DeepRisk network: an AI-based tool for digital pathology signature and treatment responsiveness of gastric cancer using whole-slide images.

BACKGROUND: Digital histopathology provides valuable information for clinical decision-making. We hypothesized that a deep risk network (DeepRisk) based on digital pathology signature (DPS) derived from whole-slide images could improve the prognostic value of the tumor, node, and metastasis (TNM) staging system and offer chemotherapeutic benefits for gastric cancer (GC). METHODS: DeepRisk is a multi-scale, attention-based learning model developed on 1120 GCs in the Zhongshan dataset and validated with two external datasets. Then, we assessed its association with prognosis and treatment response. The multi-omics analysis and multiplex Immunohistochemistry were conducted to evaluate the potential pathogenesis and spatial immune contexture underlying DPS. RESULTS: Multivariate analysis indicated that the DPS was an independent prognosticator with a better C-index (0.84 for overall survival and 0.71 for disease-free survival). Patients with low-DPS after neoadjuvant chemotherapy responded favorably to treatment. Spatial analysis indicated that exhausted immune clusters and increased infiltration of CD11b+CD11c+ immune cells were present at the invasive margin of high-DPS group. Multi-omics data from the Cancer Genome Atlas-Stomach adenocarcinoma (TCGA-STAD) hint at the relevance of DPS to myeloid derived suppressor cells infiltration and immune suppression. CONCLUSION: DeepRisk network is a reliable tool that enhances prognostic value of TNM staging and aid in precise treatment, providing insights into the underlying pathogenic mechanisms.

Automatically optimized radiomics modeling system for small gastric submucosal tumor (<2 cm) discrimination based on EUS images.

BACKGROUND AND AIMS: The clinical management of small gastric submucosal tumors (SMTs) (<2 cm) faces a non-negligible challenge because of the lack of guideline consensus and effective diagnostic tools. This article develops an automatically optimized radiomics modeling system (AORMS) based on EUS images to diagnose and evaluate SMTs. METHODS: A total of 205 patients with EUS images of small gastric SMTs (<2 cm) were retrospectively enrolled in the development phase of AORMS for the diagnosis and the risk stratification of GI stromal tumor (GIST). A total of 178 patients with images from different centers were prospectively enrolled in the independent testing phase. The performance of AORMS was compared to that of endoscopists in the development set and evaluated in the independent testing set. RESULTS: AORMS demonstrated an area under the curve (AUC) of 0.762 for the diagnosis of GIST and 0.734 for the risk stratification of GIST, respectively. In the independent testing set, AORMS achieved an AUC of 0.770 and 0.750 for the diagnosis and risk stratification of small GISTs, respectively. In comparison, the AUCs of 5 experienced endoscopists ranged from 0.501 to 0.608 for diagnosing GIST and from 0.562 to 0.748 for risk stratification. AORMS outperformed experienced endoscopists by more than 20% in diagnosing GIST. CONCLUSIONS: AORMS implements automatic parameter selection, which enhances its robustness and clinical applicability. It has demonstrated good performance in the diagnosis and risk stratification of GISTs, which could aid endoscopists in the diagnosis of small gastric SMTs (<2 cm).

Anti-HER2 therapy response assessment for guiding treatment (de-)escalation in early HER2-positive breast cancer using a novel deep learning radiomics model.

OBJECTIVES: Anti-HER2 targeted therapy significantly reduces risk of relapse in HER2 + breast cancer. New measures are needed for a precise risk stratification to guide (de-)escalation of anti-HER2 strategy. METHODS: A total of 726 HER2 + cases who received no/single/dual anti-HER2 targeted therapies were split into three respective cohorts. A deep learning model (DeepTEPP) based on preoperative breast magnetic resonance (MR) was developed. Patients were scored and categorized into low-, moderate-, and high-risk groups. Recurrence-free survival (RFS) was compared in patients with different risk groups according to the anti-HER2 treatment they received, to validate the value of DeepTEPP in predicting treatment efficacy and guiding anti-HER2 strategy. RESULTS: DeepTEPP was capable of risk stratification and guiding anti-HER2 treatment strategy: DeepTEPP-Low patients (60.5%) did not derive significant RFS benefit from trastuzumab (p = 0.144), proposing an anti-HER2 de-escalation. DeepTEPP-Moderate patients (19.8%) significantly benefited from trastuzumab (p = 0.048), but did not obtain additional improvements from pertuzumab (p = 0.125). DeepTEPP-High patients (19.7%) significantly benefited from dual HER2 blockade (p = 0.045), suggesting an anti-HER2 escalation. CONCLUSIONS: DeepTEPP represents a pioneering MR-based deep learning model that enables the non-invasive prediction of adjuvant anti-HER2 effectiveness, thereby providing valuable guidance for anti-HER2 (de-)escalation strategies. DeepTEPP provides an important reference for choosing the appropriate individualized treatment in HER2 + breast cancer patients, warranting prospective validation. CLINICAL RELEVANCE STATEMENT: We built an MR-based deep learning model DeepTEPP, which enables the non-invasive prediction of adjuvant anti-HER2 effectiveness, thus guiding anti-HER2 (de-)escalation strategies in early HER2-positive breast cancer patients. KEY POINTS: • DeepTEPP is able to predict anti-HER2 effectiveness and to guide treatment (de-)escalation. • DeepTEPP demonstrated an impressive prognostic efficacy for recurrence-free survival and overall survival. • To our knowledge, this is one of the very few, also the largest study to test the efficacy of a deep learning model extracted from breast MR images on HER2-positive breast cancer survival and anti-HER2 therapy effectiveness prediction.

