by the nomogram and the actual probability. Application of the nomogram in the validation cohort also yielded good discrimination (AUC, 0.876, 95% CI: 0.7751-0.9761) and calibration. Conclusion: The nomogram successfully predicted femoral head collapse in glucocorticoid-induced ONFH. With the nomogram, the prognosis for an individual patient with glucocorticoid-induced ONFH can be determined, which can lead to a rational therapeutic choice.

Gram-scale synthesis of small-sized PtM intermetallics as high-performance catalysts for the hydrogen evolution reaction.

Pt-based intermetallics exhibit excellent activity in electrocatalysis. However, their controlled syntheses remain difficult. Herein, carbon-supported PtM (M = Fe, Co, Ni, Zn and Mn) intermetallics with small size (3 nm) were prepared at the gramscale and applied as a highly effective electrocatalyst for the hydrogen evolution reaction.

Electrochemical oxidative decarboxylative of α-oxocarboxylic acids towards the synthesis of quinazolines and quinazolinones.

A mild and environmentally electrochemical method for the synthesis of quinazolines and quinazolinones has been developed through anodic oxidation decarboxylative of α-oxocarboxylic acids. The present reaction was efficiently conducted by using simple and cheap NH4I as the N-source and electrolyte in an undivided cell. The desired products, quinazolines and quinazolinones, were isolated in high yield under chemical oxidant free conditions.

A rationally designed nuclei-targeting FAPI 04-based molecular probe with enhanced tumor uptake for PET/CT and fluorescence imaging.

PURPOSE: Fibroblast activation protein inhibitor (FAPI) -based probes have been widely studied in the diagnosis of various malignant tumors with positron emission tomography/computed tomography (PET/CT). However, current imaging studies of FAPI-based probes face challenges in rapid clearance rate and potential false-negative results. Furthermore, FAPI has been rarely explored in optical imaging. Considering this, further modifications are imperative to improve the properties of FAPI-based probes to address existing limitations and broaden their application scenarios. In this study, we rationally introduced methylene blue (MB) to FAPIs, thereby imparting nuclei-targeting and fluorescence imaging capabilities to the probes. Furthermore, we evaluated the added value of FAPI-based fluorescence imaging to traditional PET/CT, exploring the potential application of FAPI-based probes in intraoperative fluorescence imaging. METHODS: A new FAPI-based probe, namely NOTA-FAPI-MB, was designed for both PET/CT and fluorescence imaging by conjugation of MB. The targeting efficacy of the probe was evaluated on fibroblast activation protein (FAP)-transfected cell line and human primary cancer-associated fibroblasts (CAFs). Subsequently, PET/CT and fluorescence imaging were conducted on tumor-bearing mice. The tumor detection and boundary delineation were assessed by fluorescence imaging of tissues from hepatocellular carcinoma (HCC) patients. RESULTS: NOTA-FAPI-MB demonstrated exceptional targeting ability towards FAP-transfected cells and CAFs in comparison to NOTA-FAPI. This benefit arises from the cationic methylene blue (MB) affinity for anionic nucleic acids. PET/CT imaging of tumor-bearing mice revealed significantly higher tumor uptake of [18F]F-NOTA-FAPI-MB (standard uptake value of 2.20 ± 0.31) compared to [18F]F-FDG (standard uptake value of 1.66 ± 0.14). In vivo fluorescence imaging indicated prolonged retention at the tumor site, with retention lasting up to 24 h. In addition, the fluorescent probes enabled more precise lesion detection and tumor margin delineation than clinically used indocyanine green (ICG), achieving a 100.0% (6/6) tumor-positive rate for NOTA-FAPI-MB while 33.3% (2/6) for ICG. These findings highlighted the potential of NOTA-FAPI-MB in guiding intraoperative surgical procedures. CONCLUSIONS: The NOTA-FAPI-MB was successfully synthesized, in which FAPI and MB simultaneously contributed to the targeting effect. Notably, the nuclear delivery mechanism of the probes improved intracellular retention time and targeting efficacy, broadening the imaging time window for fluorescence imaging. In vivo PET/CT demonstrated favorable performance of NOTA-FAPI-MB compared to [18F]F-FDG. This study highlights the significance of fluorescence imaging as an adjunct technique to PET/CT. Furthermore, the encouraging results obtained from the imaging of human HCC tissues hold promise for the potential application of NOTA-FAPI-MB in intraoperative fluorescent surgery guidance within clinical settings.

