Total-Body PET/CT: A Role of Artificial Intelligence?

The purpose of this paper is to provide an overview of the cutting-edge applications of artificial intelligence (AI) technology in total-body positron emission tomography/computed tomography (PET/CT) scanning technology and its profound impact on the field of medical imaging. The introduction of total-body PET/CT scanners marked a major breakthrough in medical imaging, as their superior sensitivity and ultralong axial fields of view allowed for high-quality PET images of the entire body to be obtained in a single scan, greatly enhancing the efficiency and accuracy of diagnoses. However, this advancement is accompanied by the challenges of increasing data volumes and data complexity levels, which pose severe challenges for traditional image processing and analysis methods. Given the excellent ability of AI technology to process massive and high-dimensional data, the combination of AI technology and ultrasensitive PET/CT can be considered a complementary match, opening a new path for rapidly improving the efficiency of the PET-based medical diagnosis process. Recently, AI technology has demonstrated extraordinary potential in several key areas related to total-body PET/CT, including radiation dose reductions, dynamic parametric imaging refinements, quantitative analysis accuracy improvements, and significant image quality enhancements. The accelerated adoption of AI in clinical practice is of particular interest and is directly driven by the rapid progress made by AI technologies in terms of interpretability; i.e., the decision-making processes of algorithms and models have become more transparent and understandable. In the future, we believe that AI technology will fundamentally reshape the use of PET/CT, not only playing a more critical role in clinical diagnoses but also facilitating the customization and implementation of personalized healthcare solutions, providing patients with safer, more accurate, and more efficient healthcare experiences.

Chronic thyrotoxic myopathy development is associated with thyroid hormone sensitivity index, predicted by lower-limb fatigue and the squat-up test.

Thyroid hormones (THs) may affect chronic thyrotoxic myopathy (CTM). The relationship between TH sensitivity and CTM is inconsistent. We aimed to investigate the associations between TH sensitivity and the risk of CTM and to screen potential CTMs with strength and function tests. A total of 162 Chinese patients (36.58% men) with Graves' disease were enrolled and divided into CTM and non-CTM groups. TH and sensitivity indices were measured. Muscle power and function were assessed by grip, upper-limb fatigue (ULFT), lower-limb fatigue (LLFT), and squat-up (SUT) tests, and walking pace. Association between sensitivity to TH indices and the risk of developing CTM was assessed via multivariate logistic regression. The diagnostic effectiveness of muscle power and function for predicting CTM was evaluated via receiver operating characteristic (ROC) curves. Thyroid feedback quantile-based index FT3 (TFQIFT3) and the parametric TFQIFT3 (PTFQIFT3), TFQIFT4, and PTFQIFT4 were positively associated with CTM risk by using inverse probability of treatment weighting multivariate logistic regression. For each 1-SD increase in TFQIFT3 and PTFQIFT3, TFQIFT4 and PTFQIFT4, the odds ratios for CTM were 1.67 (95% CI = 1.17-2.48) ,1.64 (95% CI = 1.51-2.93), 1.60 (95%CI = 1.12-2.32), 1.58 (95%CI = 1.11-2.30), respectively. LLFT and SUT best predicted male/female CTM, respectively (AUC = 0.89/0.85). In Graves' disease patients, TH sensitivity is associated with CTM development, which can be predicted by SUT and LLFT results.

Efficacy and safety of henagliflozin combined with continuous subcutaneous insulin infusion in the treatment of Chinese inpatients with type 2 diabetes mellitus based on a continuous glucose monitoring system: protocol of a multicentre, open-label, inpatient, randomised, controlled trial.