Preoperative Ultrasound Radomics to Predict Posthepatectomy Liver Failure in Patients With Hepatocellular Carcinoma.

PURPOSE: Posthepatectomy liver failure (PHLF) is a major cause of postoperative mortality in hepatocellular carcinoma (HCC) patients. The study aimed to develop a method based on the two-dimensional shear wave elastography and clinical data to evaluate the risk of PHLF in HCC patients with chronic hepatitis B. METHODS: This multicenter study proposed a deep learning model (PHLF-Net) incorporating dual-modal ultrasound features and clinical indicators to predict the PHLF risk. The datasets were divided into a training cohort, an internal validation cohort, an internal independent testing cohort, and three external independent testing cohorts. Based on ResNet50 pretrained on ImageNet, PHLF-Net used a progressive training strategy with images of varying granularity and incorporated conventional B-mode and elastography images and clinical indicators related to liver reserve function. RESULTS: In total, 532 HCC patients who underwent hepatectomy at five hospitals were enrolled. PHLF occurred in 147 patients (27.6%, 147/532). The PHLF-Net combining dual-modal ultrasound and clinical indicators demonstrated high effectiveness for predicting PHLF, with AUCs of 0.957 and 0.923 in the internal validation and testing sets, and AUCs of 0.950, 0.860, and 1.000 in the other three independent external testing sets. The performance of PHLF-Net outperformed models of single- and dual-modal US. CONCLUSIONS: Preoperative ultrasound imaging combining clinical indicators can effectively predict the PHLF probability in patients with HCC. In the internal and external validation sets, PHLF-Net demonstrated its usefulness in predicting PHLF.

Circ-ZNF236 mediates stem cells from apical papilla differentiation by regulating LGR4-induced autophagy.

AIM: Human stem cells from the apical papilla (SCAPs) are an appealing stem cell source for tissue regeneration engineering. Circular RNAs (circRNAs) are known to exert pivotal regulatory functions in various cell differentiation processes, including osteogenesis of mesenchymal stem cells. However, few studies have shown the potential mechanism of circRNAs in the odonto/osteogenic differentiation of SCAPs. Herein, we identified a novel circRNA, circ-ZNF236 (hsa_circ_0000857) and found that it was remarkably upregulated during the SCAPs committed differentiation. Thus, in this study, we showed the significance of circ-ZNF236 in the odonto/osteogenic differentiation of SCAPs and its underlying regulatory mechanisms. METHODOLOGY: The circular structure of circ-ZNF236 was identified via Sanger sequencing, amplification of convergent and divergent primers. The proliferation of SCAPs was detected by CCK-8, flow cytometry analysis and EdU incorporation assay. Western blotting, qRT-PCR, Alkaline phosphatase (ALP) and Alizarin red staining (ARS) were performed to explore the regulatory effect of circ-ZNF236/miR-218-5p/LGR4 axis in the odonto/osteogenic differentiation of SCAPs in vitro. Fluorescence in situ hybridization, as well as dual-luciferase reporting assays, revealed that circ-ZNF236 binds to miR-218-5p. Transmission electron microscopy (TEM) and mRFP-GFP-LC3 lentivirus were performed to detect the activation of autophagy. RESULTS: Circ-ZNF236 was identified as a highly stable circRNA with a covalent closed loop structure. Circ-ZNF236 had no detectable influence on cell proliferation but positively regulated SCAPs odonto/osteogenic differentiation. Furthermore, circ-ZNF236 was confirmed as a sponge of miR-218-5p in SCAPs, while miR-218-5p targets LGR4 mRNA at its 3'-UTR. Subsequent rescue experiments revealed that circ-ZNF236 regulates odonto/osteogenic differentiation by miR-218-5p/LGR4 in SCAPs. Importantly, circ-ZNF236 activated autophagy, and the activation of autophagy strengthened the committed differentiation capability of SCAPs. Subsequently, in vivo experiments showed that SCAPs overexpressing circ-ZNF236 promoted bone formation in a rat skull defect model. CONCLUSIONS: Circ-ZNF236 could activate autophagy through increasing LGR4 expression, thus positively regulating SCAPs odonto/osteogenic differentiation. Our findings suggested that circ-ZNF236 might represent a novel therapeutic target to prompt the odonto/osteogenic differentiation of SCAPs.

