Revealing molecular and cellular heterogeneity in hypopharyngeal carcinogenesis through single-cell RNA and TCR/BCR sequencing.

Introduction: Hypopharyngeal squamous cell carcinoma (HSCC) is one of the malignant tumors with the worst prognosis in head and neck cancers. The transformation from normal tissue through low-grade and high-grade intraepithelial neoplasia to cancerous tissue in HSCC is typically viewed as a progressive pathological sequence typical of tumorigenesis. Nonetheless, the alterations in diverse cell clusters within the tissue microenvironment (TME) throughout tumorigenesis and their impact on the development of HSCC are yet to be fully understood. Methods: We employed single-cell RNA sequencing and TCR/BCR sequencing to sequence 60,854 cells from nine tissue samples representing different stages during the progression of HSCC. This allowed us to construct dynamic transcriptomic maps of cells in diverse TME across various disease stages, and experimentally validated the key molecules within it. Results: We delineated the heterogeneity among tumor cells, immune cells (including T cells, B cells, and myeloid cells), and stromal cells (such as fibroblasts and endothelial cells) during the tumorigenesis of HSCC. We uncovered the alterations in function and state of distinct cell clusters at different stages of tumor development and identified specific clusters closely associated with the tumorigenesis of HSCC. Consequently, we discovered molecules like MAGEA3 and MMP3, pivotal for the diagnosis and treatment of HSCC. Discussion: Our research sheds light on the dynamic alterations within the TME during the tumorigenesis of HSCC, which will help to understand its mechanism of canceration, identify early diagnostic markers, and discover new therapeutic targets.

Multi-instance learning based artificial intelligence model to assist vocal fold leukoplakia diagnosis: A multicentre diagnostic study.

OBJECTIVE: To develop a multi-instance learning (MIL) based artificial intelligence (AI)-assisted diagnosis models by using laryngoscopic images to differentiate benign and malignant vocal fold leukoplakia (VFL). METHODS: The AI system was developed, trained and validated on 5362 images of 551 patients from three hospitals. Automated regions of interest (ROI) segmentation algorithm was utilized to construct image-level features. MIL was used to fusion image level results to patient level features, then the extracted features were modeled by seven machine learning algorithms. Finally, we evaluated the image level and patient level results. Additionally, 50 videos of VFL were prospectively gathered to assess the system's real-time diagnostic capabilities. A human-machine comparison database was also constructed to compare the diagnostic performance of otolaryngologists with and without AI assistance. RESULTS: In internal and external validation sets, the maximum area under the curve (AUC) for image level segmentation models was 0.775 (95 % CI 0.740-0.811) and 0.720 (95 % CI 0.684-0.756), respectively. Utilizing a MIL-based fusion strategy, the AUC at the patient level increased to 0.869 (95 % CI 0.798-0.940) and 0.851 (95 % CI 0.756-0.945). For real-time video diagnosis, the maximum AUC at the patient level reached 0.850 (95 % CI, 0.743-0.957). With AI assistance, the AUC improved from 0.720 (95 % CI 0.682-0.755) to 0.808 (95 % CI 0.775-0.839) for senior otolaryngologists and from 0.647 (95 % CI 0.608-0.686) to 0.807 (95 % CI 0.773-0.837) for junior otolaryngologists. CONCLUSIONS: The MIL based AI-assisted diagnosis system can significantly improve the diagnostic performance of otolaryngologists for VFL and help to make proper clinical decisions.

Narrow band imaging-based radiogenomics for predicting radiosensitivity in nasopharyngeal carcinoma.