INTRODUCTION: The role of sodium-glucose cotransporter 2 inhibitors (SGLT2is) in diabetes treatment is expanding; however, few studies have investigated the efficacy and safety of combining SGLT2is with insulin pump therapy. Notably, there is a scarcity of high-quality, multicentre, clinical trials. Therefore, we aim to conduct a prospective multicentre, randomised, controlled, study to investigate whether treatment of type 2 diabetes patients with continuous subcutaneous insulin infusion (CSII) combined with henagliflozin can reduce the time required for blood glucose control, decrease total insulin requirements, mitigate blood glucose fluctuations and enhance beta-cell function. METHODS AND ANALYSIS: In this inpatient, open-label, multicentre, randomised, controlled trial, 200 patients with type 2 diabetes who have not received hypoglycaemic drugs will be randomly allocated at a 1:1 ratio to either the henagliflozin combined with CSII group or the CSII group. The efficacy and safety of treatment in both groups will be compared. We will use a real-time continuous glucose monitoring system for blood glucose monitoring. The primary aim of this study is to compare the time (% time in range (TIR)) in the range of 3.9~10.0 mmol/L blood glucose between the two treatment groups. The secondary outcome measures will include comparisons of the two treatment groups with respect to the (a) time at TIR >70%; (b) mean amplitude of glycaemic excursions; (c) time below range; (d) total insulin dosage; and (e) time above range. ETHICS AND DISSEMINATION: This study was approved by the Ethics Committee of the First Affiliated Hospital of Guangxi Medical University and is to be conducted in accordance with the Declaration of Helsinki and Good Clinical Practice. The study will be disseminated through peer-reviewed publications and conference presentations. TRIAL REGISTRATION NUMBER: NCT05677334.

Exploring the mechanism of comorbidity in patients with T1DM and COVID-19: Integrating bioinformatics and Mendelian randomization methods.

During the coronavirus disease 2019 (COVID-19) pandemic, the incidence of type 1 diabetes mellitus (T1DM) has increased. Additionally, evidence suggests that individuals with diabetes mellitus may have increased susceptibility to severe acute respiratory syndrome coronavirus 2 infection. However, the specific causal relationships and interaction mechanisms between T1DM and COVID-19 remain unclear. This study aims to investigate the causal relationship between T1DM and COVID-19, utilizing differential gene expression and Mendelian randomization analyses. Differentially expressed gene sets from datasets GSE156035 and GSE171110 were intersected to identify shared genes, analyzed for functional enrichment. Mendelian randomization models were employed to assess causal effects, revealing no direct causal link between T1DM and COVID-19 in the European population (P > .05). Notably, DNA replication and sister chromatid cohesion 1 (DSCC1) showed negative causal associations with both diseases (T1DM: OR = 0.943, 95% CI: 0.898-0.991, P = .020; COVID-19: OR = 0.919, 95% CI: 0.882-0.958, P < .001), suggesting a protective effect against their comorbidity. This genetic evidence highlights DSCC1 as a potential target for monitoring and managing the co-occurrence of T1DM and COVID-19.

Risk analysis of postoperative nausea and vomiting in patients after gynecologic laparoscopic surgery.

AIMS: This study is designed to identify risk factors of postoperative nausea and vomiting (PONV) in patients after gynecologic laparoscopic surgery and establish a nomogram model. METHODS: In this retrospective and multicenter study, we collected and analyzed data from 1233 patients who underwent gynecologic laparoscopic surgery. The Lasso algorithm was used to optimize the selection of independent variables in the development group. Multivariate logistic regression analysis was used to explore the risk factors of PONV to develop the predictive nomogram model. Finally, we used an internal and external verification group and machine learning (ML) to evaluate the accuracy and clinical applicability of the model. RESULTS: The dosage of sufentanil in patient-controlled intravenous analgesia (PCIA), the dosage of remifentanil, the use of neostigmine, duration of surgery and the maximum value of the PETCO2 were risk factors of PONV in patients after gynecologic laparoscopic surgery. In contrast, the dosage of propofol during the surgery and the use of steroids were protective factors. The nomogram was then established to predict the incidence of PONV in these patients based on the above eight indicators. The C-index of the development group, internal, and external verification groups are 0.802, 0.857, and 0.966, respectively. CONCLUSION: A nomogram model was developed to predict the incidence of PONV in patients after gynecologic laparoscopic surgery. This model was found to be reliable and of high clinical value.

