Investigation of the Structural Properties and Antioxidant Potency of Pectic Polysaccharides Derived from Rohdea japonica (Thunb.) Roth.

This study investigated the structural composition and antioxidant properties of pectic polysaccharides extracted from Rohdea japonica (Thunb.) Roth. Pectins, which belong to a complex category of acidic polysaccharides, possess a wide range of biological effects stemming from their distinctive structural domains. The polysaccharides were extracted using water, and were subsequently purified through ion exchange and gel permeation chromatography. In order to elucidate their structural features, Fourier Transform Infrared Spectroscopy and Nuclear Magnetic Resonance techniques were applied. Two specific polysaccharides, WRJP-A2a and WRJP-A3b, with molecular weights of 42.7 kDa and 64.1 kDa, respectively, were identified to contain varying proportions of homogalacturonan, rhamnogalacturonan I, and rhamnogalacturonan II domains. Regarding antioxidant capacity, WRJP-A3b exhibited superior scavenging capabilities against DPPH, ABTS, and hydroxyl radicals, potentially attributed to its higher galacturonic acid content and abundance of homogalacturonan domains. These results enhance our comprehension of the structure-activity interplay of pectic polysaccharides sourced from Rohdea japonica (Thunb.) Roth and their potential utility in the healthcare and functional food sectors.

Structural modification of 2-phenylquinoline-4-carboxylic acid containing SIRT3 inhibitors for the cancer differentiation therapy.

Inhibition of SIRT3 exhibited potency in triggering leukemic cell differentiation. In discovery of potent SIRT3 inhibitors for cancer differentiation therapy, structural modification was performed on the previously developed lead compound P6. A total of 33 compounds were designed and synthesized. In the enzyme inhibitory assay, several molecules S18, S26, S27 and T5 showed potent SIRT3 inhibitory activity with IC50 value of 0.53, 1.86, 5.06, and 2.88 µM, respectively. Moreover, the tested compounds exhibited SIRT3 inhibitory selectivity over SIRT1 and SIRT2. Compounds S27 and T5 were potent in inhibition the growth of MM1.S and RPMI-8226 cells in the in vitro antiproliferative test. Significantly, representative compounds, especially S27 and T5, promoted differentiation of tested MM cells in the cellular morphological evaluation, accompanied by increasing the expression of differentiation antigen CD49e and human immunoglobulin light chain lambda and kappa. Additionally, molecule S18 without antiproliferative potency itself, showed significant inhibitory activity against growth factor IL-6 induced RPMI-8226 cell proliferation. Collectively, potent SIRT3 selective inhibitors with MM cell differentiation potency were developed for further discovery of anticancer drugs.

Successful endoscopic closure of alveolar-pleural fistula due to Aspergillus empyema using a ventricular septal defect occluder.

We report a patient with fever and cough for 2 months who was finally given a diagnosis of alveolar-pleural fistula due to aspergillus empyema. We successfully closed the alveolar-pleural fistula with a ventricular septal defect occluder through bronchoscopy. Endoscopic closure of an alveolar-pleural fistula with ventricular septal defect occluder is worth being explored.

SATB1, senescence and senescence-related diseases.

Aging leads to an accumulation of cellular mutations and damage, increasing the risk of senescence, apoptosis, and malignant transformation. Cellular senescence, which is pivotal in aging, acts as both a guard against cellular transformation and as a check against cancer progression. It is marked by stable cell cycle arrest, widespread macromolecular changes, a pro-inflammatory profile, and altered gene expression. However, it remains to be determined whether these differing subsets of senescent cells result from unique intrinsic programs or are influenced by their environmental contexts. Multiple transcription regulators and chromatin modifiers contribute to these alterations. Special AT-rich sequence-binding protein 1 (SATB1) stands out as a crucial regulator in this process, orchestrating gene expression by structuring chromatin into loop domains and anchoring DNA elements. This review provides an overview of cellular senescence and delves into the role of SATB1 in senescence-related diseases. It highlights SATB1's potential in developing antiaging and anticancer strategies, potentially contributing to improved quality of life and addressing aging-related diseases.

