Suppression of TCF4 promotes a ZC3H12A-mediated self-sustaining inflammatory feedback cycle involving IL-17RA/IL-17RE epidermal signaling.

IL-17C is an epithelial cell-derived proinflammatory cytokine whose transcriptional regulation remains unclear. Analysis of the IL17C promoter region identified TCF4 as putative regulator, and siRNA knockdown of TCF4 in human keratinocytes (KCs) increased IL17C. IL-17C stimulation of KCs (along with IL-17A and TNF-α stimulation) decreased TCF4 and increased NFKBIZ and ZC3H12A expression in an IL-17RA/RE-dependent manner, thus creating a feedback loop. ZC3H12A (MCPIP1/Regnase-1), a transcriptional immune-response regulator, also increased following TCF4 siRNA knockdown, and siRNA knockdown of ZC3H12A decreased NFKBIZ, IL1B, IL36G, CCL20, and CXCL1, revealing a proinflammatory role for ZC3H12A. Examination of lesional skin from the KC-Tie2 inflammatory dermatitis mouse model identified decreases in TCF4 protein concomitant with increases in IL-17C and Zc3h12a that reversed following the genetic elimination of Il17c, Il17ra, and Il17re and improvement in the skin phenotype. Conversely, interference with Tcf4 in KC-Tie2 mouse skin increased Il17c and exacerbated the inflammatory skin phenotype. Together, these findings identify a role for TCF4 in the negative regulation of IL-17C, which, alone and with TNF-α and IL-17A, feed back to decrease TCF4 in an IL-17RA/RE-dependent manner. This loop is further amplified by IL-17C-TCF4 autocrine regulation of ZC3H12A and IL-17C regulation of NFKBIZ to promote self-sustaining skin inflammation.

Systems-based identification of the Hippo pathway for promoting fibrotic mesenchymal differentiation in systemic sclerosis.

Systemic sclerosis (SSc) is a devastating autoimmune disease characterized by excessive production and accumulation of extracellular matrix, leading to fibrosis of skin and other internal organs. However, the main cellular participants in SSc skin fibrosis remain incompletely understood. Here using differentiation trajectories at a single cell level, we demonstrate a dual source of extracellular matrix deposition in SSc skin from both myofibroblasts and endothelial-to-mesenchymal-transitioning cells (EndoMT). We further define a central role of Hippo pathway effectors in differentiation and homeostasis of myofibroblast and EndoMT, respectively, and show that myofibroblasts and EndoMTs function as central communication hubs that drive key pro-fibrotic signaling pathways in SSc. Together, our data help characterize myofibroblast differentiation and EndoMT phenotypes in SSc skin, and hint that modulation of the Hippo pathway may contribute in reversing the pro-fibrotic phenotypes in myofibroblasts and EndoMTs.

Pipecolic acid mitigates ferroptosis in diabetic retinopathy by regulating GPX4-YAP signaling.

Diabetic retinopathy (DR) is currently recognized as the leading cause of end-stage eye disease. Pipecolic acid, a metabolite, has a significant regulatory effect on several pathological processes. However, the exact mechanism by which it causes damage in diabetic retinopathy is unknown. Between September 2021 and December 2022, 40 patients were retrospectively examined and divided into two groups: the healthy group (n = 20) and the DR group (n = 20). Metabolomic analysis found that pipecolic acid plays an important role in this process. Streptozotocin-induced diabetic mice and high-glucose cultured human retinal capillary endothelial cells (HRCECs) were then treated with pipecolic acid. Several oxidative stress measurements and RNA sequencing of retinal cells were tested. A gene interaction study was conducted using bioinformatics. Comparison of serological metabolites between healthy volunteers and DR patients showed that pipecolic acid was significantly lower in DR patients, and there was a negative correlation between the level of pipecolic acid with blood glucose and glycated hemoglobin. Yes-associated protein (YAP) mRNA, Malondialdehyde (MDA), and reactive oxygen species (ROS) levels were significantly higher in diabetic mice, but glutathione peroxidase (GSH-Px) levels were significantly lower. Pipecolic acid significantly alleviated oxidative stress and YAP expression. The number of vascular tubes was significantly higher in the DR group, and pipecolic acid treatment significantly reduced tube formation. RNA-Sequencing analysis revealed that YAP and glutathione-dependent lipid hydroperoxidase glutathione peroxidase 4 (GPX4) expression was reduced, and functional enrichment analysis revealed that ferroptosis and Hippo signaling pathways play an important role in this process. Additionally, pipecolic acid's ability to improve DR is diminished after YAP and GPX4 ablation. This study found that pipecolic acid, as a metabolite, may impede the progression of DR by inhibiting the YAP-GPX4 signaling pathway.

