ABSTRACT
INTRODUCTION: Abdominal adipose tissue (AT) mass has adverse effects on the brain. This study aimed to investigate the effect of glucose uptake by abdominal AT on brain aging. METHODS: Three-hundred twenty-five participants underwent total-body positron emission tomography scan. Brain age was estimated in an independent test set (n = 98) using a support vector regression model that was built using a training set (n = 227). Effects of abdominal subcutaneous and visceral AT (SAT/VAT) glucose uptake on brain age delta were evaluated using linear regression. RESULTS: Higher VAT glucose uptake was linked to negative brain age delta across all subgroups. Higher SAT glucose uptake was associated with negative brain age delta in lean individuals. In contrast, increased SAT glucose uptake demonstrated positive trends with brain age delta in female and overweight/obese participants. DISCUSSION: Increased glucose uptake of the abdominal VAT has positive influences on the brain, while SAT may not have such influences, except for lean individuals. HIGHLIGHTS: Higher glucose uptake of the visceral adipose tissue was linked to decelerated brain aging. Higher glucose uptake of the subcutaneous adipose tissue (SAT) was associated with negative brain age delta in lean individuals. Faster brain aging was associated with increased glucose uptake of the SAT in female and overweight and obese individuals.
ABSTRACT
OBJECTIVES: This study utilizes [99mTc]-methylene diphosphate (MDP) single photon emission computed tomography (SPECT) images as a reference standard to evaluate whether the integration of radiomics features from computed tomography (CT) and machine learning algorithms can identify microscopic early bone metastases. Additionally, we also determine the optimal machine learning approach. MATERIALS AND METHODS: We retrospectively studied 63 patients with early bone metastasis from July 2020 to March 2023. The ITK-SNAP software was used to delineate early bone metastases and normal bone tissue in SPECT images of each patient, which were then registered onto CT images to outline the volume of interest (VOI). The VOI includes 63 early bone metastasis volumes and 63 normal bone tissue volumes. 126 VOIs were randomly distributed in a 7:3 ratio between the training and testing groups, and 944 radiomics features were extracted from every VOI. We established 20 machine learning models using 5 feature selection algorithms and 4 classification methods. Evaluate the performance of the model using the area under the receiver operating characteristic curve (AUC). RESULTS: Most machine learning models demonstrated outstanding discriminative capacity, with AUCs higher than 0.70. Notably, the K-Nearest Neighbors (KNN) classifier exhibited significant performance improvement compared to the other four classifiers. Specifically, the model constructed utilizing eXtreme Gradient Boosting (XGBoost) feature selection method integrated with KNN classifier achieved the maximum AUC, which is 0.989 in the training set and 0.975 in the testing set. CONCLUSIONS: Radiomics features integrated with machine learning methods can identify early bone metastases that are not visible on CT images. In our analysis, KNN is considered the optimal classification method.
ABSTRACT
BACKGROUND: Multicenter non-small cell lung cancer (NSCLC) patient data is information-rich. However, its direct integration becomes exceptionally challenging due to constraints involving different healthcare organizations and regulations. Traditional centralized machine learning methods require centralizing these sensitive medical data for training, posing risks of patient privacy leakage and data security issues. In this context, federated learning (FL) has attracted much attention as a distributed machine learning framework. It effectively addresses this contradiction by preserving data locally, conducting local model training, and aggregating model parameters. This approach enables the utilization of multicenter data with maximum benefit while ensuring privacy safeguards. Based on pre-radiotherapy planning target volume images of NSCLC patients, a multicenter treatment response prediction model is designed by FL for predicting the probability of remission of NSCLC patients. This approach ensures medical data privacy, high prediction accuracy and computing efficiency, offering valuable insights for clinical decision-making. METHODS: We retrospectively collected CT images from 245 NSCLC patients undergoing chemotherapy and radiotherapy (CRT) in four Chinese hospitals. In a simulation environment, we compared the performance of the centralized deep learning (DL) model with that of the FL model using data from two sites. Additionally, due to the unavailability of data from one hospital, we established a real-world FL model using data from three sites. Assessments were conducted using measures such as accuracy, receiver operating characteristic curve, and confusion matrices. RESULTS: The model's prediction performance obtained using FL methods outperforms that of traditional centralized learning methods. In the comparative experiment, the DL model achieves an AUC of 0.718/0.695, while the FL model demonstrates an AUC of 0.725/0.689, with real-world FL model achieving an AUC of 0.698/0.672. CONCLUSIONS: We demonstrate that the performance of a FL predictive model, developed by combining convolutional neural networks (CNNs) with data from multiple medical centers, is comparable to that of a traditional DL model obtained through centralized training. It can efficiently predict CRT treatment response in NSCLC patients while preserving privacy.