PLD2 deletion ameliorates sepsis-induced cardiomyopathy by suppressing cardiomyocyte pyroptosis via the NLRP3/caspase 1/GSDMD pathway.

OBJECTIVE: Sepsis-induced cardiomyopathy (SICM) is a life-threatening complication. Phospholipase D2 (PLD2) is crucial in mediating inflammatory reactions and is associated with the prognosis of patients with sepsis. Whether PLD2 is involved in the pathophysiology of SICM remains unknown. This study aimed to investigate the effect of PLD2 knockout on SICM and to explore potential mechanisms. METHODS: The SICM model was established using cecal ligation and puncture in wild-type and PLD2-knockout mice and lipopolysaccharide (LPS)-induced H9C2 cardiomyocytes. Transfection with PLD2-shRNA lentivirus and a PLD2 overexpression plasmid were used to interfere with PLD2 expression in H9C2 cells. Cardiac pathological alterations, cardiac function, markers of myocardial injury, and inflammatory factors were used to evaluate the SICM model. The expression of pyroptosis-related proteins (NLRP3, cleaved caspase 1, and GSDMD-N) was assessed using western blotting, immunofluorescence, and immunohistochemistry. RESULTS: SICM mice had myocardial tissue damage, increased inflammatory response, and impaired heart function, accompanied by elevated PLD2 expression. PLD2 deletion improved cardiac histological changes, mitigated cTNI production, and enhanced the survival of the SICM mice. Compared with controls, PLD2-knockdown H9C2 exhibits a decrease in inflammatory markers and lactate dehydrogenase production, and scanning electron microscopy results suggest that pyroptosis may be involved. The overexpression of PLD2 increased the expression of NLRP3 in cardiomyocytes. In addition, PLD2 deletion decreased the expression of pyroptosis-related proteins in SICM mice and LPS-induced H9C2 cells. CONCLUSION: PLD2 deletion is involved in SICM pathogenesis and is associated with the inhibition of the myocardial inflammatory response and pyroptosis through the NLRP3/caspase 1/GSDMD pathway.

Validation of artificial intelligence-based bowel preparation assessment in screening colonoscopy (with video).

BACKGROUND AND AIMS: Accurate bowel preparation assessment is essential for determining colonoscopy screening intervals. Patients with suboptimal bowel preparation are at a high risk of missing >5 mm adenomas and should undergo an early repeat colonoscopy. In this study, we used artificial intelligence (AI) to evaluate bowel preparation and validated the ability of the system to accurately identify patients who are at high risk of having >5 mm adenomas missed due to inadequate bowel preparation. METHODS: This prospective, single-center, observational study was conducted at the Eighth Affiliated Hospital, Sun Yat-sen University, from October 8, 2021, to November 9, 2022. Eligible patients who underwent screening colonoscopy were consecutively enrolled. The AI assessed bowel preparation using the e-Boston Bowel Preparation Scale (e-BBPS) while endoscopists made evaluations using BBPS. If both BBPS and e-BBPS deemed preparation adequate, the patient immediately underwent a second colonoscopy; otherwise, the patient underwent bowel re-cleansing before the second colonoscopy. RESULTS: Among the 393 patients, 72 adenomas >5 mm in size were detected; 27 adenomas >5 mm in size were missed. In unqualified-AI patients, the >5 mm adenoma miss rate (AMR) was significantly higher than in qualified-AI patients (35.71% vs 13.19% [P = .0056]; odds ratio [OR], .2734 [95% CI, .1139-.6565]), as were the AMR (50.89% vs 20.79% [P < .001]; OR, .2532 [95% CI, .1583-.4052]) and >5 mm polyp miss rate (35.82% vs 19.48% [P = .0152]; OR, .4335 [95% CI, .2288-.8213]). CONCLUSIONS: This study confirmed that patients classified as inadequate by AI exhibited an unacceptable >5 mm AMR, providing key evidence for implementing AI in guiding bowel re-cleansing and potentially standardizing future colonoscopy screening. (Clinical trial registration number: NCT05145712.).