Non-anticoagulant factors affecting coagulation in the extracorporeal circulation circuit and the development of an individualized regional citrate anticoagulation protocol for hemodialysis: A real-world retrospective study.

OBJECTIVE: To investigate non-anticoagulant factors that affect blood coagulation in the extracorporeal circulation (ECC) circuit of regional citrate anticoagulation (RCA) protocol for hemodialysis (HD). METHOD: The clinical characteristics of patients undergoing an individualized RCA protocol for HD between February 2021 and March 2022 were collected; Coagulation scores, pressures in various parts of the ECC circuit, the incidence of coagulation, and citrate concentrations in the ECC circuit during treatment were determined, and non-anticoagulant factors affecting coagulation in the ECC circuit were analyzed. RESULT: The lowest clotting rate was 2.8% in patients with arteriovenous fistula in various vascular access. Patients on Fresenius dialysis had a lower rate of clotting in the cardiopulmonary bypass line than patients on other brands of dialyzer. Low-throughput dialyzers are less likely to clot than high-throughput dialyzers. There are significant differences in the incidence of coagulation among different nurses during citrate anticoagulant hemodialysis. CONCLUSION: In the process of citrate anticoagulant hemodialysis, non-anticoagulant factors such as coagulation status, vascular access, dialyzer selection, and operator quality will affect the anticoagulant effect.

Patching Retinal Breaks with Chitosan for Retinal Detachment in Rabbits.

BACKGROUND: Rhegmatogenous retinal detachment (RRD) is caused by one or more full-thickness retinal breaks. The current RRD treatments have several drawbacks. Chitosan is one of the most commonly used natural polymers for wound healing and has been demonstrated to be biodegradable, biocompatible, non-toxic, bioadhesive, and bioactive. This study aimed to determine the reliability and effectiveness of chitosan for sealing retinal breaks in rabbits. METHODS: Eighteen blue purple rabbits were randomly divided into three groups: chitosan (n = 6), RRD (n = 6), and control (n = 6). The RRD model was established using vitrectomy, making retinal holes, and subretinal fluid injection in the RRD and chitosan groups. One week after the establishment of the model, chitosan was applied within the range of the holes in the chitosan group, and the vitreous body was filled with perfusion fluid. Except the chitosan treatment, the RRD group underwent the same procedure. Intraocular pressure (IOP) measurement, fundus photography, B-mode ultrasound, optical coherence tomography (OCT), histology, and enzyme linked immunosorbent assay (ELISA) were performed. RESULTS: Retinas of all eyes in the RRD group were detached, whereas those of all eyes in the chitosan group remained attached. The concentrations of epidermal growth factor (EGF), fibroblast growth factor (FGF)-2, transforming growth factor ß (TGF-ß), vascular endothelial growth factor (VEGF), interleukin-6 (IL-6), and IL-8 in the vitreous fluid of the RRD group were significantly higher than those of the control group (p < 0.05). Furthermore, the concentrations of EGF, FGF-2, TGF-ß, and VEGF in the vitreous fluid of the chitosan group were higher compared to those of the RRD group (p < 0.05), whereas the concentrations of IL-6 and IL-8 were lower (p < 0.05). CONCLUSIONS: Chitosan may be a reliable method for sealing retinal breaks. Moreover, chitosan can maintain high levels of growth factors and reduce inflammatory factors in the vitreous, which may reduce and delay the death of retinal cells and help restore visual function after retinal repositioning.