Subject(s)
Carcinoma, Non-Small-Cell Lung , Lung Neoplasms , Carcinoma, Non-Small-Cell Lung/therapy , Carcinoma, Non-Small-Cell Lung/radiotherapy , Carcinoma, Non-Small-Cell Lung/pathology , Humans , Lung Neoplasms/therapy , Lung Neoplasms/pathology , Lung Neoplasms/radiotherapy , Retrospective Studies , Female , Male , Middle Aged , Deep Learning , Aged , Machine Learning , Tomography, X-Ray Computed , Treatment Outcome , Chemoradiotherapy/methodsABSTRACT
Honeybees are an indispensable pollinator in nature with pivotal ecological, economic, and scientific value. However, a full-length transcriptome for Apis mellifera, assembled with the advanced third-generation nanopore sequencing technology, has yet to be reported. Here, nanopore sequencing of the midgut tissues of uninoculated and Nosema ceranae-inoculated A. mellifera workers was conducted, and the full-length transcriptome was then constructed and annotated based on high-quality long reads. Next followed improvement of sequences and annotations of the current reference genome of A. mellifera. A total of 5,942,745 and 6,664,923 raw reads were produced from midguts of workers at 7 days post-inoculation (dpi) with N. ceranae and 10 dpi, while 7,100,161 and 6,506,665 raw reads were generated from the midguts of corresponding uninoculated workers. After strict quality control, 6,928,170, 6,353,066, 5,745,048, and 6,416,987 clean reads were obtained, with a length distribution ranging from 1 kb to 10 kb. Additionally, 16,824, 17,708, 15,744, and 18,246 full-length transcripts were respectively detected, including 28,019 nonredundant ones. Among these, 43,666, 30,945, 41,771, 26,442, and 24,532 full-length transcripts could be annotated to the Nr, KOG, eggNOG, GO, and KEGG databases, respectively. Additionally, 501 novel genes (20,326 novel transcripts) were identified for the first time, among which 401 (20,255), 193 (13,365), 414 (19,186), 228 (12,093), and 202 (11,703) were respectively annotated to each of the aforementioned five databases. The expression and sequences of three randomly selected novel transcripts were confirmed by RT-PCR and Sanger sequencing. The 5' UTR of 2082 genes, the 3' UTR of 2029 genes, and both the 5' and 3' UTRs of 730 genes were extended. Moreover, 17,345 SSRs, 14,789 complete ORFs, 1224 long non-coding RNAs (lncRNAs), and 650 transcription factors (TFs) from 37 families were detected. Findings from this work not only refine the annotation of the A. mellifera reference genome, but also provide a valuable resource and basis for relevant molecular and -omics studies.
Subject(s)
Molecular Sequence Annotation , Transcriptome , Bees/genetics , Animals , Transcriptome/genetics , Genome, Insect , Nosema/genetics , Nanopore Sequencing/methods , Gene Expression Profiling/methodsABSTRACT
OBJECTIVE: The morphology of basilar artery (BA) may affect posterior circulation blood perfusion. We aimed to investigate whether different degrees of BA tortuosity could lead to the alterations of posterior circulation perfusion. METHODS: We collected 138 subjects with different BA tortuosity scores, including 32 cases of score 0, 45 cases of score 1, 43 cases of score 2, and 18 cases of score 3. A higher score represented a higher degree of BA tortuosity. Ordered logistic regression analysis was performed to investigate the risk factors for BA tortuosity. We quantitatively measured the cerebral blood flow (CBF) in eight posterior circulation brain regions using arterial spin labeling. SPSS 25.0 was used for statistical analysis. The correlation between the CBF and BA tortuosity was corrected by the Bonferroni method. The significance level was set at 0.006 (0.05/8). RESULTS: Hypertension (HR: 2.39; 95%CI: 1.23-4.71; P = 0.01) and vertebral artery dominance (HR: 2.38; 95%CI: 1.10-4.67; P = 0.03) were risk factors for BA tortuosity. CBF in occipital gray matter (R = -0.383, P < 0.001), occipital white matter (R = -0.377, P < 0.001), temporal gray matter (R = -0.292, P = 0.001), temporal white matter (R = -0.297, P < 0.001), and cerebellum (R = -0.328, P < 0.001) were negatively correlated with BA tortuosity degree. No significant correlation was found between the BA tortuosity degree and CBF in hippocampus (R = -0.208, P = 0.014), thalamus (R = -0.001, P = 0.988) and brainstem (R = -0.204, P = 0.016). CONCLUSIONS: BA tortuosity could affect posterior circulation blood perfusion. CBF was negatively correlated with BA tortuosity degree. The morphology of BA may serve as a biomarker for posterior circulation and the severity of posterior circulation ischemia.