Identification of prognostic signatures in remnant gastric cancer through an interpretable risk model based on machine learning: a multicenter cohort study.

OBJECTIVE: The purpose of this study was to develop an individual survival prediction model based on multiple machine learning (ML) algorithms to predict survival probability for remnant gastric cancer (RGC). METHODS: Clinicopathologic data of 286 patients with RGC undergoing operation (radical resection and palliative resection) from a multi-institution database were enrolled and analyzed retrospectively. These individuals were split into training (80%) and test cohort (20%) by using random allocation. Nine commonly used ML methods were employed to construct survival prediction models. Algorithm performance was estimated by analyzing accuracy, precision, recall, F1-score, area under the receiver operating characteristic curve (AUC), confusion matrices, five-fold cross-validation, decision curve analysis (DCA), and calibration curve. The best model was selected through appropriate verification and validation and was suitably explained by the SHapley Additive exPlanations (SHAP) approach. RESULTS: Compared with the traditional methods, the RGC survival prediction models employing ML exhibited good performance. Except for the decision tree model, all other models performed well, with a mean ROC AUC above 0.7. The DCA findings suggest that the developed models have the potential to enhance clinical decision-making processes, thereby improving patient outcomes. The calibration curve reveals that all models except the decision tree model displayed commendable predictive performance. Through CatBoost-based modeling and SHAP analysis, the five-year survival probability is significantly influenced by several factors: the lymph node ratio (LNR), T stage, tumor size, resection margins, perineural invasion, and distant metastasis. CONCLUSIONS: This study established predictive models for survival probability at five years in RGC patients based on ML algorithms which showed high accuracy and applicative value.

Deep learning assists detection of esophageal cancer and precursor lesions in a prospective, randomized controlled study.

Endoscopy is the primary modality for detecting asymptomatic esophageal squamous cell carcinoma (ESCC) and precancerous lesions. Improving detection rate remains challenging. We developed a system based on deep convolutional neural networks (CNNs) for detecting esophageal cancer and precancerous lesions [high-risk esophageal lesions (HrELs)] and validated its efficacy in improving HrEL detection rate in clinical practice (trial registration ChiCTR2100044126 at www.chictr.org.cn). Between April 2021 and March 2022, 3117 patients ≥50 years old were consecutively recruited from Taizhou Hospital, Zhejiang Province, and randomly assigned 1:1 to an experimental group (CNN-assisted endoscopy) or a control group (unassisted endoscopy) based on block randomization. The primary endpoint was the HrEL detection rate. In the intention-to-treat population, the HrEL detection rate [28 of 1556 (1.8%)] was significantly higher in the experimental group than in the control group [14 of 1561 (0.9%), P = 0.029], and the experimental group detection rate was twice that of the control group. Similar findings were observed between the experimental and control groups [28 of 1524 (1.9%) versus 13 of 1534 (0.9%), respectively; P = 0.021]. The system's sensitivity, specificity, and accuracy for detecting HrELs were 89.7, 98.5, and 98.2%, respectively. No adverse events occurred. The proposed system thus improved HrEL detection rate during endoscopy and was safe. Deep learning assistance may enhance early diagnosis and treatment of esophageal cancer and may become a useful tool for esophageal cancer screening.

Clustering human dental pulp fibroblasts spontaneously activate NLRP3 and AIM2 inflammasomes and induce IL-1ß secretion.

