Integrated analyses reveal the diagnostic and predictive values of COL5A2 and association with immune environment in Crohn's disease.

The pathogenesis of Crohn's disease (CD) involves abnormal immune cell infiltration and dysregulated immune response. Therefore, thorough research on immune cell abnormalities in CD is crucial for improved treatment of this disease. Single-cell RNA sequencing (scRNA-seq) and bulk RNA-seq data of CD were obtained from the Gene Expression Omnibus (GEO) database. Cell-type identification by estimating relative subsets of RNA transcripts (CIBERSORT), weighted gene co-expression network analysis (WGCNA), protein-protein interaction (PPI) networks evaluated the proportion of immune infiltrating cells, constructed co-expression network and identified key genes, respectively. Based on the dataset (GSE134809), 15 cell clusters were defined and labeled as different cell types. Among the 11 modules, the yellow module had the closest relationship with plasma cells (cluster 5). Confirmed using RNA sequencing and IHC assay, the expression of COL5A2 in CD samples was higher than that in control samples. Furthermore, the COL5A2 protein expression remarkably decreased in the group of patients who responded to anti-tumor necrosis factor (TNF) treatments, compared to the non-response group. The comprehensive analyses described here provided novel insight into the landscape of CD-associated immune environment. In addition, COL5A2 were identified as potential diagnostic indicators for CD, as well as promising predictive markers for CD patients.

Hyperactivation and enhanced cytotoxicity of reduced CD8+ gamma delta T cells in the intestine of patients with Crohn's disease correlates with disease activity.

BACKGROUND AND AIMS: We aimed to investigate the immune characteristics of intestinal CD8+ gamma delta T (CD8+ γδ T) cells in Crohn's disease (CD) and their correlation with disease activity. METHODS: The study cohorts included 21 CD patients and 21 healthy individuals. CD8+ γδ T cells were isolated from human ileal mucosa for detection by flow cytometry. The activation or inhibition status of cells was detected by detecting the expression of activation marker HLA-DR and the immunosuppressive molecule PD-1 on cells. The cytotoxicity of cells was assessed by detecting the expression of cytotoxic molecules (Perforin, Granzyme B, and TRAIL) in cells. Ratios of investigated cells were calculated as prediction factors by receiver operating characteristic curve (ROC) analysis. RESULTS: The study revealed a reduction in intestinal CD8+ γδT cells among active CD patients, with a more pronounced reduction observed in moderately active patients compared to mildly active patients. Moreover, active CD patients exhibited heightened activation levels in their intestinal CD8+ γδT cells, whereas the activation was comparatively weakened in moderately active patients compared with mildly active patients. Additionally, the cytotoxicity of intestinal CD8+ γδT cells was enhanced solely in mildly active patients, while it was impaired in moderately active patients compared with mildly active patients. Furthermore, HLA-DR+ CD8+ γδT cell ratio, CD8+ γδT ratio, and CD8+ γδT count were identified as indicators in the diagnosis of active CD. Meanwhile, the ratios of Granzyme B+ CD8+ γδT cell and Perforin+ CD8+ γδT cell were identified as indicators that distinguish mildly moderately active CD cases. CONCLUSIONS: Intestinal CD8+ γδT was reduced in active CD patients, but their activation and cytotoxicity were enhanced. However, with increased disease activity, intestinal CD8+ γδ T cells became dysfunctional. CD-specific perturbations observed in various phenotypic markers in CD8+ γδ T cells can be used as indicators to assist in diagnosing CD patients.

The diagnostic value of capsule endoscopy in children with intestinal lymphangiectasia.