PD-1 Suppresses the Osteogenic and Odontogenic Differentiation of Stem Cells from Dental Apical Papilla via Targeting SHP2/NF-κB Axis.

Stem cells from the apical papilla (SCAPs) are important for tooth root development and regeneration of root dentin. Here, we examined the expression of programmed cell death protein-1 (PD-1) in SCAPs and investigated the effects of PD-1 on odontogenic and osteogenic differentiation, as well as the relationship between PD-1 and SHP2/NF-κB signals. SCAPs were obtained and cultured in the related medium. The proliferation ability was evaluated by the cell counting kit 8 (CCK-8) and the 5-ethynyl-20-deoxyuridine (EdU) assay. Alkaline phosphatase (ALP) activity assay, ALP staining, Western blot, real-time quantitative reverse-transcription polymerase chain reaction (RT-qPCR), Alizarin Red S (ARS) staining, and immunofluorescence (IF) staining were performed to explore the osteo/odontogenic potential and the involvement of SHP2/NF-κB pathways. Besides, we transplanted SCAPs components into mouse calvaria defects to evaluate osteogenesis in vivo. We found that human SCAPs expressed PD-1 for the first time. PD-1 knockdown enhanced the osteo/odontogenic differentiation of SCAPs by suppressing the SHP2 pathway and activating the NF-κB pathway. Overexpression of PD-1 inhibited the osteogenesis and odontogenesis of SCAPs via activation of SHP2 signal and inhibition of the NF-κB pathway. PD-1 activated SHP2 signal to block NF-κB signal and then played a vital role in osteo/odontogenic differentiation of SCAPs.

Study of radiochemotherapy decision-making for young high-risk low-grade glioma patients using a macroscopic and microscopic combined radiomics model.

OBJECTIVES: As a few types of glioma, young high-risk low-grade gliomas (HRLGGs) have higher requirements for postoperative quality of life. Although adjuvant chemotherapy with delayed radiotherapy is the first treatment strategy for HRLGGs, not all HRLGGs benefit from it. Accurate assessment of chemosensitivity in HRLGGs is vital for making treatment choices. This study developed a multimodal fusion radiomics (MFR) model to support radiochemotherapy decision-making for HRLGGs. METHODS: A MFR model combining macroscopic MRI and microscopic pathological images was proposed. Multiscale features including macroscopic tumor structure and microscopic histological layer and nuclear information were grabbed by unique paradigm, respectively. Then, these features were adaptively incorporated into the MFR model through attention mechanism to predict the chemosensitivity of temozolomide (TMZ) by means of objective response rate and progression free survival (PFS). RESULTS: Macroscopic tumor texture complexity and microscopic nuclear size showed significant statistical differences (p < 0.001) between sensitivity and insensitivity groups. The MFR model achieved stable prediction results, with an area under the curve of 0.950 (95% CI: 0.942-0.958), sensitivity of 0.833 (95% CI: 0.780-0.848), specificity of 0.929 (95% CI: 0.914-0.936), positive predictive value of 0.833 (95% CI: 0.811-0.860), and negative predictive value of 0.929 (95% CI: 0.914-0.934). The predictive efficacy of MFR was significantly higher than that of the reported molecular markers (p < 0.001). MFR was also demonstrated to be a predictor of PFS. CONCLUSIONS: A MFR model including radiomics and pathological features predicts accurately the response postoperative TMZ treatment. CLINICAL RELEVANCE STATEMENT: Our MFR model could identify young high-risk low-grade glioma patients who can have the most benefit from postoperative upfront temozolomide (TMZ) treatment. KEY POINTS: • Multimodal radiomics is proposed to support the radiochemotherapy of glioma. • Some macro and micro image markers related to tumor chemotherapy sensitivity are revealed. • The proposed model surpasses reported molecular markers, with a promising area under the curve (AUC) of 0.95.