Objectives: The objective of the present study was to investigate whether NOD-like receptor family pyrin domain-containing 3 (NLRP3) and absent in melanoma 2 (AIM2) inflammasomes pathways were involved in an experimental model of fibroblast activation named nemosis, which was used to mimic circumstances without bacteria stimulation. Methods: Nemosis of human dental pulp fibroblast (DPFs) was induced by three-dimensional culture in U-shaped 96-well plates and investigated by scanning electron microscopy (SEM). DPFs monolayers were used as control. Annexin V-FITC/7-AAD apoptosis assay was performed on the DPFs spheroids by flowcytometry. Caspase-1 activity detection assay was conducted on the DPFs spheroids. Quantitative real-time polymerase chain reaction (qRT-PCR), cytokine measurements, Western blot and the effect of COX-2 inhibitor on spheroids was studied. Results: SEM study observed human dental pulp fibroblast clusters and cell membranes damage on the surface of DPFs spheroids. The percentages of necrotic cells from DPFs spheroids gradually increased as the incubation time increased. A statistically significant increase in caspase-1 activity was observed after DPFs spheroids formation. DPFs spheroids displayed significant amounts of NLRP3, AIM2 mRNA and protein expression, caspase-1 mRNA expression and cleaved Caspase-1 protein expression and high IL-1ß concentrations (P < 0.05) than DPFs monolayers. Specific COX-2 inhibitor (NS-398) decreased NLRP3 mRNA and protein expression, cleaved Caspase-1 protein expression, Caspase-1 activity and IL-1ß mRNA expression and IL-1ß concentrations (P < 0.05). However, Specific COX-2 inhibitor had no impact on AIM2 mRNA and protein expression, caspase-1 mRNA expression and pro-Caspase-1 protein expression. Conclusions: In conclusion, clustering human DPFs spontaneously activated NLRP3 and AIM2 inflammasomes and induced IL-1ß secretion which could be partially attenuated by COX-2 inhibitor. Thus, nemosis could become a powerful model for studying mechanisms underlying aseptic pulpitis.

Role of the circular RNA regulatory network in the pathogenesis of biliary atresia.

Circular RNAs (circRNAs) serve an essential role in the occurrence and development of cholangiocarcinoma, but the expression and function of circRNA in biliary atresia (BA) is not clear. In the present study, circRNA expression profiles were investigated in the liver tissues of patients with BA as well as in the choledochal cyst (CC) tissues of control patients using RNA sequencing. A total of 78 differentially expressed circRNAs (DECs) were identified between the BA and CC tissues. The expression levels of eight circRNAs (hsa_circ_0006137, hsa_circ_0079422, hsa_circ_0007375, hsa_circ_0005597, hsa_circ_0006961, hsa_circ_0081171, hsa_circ_0084665 and hsa_circ_0075828) in the liver tissues of the BA group and control group were measured using reverse transcription-quantitative polymerase chain reaction. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis demonstrated that the identified DECs are involved in a variety of biological processes, including apoptosis and metabolism. In addition, based on the GO and KEGG pathway enrichment analyses, it was revealed that target genes that can be affected by circRNAs regulatory network were enriched in the TGF-ß signaling pathway, EGFR tyrosine kinase inhibitor resistance pathway and transcription factor regulation pathway as well as other pathways that may be associated with the pathogenesis of BA. The present study revealed that circRNAs are potentially implicated in the pathogenesis of BA and could help to find promising targets and biomarkers for BA.

The difference of transcriptome of HPV-infected patients contributes more to the occurrence of cervical cancer than the mutations of E6 and E7 genes in HPV16.