Single cell and spatial sequencing define processes by which keratinocytes and fibroblasts amplify inflammatory responses in psoriasis.

The immunopathogenesis of psoriasis, a common chronic inflammatory disease of the skin, is incompletely understood. Here we demonstrate, using a combination of single cell and spatial RNA sequencing, IL-36 dependent amplification of IL-17A and TNF inflammatory responses in the absence of neutrophil proteases, which primarily occur within the supraspinous layer of the psoriatic epidermis. We further show that a subset of SFRP2+ fibroblasts in psoriasis contribute to amplification of the immune network through transition to a pro-inflammatory state. The SFRP2+ fibroblast communication network involves production of CCL13, CCL19 and CXCL12, connected by ligand-receptor interactions to other spatially proximate cell types: CCR2+ myeloid cells, CCR7+ LAMP3+ dendritic cells, and CXCR4 expressed on both CD8+ Tc17 cells and keratinocytes, respectively. The SFRP2+ fibroblasts also express cathepsin S, further amplifying inflammatory responses by activating IL-36G in keratinocytes. These data provide an in-depth view of psoriasis pathogenesis, which expands our understanding of the critical cellular participants to include inflammatory fibroblasts and their cellular interactions.

Topical histone deacetylase 1 inhibitor Entinostat ameliorates psoriasiform dermatitis through suppression of IL-17A response.

BACKGROUND: Biologics against IL-17A, IL-23 and TNF-α achieve a great success in treating psoriasis. However, the majority of patients still have some residual lesions left and require combination therapy to reach complete clearance. Topical medicine is an optional choice but only has limited categories. Besides, drug resistance is very often. Thus, topical medicine targeting new signaling pathway is still in an urgent need in the biologics era. OBJECTIVE: To investigate the role of topical Entinostat, a selective inhibitor of histone deacetylases 1 (HDAC1) that has been tested in clinic trials to treat solid tumors and hematological malignancies, in psoriasis therapy. METHODS: Efficacious Entinostat were tested in a mouse imiquimod (IMQ)-induced psoriasiform dermatitis (PsD) model. An in vitro model consisting of human CD4 + T cell, murine T cells and NHEKs were used to screen Entinostat for inhibition of cutaneous inflammatory genes. RESULTS: Topical application of Entinostat significantly improved psoriasiform inflammation in imiquimod-induced mice model with great reduction of IL-17A+ Î³Î´T cell infiltration in skin. Entinostat is powerful agent in inhibition of Th17 cell generation and the expression of psoriasis-related inflammatory mediators by primary keratinocytes upon CD4+ T cells stimulation. CONCLUSION: Our findings suggest Entinostat is a promising topical medicine for psoriasis treatment.

A comparative study of high school mathematics teachers' audible teaching language: A student satisfaction perspective.

Teachers' audible teaching language is essential for organizing classroom instruction. This study used a questionnaire to compare expert, skilled, and novice high school mathematics teachers' audible teaching language from the perspective of student satisfaction. The sample was selected using a purposive sampling technique, and the participants were students from a key high school in Changsha, China. A research framework and research instrument with good reliability and validity were constructed for this study. The data were analyzed using SPSS 22.0 and AMOS 22.0. The results showed 263 valid questionnaires, good measurement model fit, and high reliability and validity of the questionnaire. It was found that: (1) students were highly satisfied with the audible teaching language of high school mathematics teachers; (2) student satisfaction with the audible teaching language of skilled, expert, and novice mathematics teachers declined in order, but there was no significant difference overall; (3) students were more satisfied with expert mathematics teachers than with novice teachers in terms of the tone and adaptability of the audible teaching language. The researchers discussed the study's results, suggested how pre-service and post-service mathematics teachers can improve the quality of their audible teaching language, and pointed out the value and limitations of the study.