BACKGROUND: intestinal lymphangiectasia is an unusual cause of protein-losing enteropathy due to either congenital malformation or obstruction of the intestinal lymphatics. However, few reports have investigated the use of video capsule endoscopy in children with intestinal lymphangiectasia. This study was performed to evaluate the diagnostic value of video capsule endoscopy for pediatric intestinal lymphangiectasia. METHODS: in this retrospective study, all patients who underwent video capsule endoscopy between January 2014 and July 2020 were included. Clinical information and video capsule endoscopy data were analyzed. RESULTS: twelve children were enrolled, 7 males and 5 females, with an age at disease onset of 4.5 (range: 3.2-9.3) years and a disease duration of 12.0 (range: 1.3-30.0) months. The most common symptoms were hypoproteinemia (10, 83.3 %), diarrhea (7, 58.3 %), edema (6, 50.0 %), and abdominal pain (3, 25.0 %). Eight patients had low lymphocyte counts, whereas 10 had reduced serum albumin levels (23.2 ± 5.8 g/L). Video capsule endoscopy revealed an overall white snowy appearance due to the presence of whitish, swollen villi in all patients. Regarding the macroscopic lesions of lymphangiectasia, 7 cases involved the entire small bowel from the duodenum to the ileocecal valve, while 5 cases involved part of the small bowel. All patients were treated with medium-chain triglyceride diets, and albumin infusions were administered to 10 patients; sirolimus treatment was administered to 3 patients. At the last follow-up, 5 patients still had hypoalbuminemia and one patient had died of intestinal lymphoma. CONCLUSION: video capsule endoscopy is useful for the diagnosis of intestinal lymphangiectasia and should be applied as a valuable and less invasive examination to confirm or establish a diagnosis.

Cytomegalovirus enteritis with intractable diarrhea in infants from a tertiary care center in China.

Background: Cytomegalovirus (CMV) is rarely thought to be the cause of significant gastrointestinal infection in immunocompetent children. CMV colitis is seldom observed in young infants. This study aims to examine the clinical features of CMV colitis in Chinese children.Methods: Patients with infantile onset CMV colitis diagnosed in intestinal tissue at Children's Hospital of Fudan University from 1st January 2017, to 31st January 2019 were enrolled. Clinical data were retrieved from medical records, and the literature on infant CMV colitis was also reviewed.Results: Ten patients were included with a median age of 2.5 months [interquartile range 2.0, 6.3 months]. All 10 patients had diarrhea, 10 patients had anemia, seven patients reported hematochezia, five patients had hypoalbuminemia, five patients had retinitis, two patients had hearing impairment, and one patient had perianal abscess and anal fistula. The patients had punched-out ulcerations, longitudinal ulcerations or irregular ulcerations on the rectum and/or colon. Typical histologic evaluation showed crypt distortion and inflammatory infiltration. CMV inclusion bodies were noted in four patients. Immunohistochemistry on intestinal tissue was performed to diagnose CMV, with all patients positive. After follow-up, all patients are clinically recovered or in remission; six patients received antiviral therapy, and five patients had healed ulcers on endoscopic examination.Conclusions: CMV colitis might be a rare cause of intractable diarrhea in immunocompetent children. Clinicians should be aware of the possibility of CMV colitis in patients with intractable diarrhea.

Comparative transcriptome analysis reveals Dusp1 as a critical regulator of inflammatory response to fly ash particle exposure in mouse.

Exposure to outdoor concentrations of fine particulate matter (PM2.5) is a leading global health concern. Waste incineration emission has been recognized as a potential major contributor of ambient PM2.5. Respiratory inflammation is a central feature induced by PM2.5 exposure by inhalation. However, the molecular mechanisms are not fully understood. Dual-specificity phosphatase 1 (Dusp1) plays an instrumental role in the regulation of airway inflammation. In this study, fly ash particles (20 mg/kg BW) collected from a municipal waste incinerator in China were given to BALB/c wild-type (WT) and Dusp1-/- mice by intranasal administration daily for three consecutive days. While these particles induced mild inflammation in both genotypes, a significantly higher level of serum interleukin-6 (665 pg/ml) was measured in Dusp1-/- mice challenged with fly ash particles than in their WT counterparts. Genome-wide transcriptome profiling of pulmonary coding genes in response to the exposure were performed in both genotypes by RNA sequencing. We identified 487 differentially-expressed genes (DEGs) in fly ash-challenged Dusp1-/- mice versus their WT counterparts with a log2fold-change >1.5 and p < 0.05. Functional enrichment and molecular pathway mapping of the DEGs specific to Dusp1-/- mice exposed to the particles revealed that the top 10 perturbed molecular pathways were associated with the immune response. Our study demonstrates the anti-inflammatory role of Dusp1 in protecting the lung against insults by fly ash particles, suggesting that Dusp1 might be a therapeutic target for the treatment of PM2.5-induced respiratory diseases.