ABSTRACT
Disruption of the circadian clock can affect starvation resistance, but the molecular mechanism is still unclear. Here, we found that starvation resistance was significantly reduced in the core gene BmPer deficient mutant silkworms (Per-/-), but the mutant's starvation resistance increased with larval age. Under natural physiological conditions, the weight of mutant 5th instar larvae was significantly increased compared to wild type, and the accumulation ability of triglycerides and glycogen in the fat bodies was upregulated. However, under starvation conditions, the weight consumption of mutant larvae was increased and cholesterol utilization was intensified. Transcriptome analysis showed that beta-oxidation was significantly upregulated under starvation conditions, fatty acid synthesis was inhibited, and the expression levels of genes related to mitochondrial function were significantly changed. Further investigations revealed that the redox balance, which is closely related to mitochondrial metabolism, was altered in the fat bodies, the antioxidant level was increased, and the pentose phosphate pathway, the source of reducing power in cells, was activated. Our findings suggest that one of the reasons for the increased energy burden observed in mutants is the need to maintain a more robust redox balance in metabolic tissues. This necessitates the diversion of more glucose into the pentose phosphate pathway to ensure an adequate supply of reducing power.
ABSTRACT
RATIONALE AND OBJECTIVES: Primary open-angle glaucoma (POAG) is accompanied with gray matter (GM) changes across the brain. However, causal relationships of the GM changes have not been fully understood. Our aim was to investigate the causality of GM progressive changes in POAG using Granger causality (GC) analysis and structural MRI. MATERIALS AND METHODS: Structural MRI from 20 healthy controls and 30 POAG patients with elevated intraocular pressure (IOP) were collected. We performed voxel-wise GM volume comparisons between control and POAG groups, and between control and four POAG subgroups (categorized by IOP). Then, we sequenced the structural MRI data of all POAG patients and conducted both voxel-wise and region of interest (ROI)-wise GC analysis to investigate the causality of GM volume changes in POAG brain. RESULTS: Compared to healthy controls, reduced GM volumes across the brain were found, GM volume enlargements in the thalamus, caudate nucleus and cuneus were also observed in POAG brain (false discovery rate (FDR) corrected at q< 0.05). As IOP elevated, the reductions of GM volume were more severe in the cerebellum and frontal lobe. GC analysis revealed that the bilateral cerebellum, visual cortices, and the frontal regions served independently as primary hubs of the directional causal network, and projected causal effects to the parietal and temporal regions of the brain (FDR corrected at q<0.05). CONCLUSION: POAG exhibits progressive GM alterations across the brain, with oculomotor regions and visual cortices as independent primary hubs. The current results may deepen our understanding of neuropathology of POAG.
ABSTRACT
BACKGROUND: The total-body positron emission tomography/computed tomography (PET/CT) system, with a long axial field of view, represents the state-of-the-art PET imaging technique. Recently, the total-body PET/CT system has been commercially available. The total-body PET/CT system enables high-resolution whole-body imaging, even under extreme conditions such as ultra-low dose, extremely fast imaging speed, delayed imaging more than 10 h after tracer injection, and total-body dynamic scan. The total-body PET/CT system provides a real-time picture of the tracers of all organs across the body, which not only helps to explain normal human physiological process, but also facilitates the comprehensive assessment of systemic diseases. In addition, the total-body PET/CT system may play critical roles in other medical fields, including cancer imaging, drug development and immunology. MAIN BODY: Therefore, it is of significance to summarize the existing studies of the total-body PET/CT systems and point out its future direction. This review collected research literatures from the PubMed database since the advent of commercially available total-body PET/CT systems to the present, and was divided into the following sections: Firstly, a brief introduction to the total-body PET/CT system was presented, followed by a summary of the literature on the performance evaluation of the total-body PET/CT. Then, the research and clinical applications of the total-body PET/CT were discussed. Fourthly, deep learning studies based on total-body PET imaging was reviewed. At last, the shortcomings of existing research and future directions for the total-body PET/CT were discussed. CONCLUSION: Due to its technical advantages, the total-body PET/CT system is bound to play a greater role in clinical practice in the future.