Identification of kukoamine a as an anti-osteoporosis drug target using network pharmacology and experiment verification.

BACKGROUND: Osteoporosis (OP) is a major and growing public health problem characterized by decreased bone mineral density and destroyed bone microarchitecture. Previous studies found that Lycium Chinense Mill (LC) has a potent role in inhibiting bone loss. Kukoamine A (KuA), a bioactive compound extract from LC was responsible for the anti-osteoporosis effect. This study aimed to investigate the anti-osteoporosis effect of KuA isolated from LC in treating OP and its potential molecular mechanism. METHOD: In this study, network pharmacology and molecular docking were investigated firstly to find the active ingredients of LC such as KuA, and the target genes of OP by the TCMSP platform. The LC-OP-potential Target gene network was constructed by the STRING database and network maps were built by Cytoscape software. And then, the anti-osteoporotic effect of KuA in OVX-induced osteoporosis mice and MC3T3-E1 cell lines were investigated and the potential molecular mechanism including inflammation level, cell apoptosis, and oxidative stress was analyzed by dual-energy X-ray absorptiometry (DXA), micro-CT, ELISA, RT-PCR, and Western Blotting. RESULT: A total of 22 active compounds were screened, and we found KuA was identified as the highest active ingredient. Glycogen Phosphorylase (PYGM) was the target gene associated with a maximum number of active ingredients of LC and regulated KuA. In vivo, KuA treatment significantly increased the bone mineral density and improve bone microarchitecture for example increased BV/TV, Tb.N and Tb.Th but reduced Tb.Sp in tibia and lumber 4. Furthermore, KuA increased mRNA expression of osteoblastic differentiation-related genes in OVX mice and protects against OVX-induced cell apoptosis, oxidative stress level and inflammation level. In vitro, KuA significantly improves osteogenic differentiation and mineralization in cells experiment. In addition, KuA also attenuated inflammation levels, cell apoptosis, and oxidative stress level. CONCLUSION: The results suggest that KuA could protect against the development of OP in osteoblast cells and ovariectomized OP model mice and these found to provide a better understanding of the pharmacological activities of KuA again bone loss.

Keratinocytes sense and eliminate CRISPR DNA through STING/IFN-κ activation and APOBEC3G induction.

CRISPR/Cas9 has been proposed as a treatment for genetically inherited skin disorders. Here we report that CRISPR transfection activates STING-dependent antiviral responses in keratinocytes, resulting in heightened endogenous interferon (IFN) responses through induction of IFN-κ, leading to decreased plasmid stability secondary to induction of the cytidine deaminase gene APOBEC3G. Notably, CRISPR-generated KO keratinocytes had permanent suppression of IFN-κ and IFN-stimulated gene (ISG) expression, secondary to hypermethylation of the IFNK promoter region by the DNA methyltransferase DNMT3B. JAK inhibition via baricitinib prior to CRISPR transfection increased transfection efficiency, prevented IFNK promoter hypermethylation, and restored normal IFN-κ activity and ISG responses. This work shows that CRISPR-mediated gene correction alters antiviral responses in keratinocytes, has implications for future gene therapies for inherited skin diseases using CRISPR technology, and suggests pharmacologic JAK inhibition as a tool for facilitating and attenuating inadvertent selection effects in CRISPR/Cas9 therapeutic approaches.

Preservice mathematics teachers' perceptions of mathematical problem solving and its teaching: A case from China.

Preservice mathematics teachers' accurate understanding of mathematical problem solving and its teaching is key to the performance of their professional quality. This study aims to investigate preservice mathematics teachers' understanding of problem solving and its teaching and compares it with the understanding of in-service mathematics teachers. After surveying 326 in-service mathematics teachers, this study constructs a reliable and valid tool for the cognition of mathematical problem solving and its teaching and conducts a questionnaire survey on 26 preservice mathematics teachers. Survey results reveal that preservice mathematics teachers have a good understanding of mathematical problem solving and its teaching and are more confident in the transfer value of problem solving ability. By contrast, in-service teachers are more optimistic that problem solving requires exploration, continuous thinking, and the participation of metacognition. This article concludes that preservice mathematics teachers should focus more on the initiative and creativity of students and put students at the center of education. In addition, teacher educators should provide more teaching practice opportunities for preservice teachers. The findings also show that in-service teachers' understanding of problem solving and its teaching is inferior to that of preservice teachers on some indicators, implying the importance of post-service training for in-service teachers.