Objectives: This study aims to assess the efficacy of narrow band imaging (NBI) endoscopy in utilizing radiomics for predicting radiosensitivity in nasopharyngeal carcinoma (NPC), and to explore the associated molecular mechanisms. Materials: The study included 57 NPC patients who were pathologically diagnosed and underwent RNA sequencing. They were categorized into complete response (CR) and partial response (PR) groups after receiving radical concurrent chemoradiotherapy. We analyzed 267 NBI images using ResNet50 for feature extraction, obtaining 2048 radiomic features per image. Using Python for deep learning and least absolute shrinkage and selection operator for feature selection, we identified differentially expressed genes associated with radiomic features. Subsequently, we conducted enrichment analysis on these genes and validated their roles in the tumor immune microenvironment through single-cell RNA sequencing. Results: After feature selection, 54 radiomic features were obtained. The machine learning algorithm constructed from these features showed that the random forest algorithm had the highest average accuracy rate of 0.909 and an area under the curve of 0.961. Correlation analysis identified 30 differential genes most closely associated with the radiomic features. Enrichment and immune infiltration analysis indicated that tumor-associated macrophages are closely related to treatment responses. Three key NBI differentially expressed immune genes (NBI-DEIGs), namely CCL8, SLC11A1, and PTGS2, were identified as regulators influencing treatment responses through macrophages. Conclusion: NBI-based radiomics models introduce a novel and effective method for predicting radiosensitivity in NPC. The molecular mechanisms may involve the functional states of macrophages, as reflected by key regulatory genes.

Endoscopic submucosal dissection for early esophageal squamous cell carcinoma after ligation and sclerotherapy of esophageal and gastric varices.

Esophageal cancer ranked ten of the most common cancers in China. With the advancement of high-quality endoscopy and chromoendoscopic technique, early esophageal cancer can be diagnosed more easily, even combined with esophageal-gastric fundal varices. Endoscopic resection of early esophageal cancer is a minimally invasive treatment method for early esophageal cancer, and endoscopic submucosal dissection (ESD) is one of the standard treatments for early esophageal cancer in view of the risk of bleeding, the patient in this study successfully received ESD treatment after using endoscopic variceal ligation and endoscopic injection of tissue glue and sclerosing agent before ESD surgery. ESD treatment is safe and feasible for early esophageal cancer patients with cirrhosis of esophageal-gastric fundal varices.

Diverse ALS mutations and cross-and multiple-resistance to ALS and EPSPS inhibitors in flucarbazone­sodium-resistant Bromus japonicus populations from Hebei province, China.

Japanese brome (Bromus japonicus) has become one of the main weeds in wheat fields in Hebei province of China and causes a large decrease of wheat production. A total of 44 putative resistant and 2 susceptible Japanese brome populations were collected in the 2021/2022 crop season from Hebei province of China to determine resistance levels to flucarbazone­sodium and to investigate the diversity of acetolactate synthase (ALS) mutations, as well as to confirm the cross-and multiple-resistance levels to ALS and EPSPS (5-enolpyruvate shikimate-3-phosphate synthetase) inhibitors. Whole plant bioassay results showed that 15 out of 44 populations tested or 34% were resistant to flucarbazone­sodium. The resistance indices of Japanese brome to flucarbazone­sodium ranged from 43 to 1977. The resistant populations were mainly distributed in Baoding and Shijiazhuang districts, and there was only one resistant population in Langfang district. Resistant Japanese brome had diverse ALS mutations, including Pro-197-Ser, -Thr, -Arg and Asp-376-Glu. The incidence of Pro-197-Ser mutation was the highest at 68%. Application of the CYP450 inhibitor malathion suggested that CYP450 was involved in metabolic resistance in a population without an ALS mutation. The population with Pro-197-Thr mutation evolved weak cross-resistance to mesosulfuron-methyl and pyroxsulam, and it is in the process of evolving multiple-resistance to glyphosate.

Trp-574-Leu mutation and metabolic resistance by cytochrome P450 gene conferred high resistance to ALS-inhibiting herbicides in Descurainia sophia.