ABSTRACT
OBJECTIVE: Deep learning algorithms have commonly been used for the differential diagnosis between benign and malignant thyroid nodules. The aim of the study described here was to develop an integrated system that combines a deep learning model and a clinical standard Thyroid Imaging Reporting and Data System (TI-RADS) for the simultaneous segmentation and risk stratification of thyroid nodules. METHODS: Three hundred four ultrasound images from two independent sites with TI-RADS 4 thyroid nodules were collected. The edge connection and Criminisi algorithm were used to remove manually induced markers in ultrasound images. An integrated system based on TI-RADS and a mask region-based convolution neural network (Mask R-CNN) was proposed to stratify subclasses of TI-RADS 4 thyroid nodules and to segment thyroid nodules in the ultrasound images. Accuracy and the precision-recall curve were used to evaluate stratification performance, and the Dice similarity coefficient (DSC) between the segmentation of Mask R-CNN and the radiologist's contour was used to evaluate the segmentation performance of the model. RESULTS: The combined approach could significantly enhance the performance of the proposed integrated system. Overall stratification accuracy of TI-RADS 4 thyroid nodules, mean average precision and mean DSC of the proposed model in the independent test set was 90.79%, 0.8579 and 0.83, respectively. Specifically, stratification accuracy values for TI-RADS 4a, 4b and 4c thyroid nodules were 95.83%, 84.21% and 77.78%, respectively. CONCLUSION: An integrated system combining TI-RADS and a deep learning model was developed. The system can provide clinicians with not only diagnostic assistance from TI-RADS but also accurate segmentation of thyroid nodules, which improves the applicability of the system in clinical practice.
Subject(s)
Deep Learning , Thyroid Nodule , Ultrasonography , Thyroid Nodule/diagnostic imaging , Humans , Ultrasonography/methods , Risk Assessment , Male , Female , Thyroid Gland/diagnostic imaging , Middle Aged , Adult , AgedABSTRACT
Chemodynamic therapy (CDT) is a promising cancer treatment strategy. However, mild acidic pH, insufficient H2O2 content, and overexpressed glutathione (GSH) in the tumor microenvironment (TME) severely impair CDT efficiency. In this study, a novel therapeutic nanosystem (Cu/ZIF-8/Vc-Ca/HA) was constructed for H2O2 self-supply and GSH depletion co-enhanced CDT. Typically, calcium ascorbate (Vc-Ca) loaded on the surface of Cu2+-doped ZIF-8 (Cu/ZIF-8) was designed as an original source for H2O2 generation, and a hyaluronic acid (HA) shell was subsequently coated to act as a tumor-targeted "guide" and protective layer. Along with the HA shell disintegrated in the TME, exposed Cu/ZIF-8/Vc-Ca dissociated in the tumor acidic microenvironment, thus triggering the release of Vc-Ca and Cu2+. Vc-Ca selectively produced H2O2 in tumor cells, which provided abundant H2O2 for boosting Fenton-like reactions. Meanwhile, the released Cu2+ could get converted into Cu+ by consuming excess intracellular GSH, which could reduce the tumor antioxidant capability of the nanosystem. Moreover, byproduct Cu+ reacted with abundant H2O2 by a highly efficient Fenton-like reaction to generate toxic ËOH. Biological assays indicated that the Cu/ZIF-8/HA@Vc-Ca nanosystem showed significant anticancer activity by enhancing the CDT process. This study may provide a new strategy for improving the effectiveness of CDT.