Accurate brain pharmacokinetic parametric imaging using the blood input function extracted from the cavernous sinus.

Brain pharmacokinetic parametric imaging based on dynamic positron emission tomography (PET) scan is valuable in the diagnosis of brain tumor and neurodegenerative diseases. For short-axis PET system, standard blood input function (BIF) of the descending aorta is not acquirable during the dynamic brain scan. BIF extracted from the intracerebral vascular is inaccurate, making the brain parametric imaging task challenging. This study introduces a novel technique tailored for brain pharmacokinetic parameter imaging in short-axis PET in which the head BIF (hBIF) is acquired from the cavernous sinus. The proposed method optimizes the hBIF within the Patlak model via data fitting, curve correction and Patlak graphical model rewriting. The proposed method was built and evaluated using dynamic PET datasets of 67 patients acquired by uEXPLORER PET/CT, among which 64 datasets were used for data fitting and model construction, and 3 were used for method testing; using cross-validation, a total of 15 patient datasets were finally used to test the model. The performance of the new method was evaluated via visual inspection, root-mean-square error (RMSE) measurements and VOI-based accuracy analysis using linear regression and Person's correlation coefficients (PCC). Compared to directly using the cavernous sinus BIF directly for parameter imaging, the new method achieves higher accuracy in parametric analysis, including the generation of Patlak plots closer to the standard plots, better visual effects and lower RMSE values in the Ki (P = 0.0012) and V (P = 0.0042) images. VOI-based analysis shows regression lines with slopes closer to 1 (P = 0.0019 for Ki ) and smaller intercepts (P = 0.0085 for V). The proposed method is capable of achieving accurate brain pharmacokinetic parametric imaging using cavernous sinus BIF with short-axis PET scan. This may facilitate the application of this imaging technology in the clinical diagnosis of brain diseases.

Multimodal radiomics-based methods using deep learning for prediction of brain metastasis in non-small cell lung cancer with18F-FDG PET/CT images.

Objective. Approximately 57% of non-small cell lung cancer (NSCLC) patients face a 20% risk of brain metastases (BMs). The delivery of drugs to the central nervous system is challenging because of the blood-brain barrier, leading to a relatively poor prognosis for patients with BMs. Therefore, early detection and treatment of BMs are highly important for improving patient prognosis. This study aimed to investigate the feasibility of a multimodal radiomics-based method using 3D neural networks trained on18F-FDG PET/CT images to predict BMs in NSCLC patients.Approach. We included 226 NSCLC patients who underwent18F-FDG PET/CT scans of areas, including the lung and brain, prior to EGFR-TKI therapy. Moreover, clinical data (age, sex, stage, etc) were collected and analyzed. Shallow lung features and deep lung-brain features were extracted using PyRadiomics and 3D neural networks, respectively. A support vector machine (SVM) was used to predict BMs. The receiver operating characteristic (ROC) curve and F1 score were used to assess BM prediction performance.Main result. The combination of shallow lung and shallow-deep lung-brain features demonstrated superior predictive performance (AUC = 0.96 ± 0.01). Shallow-deep lung-brain features exhibited strong significance (P < 0.001) and potential predictive performance (coefficient > 0.8). Moreover, BM prediction by age was significant (P < 0.05).Significance. Our approach enables the quantitative assessment of medical images and a deeper understanding of both superficial and deep tumor characteristics. This noninvasive method has the potential to identify BM-related features with statistical significance, thereby aiding in the development of targeted treatment plans for NSCLC patients.

Fusion of shallow and deep features from 18F-FDG PET/CT for predicting EGFR-sensitizing mutations in non-small cell lung cancer.

