Objective
Osteoporosis is a systemic bone disease characterized by low bone mass, damaged bone microstructure, increased bone fragility, and susceptibility to fractures. With the rapid development of ...artificial intelligence, a series of studies have reported deep learning applications in the screening and diagnosis of osteoporosis. The aim of this review was to summary the application of deep learning methods in the radiologic diagnosis of osteoporosis.
Methods
We conducted a two-step literature search using the PubMed and Web of Science databases. In this review, we focused on routine radiologic methods, such as X-ray, computed tomography, and magnetic resonance imaging, used to opportunistically screen for osteoporosis.
Results
A total of 40 studies were included in this review. These studies were divided into three categories: osteoporosis screening (n = 20), bone mineral density prediction (n = 13), and osteoporotic fracture risk prediction and detection (n = 7).
Conclusions
Deep learning has demonstrated a remarkable capacity for osteoporosis screening. However, clinical commercialization of a diagnostic model for osteoporosis remains a challenge.
The surgical treatment of thoracic myelopathy is still controversial and also a challenge for spine surgeons. Therefore, the objective of this study was to review the related literature on the ...surgical treatment of thoracic myelopathy and try to define treatment guidelines for spine surgeons on thoracic myelopathy.
Relevant literatures were searched based on the PubMed, EMBASE, and Cochrane Library between January 2008 and December 2018. Some data on the characteristics of patients were extracted, including number of patients, mean age, surgical procedures, blood loss, complications, and pre-/post-operation modified JOA score. Recovery rate was used to assess the effect of surgery outcome, and the safety was evaluated by blood loss and incidence of complications.
Thirty-five studies met the inclusion criteria and were retrieved. A total of 2183 patients were included in our systematic review, with the average age of 55.2 years. There were 69.8% patients diagnosed as ossification of ligamentum flavum (OLF), 20.0% as ossification of posterior longitudinal ligament (OPLL), 9.3% as disk herniation (DH), and 0.9% as others including diffuse idiopathic skeletal hyperostosis (DISH) and ankylosing spondylitis (AS). The volume of blood loss was more in the treatment of circumferential decompression (CD) than posterior decompression (PD), and the incidence of complications was higher in CD (P < 0.05). The volume of blood loss in minimally invasive surgery (MIS) was lowest and the incidence of complications was 19.2%. Post-operation recovery rate was 0.49 in PD, 0.35 in CD, and 0.29 in MIS while the recovery rate was 0.54 in PD, 0.55 in CD, and 0.49 in MIS at the last follow-up. When focusing on the OLF specifically, incidence of complications in PD was much lower than CD, with less blood loss and higher recovery rate. Focusing on the OPLL specifically, incidence of complications in PD was much lower than CD, with less blood loss while there was no statistical difference in recovery rate between these two methods.
This systematic review showed that posterior decompression for thoracic myelopathy is safer and better than circumferential decompression according to the complication rate and surgical outcome. And we should also consider the location of compression before the operation.
Objective
Esophageal varix (EV) bleeding is a particularly serious complications of cirrhosis. Prediction of EV bleeding requires extensive endoscopy experience; it remains unreliable and ...inefficient. This retrospective cohort study evaluated the feasibility of using deep learning (DL) to predict the 12-month risk of EV bleeding based on endoscopic images.
Methods
Six DL models were trained to perform binary classification of endoscopic images of EV bleeding. The models were subsequently validated using an external test dataset, then compared with classifications performed by two endoscopists.
Results
In the validation dataset, EfficientNet had the highest accuracy (0.910), followed by ConvMixer (0.898) and Xception (0.875). In the test dataset, EfficientNet maintained the highest accuracy (0.893), which was better than the endoscopists (0.800 and 0.763). Notably, one endoscopist displayed higher recall (0.905), compared with EfficientNet (0.870). When their predictions were assisted by artificial intelligence, the accuracies of the two endoscopists increased by 17.3% and 19.0%. Moreover, statistical agreement among the models was dependent on model architecture.
Conclusions
This study demonstrated the feasibility of using DL to predict the 12-month risk of EV bleeding based on endoscopic images. The findings suggest that artificial intelligence-aided diagnosis will be a useful addition to cirrhosis management.
Materials that absorb electromagnetic waves over an ultra-wide frequency band have great potential for military and civilian applications. In this study, a square-frustum-type metamaterial structure ...was designed and prepared using CI/silica gel composites and flake-shaped FeNi/silica gel composites as the filling substrate. The structural parameters of the square frustum were simulated and optimized using CST Studio Suite. The results show that the optimal performance was achieved when the base consisted of 50 vol.% CI/silica gel composites and 25 vol.% FeNi/silica gel composites with a cross-pattern distribution, the square frustum consisted of 50 vol.% CI/silica gel composites, and the total thickness, base thickness, base-edge length, and top-edge lengths were 5, 1.8, 2.5, and 1.5 mm, respectively. This arrangement can effectively absorb frequencies between 1.8 and 40 GHz, realizing ultra-broadband absorption. The excellent absorption performance of the absorber is attributed to multiple quarter-wavelength resonances and edge diffraction effects.