Evaluation of Foldable Capsular Vitreous Body Implantation Surgery.

Background: Foldable capsular vitreous body (FCVB), a novel artificial vitreous substitute product, has been used clinically in recent years. The aim of this study was to evaluate the outcomes and complications of FCVB implantation surgery during the postoperative period. Methods: We performed a prospective, nonrandomized study from November 2021 to March 2022. Eight patients with severe retinal detachment that could not be easily reattached were included in this study. Before and after surgery, visual acuity (VA), intraocular pressure (IOP), slit-lamp microscopy, optical coherence tomography (OCT), B-scan and CT were performed. Results: After the operation, the FCVB was well distributed in the vitreous cavity and supported the retina according to the B-scan and CT images. During the follow-up period, no vitreous hemorrhage or retinal detachment was found in any of the patients. On the first postoperative day, the average IOP increased from 9.6 ± 7.7 mmHg preoperatively to 13.8 ± 14.3 mmHg. Although the IOP of two patients fell outside the normal range, IOP was finally held steady after the fifth postoperative day in all cases. In addition, three patients (37.5%) experienced eye ache, and after taking a Saridon tablet, the pain was greatly alleviated. Moreover, no adverse events, such as silicone oil (SO) spillage and emulsification or serious complications, were observed. Conclusion: The current vitreous substitute FCVB is effective and safe for treating complicated retinal detachments in ophthalmic applications. Further multiple-center clinical designs should focus on indications and complications of FCVB during long-term follow-up periods.

Metabolomic study of eyeball rupture and patients with cataracts in aqueous humor.

The purpose of the present study was to identify metabolic biomarkers and study the metabolic changes in relation to cataracts and eyeball rupture in human aqueous humor. This case-control study included 3 patients with traumatic ocular rupture treated by surgery as the control group, 10 patients with severe cataracts as the severe cataracts group and 10 patients with mild cataracts as the mild cataracts group. The present study used liquid chromatography-mass spectrometry to analyze the metabolomics of aqueous humor samples. Databases including the Kyoto Encyclopedia of Genes and Genomes and MetaboAnalyst were used to find potential pathways for metabolites. Aqueous humor metabolic spectrum can competently distinguish patients with different degrees of cataracts from the control group. A total of 34 metabolites were identified as potential biomarkers that could distinguish patients with different degrees of cataracts; 36 metabolites were identified as potential biomarkers that could distinguish patients with severe cataracts from the control group; 34 metabolites were identified as potential biomarkers that could distinguish patients with mild cataracts from controls. In pathway analysis, glycerolphospholipid metabolism was highly affected, which meant that these metabolic markers serve an important role in the regulation of this pathway. The present study identified valuable metabolic biomarkers and pathways, which is helpful for an improved understanding of the pathogenesis of cataracts. This discovery has transformation value for the development of new treatment methods for cataracts.

Profiling Serum Cytokines and Anticytokine Antibodies in Psoriasis Patients.