Subject(s)
Ascorbic Acid , Metal-Organic Frameworks , Neoplasms , Humans , Copper , Hydrogen Peroxide , Glutathione , Hyaluronic Acid , Tumor Microenvironment , Cell Line, Tumor , Neoplasms/drug therapyABSTRACT
BACKGROUND: The menopause transition is associated with an increasing risk of cerebrovascular disorders. However, the direct effect of menopause status on brain perfusion hemodynamics remains unclear. This study aimed to explore the influence of menopause status on cerebral blood flow (CBF) using arterial spin labeling magnetic resonance imaging. METHODS: In this cross-sectional study, 185 subjects underwent arterial spin labeling magnetic resonance imaging at a hospital in China between September 2020 and December 2022, including 38 premenopausal women (mean age, 47.74±2.02 years), 42 perimenopausal women (mean age, 50.62±3.15 years), 42 postmenopausal women (mean age, 54.02±4.09 years), and 63 men (mean age, 52.70±4.33 years) of a similar age range. Mean CBF values in the whole brain, gray matter, white matter, cortical gray matter, subcortical gray matter, juxtacortical white matter, deep white matter, and periventricular white matter were extracted. ANCOVA was used to compare mean CBF among the 4 groups, controlling for confounding factors. Student t test was applied to compare mean CBF between the 3 female groups and age-matched males, respectively. Multivariable regression analysis was used to analysis the effect of age, sex, and menopause status on the CBF of the whole brain, gray matter, white matter, and subregions. RESULTS: Perimenopausal and postmenopausal women showed a higher proportion of white matter hyperintensities compared with the other 2 groups (P<0.001). Premenopausal women exhibited higher CBF in the whole brain, gray matter, white matter, and subregions, compared with perimenopausal, postmenopausal women and men (P≤0.001). Multivariable regression analysis demonstrated significant effect of age and insignificant effect of sex on CBF for all participants. In addition, menopause status and the interaction between age and menopause status on CBF of whole brain, gray matter, white matter, and the subregions were observed in female participants, except for the deep and periventricular white matter regions, with premenopausal women exhibited a slight increase in CBF with age, while perimenopausal and postmenopausal women exhibited declines in CBF with age. CONCLUSIONS: The current findings suggest that alterations of brain perfusion hemodynamics begin during the perimenopause period, which may be due to the increased burden of white matter hyperintensities.
Subject(s)
Brain , White Matter , Male , Humans , Female , Middle Aged , Cross-Sectional Studies , Brain/diagnostic imaging , Brain/blood supply , Magnetic Resonance Imaging/methods , White Matter/pathology , Hemodynamics , Perfusion , Menopause , Cerebrovascular Circulation/physiology , Spin LabelsABSTRACT
High-tension glaucoma (HTG) is one of the most common forms of primary open angle glaucoma. The purpose of this study was to assess in HTG brain, whether the elevated intraocular pressure (IOP) had an effect on the brain morphological alterations via structural MRI. We acquired T1WI structural MRI images from 56 subjects including 36 HTG patients and 20 healthy controls. We tested whether the brain morphometry was associated with the mean IOP in HTG patients. Moreover, we conducted moderation analysis to assess the interactions between subject type (HTG - healthy controls) and IOP. In HTG group, cortical thickness was negatively correlated with the mean IOP in the left rostral middle frontal gyrus, left pars triangularis, right precentral gyrus, left postcentral gyrus, left superior temporal gyrus (pâ¯<â¯0.05, FDR corrected). Four of the five regions negatively correlated with mean IOP showed reduced cortical thickness in HTG group compared with healthy controls, which were the left rostral middle frontal gyrus, left pars triangularis, left postcentral gyrus and left superior temporal gyrus (pâ¯<â¯0.05, FDR corrected). IOP moderated the interaction between subject type and cortical thickness of the left rostral middle frontal gyrus (pâ¯=â¯0.0017), left pars triangularis (pâ¯=â¯0.0011), left postcentral gyrus (pâ¯=â¯0.0040) and left superior temporal gyrus (pâ¯=â¯0.0066). Elevated IOP may result brain morphometry alterations such as cortical thinning. The relationship between IOP and brain morphometry underlines the importance of the IOP regulation for HTG patients.