Background: Non-small cell lung cancer (NSCLC) patients with epidermal growth factor receptor-sensitizing (EGFR-sensitizing) mutations exhibit a positive response to tyrosine kinase inhibitors (TKIs). Given the limitations of current clinical predictive methods, it is critical to explore radiomics-based approaches. In this study, we leveraged deep-learning technology with multimodal radiomics data to more accurately predict EGFR-sensitizing mutations. Methods: A total of 202 patients who underwent both flourine-18 fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) scans and EGFR sequencing prior to treatment were included in this study. Deep and shallow features were extracted by a residual neural network and the Python package PyRadiomics, respectively. We used least absolute shrinkage and selection operator (LASSO) regression to select predictive features and applied a support vector machine (SVM) to classify the EGFR-sensitive patients. Moreover, we compared predictive performance across different deep models and imaging modalities. Results: In the classification of EGFR-sensitive mutations, the areas under the curve (AUCs) of ResNet-based deep-shallow features and only shallow features from different multidata were as follows: RES_TRAD, PET/CT vs. CT-only vs. PET-only: 0.94 vs. 0.89 vs. 0.92; and ONLY_TRAD, PET/CT vs. CT-only vs. PET-only: 0.68 vs. 0.50 vs. 0.38. Additionally, the receiver operating characteristic (ROC) curves of the model using both deep and shallow features were significantly different from those of the model built using only shallow features (P<0.05). Conclusions: Our findings suggest that deep features significantly enhance the detection of EGFR-sensitizing mutations, especially those extracted with ResNet. Moreover, PET/CT images are more effective than CT-only and PET-only images in producing EGFR-sensitizing mutation-related signatures.

Thyroid dysfunction and risk of different types of dementia: A systematic review and meta-analysis.

BACKGROUND: The impact of thyroid function on the risk of various types of dementia, including Alzheimer's disease (AD) and vascular dementia (VD), remains unclear. This meta-analysis investigates the association between thyroid dysfunction and the risk of these dementia types, aiming to inform strategies for dementia prevention. METHODS: A comprehensive search was conducted in PubMed, Embase, and the Cochrane Library for studies published up to February 2023, focusing on the risk of thyroid dysfunction in dementia. We excluded duplicates, studies without full text, those with incomplete data, animal studies, case reports, and reviews. Data analysis was performed using STATA 15.1 software. RESULTS: Our analysis indicated that overt hyperthyroidism significantly increases the risk of all studied dementia types (OR = 1.18, 95% CI: 1.04-1.35). In contrast, overt hypothyroidism was associated with a decreased risk of AD (OR = 0.73, 95% CI: 0.55-0.98) and VD (OR = 0.71, 95% CI: 0.62-0.82). Subclinical hyperthyroidism also showed a significant association with an increased risk of any dementia (OR = 1.26, 95% CI: 1.09-1.46) and specifically VD (OR = 6.70; 95% CI: 1.38-32.58). CONCLUSION: This study suggests that overt hypothyroidism may reduce the risk of dementia, including AD and VD, whereas overt and subclinical hyperthyroidism are linked to an increased risk. These findings highlight the importance of monitoring thyroid function as a preventative measure against dementia.

Deep learning for intracranial aneurysm segmentation using CT angiography.

Objective.This study aimed to employ a two-stage deep learning method to accurately detect small aneurysms (4-10 mm in size) in computed tomography angiography images.Approach.This study included 956 patients from 6 hospitals and a public dataset obtained with 6 CT scanners from different manufacturers. The proposed method consists of two components: a lightweight and fast head region selection (HRS) algorithm and an adaptive 3D nnU-Net network, which is used as the main architecture for segmenting aneurysms. Segments generated by the deep neural network were compared with expert-generated manual segmentation results and assessed using Dice scores.MainResults.The area under the curve (AUC) exceeded 79% across all datasets. In particular, the precision and AUC reached 85.2% and 87.6%, respectively, on certain datasets. The experimental results demonstrated the promising performance of this approach, which reduced the inference time by more than 50% compared to direct inference without HRS.Significance.Compared with a model without HRS, the deep learning approach we developed can accurately segment aneurysms by automatically localizing brain regions and can accelerate aneurysm inference by more than 50%.