Spectrum learning for super-resolution tomographic reconstruction.

Objective. Computed Tomography (CT) has been widely used in industrial high-resolution non-destructive testing. However, it is difficult to obtain high-resolution images for large-scale objects due to their physical limitations. The objective is to develop an improved super-resolution technique that preserves small structures and details while efficiently capturing high-frequency information.Approach. The study proposes a new deep learning based method called spectrum learning (SPEAR) network for CT images super-resolution. This approach leverages both global information in the image domain and high-frequency information in the frequency domain. The SPEAR network is designed to reconstruct high-resolution images from low-resolution inputs by considering not only the main body of the images but also the small structures and other details. The symmetric property of the spectrum is exploited to reduce weight parameters in the frequency domain. Additionally, a spectrum loss is introduced to enforce the preservation of both high-frequency components and global information.Main results. The network is trained using pairs of low-resolution and high-resolution CT images, and it is fine-tuned using additional low-dose and normal-dose CT image pairs. The experimental results demonstrate that the proposed SPEAR network outperforms state-of-the-art networks in terms of image reconstruction quality. The approach successfully preserves high-frequency information and small structures, leading to better results compared to existing methods. The network's ability to generate high-resolution images from low-resolution inputs, even in cases of low-dose CT images, showcases its effectiveness in maintaining image quality.Significance. The proposed SPEAR network's ability to simultaneously capture global information and high-frequency details addresses the limitations of existing methods, resulting in more accurate and informative image reconstructions. This advancement can have substantial implications for various industries and medical diagnoses relying on accurate imaging.

Network Analysis of Borderline Personality Features in Adolescence Using a Screening Tool in a Chinese Community Sample.

INTRODUCTION: This study investigated the structure of the borderline personality features (BPFs) network and the most central BPF in adolescence. METHODS: Cross-sectional self-report data from 4,866 Chinese adolescents (M = 13.96, SD = 1.64; 61.3% girls) were included in the network analysis models. BPFs were assessed with the McLean Screening Instrument for Borderline Personality Disorder. RESULTS: Identity disturbance and affective instability emerged as the most central BPF in the current adolescent sample. In addition, chronic emptiness was also found with high centrality. The general networks of BPF were very similar between adolescent boys and girls, although some differences were detected. DISCUSSION: This study further supports the necessity of BPD assessment and diagnosis in adolescence and identifies the distinctive importance of identity and affective dysregulation in the early development of BPD. The findings provide empirical insights into the interconnections of BPF, which resonate with therapeutic mechanisms of evidence-based treatments for BPD. However, the research was limited in its use of a screening measurement rather than a diagnostic tool. Future studies can further explore BPD psychopathology in adolescence with longitudinal data and clinical interviews.

Two-and-a-half order score-based model for solving 3D ill-posed inverse problems.

Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) are crucial technologies in the field of medical imaging. Score-based models demonstrated effectiveness in addressing different inverse problems encountered in the field of CT and MRI, such as sparse-view CT and fast MRI reconstruction. However, these models face challenges in achieving accurate three dimensional (3D) volumetric reconstruction. The existing score-based models predominantly concentrate on reconstructing two-dimensional (2D) data distributions, resulting in inconsistencies between adjacent slices in the reconstructed 3D volumetric images. To overcome this limitation, we propose a novel two-and-a-half order score-based model (TOSM). During the training phase, our TOSM learns data distributions in 2D space, simplifying the training process compared to working directly on 3D volumes. However, during the reconstruction phase, the TOSM utilizes complementary scores along three directions (sagittal, coronal, and transaxial) to achieve a more precise reconstruction. The development of TOSM is built on robust theoretical principles, ensuring its reliability and efficacy. Through extensive experimentation on large-scale sparse-view CT and fast MRI datasets, our method achieved state-of-the-art (SOTA) results in solving 3D ill-posed inverse problems, averaging a 1.56 dB peak signal-to-noise ratio (PSNR) improvement over existing sparse-view CT reconstruction methods across 29 views and 0.87 dB PSNR improvement over existing fast MRI reconstruction methods with × 2 acceleration. In summary, TOSM significantly addresses the issue of inconsistency in 3D ill-posed problems by modeling the distribution of 3D data rather than 2D distribution which has achieved remarkable results in both CT and MRI reconstruction tasks.

Prediction of Radiation Treatment Response for Locally Advanced Rectal Cancer via a Longitudinal Trend Analysis Framework on Cone-Beam CT.

Locally advanced rectal cancer (LARC) presents a significant challenge in terms of treatment management, particularly with regards to identifying patients who are likely to respond to radiation therapy (RT) at an individualized level. Patients respond to the same radiation treatment course differently due to inter- and intra-patient variability in radiosensitivity. In-room volumetric cone-beam computed tomography (CBCT) is widely used to ensure proper alignment, but also allows us to assess tumor response during the treatment course. In this work, we proposed a longitudinal radiomic trend (LRT) framework for accurate and robust treatment response assessment using daily CBCT scans for early detection of patient response. The LRT framework consists of four modules: (1) Automated registration and evaluation of CBCT scans to planning CT; (2) Feature extraction and normalization; (3) Longitudinal trending analyses; and (4) Feature reduction and model creation. The effectiveness of the framework was validated via leave-one-out cross-validation (LOOCV), using a total of 840 CBCT scans for a retrospective cohort of LARC patients. The trending model demonstrates significant differences between the responder vs. non-responder groups with an Area Under the Curve (AUC) of 0.98, which allows for systematic monitoring and early prediction of patient response during the RT treatment course for potential adaptive management.

Radiomics-clinical nomogram based on pretreatment 18F-FDG PET-CT radiomics features for individualized prediction of local failure in nasopharyngeal carcinoma.

To explore the prognostic significance of PET/CT-based radiomics signatures and clinical features for local recurrence-free survival (LRFS) in nasopharyngeal carcinoma (NPC). We retrospectively reviewed 726 patients who underwent pretreatment PET/CT at our center. Least absolute shrinkage and selection operator (LASSO) regression and the Cox proportional hazards model were applied to construct Rad-score, which represented the radiomics features of PET-CT images. Univariate and multivariate analyses were used to establish a nomogram model. The concordance index (C-index) and calibration curve were used to evaluate the predictive accuracy and discriminative ability. Receiver operating characteristic analysis was performed to stratify the local recurrence risk of patients. The nomogram was validated by evaluating its discrimination ability and calibration in the validation cohort. A total of eight features were selected to construct Rad-score. A radiomics-clinical nomogram was built after the selection of univariate and multivariable Cox regression analyses, including the Rad-score and maximum standardized uptake value (SUVmax). The C-index was 0.71 (0.67-0.74) in the training cohort and 0.70 (0.64-0.76) in the validation cohort. The nomogram also performed far better than the 8th T-staging system with an area under the receiver operating characteristic curve (AUC) of 0.75 vs. 0.60 for 2 years and 0.71 vs. 0.60 for 3 years. The calibration curves show that the nomogram indicated accurate predictions. Decision curve analysis (DCA) revealed significantly better net benefits with this nomogram model. The log-rank test results revealed a distinct difference in prognosis between the two risk groups. The PET/CT-based radiomics nomogram showed good performance in predicting LRFS and showed potential to identify patients at high-risk of developing NPC.

Decarboxylative N-Formylation of Amines with Glyoxylic Acid Promoted by H2O2.