Although the mid-deep ground source heat pump could be more excellent for heating compared to other heat pumps, whose well depth is usually 2000–4000 m underground, the references on it is far fewer ...than the market demand to apply it more. To facility the application of the mid-deep ground source heat pump and the heating problem solution to transform the coal-boiler used in a Logistics Park of Lanzhou city, firstly, this paper established a three-dimensional numerical model of mid-deep ground source heat exchanger, and analyzed the effects of well flow, diameter and depth on heat pump performance with the help of Fluent software. And then, the heating source renovation to mid-deep ground source heat pump was carried out and the test funded by the local government was followed from February 1, 2018 to March 31, 2018. It is concluded that the numerical analysis is reasonable and the heating system is effective and reliable, whose average COP (coefficient of performance) and cumulative power consumption is 3.47 and 67 727 kWh respectively during the test period.
Pancreatic cancer remains an extremely malignant digestive tract tumor, posing a significant global public health burden. Patients with pancreatic cancer, once metastasis occurs, lose all hope of ...cure, and prognosis is extremely poor. It is important to investigate liver metastasis of Pancreatic cancer in depth, not just because it is the most common form of metastasis in pancreatic cancer, but also because it is crucial for treatment planning and prognosis assessment. This study aims to delve into the mechanisms of pancreatic cancer liver metastasis, with the goal of providing crucial scientific groundwork for the development of future treatment methods and drugs.
We explored the mechanisms of pancreatic cancer liver metastasis using single-cell sequencing data (GSE155698 and GSE154778) and bulk data (GSE71729, GSE19279, TCGA-PAAD). Initially, Seurat package was employed for single-cell data processing to obtain expression matrices for primary pancreatic cancer lesions and liver metastatic lesions. Subsequently, high-dimensional weighted gene co-expression network analysis (hdWGCNA) was used to identify genes associated with liver metastasis. Machine learning algorithms and COX regression models were employed to further screen genes related to patient prognosis. Informed by both biological understanding and the outcomes of algorithms, we meticulously identified the ultimate set of liver metastasis-related gene (LRG). In the study of LRG genes, various databases were utilized to validate their association with pancreatic cancer liver metastasis. In order to analyze the effects of these agents on tumor microenvironment, we conducted an in-depth analysis, including changes in signaling pathways (GSVA), cell differentiation (pseudo-temporal analysis), cell communication networks (cell communication analysis), and downstream transcription factors (transcription factor activity prediction). Additionally, drug sensitivity analysis and metabolic analysis were performed to reveal the effects of LRG on gemcitabine resistance and metabolic pathways. Finally, functional experiments were conducted by silencing the expression of LRG in PANC-1 and Bx-PC-3 cells to validate its influence to proliferation and invasiveness on PANC-1 and Bx-PC-3 cells.
Through a series of algorithmic filters, we identified PAK2 as a key gene promoting pancreatic cancer liver metastasis. GSVA analysis elucidated the activation of the TGF-beta signaling pathway by PAK2 to promote the occurrence of liver metastasis. Pseudo-temporal analysis revealed a significant correlation between PAK2 expression and the lower differentiation status of pancreatic cancer cells. Cell communication analysis revealed that overexpression of PAK2 promotes communication between cancer cells and the tumor microenvironment. Transcription factor activity prediction displayed the transcription factor network regulated by PAK2. Drug sensitivity analysis and metabolic analysis revealed the impact of PAK2 on gemcitabine resistance and metabolic pathways. CCK8 experiments showed that silencing PAK2 led to a decrease in the proliferative capacity of pancreatic cancer cells and scratch experiments demonstrated that low expression of PAK2 decreased invasion capability in pancreatic cancer cells. Flow cytometry reveals that PAK2 significantly inhibited apoptosis in pancreatic cancer cell lines. Molecules related to the TGF-beta pathway decreased with the inhibition of PAK2, and there were corresponding significant changes in molecules associated with EMT.
PAK2 facilitated the angiogenic potential of cancer cells and promotes the epithelial-mesenchymal transition process by activating the TGF-beta signaling pathway. Simultaneously, it decreased the differentiation level of cancer cells, consequently enhancing their malignancy. Additionally, PAK2 fostered communication between cancer cells and the tumor microenvironment, augments cancer cell chemoresistance, and modulates energy metabolism pathways. In summary, PAK2 emerged as a pivotal gene orchestrating pancreatic cancer liver metastasis. Intervening in the expression of PAK2 may offer a promising therapeutic strategy for preventing liver metastasis of pancreatic cancer and improving its prognosis.
The development of microwave absorption materials with good environmental adaptability is a hot topic in the electromagnetic protection field. In this research, Expanded graphite (EG)/ZIF-67 ...nanocubes-derived (Co@C) composites were successfully fabricated by electrostatic assembly and subsequent heat treatment. The results show that the involvement of an appropriate content of Co@C not only overcomes the problem of single EG impedance mismatch but also introduces additional magnetic loss for the absorber. At the thicknesses of 1.6 mm and 1.5 mm, an effective absorption bandwidth (EAB) of 4.52 GHz and a minimum reflection loss (RLmin) of −48.4 dB were achieved for the Z2-700 sample with a low filling ratio (20 wt%). The enhancement of EMW-absorption performance is attributed to the optimization of impedance matching and the synergistic action between multiple loss mechanisms. Electrochemical corrosion test showed that graphite nanoflakes of EG enhanced the transfer resistance during corrosion, and the corrosion resistance of pure Co@C was enhanced with the protection of EG. This work provides a reasonable attempt to design and fabricate efficient microwave absorption materials suitable for harsh environments.