Rare correlation of somatic PRKACA mutations with pregnancy-associated aldosterone- and cortisol-producing adenomas: a case report and literature review.

BACKGROUND: Somatic mutations have been observed to induce aldosterone-producing adenomas (APAs). These may be accelerated during pregnancy. Somatic PRKACA mutations are common in cortisol-producing adenomas (CPAs). However, their role in APAs, particularly aldosterone- and cortisol-producing adenomas (A/CPAs), is not well understood. This study aims to investigate the association between PRKACA mutations and the accelerated development of A/CPAs during pregnancy. CASE PRESENTATION: A patient with primary aldosteronism (PA) associated with severe Cushing's syndrome (CS) underwent surgical resection of an adrenal tumor one year after delivery. Pathologic examination revealed an adrenocortical adenoma characterized primarily by zona glomerulosa hyperplasia. Somatic mutation analysis revealed the presence of the somatic PRKACA mutation, which was validated as a deleterious mutation by various computational databases. Immunohistochemical results showed positive staining for cytochrome P450 family 11 subfamily B member 1 (CYP11B1), cytochrome P450 family 11 subfamily B member 2 (CYP11B2), and luteinizing hormone/chorionic gonadotropin receptor (LHCGR). Our study included a review of 20 previously documented cases of aldosterone- and cortisol-producing adenomas (A/CPAs), two of which were concurrently positive for both CYP11B1 and CYP11B2, consistent with our findings. CONCLUSION: Somatic mutations in PRKACA may correlate with the upregulation of LHCGR, which synergistically drives the accelerated growth of co-secretion tumors during pregnancy, thereby exacerbating disease progression.

Pulsatile gonadotropin releasing hormone therapy for spermatogenesis in congenital hypogonadotropic hypogonadism patients who had poor response to combined gonadotropin therapy.

Objective: Both pulsatile gonadotropin-releasing hormone (GnRH) and combined gonadotropin therapy are effective to induce spermatogenesis in men with congenital hypogonadotropic hypogonadism (CHH). This study aimed to evaluate the effect of pulsatile GnRH therapy on spermatogenesis in male patients with CHH who had poor response to combined gonadotropin therapy. Materials and methods: Patients who had poor response to combined gonadotropin therapy ≥ 6 months were recruited and shifted to pulsatile GnRH therapy. The rate of successful spermatogenesis, the median time to achieve spermatogenesis, serum gonadotropins, testosterone, and testicular volume were used for data analysis. Results: A total of 28 CHH patients who had poor response to combined gonadotropin (HCG/HMG) therapy for 12.5 (6.0, 17.75) months were recruited and switched to pulsatile GnRH therapy for 10.0 (7.25, 16.0) months. Sperm was detected in 17/28 patients (60.7%). The mean time for the appearance of sperm in semen was 12.0 (7.5, 17.5) months. Compared to those who could not achieve spermatogenesis during pulsatile GnRH therapy, the successful group had a higher level of LH60min (4.32 vs. 1.10 IU/L, P = 0.043) and FSH60min (4.28 vs. 1.90 IU/L, P = 0.021). Testicular size increased during pulsatile GnRH therapy, compared to previous HCG/ HMG therapy (P < 0.05). Conclusion: For CHH patients with prior poor response to one year of HCG/ HMG therapy, switching to pulsatile GnRH therapy may induce spermatogenesis.

MMCA-NET: A Multimodal Cross Attention Transformer Network for Nasopharyngeal Carcinoma Tumor Segmentation Based on a Total-Body PET/CT System.