Low-rank fusion convolutional neural network for prediction of remission after stereotactic radiosurgery in patients with acromegaly: a proof-of-concept study.

Artificial intelligence approaches to analyze pathological images (pathomic) for outcome prediction have not been sufficiently considered in the field of pituitary research. A total of 5,504 hematoxylin & eosin-stained pathology image tiles from 58 acromegalic patients with a good or poor outcome were integrated with other clinical and genetic information to train a low-rank fusion convolutional neural network (LFCNN). The model was externally validated in 1,536 patches from an external cohort. The primary outcome was the time to the first endocrine remission after stereotactic radiosurgery (SRS). The median time of initial endocrine remission was 43 months (interquartile range [IQR]: 13-60 months) after SRS, and the 24-month initial cumulative remission rate was 57.9% (IQR: 46.4-72.3%). The patient-wise accuracy of the LFCNN model in predicting the primary outcome was 92.9% in the internal test dataset, and the sensitivity and specificity were 87.5 and 100.0%, respectively. The LFCNN model was a strong predictor of initial cumulative remission in the training cohort (hazard ratio [HR] 9.58, 95% confidence interval [CI] 3.89-23.59; p < 0.001) and was higher than that of established prognostic markers. The predictive value of the LFCNN model was further validated in an external cohort (HR 9.06, 95% CI 1.14-72.25; p = 0.012). In this proof-of-concept study, clinically and genetically useful prognostic markers were integrated with digital images to predict endocrine outcomes after SRS in patients with active acromegaly. The model considerably outperformed established prognostic markers and can potentially be used by clinicians to improve decision-making regarding adjuvant treatment choices. © 2022 The Pathological Society of Great Britain and Ireland.

A fractal structural feature related to dynamic crossover in metallic glass-forming liquids.

The dynamic crossover in supercooled liquids initially predicted by model coupling theory has been widely accepted, but its underlying structural origin is still an open issue for glass-forming liquids. By molecular dynamics simulations of binary CuZr liquids, the present work verifies that high pressure could enhance this crossover, facilitating the studies on the structural features at the crossover temperature Tc. We discover that the topological connectivity of icosahedral clusters is responsible for this dynamic crossover, rather than all clusters. Tc is the temperature at which the connectivity degree between these clusters reaches a maximum and the dynamic heterogeneity begins to keep stable. Below Tc, the fractal topological structures appear in the medium-range order scale. The icosahedral clusters with a certain connectivity pattern can be regarded as a fractal structural unit. By employing the established fractal analysis method, the fractal dimension D of the icosahedral network is calculated. Our results indicate that the D value increases monotonically with increasing pressure and the fractal behavior of the icosahedral network is an inherent feature of metallic glasses. We also find similar fractal behavior in clusters with high local five-fold symmetry. Our findings shed light on the origin of a dynamic crossover in the deep supercooled region of metallic glasses and also demonstrate the important role of icosahedral clusters in uncovering the fractal behavior of metallic glass.

SHED-derived exosomes attenuate trigeminal neuralgia after CCI of the infraorbital nerve in mice via the miR-24-3p/IL-1R1/p-p38 MAPK pathway.