A novel method for the synthesis of formamides through the decarboxylative N-formylation of amines with glyoxylic acid has been developed. This transformation provides an efficient protocol for the synthesis of various formamides with moderate to excellent yields, and it can accommodate a wide range of functional groups under metal free and base free conditions. In addition, the large-scale experiments and high chemoselectivity have shown great potential application of this strategy.

[Expert consensus on clinical drug prevention and treatment of osteonecrosis of the femoral head(2022)].

With the in-depth understanding of osteonecrosis of femoral head (ONFH), and more and more patients seeking medical treatment in the early stage of the disease, surgical treatment of femoral head necrosis alone is no longer sufficient for the current treatment of patients' demand, how to rationally and effectively apply drugs to strengthen the early prevention and treatment of femoral head necrosis and delay the progression of disease is becoming more and more important. This article combines the latest expert consensus and evidence-based medical evidence on the principles of ONFH diagnosis and treatment in Chinese and Western medicine at home and abroad, combined with domestic actual clinical application experience, and is organized by experts from Association Related to Circulation Osseous Chinese Microcirculation Society (CSM-ARCO) to write this consensus, focusing on the types of ONFH drugs, the characteristics, safety, rationality and basic principles of drug use provide reference opinions for the safe, reasonable, standardized and effective drug use of medical institutions at all levels. This consensus is only an expert guideline based on literature and clinical experience, not as a requirement for mandatory implementation, let alone as a legal basis. The clinical practice could be tailored to the actual local conditions to develop appropriate prevention and treatment measures for patients.

Preliminary psychometric properties of the Chinese version of the structured interview of personality organization (STIPO-CH).

BACKGROUND: Kernberg originally proposed the psychoanalytic concept of personality organization (PO), which measures personality pathology from a dimensional approach with multiple scales and can be evaluated using the Structured Interview of Personality Organization (STIPO) from six domains: identity, object relations, primitive defenses, coping vs. rigidity, aggression, and moral values. The present study translated the original version into the Chinese STIPO (STIPO-CH) version and evaluated its reliability and validity. METHODS: The STIPO-CH was administered to 49 non-clinical subjects. They also completed the Chinese version of the Inventory of Personality Organization and the Millon Clinical Multiaxial Inventory to evaluate criterion-related reliability. Interrater reliability was assessed with intraclass correlations. An item analysis was carried out to explore the structure and internal consistency. RESULTS: Interrater reliability (intraclass correlations) ranged from 0.98 to 0.99. Results suggested acceptable internal consistency for identity and moral values. The correlations between STIPO-CH domains and self-report questionnaires indicated that construct validity and criterion-related validity were acceptable to good. CONCLUSIONS: Overall, this study presents preliminary psychometric properties of STIPO-CH. Limitations regarding the sample, interviewers, and cultural differences are discussed. Future research is highly recommended.

The Pathological Mechanism of Neuronal Autophagy-Lysosome Dysfunction After Ischemic Stroke.

The abnormal initiation of autophagy flux in neurons after ischemic stroke caused dysfunction of autophagy-lysosome, which not only led to autophagy flux blockage, but also resulted in autophagic death of neurons. However, the pathological mechanism of neuronal autophagy-lysosome dysfunction did not form a unified viewpoint until now. In this review, taking the autophagy lysosomal dysfunction of neurons as a starting point, we summarized the molecular mechanisms that led to neuronal autophagy lysosomal dysfunction after ischemic stroke, which would provide theoretical basis for the clinical treatment of ischemic stroke.

Retrospective reports of perceived parental invalidation and borderline personality traits: The indirect effect of personality functioning.