Treatment of congenital hemivertebra is challenging and data on long-term follow-up (≥ 5 years) are lacking. This study evaluated the surgical outcomes of posterior thoracolumbar hemivertebra ...resection and short-segment fusion with pedicle screw fixation for treatment of congenital scoliosis with over 5-year follow-up.
This study evaluated 27 consecutive patients with congenital scoliosis who underwent posterior thoracolumbar hemivertebra resection and short-segment fusion from January 2007 to January 2015. Segmental scoliosis, total main scoliosis, compensatory cranial curve, compensatory caudal curve, trunk shift, shoulder balance, segmental kyphosis, and sagittal balance were measured on radiographs. Radiographic outcomes and all intraoperative and postoperative complications were recorded.
The segmental main curve was 40.35° preoperatively, 11.94° postoperatively, and 13.24° at final follow-up, with an average correction of 65.9%. The total main curve was 43.39° preoperatively, 14.13° postoperatively, and 16.06° at final follow-up, with an average correction of 60.2%. The caudal and cranial compensatory curves were corrected from 15.78° and 13.21° to 3.57° and 6.83° postoperatively and 4.38° and 7.65° at final follow-up, with an average correction of 69.2% and 30.3%, respectively. The segmental kyphosis was corrected from 34.30° to 15.88° postoperatively and 15.12° at final follow-up, with an average correction of 61.9%. A significant correction (p < 0.001) in segmental scoliosis, total main curve, caudal compensatory curves and segmental kyphosis was observed from preoperative to the final follow-up. The correction in the compensatory cranial curve was significant between preoperative and postoperative and 2-year follow-up (p < 0.001), but a statistically significant difference was not observed between the preoperative and final follow-up (p > 0.001). There were two implant migrations, two postoperative curve progressions, five cases of proximal junctional kyphosis, and four cases of adding-on phenomena.
Posterior thoracolumbar hemivertebra resection after short-segment fusion with pedicle screw fixation in congenital scoliosis is a safe and effective method for treatment and can achieve rigid fixation and deformity correction.
Standard deep learning methods have been found inadequate in distinguishing between intestinal tuberculosis (ITB) and Crohn's disease (CD), a shortcoming largely attributed to the scarcity of ...available samples. In light of this limitation, our objective is to develop an innovative few-shot learning (FSL) system, specifically tailored for the efficient categorization and differential diagnosis of CD and ITB, using endoscopic image data with minimal sample requirements.
A total of 122 white-light endoscopic images (99 CD images and 23 ITB images) were collected (one ileum image from each patient). A 2-way, 3-shot FSL model that integrated dual transfer learning and metric learning strategies was devised. Xception architecture was selected as the foundation and then underwent a dual transfer process utilizing oesophagitis images sourced from HyperKvasir. Subsequently, the eigenvectors derived from the Xception for each query image were converted into predictive scores, which were calculated using the Euclidean distances to six reference images from the support sets.
The FSL model, which leverages dual transfer learning, exhibited enhanced performance metrics (AUC 0.81) compared to a model relying on single transfer learning (AUC 0.56) across three evaluation rounds. Additionally, its performance surpassed that of a less experienced endoscopist (AUC 0.56) and even a more seasoned specialist (AUC 0.61).
The FSL model we have developed demonstrates efficacy in distinguishing between CD and ITB using a limited dataset of endoscopic imagery. FSL holds value for enhancing the diagnostic capabilities of rare conditions.
A series of Ga-substituted Ce3+-doped yttrium aluminum garnet (Y2.94Al5-xGaxO12: 0.06Ce3+) phosphors were synthesized at different atmospheres and temperatures. The structure, optical and thermal ...stability properties were analyzed using X-ray diffraction (XRD), photoluminescence (PL) and thermal measurements. A novel finding was revealed that gallium oxide (Ga2O3) was unstable in reducing atmosphere by XRD, and we explained the mechanism for the first time. In addition, it was found that Y3Al3Ga2O12 was formed due to Al3+ ions entering the lattice of Y3Ga5O12 gradually and the mechanism was clearly illustrated. The emission intensity of Y2.94Al5-xGaxO12: 0.06Ce3+ phosphors was determined by two aspects—the phase formation temperature and the band gap of host lattice. What's more, introducing 6 wt% H3BO3 as flux can improve thermal stability to maximum extent and the thermal ionization model was used to explain the thermal quenching mechanism. Finally, the critical parameters including color rendering index (CRI), correlated color temperature (CCT), light efficiency of light emitting diodes (LEDs) packaged with the resultant green phosphors and red phosphors were studied.