Nasopharyngeal carcinoma (NPC) is a malignant tumor primarily treated by radiotherapy. Accurate delineation of the target tumor is essential for improving the effectiveness of radiotherapy. However, the segmentation performance of current models is unsatisfactory due to poor boundaries, large-scale tumor volume variation, and the labor-intensive nature of manual delineation for radiotherapy. In this paper, MMCA-Net, a novel segmentation network for NPC using PET/CT images that incorporates an innovative multimodal cross attention transformer (MCA-Transformer) and a modified U-Net architecture, is introduced to enhance modal fusion by leveraging cross-attention mechanisms between CT and PET data. Our method, tested against ten algorithms via fivefold cross-validation on samples from Sun Yat-sen University Cancer Center and the public HECKTOR dataset, consistently topped all four evaluation metrics with average Dice similarity coefficients of 0.815 and 0.7944, respectively. Furthermore, ablation experiments were conducted to demonstrate the superiority of our method over multiple baseline and variant techniques. The proposed method has promising potential for application in other tasks.

Accurate Whole-Brain Image Enhancement for Low-Dose Integrated PET/MR Imaging Through Spatial Brain Transformation.

Positron emission tomography/magnetic resonance imaging (PET/MRI) systems can provide precise anatomical and functional information with exceptional sensitivity and accuracy for neurological disorder detection. Nevertheless, the radiation exposure risks and economic costs of radiopharmaceuticals may pose significant burdens on patients. To mitigate image quality degradation during low-dose PET imaging, we proposed a novel 3D network equipped with a spatial brain transform (SBF) module for low-dose whole-brain PET and MR images to synthesize high-quality PET images. The FreeSurfer toolkit was applied to derive the spatial brain anatomical alignment information, which was then fused with low-dose PET and MR features through the SBF module. Moreover, several deep learning methods were employed as comparison measures to evaluate the model performance, with the peak signal-to-noise ratio (PSNR), structural similarity (SSIM) and Pearson correlation coefficient (PCC) serving as quantitative metrics. Both the visual results and quantitative results illustrated the effectiveness of our approach. The obtained PSNR and SSIM were 41.96 ± 4.91 dB (p < 0.01) and 0.9654 ± 0.0215 (p < 0.01), which achieved a 19% and 20% improvement, respectively, compared to the original low-dose brain PET images. The volume of interest (VOI) analysis of brain regions such as the left thalamus (PCC = 0.959) also showed that the proposed method could achieve a more accurate standardized uptake value (SUV) distribution while preserving the details of brain structures. In future works, we hope to apply our method to other multimodal systems, such as PET/CT, to assist clinical brain disease diagnosis and treatment.

WTAP-induced N6-methyladenosine of PD-L1 blocked T-cell-mediated antitumor activity under hypoxia in colorectal cancer.

N6-Methyladenosine (m6A) is a important process regulating gene expression post-transcriptionally. Programmed death ligand 1 (PD-L1) is a major immune inhibitive checkpoint that facilitates immune evasion and is expressed in tumor cells. In this research we discovered that Wilms' tumor 1-associated protein (WTAP) degradation caused by ubiquitin-mediated cleavage in cancer cells (colorectal cancer, CRC) under hypoxia was inhibited by Pumilio homolog 1 (PUM1) directly bound to WTAP. WTAP enhanced PD-L1 expression in a way that was m6A-dependent. m6A "reader," Insulin-like growth factor 2 mRNA-binding protein 2 (IGF2BP2) identified methylated PD-L1 transcripts and subsequently fixed its mRNA. Additionally, we found that T-cell proliferation and its cancer cell-killing effects were prevented by overexpression of WTAP in vitro and in vivo. Overexpression prevented T cells from proliferating and killing CRC by maintaining the expression of PD-L1. Further evidence supporting the WTAP-PD-L1 regulatory axis was found in human CRC and organoid tissues. Tumors with high WTAP levels appeared more responsive to anti-PD1 immunotherapy, when analyzing samples from patients undergoing treatment. Overall, our findings demonstrated a novel PD-L1 regulatory mechanism by WTAP-induced mRNA epigenetic regulation and the possible application of targeting WTAP as immunotherapy for tumor hypoxia.

In-situ methane enrichment in anaerobic digestion of food waste slurry by nano zero-valent iron: Long-term performance and microbial community succession.