The clinicopathologic features of chronic active Epstein-Barr virus infective enteritis.

Chronic active Epstein-Barr virus infective enteritis (CAEBV enteritis) is rare and has not been well described yet. Therefore, we reported the clinicopathologic features of 11 patients with chronic active Epstein-Barr virus infective enteritis and their differences from inflammatory bowel disease. The major clinical presentations of chronic active Epstein-Barr virus infective enteritis were intermittent fever over 39 °C (100%), diarrhea (73%), abdominal pain (64%), lymphadenopathy (64%), splenomegaly (64%), and hepatomegaly (27%). The main endoscopic findings included numerous shallow, small, and irregular ulcers, mainly involving colon and small intestine together, no cobble-like appearance, and longitudinal ulcers. Compared to inflammatory bowel disease patients, the frequency of intermittent fever, hepatomegaly, splenomegaly, lymphadenopathy, the value of C-reactive protein, and serum Epstein-Barr virus DNA (EBV DNA) were significantly higher in chronic active Epstein-Barr virus infective enteritis patients (p < 0.01). The histologic findings show transmural inflammation with extended lymphoid infiltration, fissuring ulcers, and intraepithelial lymphocytosis. But chronic active Epstein-Barr virus infective enteritis lacked granulomas and connective tissue changes such as neural hypertrophy and thickened muscularis mucosae. Three chronic active Epstein-Barr virus infective enteritis patients died within 5 years of disease onset, and those three patients have received total colectomy, two of them died within 1 month after surgery. In this study, clinicopathologic features have been summarized to better recognize chronic active Epstein-Barr virus infective enteritis. There are resemblances between chronic active Epstein-Barr virus infective enteritis and inflammatory bowel disease, but some symptoms, signs, and indexes like intermittent fever, hepatomegaly, splenomegaly, lymphadenopathy, and elevated C-reactive protein, Epstein-Barr virus DNA are characteristics to differentiate chronic active Epstein-Barr virus infective enteritis and inflammation. Histopathological features also help the discrimination. Serum Epstein-Barr virus DNA and intestinal tissue in situ hybridization for Epstein-Barr virus-encoded RNA are recommended to exclude chronic active Epstein-Barr virus infective enteritis.

A Variational Stacked Autoencoder with Harmony Search Optimizer for Valve Train Fault Diagnosis of Diesel Engine.

Diesel engine fault diagnosis is vital due to enhanced reliability and economic efficiency requirements. The extracted features in traditional fault diagnosis are constructed manually, which is very cumbersome because of the requirement for lots of expertise. To handle this issue, this paper proposed a variational stacked autoencoder (VSAE) to adaptively extract features from angular domain signals. As an unsupervised algorithm, VSAE can extract high-level features with the help of multiple encoding layers. Layer-wise pre-training and fine-tuning are introduced to get a better network initialization value. Moreover, the dropout technique and the batch normalization technique are carried out to prevent over-fitting and implement fast convergence. Finally, the harmony search optimizer (HSO) algorithm is introduced to get an appropriate hyper-parameter setting in the VSAE model, as well as make adaptive adjustment of the network structure. In order to verify the proposed method, the valve train fault data is collected on the diesel engine test rig under twelve operating conditions. The results indicate that the proposed scheme can effectively diagnose different degrees of intake valve fault, exhaust valve fault, and coupling fault under various operating conditions. Furthermore, the classification accuracy improved from 94.10% to 98.85%VSAE compared with stacked autoencoder (SAE) and some other traditional fault diagnosis algorithms.

Bearing State Recognition Method Based on Transfer Learning Under Different Working Conditions.

