Objective To construct a quality control model for cervical liquid-based thin cell smears using two different artificial intelligence(AI)techniques and to compare the total use of the two methods to improve the level of quality control of cervical liquid-based thin cell smears through the assistance of hybrid AI.Methods In this study,105 cervical liquid-based thin cell smear samples were used.Convolutional neural network(CNN)algorithm and Transformer network algorithm were used as specific AI algorithms in the AI model.The labeled features included the number of cells in the slice,excessive red blood cells,excessive inflammatory cells,and air bubbles.The smear samples were pre-processed and digitized by smear,followed by image segmentation and feature extraction.Using the labeled feature data,machine learning models were trained and optimized.Statistical AI and physician QC results were analyzed by calculating KAPPA index,sensitivity,specificity,area under the curve(AUC),and other indexes for AI QC results.Results CNN algorithm QC results in normal smear,inflammatory background and bloody background were significantly different from the expert review QC results(P＜0.001).Transformer algorithm QC results were similar to the expert review results,with no statistical difference(P＞0.05).General practitioner QC results were statistically different from the expert review QC results in normal smear detection rate and bloody background(P＜0.001).CNN algorithm Kappa value was 0.567,which had medium consistency with expert review results.Transformer algorithm Kappa value was 0.890,with the best consistency with expert review results.General practitioner Kappa value was 0.675,which had better consistency with expert review results.Using the expert review results as a reference standard,the predictive efficacy of the Transformer algorithm and the general practitioners' QC results was evaluated,and the predictive efficacy of the Transformer algorithm was higher than that of the general practitioners in detecting hemorrhagic backgrounds and normal smears(inflammatory backgrounds:AUC=1.000;normal smears:AUC=0.768)(hemorrhagic backgrounds:AUC=0.849;normal smears:AUC=0.849;normal smear:AUC=0.500).Conclusion In this study,we found that the Transformer algorithm was effective in improving the quality control of cervical liquid-based thin-layer cell smears by assisting doctors to perform smear quality control scoring and improving the efficiency and accuracy of smear sample quality control.It can be used as a new quality control method for cervical cancer cytological screening and has potential clinical applications.

Objective:To uncover alterations in the metabolic microenvironment of lymph node metastasis (LNM) in oral squamous cell carcinoma (OSCC) and identify potential metabolic biomarkers for the early diagnosis of LNM using desorption electrospray ionization mass spectrometry imaging (DESI-MSI) spatial metabolomics.Methods:Six OSCC patients with LNM, who underwent neck dissection surgery at the Department of Oral and Maxillofacial Surgery, Affiliated Hospital of Jiangsu University between October 2020 and October 2022, were enrolled. Matched metastatically involved (positive) and benign (negative) lymph node tissue samples were collected and analyzed using DESI-MSI. Univariate and multivariate statistical analyses were employed to identify differentially abundant metabolites. The diagnostic efficacy of these metabolites was evaluated using receiver operating characteristic (ROC) curve analysis. Finally, Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis was performed to determine the implicated metabolic pathways.Results:A total of 62 and 29 differentially abundant metabolites were identified in the metastatically involved lymph nodes compared to benign lymph nodes under positive-ion mode and negative-ion mode, respectively. These metabolites were predominantly amino acids and lipids. Four metabolites common to both ionization modes were selected for ROC curve analysis: phenylalanine, phosphoethanolamine, histidine, and taurine. The area under the curve values were 0.861, 0.802, 0.729, and 0.722, respectively, indicating promising diagnostic performance. Metabolic pathway analysis revealed significantly heightened activity in Amino acid metabolism ( P=0.469) and Glycerophospholipid metabolism ( P=0.006) within the LNM microenvironment. Conclusions:This DESI-MSI-based study identified disruptions in amino acid and glycerophospholipid metabolism within OSCC metastatic lymph node tissues. The associated differentially abundant metabolites represent potential candidate molecules for diagnosing OSCC LNM.