Human papillomavirus (HPV) E6 and E7 genes are biomarkers and drivers of the progression of cervical cancer (CxCa). The aim of this study was to investigate the relationship between HPV16 E6, E7 gene mutations and the occurrence and development of CxCa. Cervical exfoliated cells and clinical data of patients with cervical diseases were collected. Sample DNA was extracted, the E6 and E7 gene fragments were amplified by PCR, and the mutations were detected by Sanger sequencing and compared with standard sequences. Microarray was used to sequence the transcriptome of cells. Data of transcriptome analyzed and visualized using R software and its packages. Analysis of clinical characteristics demonstrated the association of HPV16 infection with CxCa (P < .05). Sanger sequencing results showed that the mutation sites of E6 gene included T178G/A, T350G, A131C, and T241G; among these, A131C and T241G were synonymous mutations. The mutation sites of E7 gene included A647G, T846C, G666A, T843C, and T760C, and all of them were synonymous mutations except A647G. There was no significant difference in the distribution of HPV16 E6, E7 mutations among CxCa, cervical intraepithelial neoplasia, and infection groups (P > .05). Compared with the non- CxCa group, gene ontology and Kyoto Encyclopedia of Genes and Genomes enrichment analysis of differentially expressed genes (DEGs) showed more significant enrichment of DEGs in the biological processes, pathways, and diseases closely related to cancer. Compared with the non-mutation group, the DEGs in the E6, E7 gene mutation group were significantly enriched in the events related to infection and immunity. To summarize, HPV16 may be associated with the occurrence and development of CxCa, but HPV16 E6 and E7 gene mutations have little effect on the occurrence and development of CxCa. Individual differences may have a greater effect on the progression of CxCa.

Current status of quality control in screening esophagogastroduodenoscopy and the emerging role of artificial intelligence.

Esophagogastroduodenoscopy (EGD) screening is being implemented in countries with a high incidence of upper gastrointestinal (UGI) cancer. High-quality EGD screening ensures the yield of early diagnosis and prevents suffering from advanced UGI cancer and minimal operational-related discomfort. However, performance varied dramatically among endoscopists, and quality control for EGD screening remains suboptimal. Guidelines have recommended potential measures for endoscopy quality improvement and research has been conducted for evidence. Moreover, artificial intelligence offers a promising solution for computer-aided diagnosis and quality control during EGD examinations. In this review, we summarized the key points for quality assurance in EGD screening based on current guidelines and evidence. We also outline the latest evidence, limitations, and future prospects of the emerging role of artificial intelligence in EGD quality control, aiming to provide a foundation for improving the quality of EGD screening.

Discovery of (2-(4-Substituted phenyl)quinolin-4-yl)(4-isopropylpiperazin-1-yl)methanone Derivatives as Potent Proprotein Convertase Subtilisin/Kexin Type 9 Inhibitors.

Inhibition of proprotein convertase subtilisin/kexin type 9 (PCSK9) plays an increasingly important role in the treatment of hyperlipidemia. In pursuit of potent small molecules that block the PCSK9/low-density lipoprotein receptor (LDLR) protein-protein interaction (PPI), a series of 2-phenylquinoline-4-carboxylic acid derivatives were designed and synthesized based on previously derived molecules. In the in vitro PPI inhibition test, compounds M1, M12, M14, M18 and M27 exhibited potent activities with IC50 values of 6.25 µM, 0.91 µM, 2.81 µM, 4.26 µM and 0.76 µM, respectively, compared with SBC-115337 (IC50 value of 9.24 µM). Molecular docking and molecular dynamics simulations revealed the importance of hydrophobic interactions in the binding of inhibitors to the PPI interface of PCSK9. In LDLR expression and LDL uptake assays, the tested compounds M1, M12 and M14 were found to restore LDLR expression levels and to increase the extracellular LDL uptake capacity of HepG2 cells in the presence of exogenous PCSK9. Collectively, novel small-molecule PCSK9/LDLR PPI inhibitors (especially M12) with in vitro lipid lowering ability, were discovered as lead compounds for further development of hypolipidemic drugs.

Effect of artificial intelligence on novice-performed colonoscopy: a multicenter randomized controlled tandem study.