Bearing state recognition, especially under variable working conditions, has the problems of low reusability of monitoring data, low state recognition accuracy and low generalization ability of the model. The feature-based transfer learning method can solve the above problems, but it needs to rely on signal processing knowledge and expert diagnosis experience to obtain the cross-characteristics of different working conditions data in advance. Therefore, this paper proposes an improved balanced distribution adaptation (BDA), named multi-core balanced distribution adaptation (MBDA). This method constructs a weighted mixed kernel function to map different working conditions data to a unified feature space. It does not need to obtain the cross-characteristics of different working conditions data in advance, which simplifies the data processing and meet end-to-end state recognition in practical applications. At the same time, MBDA adopts the A-Distance algorithm to estimate the balance factor of the distribution and the balance factor of the kernel function, which not only effectively reduces the distribution difference between different working conditions data, but also improves efficiency. Further, feature self-learning and rolling bearing state recognition are realized by the stacked autoencoder (SAE) neural network with classification function. The experimental results show that compared with other algorithms, the proposed method effectively improves the transfer learning performance and can accurately identify the bearing state under different working conditions.

Multi-Factor Operating Condition Recognition Using 1D Convolutional Long Short-Term Network.

: For a diesel engine, operating conditions have extreme importance in fault detection and diagnosis. Limited to various special circumstances, the multi-factor operating conditions of a diesel engine are difficult to measure, and the demand of automatic condition recognition based on vibration signals is urgent. In this paper, multi-factor operating condition recognition using a one-dimensional (1D) convolutional long short-term network (1D-CLSTM) is proposed. Firstly, a deep neural network framework is proposed based on a 1D convolutional neural network (CNN) and long short-Term network (LSTM). According to the characteristics of vibration signals of a diesel engine, batch normalization is introduced to regulate the input of each convolutional layer by fixing the mean value and variance. Subsequently, adaptive dropout is proposed to improve the model sparsity and prevent overfitting in model training. Moreover, the vibration signals measured under 12 operating conditions were used to verify the performance of the trained 1D-CLSTM classifier. Lastly, the vibration signals measured from another kind of diesel engine were applied to verify the generalizability of the proposed approach. Experimental results show that the proposed method is an effective approach for multi-factor operating condition recognition. In addition, the adaptive dropout can achieve better training performance than the constant dropout ratio. Compared with some state-of-the-art methods, the trained 1D-CLSTM classifier can predict new data with higher generalization accuracy.

A New Fault Diagnosis Method for a Diesel Engine Based on an Optimized Vibration Mel Frequency under Multiple Operation Conditions.

The diesel engine has been a significant component of large-scale mechanical systems for the intelligent manufacturing industry. Because of its complex structure and poor working environment, it has trouble effectively acquiring the representative fault features. Further, fault diagnosis of the diesel engine faces great challenges. This paper presents a new fault diagnosis method for the detection of diesel engine faults under multiple operation conditions instead of conventional methods confined to a single condition. First, an adaptive correlation threshold process is designed as a preprocessing unit to enhance data quality by weakening non-impact region characteristics. Next, a feature extraction method for sound signals based on the Mel frequency cepstrum (MFC) is improved and introduced into the machinery fault diagnosis. Then, the combination of the improved feature and vibrational mode decomposition (VMD) is proposed to incorporate VMD into an effective adaptive decomposition of non-stationary signals to combine it with an excellent feature representation of the vibration signal. Finally, the vector quantization algorithm is adopted to reduce the feature dimensions and generate codebook model bases, which trains the K-Nearest Neighbor classifiers. Five comparative methods were carried out, and the experimental results show that the proposed method offers a good effect of the common valve clearance fault of diesel engines under different conditions.

Fault Diagnosis of Internal Combustion Engine Valve Clearance Using the Impact Commencement Detection Method.