Objective To construct a quality control model for cervical liquid-based thin cell smears using two different artificial intelligence(AI)techniques and to compare the total use of the two methods to improve the level of quality control of cervical liquid-based thin cell smears through the assistance of hybrid AI.Methods In this study,105 cervical liquid-based thin cell smear samples were used.Convolutional neural network(CNN)algorithm and Transformer network algorithm were used as specific AI algorithms in the AI model.The labeled features included the number of cells in the slice,excessive red blood cells,excessive inflammatory cells,and air bubbles.The smear samples were pre-processed and digitized by smear,followed by image segmentation and feature extraction.Using the labeled feature data,machine learning models were trained and optimized.Statistical AI and physician QC results were analyzed by calculating KAPPA index,sensitivity,specificity,area under the curve(AUC),and other indexes for AI QC results.Results CNN algorithm QC results in normal smear,inflammatory background and bloody background were significantly different from the expert review QC results(P＜0.001).Transformer algorithm QC results were similar to the expert review results,with no statistical difference(P＞0.05).General practitioner QC results were statistically different from the expert review QC results in normal smear detection rate and bloody background(P＜0.001).CNN algorithm Kappa value was 0.567,which had medium consistency with expert review results.Transformer algorithm Kappa value was 0.890,with the best consistency with expert review results.General practitioner Kappa value was 0.675,which had better consistency with expert review results.Using the expert review results as a reference standard,the predictive efficacy of the Transformer algorithm and the general practitioners' QC results was evaluated,and the predictive efficacy of the Transformer algorithm was higher than that of the general practitioners in detecting hemorrhagic backgrounds and normal smears(inflammatory backgrounds:AUC=1.000;normal smears:AUC=0.768)(hemorrhagic backgrounds:AUC=0.849;normal smears:AUC=0.849;normal smear:AUC=0.500).Conclusion In this study,we found that the Transformer algorithm was effective in improving the quality control of cervical liquid-based thin-layer cell smears by assisting doctors to perform smear quality control scoring and improving the efficiency and accuracy of smear sample quality control.It can be used as a new quality control method for cervical cancer cytological screening and has potential clinical applications.

Objective:To uncover alterations in the metabolic microenvironment of lymph node metastasis (LNM) in oral squamous cell carcinoma (OSCC) and identify potential metabolic biomarkers for the early diagnosis of LNM using desorption electrospray ionization mass spectrometry imaging (DESI-MSI) spatial metabolomics.Methods:Six OSCC patients with LNM, who underwent neck dissection surgery at the Department of Oral and Maxillofacial Surgery, Affiliated Hospital of Jiangsu University between October 2020 and October 2022, were enrolled. Matched metastatically involved (positive) and benign (negative) lymph node tissue samples were collected and analyzed using DESI-MSI. Univariate and multivariate statistical analyses were employed to identify differentially abundant metabolites. The diagnostic efficacy of these metabolites was evaluated using receiver operating characteristic (ROC) curve analysis. Finally, Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis was performed to determine the implicated metabolic pathways.Results:A total of 62 and 29 differentially abundant metabolites were identified in the metastatically involved lymph nodes compared to benign lymph nodes under positive-ion mode and negative-ion mode, respectively. These metabolites were predominantly amino acids and lipids. Four metabolites common to both ionization modes were selected for ROC curve analysis: phenylalanine, phosphoethanolamine, histidine, and taurine. The area under the curve values were 0.861, 0.802, 0.729, and 0.722, respectively, indicating promising diagnostic performance. Metabolic pathway analysis revealed significantly heightened activity in Amino acid metabolism ( P=0.469) and Glycerophospholipid metabolism ( P=0.006) within the LNM microenvironment. Conclusions:This DESI-MSI-based study identified disruptions in amino acid and glycerophospholipid metabolism within OSCC metastatic lymph node tissues. The associated differentially abundant metabolites represent potential candidate molecules for diagnosing OSCC LNM.