Cytokines like IL-17A have been consistently found to be elevated in psoriatic lesional skin, and therapeutic antibodies to IL-17 have demonstrated efficacy in treating psoriatic skin and joint disease. However, results about the circulating cytokines in psoriasis patients remained controversial. Anticytokine autoantibodies (ACAAs) were detected in various autoimmune diseases but remained largely unknown in psoriasis. We aimed to investigate the serum levels of cytokines and ACAAs in psoriasis patients. The study included 44 biologics-naive psoriasis patients and 40 healthy controls. Serum cytokines and the corresponding autoantibodies were measured by multiplex bead-based technology. The bioactivity of serum IL-17A was determined by IL-8 production in primary keratinocytes. Herein, we found serum levels of IL-12B (median: 6.16 vs. 9.03, p = 0.0194) and Th17 cytokines (IL-17A: median: 0.32 vs. 1.05, p = 0.0026; IL-22: median: 4.41 vs. 4.41, p = 0.0120) were increased in psoriasis patients. More interestingly, bioactive IL-17A was identified in a proportion of patients and positively correlated with disease severity. A few of cytokines were closely associated with each other and formed into a distinct panel in psoriasis. Of 13 anticytokine antibodies, anti-IL-22 was moderately lower (median: 262.8 vs.190.5, p = 0.0418), and anti-IL-15 was slightly higher (median: 25.5 vs. 30.5, p = 0.0069) in psoriasis than controls. None of ACAAs was related to disease severity. Consequently, the ratios of antibodies to cytokines varied with the pattern of cytokines. In summary, our finding suggested that the levels of circulating bioactive IL-17A were associated with disease activity in psoriasis patients. In contrast, the titers of ACAAs were not significantly altered nor correlated with disease severity. However, the functionality of ACAAs remains to be further demonstrated in vitro in future studies.

LAD-GCN: Automatic diagnostic framework for quantitative estimation of growth patterns during clinical evaluation of lung adenocarcinoma.

Quantitative estimation of growth patterns is important for diagnosis of lung adenocarcinoma and prediction of prognosis. However, the growth patterns of lung adenocarcinoma tissue are very dependent on the spatial organization of cells. Deep learning for lung tumor histopathological image analysis often uses convolutional neural networks to automatically extract features, ignoring this spatial relationship. In this paper, a novel fully automated framework is proposed for growth pattern evaluation in lung adenocarcinoma. Specifically, the proposed method uses graph convolutional networks to extract cell structural features; that is, cells are extracted and graph structures are constructed based on histopathological image data without graph structure. A deep neural network is then used to extract the global semantic features of histopathological images to complement the cell structural features obtained in the previous step. Finally, the structural features and semantic features are fused to achieve growth pattern prediction. Experimental studies on several datasets validate our design, demonstrating that methods based on the spatial organization of cells are appropriate for the analysis of growth patterns.

Relationship Between Risk Factors and Macular Thickness in Patients with Early Diabetic Retinopathy.

Purpose: The purpose of this study was to explore the changes in macular thickness (MT) in normal people, patients without obvious diabetic retinopathy (NDR) and patients with nonproliferative diabetic retinopathy (NPDR) and to study the possible risk factors for early diabetic retinopathy (DR). Methods: Thirty-one healthy individuals, 40 people with no sign of DR and 60 people with mild NPDR were included in this cross-sectional study. All patients underwent a complete ophthalmological examination. Optical coherence tomography (OCT) was used to measure the MT of each participant. The potential relationship between MT and systemic risk factors for DR, including diabetes duration, body mass index (BMI), hemoglobin A1c (HbA1c), serum lipids, and blood pressure, was analyzed. Results: The MT of the right and left eyes in the central and inner ring regions of the NPDR group and NDR group were significantly different from that in the control group. The MTs of the right and left eyes in the central region and inner ring region were also significantly different between the NPDR group and NDR group, but the MTs of the right and left eyes in the outer ring region were not significantly different among the three groups. Diabetic duration, total cholesterol (TC), triglycerides (TGs), systolic pressure, and diastolic pressure were positively correlated with the MT of the right and left eyes in the central region. Conclusion: MT increases, especially in the central region and inner ring, may be the first structural retinal change in diabetic patients and is related to the duration of diabetes, TC, TG, systolic pressure and diastolic pressure.

Secreted Protein Acidic and Rich in Cysteine Mediates the Development and Progression of Diabetic Retinopathy.