Internal combustion engines (ICEs) are widely used in many important fields. The valve train clearance of an ICE usually exceeds the normal value due to wear or faulty adjustment. This work aims at diagnosing the valve clearance fault based on the vibration signals measured on the engine cylinder heads. The non-stationarity of the ICE operating condition makes it difficult to obtain the nominal baseline, which is always an awkward problem for fault diagnosis. This paper overcomes the problem by inspecting the timing of valve closing impacts, of which the referenced baseline can be obtained by referencing design parameters rather than extraction during healthy conditions. To accurately detect the timing of valve closing impact from vibration signals, we carry out a new method to detect and extract the commencement of the impacts. The results of experiments conducted on a twelve-cylinder ICE test rig show that the approach is capable of extracting the commencement of valve closing impact accurately and using only one feature can give a superior monitoring of valve clearance. With the help of this technique, the valve clearance fault becomes detectable even without the comparison to the baseline, and the changing trend of the clearance could be trackable.

The tumor promoting roles of erythropoietin/erythropoietin receptor signaling pathway in gastric cancer.

Erythropoietin (EPO), binding with its receptor (EPOR), plays an important role in erythropoiesis. EPOR is reported to be expressed in various non-hematopoietic cancers, including gastric cancer. Although recombinant human EPO (rhEPO) has been widely used clinically in anemia patients, it remains controversial whether it would promote tumor progression. In this study, we used siRNA interference method to downregulate EPOR expression to investigate the function of EPO/EPOR pathway in human gastric cancer cells. We found EPOR expressed significantly higher in gastric cancer tissues, and also in most gastric cancer cell lines. RhEPO promoted gastric cancer cell proliferation, migration in AGS cells, and promoted cells from G0/G1 stage to G2/M stage, but had no regulation on AGS cell apoptosis. Downregulation of EPOR expression by siRNA interference in AGS cells resulted in no significant effects on proliferation and invasiveness of the cells, but induced apoptosis (p < 0.05). Xenografted gastric tumor model was used to explore the effect of EPOR-overexpression on gastric cancer cells in vivo. Our result showed that overexpression of EPOR enhanced tumor formation in nude mice (p < 0.01). Our results suggest that EPO/EPOR pathway promotes gastric cancer formation, proliferation, migration, and decreases apoptosis.

The effect of a high progesterone concentration before oocyte retrieval on the peri-implantation endometrium.

In this single-centre, prospective cohort study, the effect of high progesterone level before oocyte retrieval on endometrial morphology and uterine natural killer cell (uKN) count in the peri-implantation period was investigated. A total of 106 women undergoing IVF treatment who did not proceed to fresh embryo transfer were included. Endometrial samples were obtained 7 days after HCG administration. Multiple regression analysis was used to identify factors affecting the results of histological staging and uNK cell count. Progesterone level on the day after HCG administration was the only significant variable associated with the results of histological staging (P = 0.004). Endometrial development in women with high progesterone level was significantly (P < 0.001) more advanced than that of women with normal progesterone; progesterone level on the day of HCG administration was the only significant variable associated with uNK cell count. The median (range) of uNK cell count of 9.6% (2.3-21.6%) in women with high progesterone was significantly (P < 0.001) higher than the median (range) of uNK cell count of 5.7% (1.4-18.7%) in women with normal progesterone. High progesterone level before oocyte retrieval was correlated with advancement in endometrial development as well as increased uNK cell count.

[Primary culture and characteristics of colorectal cancer-associated fibroblasts].

OBJECTIVE: To compare the biological characteristics of colorectal cancer associated fibroblasts (CAFs) with normal fibroblasts (NFs). METHODS: CAFs and NFs were isolated from fresh specimens of colorectal cancer and their paired normal colon tissue and cultured by tissue explant method. Light microscopy, quantitative polymerase chain reaction (qPCR), Western blot, immunofluorescence microscopy, electron microscopy and flow cytometry were used to identify isolated fibroblasts and to explore their characteristics of activation and growth. RESULTS: Primary colorectal CAFs and NFs were isolated and cultured successfully. NFs showed spindled morphology and were arranged in interlacing or spiral bundles. CAFs were polygonal or spindle, but were fatter than NFs. They were distributed randomly and arranged irregularly, and had obvious actin expression. CAFs and NFs both expressed fibronectin, but not E-cadherin, CD31 and caldesmon. qPCR showed that CAFs expressed more fibroblast activation protein (FAP) and less fibroblast specific protein 1 (FSP1) than that of NFs. There was no difference in the expression of α-SMA between NFs and CAFs by Western blot. α-SMA was bundled in parallel to the long axis of the cell by immunofluorescence. By electron microscopy, CAFs but not NFs showed dense myofilament that was arranged regularly. Flow cytometry showed that the percentage of S- and G2-phase in CAFs were significantly lower than that in NFs. mRNA expression of transforming growth factor ß1, stromal derived factor 1 (SDF-1) and platelet derived growth factor (PDGF)-D in CAFs were lower while that for PDGFC was higher than that in NFs. That indicated the proliferation of CAFs was inhibited and the secretion of some cytokines was different when compared with NFs. CONCLUSIONS: CAFs show differences with NFs in morphology, characteristics of activation and secretion of some cytokines. The proliferation of CAFs is down regulated as compared with NFs.