Objective To explore and validate the application value of a deep learning model based on the Huawei Cloud ModelArts platform in the diagnosis of atypical cervical cells in liquid-based cytology(LBC)and to evaluate its assistive effect for pathologists with different diagnostic experiences.Methods We retrospectively analyzed 1 044 cervical cytology specimens from Dongguan People's Hospital in 2020.The artifical intelligence(AI)-assisted diagnostic system developed on the Huawei Cloud ModelArts platform was compared with junior,intermediate,and senior pathologists for diagnosis.Sensitivity,specificity,precision,recall,and area under the receiver operating characteristic curve(AUC)were calculated to assess the diagnostic performance of the Al system and its assistive effect for pathologists with different levels of experience.The McNemar test was used to compare the differences between the Al system and manual diagnosis.P＜0.05 was considered statistically significant.Results For the 1 044 cervical exfoliated cytology specimens,the sensitivity and specificity of the AI system in detecting atypical cells was 98.96％and 89.15％,both of which were higher than those of junior doctors(81.95％and 91.81％,respectively).The overall diagnostic accuracy of the Al system was 93.68％,which was significantly higher than that of junior doctors(87.26％,P＜0.001).Al assistance could significantly improve junior doctors'ability to detect atypical cells,with the sensitivity and specificity increasing from 80.1％to 96.5％and from 85.6％to 92.3％,respectively.Conclusion The AI-assisted cervical cytology diagnostic system developed in this study demonstrated superior performance,particularly in significantly improving the diagnostic level of junior pathologists,showing promising clinical application prospects.

Objective: To investigate the high-risk factors for parotid lymph node (PLN) metastasis from nasopharyngeal carcinoma (NPC) and evaluate the feasibility of local intensity-modulated radiotherapy (IMRT) in patients with high-risk NPC. Methods: Clinical data of 440 NPC patients admitted to Department of Radiotherapy of Jiangsu Cancer Hospital from May, 2011 to March, 2017 were collected. The imaging features, treatment strategies and clinical prognosis of PLN metastasis were retrospectively analyzed. The whole group adopts the technique of intensity modulated radiotherapy. Total parotid or partial parotid irradiation, selective PLN irradiation, X-Ray and/or electronic line supplementation, dose 45-60 Gy. The χ² test or Fisher′s accurate probability method test and single factor analysis, Logistic regression model multi-factor analysis. Kaplan-Meier survival analysis, log-rank test differences. Results: PLN was observed in the parotid of 230 cases. At the end of follow-up, 11 patients (2.5%, 11/440) were diagnosed with PLN metastases. Among 11 cases, 9 patients (81.8%) had PLN size ≥5 mm. Multivariate analysis demonstrated that extracapsular spread of level Ⅱ was an independent risk factor for PLN metastasis. The patients with PLN size ≥5 mm or extracapsular spread of level Ⅱ were assigned into the high-risk PLN metastasis group. The patients in the high-risk group were further divided into the radiotherapy and non-radiotherapy subgroups. Survival analysis demonstrated that for 230 patients with PLN metastasis, the local recurrence-free survival (LRFS) significantly differed, whereas the overall survival (OS), disease metastasis-free survival (DMFS) and progression-free survival (PFS) did not considerably differ between the radiotherapy and non-radiotherapy subgroups in the high-risk PLN metastasis patients. Conclusions The PLN metastasis rate of NPC is low. Extracapsular spread of level Ⅱ is an independent risk factor. Radiotherapy of the parotid region is considered for patients with PLN size≥5 mm or those with PLN size<5 mm complicated with extracapsular spread of level Ⅱ.

Objective The purpose of this study was to investigate the expression of human mitochondrial transcription termi-nation factor-3 ( hMTERF3) in non-small cell lung cancer ( NSCLS) and to analyze its clinicopathological significance. Methods The paraffin block samples used in this study included 65 cases of NSCLC and 32 cases of normal alveolar epithelial tissues. We determined the expressions of hMTERF3 in NSCLC and normal alveolar epithelial tis-sues by immunohistochemistry, calculate the survival rate using the Kaplan-Meier method, and analyzed the risk factors affecting the prognosis of NSCLC using the Cox Proportional Hazard Model. Results In the 65 cases of NSCLC, 31 ( 47. 69%) showed positive expression of hMTERF3. The total survival time was significantly shor-ter in the patients with a high than in those with a low hMTERF3 ex-pression ([30.39±3.35] vs [57.61±7.12] mo, P<0.05). The riskfactors affecting the prognosis of NSCLC included positive expression of hMTERF3 (HR=3.302, 95% CI:1.598-6.905) and lymph node metastasis (HR=4.052, 95% CI: 1.212-12.398). Conclusion hMTERF3 is overexpressed in NSCLC. Highly expressed hMTERF3 and lymph node metastasis reduce the survival time of NSCLC patients, suggesting that hMTERF3 may be a potential bio-marker for the prognosis of NSCLC.