BACKGROUND: Microglial activation in the spinal trigeminal nucleus (STN) plays a crucial role in the development of trigeminal neuralgia (TN). The involvement of adenosine monophosphate-activated protein kinase (AMPK) and N-methyl-D-aspartate receptor 1 (NMDAR1, NR1) in TN has been established. Initial evidence suggests that stem cells from human exfoliated deciduous teeth (SHED) have a potential therapeutic effect in attenuating TN. In this study, we propose that SHED-derived exosomes (SHED-Exos) may alleviate TN by inhibiting microglial activation. This study sought to assess the curative effect of SHED-Exos administrated through the tail vein on a unilateral infraorbital nerve chronic constriction injury (CCI-ION) model in mice to reveal the role of SHED-Exos in TN and further clarify the potential mechanism. RESULTS: Animals subjected to CCI-ION were administered SHED-Exos extracted by differential ultracentrifugation. SHED-Exos significantly alleviated TN in CCI mice (increasing the mechanical threshold and reducing p-NR1) and suppressed microglial activation (indicated by the levels of TNF-α, IL-1ß and IBA-1, as well as p-AMPK) in vivo and in vitro. Notably, SHED-Exos worked in a concentration dependent manner. Mechanistically, miR-24-3p-upregulated SHED-Exos exerted a more significant effect, while miR-24-3p-inhibited SHED-Exos had a weakened effect. Bioinformatics analysis and luciferase reporter assays were utilized for target gene prediction and verification between miR-24-3p and IL1R1. Moreover, miR-24-3p targeted the IL1R1/p-p38 MAPK pathway in microglia was increased in CCI mice, and participated in microglial activation in the STN. CONCLUSIONS: miR-24-3p-encapsulated SHED-Exos attenuated TN by suppressing microglial activation in the STN of CCI mice. Mechanistically, miR-24-3p blocked p-p38 MAPK signaling by targeting IL1R1. Theoretically, targeted delivery of miR-24-3p may offer a potential strategy for TN.

Integrative Analysis of ceRNA Networks in human periodontal ligament stem cells under hypoxia.

OBJECTIVE: This study aims to investigate the regulatory effect of hypoxia on human periodontal ligament stem cells (PDLSCs) through RNA sequencing (RNA SEQ). Human PDLSCs were cultured in normoxia (20% O2 ) or hypoxia (2% O2 ). MATERIAL AND METHODS: Total RNA was extracted and sequenced. The expression profiles of circRNAs, lncRNAs, and miRNAs were determined, and the lncRNA/circRNA-miRNA-mRNA networks were analyzed. RESULTS: In total, 15 miRNAs, 449 lncRNAs, and 53 circRNAs were differentially expressed. Among them, 21 circRNAs, 262 lncRNAs, 5 miRNAs, and 5 mRNAs were selected to construct competing endogenous RNA (ceRNA) networks. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses were carried out to explore potential related pathways and regulatory functions. Several ceRNA axes (lncRNA-FTX/circRNA-FAT1-hsa-miR-4781-3p-SMAD5 and circRNA LPAR1-hsa-miR-342-3p-ADAR) may provide a theoretical basis on the study of osteogenic differentiation of PDLSCs under hypoxia. CONCLUSION: This study revealed that the expression profiles of circRNAs, lncRNAs, and miRNAs had changed significantly in PDLSCs cultured in 2% O2 ; specific circRNAs/lncRNAs may play a competitive role in the differentiation of PDLSCs.

Hsa-miR-27b-5p suppresses the osteogenic and odontogenic differentiation of stem cells from human exfoliated deciduous teeth via targeting BMPR1A: An ex vivo study.

AIM: Recently, miR-27b-5p was shown to be abundantly expressed in extracellular vehicles (EVs) from the inflammatory microenvironment. This study determined the role of miR-27b-5p in regulating osteogenic and odontogenic differentiation of stem cells from human exfoliated deciduous teeth (SHEDs) and further examined the regulatory mechanism of bone morphogenetic protein receptor type-1A (BMPR1A). METHODOLOGY: Characteristics of SHEDs and SHEDs-EVs derived from SHEDs were evaluated respectively. The expression of miR-27b-5p in SHEDs and EVs was detected during osteo-induction. Mechanically, SHEDs were treated with miR-27b-5p mimics or an inhibitor, and the osteogenic/odontogenic differentiation and proliferation were assessed. Bioinformatic analysis and luciferase reporter were utilized for target gene prediction and verification. Finally, BMPR1A-overexpressed plasmids were transfected into SHEDs to investigate the participation of the BMPR1A/SMAD4 pathway. Data were analysed using Student's t-test, one-way analysis of variance and Chi-square test. RESULTS: MiR-27b-5p was expressed in both SHEDs and EVs and was significantly increased at the initial stage of differentiation and then decreased in a time-dependent manner (p < .01). Upregulation of miR-27b-5p significantly suppressed osteogenic/odontogenic differentiation of SHEDs and inhibited proliferation (p < .05), whereas inhibition of miR-27b-5p enhanced the differentiation (p < .05). Dual-luciferase reporter assay and pull-down assay confirmed the binding site between miR-27b-5p and BMPR1A (p < .05). The overexpression of BMPR1A rescued the effect of miR-27b-5p, while contributed to the decrease of pluripotency (p < .05). Additionally, miR-27b-5p maintained pluripotency in BMPR1A-overexpressed SHEDs (p < .05). CONCLUSIONS: MiR-27b-5p in SHEDs/EVs was inversely associated with differentiation and suppressed the osteogenic and odontogenic differentiation of SHEDs and maintained the pluripotency of SHEDs partly by shuttering BMPR1A-targeting BMP signalling. Theoretically, inhibition of miR-27b-5p represents a potential strategy to promote osteanagenesis and dentinogenesis. However, miR-27b-5p capsuled EVs might maintain cell pluripotency and self-renewal for non-cell-targeted therapy.