Subject(s)
Glaucoma, Open-Angle , Glaucoma , Motor Cortex , Humans , Glaucoma, Open-Angle/diagnostic imaging , Intraocular Pressure , Brain , Magnetic Resonance Imaging/methodsABSTRACT
Human brain structure shows heterogeneous patterns of change across adults aging and is associated with cognition. However, the relationship between cortical structural changes during aging and gene transcription signatures remains unclear. Here, using structural magnetic resonance imaging data of two separate cohorts of healthy participants from the Cambridge Centre for Aging and Neuroscience (n = 454, 18-87 years) and Dallas Lifespan Brain Study (n = 304, 20-89 years) and a transcriptome dataset, we investigated the link between cortical morphometric similarity network and brain-wide gene transcription. In two cohorts, we found reproducible morphometric similarity network change patterns of decreased morphological similarity with age in cognitive related areas (mainly located in superior frontal and temporal cortices), and increased morphological similarity in sensorimotor related areas (postcentral and lateral occipital cortices). Changes in morphometric similarity network showed significant spatial correlation with the expression of age-related genes that enriched to synaptic-related biological processes, synaptic abnormalities likely accounting for cognitive decline. Transcription changes in astrocytes, microglia, and neuronal cells interpreted most of the age-related morphometric similarity network changes, which suggest potential intervention and therapeutic targets for cognitive decline. Taken together, by linking gene transcription signatures to cortical morphometric similarity network, our findings might provide molecular and cellular substrates for cortical structural changes related to cognitive decline across adults aging.
Subject(s)
Aging , Brain , Adult , Humans , Brain/physiology , Aging/physiology , Cognition/physiology , Temporal Lobe , Magnetic Resonance Imaging/methodsABSTRACT
BACKGROUND AND OBJECTIVES: Overweight and obesity is a complex condition resulting from unbalanced energy homeostasis among various organs. However, systemic abnormalities in overweight and obese people are seldom explored in vivo by metabolic imaging techniques. The aim of this study was to determine metabolic abnormities throughout the body in overweight and obese adults using total-body positron emission tomography (PET) glucose uptake imaging. METHODS: Thirty normal weight subjects [body mass index (BMI) < 25 kg/m2, 55.47 ± 13.94 years, 16 men and 14 women], and 26 overweight and obese subjects [BMI ≥ 25 kg/m2, 52.38 ± 9.52 years, 21 men and 5 women] received whole-body 18F-fluorodeoxyglucose PET imaging using the uEXPLORER. Whole-body standardized uptake value normalized by lean body mass (SUL) images were calculated. Metabolic networks were constructed based on the whole-body SUL images using covariance network approach. Both group-level and individual-level network differences between normal weight and overweight/obese subjects were evaluated. Correlation analysis was conducted between network properties and BMI for the overweight/obese subjects. RESULTS: Compared with normal weight subjects, overweight/obese subjects exhibited altered network connectivity strength in four network nodes, namely the pancreas (p = 0.033), spleen (p = 0.021), visceral adipose tissue (VAT) (p = 1.12 × 10-5) and bone (p = 0.021). Network deviations of overweight/obese subjects from the normal weight were positively correlated with BMI (r = 0.718, p = 3.64 × 10-5). In addition, overweight/obese subjects experienced altered connections between organs, and some of the altered connections, including pancreas-right lung and VAT-bilateral lung connections were significantly correlated with BMI. CONCLUSION: Overweight/obese individuals exhibit metabolic alterations in organ level, and altered metabolic interactions at the systemic level. The proposed approach using total-body PET imaging can reveal individual metabolic variability and metabolic deviations between organs, which would open up a new path for understanding metabolic alterations in overweight and obesity.