This study examined the indirect effect via Criterion A (personality functioning) of the Alternative Model for Personality Disorders (AMPD) in the relationship between retrospective reports of perceived parental invalidation and borderline personality traits measured by Criterion B (pathological personality traits). A total of 3,019 college students completed self-report scales of the Chinese Invalidating Family Scale, Level of Personality Functioning Scale-Brief Form 2.0, and Personality Inventory for DSM-5. It was found that the indirect effect of personality functioning was significant for the association between levels of perceived overall-B = 0.52, 95% CI [0.47, 0.57], maternal-B = 0.83, [0.75, 0.91], and paternal-B = 0.97, [0.87, 1.08] invalidation, and BPD traits. The outcomes of the research suggested the critical role of personality functioning as a potential mediator in the pathological effect of perceived parental invalidation on the development of borderline personality disorder features. While the study is limited by the use of self-report measurement, retrospective responding, and cross-sectional design, significant implications on the biosocial model and AMPD were discussed. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

DT-PICS: An Efficient and Cost-Effective SNP Selection Method for the Germplasm Identification of Arabidopsis.

Germplasm identification is essential for plant breeding and conservation. In this study, we developed a new method, DT-PICS, for efficient and cost-effective SNP selection in germplasm identification. The method, based on the decision tree concept, could efficiently select the most informative SNPs for germplasm identification by recursively partitioning the dataset based on their overall high PIC values, instead of considering individual SNP features. This method reduces redundancy in SNP selection and enhances the efficiency and automation of the selection process. DT-PICS demonstrated significant advantages in both the training and testing datasets and exhibited good performance on independent prediction, which validates its effectiveness. Thirteen simplified SNP sets were extracted from 749,636 SNPs in 1135 Arabidopsis varieties resequencing datasets, including a total of 769 DT-PICS SNPs, with an average of 59 SNPs per set. Each simplified SNP set could distinguish between the 1135 Arabidopsis varieties. Simulations demonstrated that using a combination of two simplified SNP sets for identification can effectively increase the fault tolerance in independent validation. In the testing dataset, two potentially mislabeled varieties (ICE169 and Star-8) were identified. For 68 same-named varieties, the identification process achieved 94.97% accuracy and only 30 shared markers on average; for 12 different-named varieties, the germplasm to be tested could be effectively distinguished from 1,134 other varieties while grouping extremely similar varieties (Col-0) together, reflecting their actual genetic relatedness. The results suggest that the DT-PICS provides an efficient and accurate approach to SNP selection in germplasm identification and management, offering strong support for future plant breeding and conservation efforts.

The Efficacy of Pretreatment 18F-FDG PET-CT-Based Deep Learning Network Structure to Predict Survival in Nasopharyngeal Carcinoma.

Background: Previous studies have shown that the 5-year survival rates of patients with nasopharyngeal carcinoma (NPC) were still not ideal despite great improvement in NPC treatments. To achieve individualized treatment of NPC, we have been looking for novel models to predict the prognosis of patients with NPC. The objective of this study was to use a novel deep learning network structural model to predict the prognosis of patients with NPC and to compare it with the traditional PET-CT model combining metabolic parameters and clinical factors. Methods: A total of 173 patients were admitted to 2 institutions between July 2014 and April 2020 for the retrospective study; each received a PET-CT scan before treatment. The least absolute shrinkage and selection operator (LASSO) was employed to select some features, including SUVpeak-P, T3, age, stage II, MTV-P, N1, stage III and pathological type, which were associated with overall survival (OS) of patients. We constructed 2 survival prediction models: an improved optimized adaptive multimodal task (a 3D Coordinate Attention Convolutional Autoencoder and an uncertainty-based jointly Optimizing Cox Model, CACA-UOCM for short) and a clinical model. The predictive power of these models was assessed using the Harrell Consistency Index (C index). Overall survival of patients with NPC was compared by Kaplan-Meier and Log-rank tests. Results: The results showed that CACA-UOCM model could estimate OS (C index, 0.779 for training, 0.774 for validation, and 0.819 for testing) and divide patients into low and high mortality risk groups, which were significantly associated with OS (P < .001). However, the C-index of the model based only on clinical variables was only 0.42. Conclusions: The deep learning network model based on 18F-FDG PET/CT can serve as a reliable and powerful predictive tool for NPC and provide therapeutic strategies for individual treatment.