Learning spatiotemporal features of DSA using 3D CNN and BiConvGRU for ischemic moyamoya disease detection.

BACKGROUND: Moyamoya disease (MMD) is a serious intracranial cerebrovascular disease. Cerebral hemorrhage caused by MMD will bring life risk to patients. Therefore, MMD detection is of great significance in the prevention of cerebral hemorrhage. In order to improve the accuracy of digital subtraction angiography (DSA) in the diagnosis of ischemic MMD, in this paper, a deep network architecture combined with 3D convolutional neural network (3D CNN) and bidirectional convolutional gated recurrent unit (BiConvGRU) is proposed to learn the spatiotemporal features for ischemic MMD detection. METHODS: Firstly, 2D convolutional neural network (2D CNN) is utilized to extract spatial features for each frame of DSA. Secondly, the long-term spatiotemporal features of DSA sequence are extracted by BiConvGRU. Thirdly, the short-term spatiotemporal features of DSA are further extracted by 3D convolutional neural network (3D CNN). In addition, different features are extracted when gray images and optical flow images pass through the network, and multiple features are extracted by features fusion. Finally, the fused features are utilized to classify. RESULTS: The proposed method was quantitatively evaluated on a data sets of 630 cases. The experimental results showed a detection accuracy of 0.9788, sensitivity and specificity were 0.9780 and 0.9796, respectively, and area under curve (AUC) was 0.9856. Compared with other methods, we can get the highest accuracy and AUC. CONCLUSIONS: The experimental results show that the proposed method is stable and reliable for ischemic MMD detection, which provides an option for doctors to accurately diagnose ischemic MMD.

Deep learning and radiomics based automatic diagnosis of hippocampal sclerosis.

Accurate and rapid segmentation of the hippocampus can help doctors perform intractable temporal lobe epilepsy (TLE) preoperative evaluations to identify good surgical candidates. This study aims to establish a radiomics system for the automatic diagnosis of hippocampal sclerosis with the help of machine learning. A total of 240 cases were analysed to develop a diagnostic model. First, an automatic hippocampal segmentation process was established that exploits a priori knowledge of the relatively fixed location of the hippocampus in brain partitions, as well as a deep-learning segmentation network based on an Attention U-net. Then, we extracted 527 radiomics features from each side of the segmented hippocampus. The iterative sparse representation based on feature selection and a support vector machine classifier were finally used to establish the diagnostic model of hippocampal sclerosis. The diagnostic model consists of two consecutive steps: distinguish hippocampal sclerosis (HS) from normal control (NC) and detect whether the HS is located on the left or right side. When the automatic diagnosis model identified HS and NC, the sensitivity and specificity reached 0.941 and 0.917 in the 10-fold cross-validation set and 0.920 and 0.909 in the independent testing set. When the diagnostic model detected HS lateralization, the sensitivity and specificity reached 0.923 and 0.920 in cross-validation and 0.909 and 0.929 in independent testing. Our results show that the developed radiomics model can help detect TLE patients with hippocampal sclerosis and has the potential to simplify preoperative evaluations and select surgical candidates.

Extracellular vesicles from the inflammatory microenvironment regulate the osteogenic and odontogenic differentiation of periodontal ligament stem cells by miR-758-5p/LMBR1/BMP2/4 axis.