Backgrounds: Diabetic retinopathy (DR) is one of the most severe microvascular complications of diabetes mellitus (DM). Secreted protein acidic and rich in cysteine (SPARC) has been found to play an important role in many diseases, but its role and mechanism in DR remain unknown. Methods: We studied the role of SPARC and integrin ß1 in vascular pathophysiology and identified potential therapeutic translation. The SPARC levels were tested in human serum and vitreous by ELISA assay, and then the Gene Expression Omnibus (GEO) dataset was used to understand the key role of the target gene in DR. In human retinal capillary endothelial cells (HRCECs), we analyzed the mRNA and protein level by RT-PCR, immunohistochemistry, and Western blotting. The cell apoptosis, cell viability, and angiogenesis were analyzed by flow cytometry, CCK-8, and tube formation. Results: In this study, we investigated the role of SPARC in the development and progression of human DR and high glucose-induced HRCEC cells and found that the SPARC-ITGB1 signaling pathway mimics early molecular and advanced neurovascular pathophysiology complications of DR. The result revealed that DR patients have a high-level SPARC expression in serum and vitreous. Knockdown of SPARC could decrease the expressions of inflammatory factors and VEGFR, inhibit cell apoptosis and angiogenesis, and increase cell viability by regulating integrin ß1 in HRCECs. Conclusion: SPARC promotes diabetic retinopathy via the regulation of integrin ß1. The results of this study can provide a potential therapeutic application for the treatment of DR.

SymReg-GAN: Symmetric Image Registration With Generative Adversarial Networks.

Symmetric image registration estimates bi-directional spatial transformations between images while enforcing an inverse-consistency. Its capability of eliminating bias introduced inevitably by generic single-directional image registration allows more precise analysis in different interdisciplinary applications of image registration, e.g., computational anatomy and shape analysis. However, most existing symmetric registration techniques especially for multimodal images are limited by low speed from the commonly-used iterative optimization, hardship in exploring inter-modality relations or high labor cost for labeling data. We propose SymReg-GAN to shatter these limits, which is a novel generative adversarial networks (GAN) based approach to symmetric image registration. We formulate symmetric registration of unimodal/multimodal images as a conditional GAN and train it with a semi-supervised strategy. The registration symmetry is realized by introducing a loss for encouraging that the cycle composed of the geometric transformation from one image to another and its reverse should bring an image back. The semi-supervised learning enables both the precious labeled data and large amounts of unlabeled data to be fully exploited. Experimental results from six public brain magnetic resonance imaging (MRI) datasets and 1 our own computed tomography (CT) and MRI dataset demonstrate the superiority of SymReg-GAN to several existing state-of-the-art methods.

A semi-supervised learning approach with consistency regularization for tumor histopathological images analysis.

Introduction: Manual inspection of histopathological images is important in clinical cancer diagnosis. Pathologists implement pathological diagnosis and prognostic evaluation through the microscopic examination of histopathological slices. This entire process is time-consuming, laborious, and challenging for pathologists. The modern use of whole-slide imaging, which scans histopathology slides to digital slices, and analysis using computer-aided diagnosis is an essential problem. Methods: To solve the problem of difficult labeling of histopathological data, and improve the flexibility of histopathological analysis in clinical applications, we herein propose a semi-supervised learning algorithm coupled with consistency regularization strategy, called"Semi- supervised Histopathology Analysis Network"(Semi-His-Net), for automated normal-versus-tumor and subtype classifications. Specifically, when inputted disturbing versions of the same image, the model should predict similar outputs. Based on this, the model itself can assign artificial labels to unlabeled data for subsequent model training, thereby effectively reducing the labeled data required for training. Results: Our Semi-His-Net is able to classify patches from breast cancer histopathological images into normal tissue and three other different tumor subtypes, achieving an accuracy was 90%. The average AUC of cross-classification between tumors reached 0.893. Discussion: To overcome the limitations of visual inspection by pathologists for histopathology images, such as long time and low repeatability, we have developed a deep learning-based framework (Semi-His-Net) for automatic classification subdivision of the subtypes contained in the whole pathological images. This learning-based framework has great potential to improve the efficiency and repeatability of histopathological image diagnosis.