In this work, nano zero-valent iron (nZVI) was added to a lab-scale continuous stirring tank reactor (CSTR) for food waste slurry treatment, and the effect of dosing rate and dosage of nZVI were attempted to be changed. The results showed that anaerobic digestion (AD) efficiency and biomethanation stability were optimum under the daily dosing and dosage of 0.48 g/gTCOD. The average daily methane (CH4) yield reached 495.38 mL/gTCOD, which was 43.65% higher than that at control stage, and the maximum CH4 content reached 95%. However, under single dosing rate conditions, high nZVI concentrations caused microbial cell rupture and loosely bound extracellular polymeric substances (LB-EPS) precipitation degradation. The daily dosing rate promoted the hydrogenotrophic methanogenesis pathway, and the activity of coenzyme F420 increased by 400.29%. The microbial analysis indicated that daily addition of nZVI could promote the growth of acid-producing bacteria (Firmicutes and Bacteroidetes) and methanogens (Methanothrix).

Volatile fatty acids production from kitchen waste slurry using anaerobic membrane bioreactor via alkaline fermentation with high salinity: Evaluation on process performance and microbial succession.

In this study, a pilot-scale anaerobic membrane bioreactor (AnMBR) was developed to continuously produce volatile fatty acids (VFAs) from kitchen waste slurry under an alkaline condition. The alkaline fermentation effectively suppressed methanogenesis, thus achieving high VFAs production of 60.3 g/L. Acetic acid, propionic acid, and butyric acid accounted for over 95.0 % of the total VFAs. The VFAs yield, productivity, and chemical oxygen demand (COD) recovery efficiency reached 0.5 g/g-CODinfluent, 6.0 kg/m3/d, and 62.8 %, respectively. Moreover, the CODVFAs/CODeffluent ratio exceeded 96.0 %, and the CODVFAs/NH3-N ratio through ammonia distillation reached up to 192.5. The microbial community was reshaped during the alkaline fermentation with increasing salinity. The membrane fouling of the AnMBR was alleviated by chemical cleaning and sludge discharge, and membrane modules displayed a sustained filtration performance. In conclusion, this study demonstrated that high-quality VFAs could be efficiently produced from kitchen waste slurry using an AnMBR process via alkaline fermentation.

Learning CT-free attenuation-corrected total-body PET images through deep learning.

OBJECTIVES: Total-body PET/CT scanners with long axial fields of view have enabled unprecedented image quality and quantitative accuracy. However, the ionizing radiation from CT is a major issue in PET imaging, which is more evident with reduced radiopharmaceutical doses in total-body PET/CT. Therefore, we attempted to generate CT-free attenuation-corrected (CTF-AC) total-body PET images through deep learning. METHODS: Based on total-body PET data from 122 subjects (29 females and 93 males), a well-established cycle-consistent generative adversarial network (Cycle-GAN) was employed to generate CTF-AC total-body PET images directly while introducing site structures as prior information. Statistical analyses, including Pearson correlation coefficient (PCC) and t-tests, were utilized for the correlation measurements. RESULTS: The generated CTF-AC total-body PET images closely resembled real AC PET images, showing reduced noise and good contrast in different tissue structures. The obtained peak signal-to-noise ratio and structural similarity index measure values were 36.92 ± 5.49 dB (p < 0.01) and 0.980 ± 0.041 (p < 0.01), respectively. Furthermore, the standardized uptake value (SUV) distribution was consistent with that of real AC PET images. CONCLUSION: Our approach could directly generate CTF-AC total-body PET images, greatly reducing the radiation risk to patients from redundant anatomical examinations. Moreover, the model was validated based on a multidose-level NAC-AC PET dataset, demonstrating the potential of our method for low-dose PET attenuation correction. In future work, we will attempt to validate the proposed method with total-body PET/CT systems in more clinical practices. CLINICAL RELEVANCE STATEMENT: The ionizing radiation from CT is a major issue in PET imaging, which is more evident with reduced radiopharmaceutical doses in total-body PET/CT. Our CT-free PET attenuation correction method would be beneficial for a wide range of patient populations, especially for pediatric examinations and patients who need multiple scans or who require long-term follow-up. KEY POINTS: • CT is the main source of radiation in PET/CT imaging, especially for total-body PET/CT devices, and reduced radiopharmaceutical doses make the radiation burden from CT more obvious. • The CT-free PET attenuation correction method would be beneficial for patients who need multiple scans or long-term follow-up by reducing additional radiation from redundant anatomical examinations. • The proposed method could directly generate CT-free attenuation-corrected (CTF-AC) total-body PET images, which is beneficial for PET/MRI or PET-only devices lacking CT image poses.