Lin28 Mediates Cancer Chemotherapy Resistance via Regulation of miRNA Signaling.

Chemotherapy resistance is one of the major obstacles limiting the success of cancer drug treatment. Among the mechanisms of resistance to chemotherapy treatment, there are those closely related to P-Glycoprotein, multidrug resistance-related protein, glutathione S-transferase pi and topoisomerase-II. Lin28 is a highly conserved RNA-binding protein, it consists of a cold shock domain and retroviral-type (CCHC) zinc finger motifs. In previous preclinical and clinical studies, positive Lin28 expression in cancer cells was correlated with decreased sensitivity to chemotherapy. And Lin28 could mediate cancer chemotherapy resistance via regulation of miR107 and Let-7 MiRNA. This article reviews current knowledge on predictive value of Lin28 in response to chemotherapy. Better understanding of its role may facilitate patient's selection of therapeutic regimen and lead to optimal clinical outcome.

Mucosal Architectural Change is an Important Feature in Distinguishing Crohn's Disease From Others in Terminal Ileum Ulcer Biopsy.

BACKGROUND: Besides Crohn's disease (CD), there are a variety of other causes that can also lead to ulcerations in the terminal ileum. The purpose of this study was to identify useful diagnostic features for CD when evaluating terminal ileum biopsies in patients with endoscopic finding of ulcers. METHODS: Five hundred and seventy-one patients with endoscopic finding of ulcers were included in this retrospective study. Five main histological features were analysed, which were crypt irregularity, mucosal thickening, villous stromal widening (including villous atrophy), granulomas, and pseudopyloric gland metaplasia. Clinical and pathological features were determined by uni- and multivariable logistic regression. Then another independent cohort of 99 patients was established for verifying this nomogram. RESULTS: The crypt irregularity, mucosal thickening, and villous stromal widening were combined to be considered as one new variable named mucosal architectural change which was an independent variable in diagnosing CD. We found that mucosal architectural change, age <40 years, the presence of granulomas, and the presence of pseudopyloric gland metaplasia were independent factors for the pathological diagnosis of CD. Then nomogram was developed, with receiver operating characteristic (ROC) curve (area under the ROC curve [AUC] = 0.927) in training sets, and ROC curve (AUC = 0.913) in validation sets. CONCLUSIONS: We found mucosal architectural change is very helpful in distinguishing CD from non-CD patients. In the context of small biopsy which may lack full scope of changes, the model developed by combining these key features is valuable in predicting a diagnosis of CD, especially in younger patients (age <40 years).

Understanding endoscopic and clinicopathological features of patients with very early onset inflammatory bowel disease: Results from a decade of study.