Subject(s)
Obesity , Overweight , Male , Adult , Humans , Female , Overweight/diagnostic imaging , Overweight/metabolism , Obesity/diagnostic imaging , Obesity/metabolism , Positron-Emission Tomography , Body Composition , Body Mass IndexABSTRACT
OBJECTIVES: To develop an end-to-end deep neural network for the classification of contrast-enhanced mammography (CEM) images to facilitate breast cancer diagnosis in the clinic. METHODS: In this retrospective mono-centric study, patients who underwent CEM examinations from January 2019 to August 2021 were enrolled. A multi-feature fusion network combining low-energy (LE) and dual-energy subtracted (DES) images and dual view, as well as bilateral information, was trained and tested using a large CEM dataset with a diversity of breast tumors for breast lesion classification. Its generalization performance was further evaluated on two external datasets. Results were reported using AUC, accuracy, sensitivity, and specificity. RESULTS: A total of 2496 patients (mean age, 53 years ± 12 (standard deviation)) were included and divided into a training set (1718), a validation set (255), and a testing set (523). The proposed CEM-based multi-feature fusion network achieved the best diagnosis performance with an AUC of 0.96 (95% confidence interval (CI): 0.95, 0.97), compared with the no-fusion model, the left-right fusion model, and the multi-feature fusion network with only LE image inputs. Our models reached an AUC of 0.90 (95% CI: 0.85, 0.94) on a full-field digital mammograph (FFDM) external dataset (86 patients), and an AUC of 0.92 (95% CI: 0.89, 0.95) on a CEM external dataset (193 patients). CONCLUSION: The developed multi-feature fusion neural network achieved high performance in CEM image classification and was able to facilitate CEM-based breast cancer diagnosis. CLINICAL RELEVANCE STATEMENT: Compared with low-energy images, CEM images have greater sensitivity and similar specificity in malignant breast lesion detection. The multi-feature fusion neural network is a promising computer-aided diagnostic tool for the clinical diagnosis of breast cancer. KEY POINTS: ⢠Deep convolutional neural networks have the potential to facilitate contrast-enhanced mammography-based breast cancer diagnosis. ⢠The multi-feature fusion neural network reaches high accuracies in the classification of contrast-enhanced mammography images. ⢠The developed model is a promising diagnostic tool to facilitate clinical breast cancer diagnosis.
Subject(s)
Breast Neoplasms , Humans , Middle Aged , Female , Breast Neoplasms/diagnostic imaging , Retrospective Studies , Mammography/methods , Breast/diagnostic imaging , Neural Networks, ComputerABSTRACT
BACKGROUND: Bone metastasis is a common event in lung cancer progression. Early diagnosis of lung malignant tumor with bone metastasis is crucial for selecting effective treatment strategies. However, 14.3% of patients are still difficult to diagnose after SPECT/CT examination. PURPOSE: Machine learning analysis of [99mTc]-methylene diphosphate (99mTc-MDP) SPECT/CT scans to distinguish bone metastases from benign bone lesions in patients with lung cancer. METHODS: One hundred forty-one patients (69 with bone metastases and 72 with benign bone lesions) were randomly assigned to the training group or testing group in a 7:3 ratio. Lesions were manually delineated using ITK-SNAP, and 944 radiomics features were extracted from SPECT and CT images. The least absolute shrinkage and selection operator (LASSO) regression was used to select the radiomics features in the training set, and the single/bimodal radiomics models were established based on support vector machine (SVM). To further optimize the model, the best bimodal radiomics features were combined with clinical features to establish an integrated Radiomics-clinical model. The diagnostic performance of models was evaluated using receiver operating characteristic (ROC) curve and confusion matrix, and performance differences between models were evaluated using the Delong test. RESULTS: The optimal radiomics model comprised of structural modality (CT) and metabolic modality (SPECT), with an area under curve (AUC) of 0.919 and 0.907 for the training and testing set, respectively. The integrated model, which combined SPECT, CT, and two clinical features, exhibited satisfactory differentiation in the training and testing set, with AUC of 0.939 and 0.925, respectively. CONCLUSIONS: The machine learning can effectively differentiate between bone metastases and benign bone lesions. The Radiomics-clinical integrated model demonstrated the best performance.
Subject(s)
Bone Neoplasms , Lung Neoplasms , Humans , Single Photon Emission Computed Tomography Computed Tomography , Bone Neoplasms/diagnostic imaging , Lung Neoplasms/diagnostic imaging , Tomography, Emission-Computed, Single-Photon , Machine Learning , Retrospective StudiesABSTRACT
Background and Objective: Terahertz (THz) imaging has wide applications in biomedical research due to its properties, such as non-ionizing, non-invasive and distinctive spectral fingerprints. Over the past 6 years, the application of THz imaging in tumor tissue has made encouraging progress. However, due to the strong absorption of THz by water, the large size, high cost, and low sensitivity of THz devices, it is still difficult to be widely used in clinical practice. This paper provides ideas for researchers and promotes the development of THz imaging in clinical research. Methods: The literature search was conducted in the Web of Science and PubMed databases using the keywords "Terahertz imaging", "Breast", "Brain", "Skin" and "Cancer". A total of 94 English language articles from 1 January, 2017 to 30 December, 2022 were reviewed. Key Content and Findings: In this review, we briefly introduced the recent advances in THz near-field imaging, single-pixel imaging and real-time imaging, the applications of THz imaging for detecting breast, brain and skin tissues in the last 6 years were reviewed, and the advantages and existing challenges were identified. It is necessary to combine machine learning and metamaterials to develop real-time THz devices with small size, low cost and high sensitivity that can be widely used in clinical practice. More powerful THz detectors can be developed by combining graphene, designing structures and other methods to improve the sensitivity of the devices and obtain more accurate information. Establishing a THz database is one of the important methods to improve the repeatability and accuracy of imaging results. Conclusions: THz technology is an effective method for tumor imaging. We believe that with the joint efforts of researchers and clinicians, accurate, real-time, and safe THz imaging will be widely applied in clinical practice in the future.