BACKGROUND AND AIMS: The efficacy and safety of colonoscopy performed by artificial intelligence (AI)-assisted novices remain unknown. The aim of this study was to compare the lesion detection capability of novices, AI-assisted novices, and experts. METHODS: This multicenter, randomized, noninferiority tandem study was conducted across 3 hospitals in China from May 1, 2022, to November 11, 2022. Eligible patients were randomized into 1 of 3 groups: the CN group (control novice group, withdrawal performed by a novice independently), the AN group (AI-assisted novice group, withdrawal performed by a novice with AI assistance), or the CE group (control expert group, withdrawal performed by an expert independently). Participants underwent a repeat colonoscopy conducted by an AI-assisted expert to evaluate the lesion miss rate and ensure lesion detection. The primary outcome was the adenoma miss rate (AMR). RESULTS: A total of 685 eligible patients were analyzed: 229 in the CN group, 227 in the AN group, and 229 in the CE group. Both AMR and polyp miss rate were lower in the AN group than in the CN group (18.82% vs 43.69% [P < .001] and 21.23% vs 35.38% [P < .001], respectively). The noninferiority margin was met between the AN and CE groups of both AMR and polyp miss rate (18.82% vs 26.97% [P = .202] and 21.23% vs 24.10% [P < .249]). CONCLUSIONS: AI-assisted colonoscopy lowered the AMR of novices, making them noninferior to experts. The withdrawal technique of new endoscopists can be enhanced by AI-assisted colonoscopy. (Clinical trial registration number: NCT05323279.).

Bioremediation of environmental organic pollutants by Pseudomonas aeruginosa: Mechanisms, methods and challenges.

The development of the chemical industry has led to a boom in daily consumption and convenience, but has also led to the release of large amounts of organic pollutants, such as petroleum hydrocarbons, plastics, pesticides, and dyes. These pollutants are often recalcitrant to degradation in the environment, whereby the most problematic compounds may even lead to carcinogenesis, teratogenesis and mutagenesis in animals and humans after accumulation in the food chain. Microbial degradation of organic pollutants is efficient and environmentally friendly, which is why it is considered an ideal method. Numerous studies have shown that Pseudomonas aeruginosa is a powerful platform for the remediation of environmental pollution with organic chemicals due to its diverse metabolic networks and its ability to secrete biosurfactants to make hydrophobic substrates more bioavailable, thereby facilitating degradation. In this paper, the mechanisms and methods of the bioremediation of environmental organic pollutants (EOPs) by P. aeruginosa are reviewed. The challenges of current studies are highlighted, and new strategies for future research are prospected. Metabolic pathways and critical enzymes must be further deciphered, which is significant for the construction of a bioremediation platform based on this powerful organism.

Identification and validation of hub genes involved in foam cell formation and atherosclerosis development via bioinformatics.

Background: Foam cells play crucial roles in all phases of atherosclerosis. However, until now, the specific mechanisms by which these foam cells contribute to atherosclerosis remain unclear. We aimed to identify novel foam cell biomarkers and interventional targets for atherosclerosis, characterizing their potential mechanisms in the progression of atherosclerosis. Methods: Microarray data of atherosclerosis and foam cells were downloaded from the Gene Expression Omnibus (GEO) database. Differentially expression genes (DEGs) were screened using the "LIMMA" package in R software. The Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis and Gene Ontology (GO) annotation were both carried out. Hub genes were found in Cytoscape after a protein-protein interaction (PPI) enrichment analysis was carried out. Validation of important genes in the GSE41571 dataset, cellular assays, and tissue samples. Results: A total of 407 DEGs in atherosclerosis and 219 DEGs in foam cells were identified, and the DEGs in atherosclerosis were mainly involved in cell proliferation and differentiation. CSF1R and PLAUR were identified as common hub genes and validated in GSE41571. In addition, we also found that the expression of CSF1R and PLAUR gradually increased with the accumulation of lipids and disease progression in cell and tissue experiments. Conclusion: CSF1R and PLAUR are key hub genes of foam cells and may play an important role in the biological process of atherosclerosis. These results advance our understanding of the mechanism behind atherosclerosis and potential therapeutic targets for future development.

Multiple synchronous primary malignant neoplasms: A case report and literature review.