BACKGROUND: Very early onset inflammatory bowel disease (VEOIBD) is associated with a unique disease course and distinct endoscopic features. AIMS: This study aims to provide a comprehensive description of the endoscopic and histologic features observed in a large cohort of patients with VEOIBD from a tertiary medical center. METHODS: A retrospective review of medical records from 2011 to 2021 was conducted to analyze clinical data, including disease phenotypes, endoscopic and histologic findings. Next generation sequencing was performed. RESULTS: A total of 225 VEOIBD subjects were included in this study. Monogenic defects were identified in 161 patients. Monogenic IBD patients more commonly had CD-like disease. Colonic involvement was more prevalent among those with monogenic IBD (P<0.001). Pseudo-polyps were significantly more common in the monogenic IBD group (P<0.001), while ileal edema and ulcers were significantly more prevalent in non-monogenic IBD cases. IL10RA deficiency were characterized by colonic ulcers and pseudo-polyps without upper gastrointestinal tract lesions, while patients with TNFAIP3 mutations demonstrated both upper and lower gastrointestinal tract involvement. The non-monogenic IBD patients showed a higher incidence of chronic architectural changes of crypt, increased apoptosis and eosinophils infiltration. CONCLUSIONS: Endoscopic and histologic analysis of children with VEOIBD plays a crucial role in facilitating accurate diagnosis. Various forms of monogenic IBD exhibit distinct endoscopic and pathologic changes.

Clinical value of multi-gene testing in distinguishing benign and malignant thyroid nodules.

BACKGROUND: The newly released 2022 WHO Classification of Neuroendocrine Neoplasms (version 5) and a recent update on thyroid tumor classifications have emphasized genetic testing to an unprecedented level. Fine needle aspiration (FNA) has been widely applied for the preoperative diagnosis of thyroid nodules. However, it is limited mainly to testing for a single gene-BRAFV600E, whereas multi-gene testing data are scarce, especially in the Asian population. This study aimed to explore the clinical value of multi-gene testing in the differential diagnosis of benign and malignant thyroid nodules based on the 2023 Bethesda System for Reporting Thyroid Cytopathology (BSRTC). METHODS: A total of 615 thyroid nodules underwent ultrasound-guided fine-needle aspiration cytology (FNAC) were collected from Sir Run Run Shaw Hospital, Zhejiang University School of Medicine. The next-generation sequencing platform was applied for multi-gene testing. A panel of well-recognized commonly mutated genes in thyroid cancer were analyzed, including BRAFV600E, KRAS, NRAS, HRAS, TERT, TP53, PAX8/PPARG, CCDC6/ RET and NCOA4/ RET. RESULTS: Gene mutations were identified in 324 nodules (52.7%), with BRAFV600E being the most prevalent driver gene alteration observed in this cohort (233/324; 79.1%), followed by RAS (77/324, 23.8%). The overall malignancy rate of gene mutations was 89.7% in our cohort, of which the lymph node metastasis rate was 45.3%. The combination of multi-gene testing and cytology resulted in 89.3% sensitivity, 95.2% specificity, 98.9% positive predictive value, 64.5% negative predictive value and 90.3% accuracy, which were significantly higher than those from mere cytology (sensitivity 68.6%, specificity 87.5%, positive predictive value 95.9%, negative predictive value 39.8%, accuracy 72.2%). CONCLUSIONS: Multi-gene testing could substantially enhance the detection rate of malignant thyroid nodules and protect patients with benign nodules from unnecessary surgeries. Multi-gene testing provides a valuable reference for individualized preoperative decision-making, which may serve as a crucial method for postoperative treatment and prognosis assessment.

A study of machine learning models for rapid intraoperative diagnosis of thyroid nodules for clinical practice in China.

BACKGROUND: In China, rapid intraoperative diagnosis of frozen sections of thyroid nodules is used to guide surgery. However, the lack of subspecialty pathologists and delayed diagnoses are challenges in clinical treatment. This study aimed to develop novel diagnostic approaches to increase diagnostic effectiveness. METHODS: Artificial intelligence and machine learning techniques were used to automatically diagnose histopathological slides. AI-based models were trained with annotations and selected as efficientnetV2-b0 from multi-set experiments. RESULTS: On 191 test slides, the proposed method predicted benign and malignant categories with a sensitivity of 72.65%, specificity of 100.0%, and AUC of 86.32%. For the subtype diagnosis, the best AUC was 99.46% for medullary thyroid cancer with an average of 237.6 s per slide. CONCLUSIONS: Within our testing dataset, the proposed method accurately diagnosed the thyroid nodules during surgery.