Few-shot segmentation framework for lung nodules via an optimized active contour model.

BACKGROUND: Accurate segmentation of lung nodules is crucial for the early diagnosis and treatment of lung cancer in clinical practice. However, the similarity between lung nodules and surrounding tissues has made their segmentation a longstanding challenge. PURPOSE: Existing deep learning and active contour models each have their limitations. This paper aims to integrate the strengths of both approaches while mitigating their respective shortcomings. METHODS: In this paper, we propose a few-shot segmentation framework that combines a deep neural network with an active contour model. We introduce heat kernel convolutions and high-order total variation into the active contour model and solve the challenging nonsmooth optimization problem using the alternating direction method of multipliers. Additionally, we use the presegmentation results obtained from training a deep neural network on a small sample set as the initial contours for our optimized active contour model, addressing the difficulty of manually setting the initial contours. RESULTS: We compared our proposed method with state-of-the-art methods for segmentation effectiveness using clinical computed tomography (CT) images acquired from two different hospitals and the publicly available LIDC dataset. The results demonstrate that our proposed method achieved outstanding segmentation performance according to both visual and quantitative indicators. CONCLUSION: Our approach utilizes the output of few-shot network training as prior information, avoiding the need to select the initial contour in the active contour model. Additionally, it provides mathematical interpretability to the deep learning, reducing its dependency on the quantity of training samples.

The potential causal association between systemic lupus erythematosus and endocrine and metabolic disorders in the East Asian population: A bidirectional two-sample Mendelian randomization study.

OBJECTIVES: Observational studies indicate a significant correlation between systemic lupus erythematosus (SLE) and endocrine and metabolic disorders, but the causal association between SLE and endocrine and metabolic disorders remains unclear due to the reverse causality and confounding biases commonly presented in conventional observational research. This study endeavors to uncover the causal association between SLE and three common endocrine and metabolic disorders, including Graves' disease (GD), type 2 diabetes mellitus (T2DM), and osteoporosis (OP). METHODS: We used genome-wide association study data for SLE and three endocrine and metabolic disorders in an East Asian population, employing bidirectional two-sample Mendelian randomization (MR) analysis and sensitivity analysis to ascertain the causal association between SLE and endocrine and metabolic disorders. RESULTS: A multiplicative random-effect inverse-variance weighted approach revealed a significant positive correlation between SLE and an elevated risk of GD with an odds ratio (OR) of 1.12 (95% CI: 1.04-1.22, p < .01), and inverse-variance weighted (IVW) analysis also indicated that SLE increased the risk of OP with an OR of 1.035 (95% CI: 1.003-1.068, p < .05). Additionally, GD causally affected SLE in an IVW analysis after Bonferroni correction, with an OR of 1.33 (95% CI: 1.19-1.49, p < .05/3), but the application of multivariable MR analysis resulted in the absence of a causal association of GD on SLE (OR 1.047, 95% CI: 0.952-1.151, p > .05). Lastly, the robustness and validity of the findings were verified through a sensitivity analysis. CONCLUSIONS: We confirmed that SLE has a causal effect on GD as well as OP, but no evidence exists to substantiate a causal link between SLE and T2DM. Our study offers valuable contributions for uncovering the etiology of SLE and endocrine and metabolic disorders and furthering disease risk research while providing potential targets for disease monitoring and therapeutic intervention.