Multiple primary malignant neoplasms (MPMN) are defined as two or more primary malignancies diagnosed in an individual. There is no association between these cancers, which can be classified into synchronous and heterochronous cancers depending on the time of diagnosis. The present study presented a rare case of bilateral breast, endometrial, cervical and ovarian cancers. Through thorough physical examination, pathology and immunohistochemistry, it could be determined that bilateral breast, endometrial and cervical cancers were primary malignant tumors and that ovarian cancer cannot be excluded as a result of metastasis. the present study also summarized the definitions, risk factors, prevalence characteristics, diagnostic ideas and treatment options for MPMN by reviewing the literature.

USP5 promotes lipopolysaccharide-induced apoptosis and inflammatory response by stabilizing the TXNIP protein.

BACKGROUND: The role of thioredoxin-interacting protein (TXNIP) in lipopolysaccharide-induced liver injury in mice has been reported, but the underlying mechanisms are poorly understood. METHODS: We overexpressed deubiquitinase in cells overexpressing TXNIP and then detected the level of TXNIP to screen out the deubiquitinase regulating TXNIP; the interaction between TXNIP and deubiquitinase was verified by coimmunoprecipitation. After knockdown of a deubiquitinase and overexpression of TXNIP in Huh7 and HepG2 cells, lipopolysaccharide was used to establish a cellular inflammatory model to explore the role of deubiquitinase and TXNIP in hepatocyte inflammation. RESULTS: In this study, we discovered that ubiquitin-specific protease 5 (USP5) interacts with TXNIP and stabilizes it through deubiquitylation in Huh-7 and HepG2 cells after treatment with lipopolysaccharide. In lipopolysaccharide-treated Huh-7 and HepG2 cells, USP5 knockdown increased cell viability, reduced apoptosis, and decreased the expression of inflammatory factors, including NLRP3, IL-1ß, IL-18, ASC, and procaspase-1. Overexpression of TXNIP reversed the phenotype induced by knockdown USP5. CONCLUSIONS: In summary, USP5 promotes lipopolysaccharide-induced apoptosis and inflammatory response by stabilizing the TXNIP protein.

Development and Validation of a Deep Learning-Based Histologic Diagnosis System for Diagnosing Colorectal Sessile Serrated Lesions.

OBJECTIVES: The histopathologic diagnosis of colorectal sessile serrated lesions (SSLs) and hyperplastic polyps (HPs) is of low consistency among pathologists. This study aimed to develop and validate a deep learning (DL)-based logical anthropomorphic pathology diagnostic system (LA-SSLD) for the differential diagnosis of colorectal SSL and HP. METHODS: The diagnosis framework of the LA-SSLD system was constructed according to the current guidelines and consisted of 4 DL models. Deep convolutional neural network (DCNN) 1 was the mucosal layer segmentation model, DCNN 2 was the muscularis mucosa segmentation model, DCNN 3 was the glandular lumen segmentation model, and DCNN 4 was the glandular lumen classification (aberrant or regular) model. A total of 175 HP and 127 SSL sections were collected from Renmin Hospital of Wuhan University during November 2016 to November 2022. The performance of the LA-SSLD system was compared to 11 pathologists with different qualifications through the human-machine contest. RESULTS: The Dice scores of DCNNs 1, 2, and 3 were 93.66%, 58.38%, and 74.04%, respectively. The accuracy of DCNN 4 was 92.72%. In the human-machine contest, the accuracy, sensitivity, and specificity of the LA-SSLD system were 85.71%, 86.36%, and 85.00%, respectively. In comparison with experts (pathologist D: accuracy 83.33%, sensitivity 90.91%, specificity 75.00%; pathologist E: accuracy 85.71%, sensitivity 90.91%, specificity 80.00%), LA-SSLD achieved expert-level accuracy and outperformed all the senior and junior pathologists. CONCLUSIONS: This study proposed a logical anthropomorphic diagnostic system for the differential diagnosis of colorectal SSL and HP. The diagnostic performance of the system is comparable to that of experts and has the potential to become a powerful diagnostic tool for SSL in the future. It is worth mentioning that a logical anthropomorphic system can achieve expert-level accuracy with fewer samples, providing potential ideas for the development of other artificial intelligence models.