BACKGROUND: Extracellular vesicles (EVs) play a key role in constructing a microenvironment that favors the differentiation of stem cells. The present work aimed to determine the molecular mechanisms by which EV derived from inflammatory dental pulp stem cell (iDPSC-EV) influence periodontal ligament stem cells (PDLSCs) and provide a potential strategy for bone and dental pulp regeneration. METHODS: The osteogenic and odontogenic differentiation was assessed by quantitative real-time polymerase chain reaction (qRT-PCR), western blot, alkaline phosphatase (ALP) activity assay, ALP staining, alizarin red S (ARS) staining, and immunofluorescence staining. To detect proliferation, the Cell Counting Kit-8 (CCK-8) assay, and flow cytometry analysis were used. EVs were isolated by the Exoperfect kit and ultrafiltration and characterized by transmission electron microscopy (TEM), nanoparticle tracking analysis (NTA), and western blot. The expression profile of miRNAs in EVs was studied using miRNA sequence and bioinformatics, and one of the upregulated miRNAs was evaluated on PDLSCs. RESULTS: The inflammatory microenvironment stimulated osteogenic and odontogenic differentiation of DPSCs and iDPSC-EV behaved alike on PDLSCs. MiR-758-5p was upregulated in iDPSC-EV and was demonstrated to play a significant role in the osteogenic and odontogenic commitment of PDLSCs. A dual-luciferase reporter assay confirmed the binding site between miR-758-5p and limb development membrane protein 1 (LMBR1). The knockdown of LMBR1 also enhanced the above potential. Mechanically, bone morphogenetic protein (BMP) signaling was activated. CONCLUSIONS: EVs from the inflammatory microenvironment enhanced the osteogenic and odontogenic differentiation of PDLSCs partly by shuttering LMBR1-targeting miR-758-5p via BMP signaling.

Prediction of programmed cell death protein 1 in hepatocellular carcinoma patients using radiomics analysis with radiofrequency-based ultrasound multifeature maps.

BACKGROUND: This study explored the feasibility of radiofrequency (RF)-based radiomics analysis techniques for the preoperative prediction of programmed cell death protein 1 (PD-1) in patients with hepatocellular carcinoma (HCC). METHODS: The RF-based radiomics analysis method used ultrasound multifeature maps calculated from the RF signals of HCC patients, including direct energy attenuation (DEA) feature map, skewness of spectrum difference (SSD) feature map, and noncentrality parameter S of the Rician distribution (NRD) feature map. From each of the above ultrasound maps, 345 high-throughput radiomics features were extracted. Then, the useful radiomics features were selected by the sparse representation method and input into support vector machine (SVM) classifier for PD-1 prediction. RESULTS AND CONCLUSION: Among all the RF-based prediction models and the ultrasound grayscale comparative model, the RF-based model using all of the three ultrasound feature maps had the highest prediction accuracy (ACC) and area under the curve (AUC), which were 92.5% and 94.23%, respectively. The method proposed in this paper is effective for the meaningful feature extraction of RF signals and can effectively predict PD-1 in patients with HCC.

Extracellular IL-37 promotes osteogenic and odontogenic differentiation of human dental pulp stem cells via autophagy.

The osteogenic and odontogenic differentiation of dental pulp stem cells (DPSCs) contribute to restoration and regeneration of dental tissue. Previous study indicated that interleukin-37 (IL-37) was an anti-inflammatory factor that affected other pro-inflammatory signals. The aim of this study was to explore the effects of IL-37 on the differentiation of DPSCs. DPSCs were cultured in growth medium with different concentrations of IL-37. We selected the optimal concentration for the following experiments by alkaline phosphatase (ALP) activity analysis, quantitative reverse-transcription polymerase chain reaction (qRT-PCR) and Western blot. Cell counting kit assay (CCK-8) and 5-Ethynyl-2'-Deoxyuridine (EdU) assay were conducted to assess the effects of IL-37 on the proliferation of DPSCs. ALP activity assay and staining, alizarin red S (ARS) staining, qRT-PCR, Western blot as well as immunofluorescence staining were conducted to assess differentiation ability of DPSCs. Western blot, immunofluorescence staining and transmission electron microscopy (TEM) were utilized to examine cell autophagy. Results showed that IL-37 enhanced the osteogenic and odontogenic differentiation ability of DPSCs with no significant influence on the proliferation of DPSCs. Autophagy in DPSCs was activated by IL-37. Activation of autophagy enhanced osteogenesis and odontogenesis of DPSCs, whereas inhibition of autophagy suppressed DPSCs osteogenic and odontogenic differentiation. In conclusion, IL-37 increased osteogenic and odontogenic differentiation via autophagy.

Ultrasound-based radiomics analysis for preoperative prediction of central and lateral cervical lymph node metastasis in papillary thyroid carcinoma: a multi-institutional study.