ABSTRACT
Intravoxel incoherent motion (IVIM) modeling is a widely used double-exponential model for describing diffusion-weighted imaging (DWI) signal, with a slow component related to pure molecular diffusion and a fast component associated with microcirculatory perfusion, which compensates for the limitations of traditional DWI. IVIM is a noninvasive technique for obtaining liver pathological information and characterizing liver lesions, and has potential applications in the initial diagnosis and treatment monitoring of liver diseases. Recent studies have demonstrated that IVIM-derived parameters are useful for evaluating liver lesions, including nonalcoholic fatty liver disease (NAFLD), liver fibrosis and liver tumors. However, the results are not stable. Therefore, it is necessary to summarize the current applications of IVIM in liver disease research, identify existing shortcomings, and point out the future development direction. In this review, we searched for studies related to hepatic IVIM-DWI applications over the past two decades in the PubMed database. We first introduce the fundamental principles and influential factors of IVIM, and then discuss its application in NAFLD, liver fibrosis, and focal hepatic lesions. It has been found that IVIM is still unstable in ensuring the robustness and reproducibility of measurements in the assessment of liver fibrosis grade and liver tumors differentiation, due to inconsistent and substantial overlap in the range of IVIM-derived parameters for different fibrotic stages. In the end, the future direction of IVIM-DWI in the assessment of liver diseases is discussed, emphasizing the need for further research on the stability of IVIM-derived parameters, particularly perfusion-related parameters, in order to promote the clinical practice of IVIM-DWI. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 3.
ABSTRACT
BACKGROUND: For some ICU patients, an artificial airway must be established with an endotracheal tube, but Candida albicans can easily adhere to the tube surface and form a biofilm, leading to potentially life threatening fungal infections. Therefore, it is urgent to prevent and reduce C. albicans infections introduced by the endotracheal tube. However, there are few antifungal drugs effective against C. albicans, and each of these drugs may have adverse effects on human cells. Saccharomyces boulardii is regarded as an alternative strategy to inhibit the adhesion of C. albicans, but it is affected by environmental stress. We hypothesized that it is feasible to strengthen the antagonistic ability of S. boulardii via encapsulating and genetically modification. METHODS: In this study, a bioactive material carrying the overexpressed MCP1 gene of Saccharomyces boulardii was constructed based on one-step photo-crosslinking. This material achieved spatial growth control of S. boulardii by encapsulating each S. boulardii cell within a hydrogel pore. The bioactive material was coated on an endotracheal tube and tested for its ability to inhibit the adhesion of C. albicans. Additionally, the material's antagonistic activity towards C. albicans was evaluated by detecting intracellular Adenosine-triphosphate content, reactive oxygen species level and the activity of antioxidative enzymes. Tissue invasion experiment was executed to further evaluate the anti-adhesion ability of S. boulardii bio-coating. RESULTS: Encapsulating the overexpression of MCP1 by S. boulardii in hydrogel pores enhanced the viability of probiotics in the presence of high salt and oxidation stress. When used as the coating of an endotracheal tube, the S. boulardii bioactive material efficiently inhibited the adhesion of C. albicans by impairing the activities of superoxide dismutase and catalase and disturbing mitochondrial functions. In vivo, the S. boulardii bioactive material coating displayed good biocompatibility and reduced the host tissue invasion and virulence of C. albicans. CONCLUSIONS: The integration of genetic modification and immobilization model breaks the bottleneck of previous application of microorganisms, and provides a new way to prevent fungal infections introduced by endotracheal tubes.