BACKGROUND: An accurate preoperative assessment of cervical lymph node metastasis (LNM) is important for choosing an optimal therapeutic strategy for papillary thyroid carcinoma (PTC) patients. This study aimed to develop and validate two ultrasound (US) nomograms for the individual prediction of central and lateral compartment LNM in patients with PTC. METHODS: A total of 720 PTC patients from 3 institutions were enrolled in this study. They were categorized into a primary cohort, an internal validation, and two external validation cohorts. Radiomics features were extracted from conventional US images. LASSO regression was used to select optimized features to construct the radiomics signature. Two nomograms integrating independent clinical variables and radiomics signature were established with multivariate logistic regression. The performance of the nomograms was assessed with regard to discrimination, calibration, and clinical usefulness. RESULTS: The radiomics scores were significantly higher in patients with central/lateral LNM. A radiomics nomogram indicated good discrimination for central compartment LNM, with an area under the curve (AUC) of 0.875 in the training set, the corresponding value in the validation sets were 0.856, 0.870 and 0.870, respectively. Another nomogram for predicting lateral LNM also demonstrated good performance with an AUC of 0.938 and 0.905 in the training and internal validation cohorts, respectively. The AUC for the two external validation cohorts were 0.881 and 0.903, respectively. The clinical utility of the nomograms was confirmed by the decision curve analysis. CONCLUSION: The nomograms proposed here have favorable performance for preoperatively predicting cervical LNM, hold promise for optimizing the personalized treatment, and might greatly facilitate the decision-making in clinical practice.

Combined Radiomics Model for Prediction of Hematoma Progression and Clinical Outcome of Cerebral Contusions in Traumatic Brain Injury.

BACKGROUND: Traumatic brain injury is a common and devastating injury that is the leading cause of neurological disability and death worldwide. Patients with cerebral lobe contusion received conservative treatment because of their mild manifestations, but delayed intracranial hematoma may increase and even become life-threatening. We explored the noninvasive method to predict the prognosis of progression and Glasgow Outcome Scale (GOS) by using a quantitative radiomics approach and statistical analysis. METHODS: Eighty-eight patients who were pathologically diagnosed were retrospectively studied. The radiomics method developed in this work included image segmentation, feature extraction, and feature selection. The nomograms were established based on statistical analysis and a radiomics method. We conducted a comparative study of hematoma progression and GOS between the clinical factor alone and fusion radiomics features. RESULTS: Nineteen clinical factors, 513 radiomics features, and 116 locational features were considered. Among clinical factors, international normalized ratio, prothrombin time, and fibrinogen were enrolled for hematoma progression. As for GOS, treatment strategy, age, Glasgow Coma Scale score, and blood platelet were associated factors. Eight features for GOS and five features for hematoma progression were filtered by using sparse representation and locality preserving projection-combined method. Four nomograms were constructed. After fusion radiomics features, area under the curve of hematoma progression prediction increased from 0.832 to 0.899, whereas GOS prediction went from 0.794 to 0.844. CONCLUSIONS: A radiomic-based model that merges radiomics and clinical features is a noninvasive approach to predict hematoma progression and clinical outcomes of cerebral contusions in traumatic brain injury.

MRI-based brain tumor segmentation using FPGA-accelerated neural network.

BACKGROUND: Brain tumor segmentation is a challenging problem in medical image processing and analysis. It is a very time-consuming and error-prone task. In order to reduce the burden on physicians and improve the segmentation accuracy, the computer-aided detection (CAD) systems need to be developed. Due to the powerful feature learning ability of the deep learning technology, many deep learning-based methods have been applied to the brain tumor segmentation CAD systems and achieved satisfactory accuracy. However, deep learning neural networks have high computational complexity, and the brain tumor segmentation process consumes significant time. Therefore, in order to achieve the high segmentation accuracy of brain tumors and obtain the segmentation results efficiently, it is very demanding to speed up the segmentation process of brain tumors. RESULTS: Compared with traditional computing platforms, the proposed FPGA accelerator has greatly improved the speed and the power consumption. Based on the BraTS19 and BraTS20 dataset, our FPGA-based brain tumor segmentation accelerator is 5.21 and 44.47 times faster than the TITAN V GPU and the Xeon CPU. In addition, by comparing energy efficiency, our design can achieve 11.22 and 82.33 times energy efficiency than GPU and CPU, respectively. CONCLUSION: We quantize and retrain the neural network for brain tumor segmentation and merge batch normalization layers to reduce the parameter size and computational complexity. The FPGA-based brain tumor segmentation accelerator is designed to map the quantized neural network model. The accelerator can increase the segmentation speed and reduce the power consumption on the basis of ensuring high accuracy which provides a new direction for the automatic segmentation and remote diagnosis of brain tumors.