Descurainia sophia (flixweed) is a troublesome weed in winter wheat fields in North China. Resistant D. sophia populations with different acetolactate synthetase (ALS) mutations have been reported in recent years. In addition, metabolic resistance to ALS-inhibiting herbicides has also been identified. In this study, we collected and purified two resistant D. sophia populations (R1 and R2), which were collected from winter wheat fields where tribenuron-methyl provided no control of D. sophia at 30 g a.i. ha-1. Whole plant bioassay and ALS activity assay results showed the R1 and R2 populations had evolved high-level resistance to tribenuron-methyl and florasulam and cross-resistance to imazethapyr and pyrithiobac­sodium. The two ALS genes were cloned from the leaves of R1 and R2 populations, ALS1 (2004 bp) and ALS2 (1998 bp). A mutation of Trp 574 to Leu in ALS1 was present in both R1 and R2. ALS1 and ALS2 were cloned from R1 and R2 populations respectively and transferred into Arabidopsis thaliana. Homozygous T3 transgenic seedlings with ALS1 of R1 or R2 were resistant to ALS-inhibiting herbicides and the resistant levels were the same. Transgenic seedlings with ALS2 from R1 or R2 were susceptible to ALS-inhibiting herbicides. Treatment with cytochrome P450 inhibitor malathion decreased the resistant levels to tribenuron-methyl in R1 and R2. RNA-Seq was used to identify target cytochrome P450 genes possibly involved in resistance to ALS-inhibiting herbicides. There were five up-regulated differentially expressed cytochrome P450 genes: CYP72A15, CYP83B1, CYP81D8, CYP72A13 and CYP71A12. Among of them, CYP72A15 had the highest expression level in R1 and R2 populations. The R1 and R2 populations of D. sophia have evolved resistance to ALS-inhibiting herbicides due to Trp 574 Leu mutation in ALS1 and possibly other mechanisms. The resistant function of CYP72A15 needs further research.

Long-term outcomes of endoscopic or surgical resection in T1 colorectal cancer patients: a retrospective cohort study.

BACKGROUND: The personalized treatments of T1 colorectal cancer (CRC) remains controversial. We compared the long-term outcomes of T1 CRC patients after endoscopic resection (ER) and surgery, and evaluated the risk factors for the long-term prognosis. METHODS: T1 CRCs after resection at the Cancer Hospital, Chines Academy of Medical Sciences from June 2011 to November 2021 were reviewed. High-risk factors included positive resection margin, poor differentiation, deep submucosal invasion (DSI ≥ 1000 µm), lymphovascular invasion and intermediate/high tumor budding. Comparative analyses were conducted based on three treatment methods: follow-up after ER (Group A), additional surgery after ER (Group B) and initial surgery (Group C). The primary endpoints included recurrence-free survival (RFS) and overall survival (OS). Cox proportional hazard regression models were constructed to identify risk factors for RFS and OS. RESULTS: A total of 528 patients were enrolled (173 patients in Group A, 102 patients in Group B, 253 patients in Group C). The 3-year RFS, 5-year RFS, 3-year OS, and 5-year OS rates were 96.7%, 94.7%, 99.1%, and 97.8%, respectively. In the absence of other high-risk factors, RFS (P = 0.321) and OS (P = 0.155) of patients with DSI after ER were not inferior to those after surgery. Multivariate analyses identified sex (HR 0.379; 95% CI 0.160-0.894), Charlson comorbidities index (CCI) (HR 3.330; 95% CI 1.571-7.062), margin (HR 8.212; 95% CI 2.325-29.006), and budding (HR 3.794; 95% CI 1.686-8.541) as independent predictive factors of RFS, and identified CCI (HR 10.266; 95% CI 2.856-36.899) as an independent predictive factor of OS. CONCLUSION: The long-term outcomes of ER are comparable to those of surgery in T1 CRC patients with DSI when other high-risk factors are negative. Resection margin, tumor budding, sex, and CCI may be the most important long-term prognostic factors for T1 CRC patients.

A strategy combining endoscopic hand-suturing with clips for closure of rectal defects after endoscopic submucosal dissection with or without myectomy (with video).

BACKGROUND AND AIMS: Endoscopic hand-suturing (EHS) has been preliminarily demonstrated to be effective in closing defects after endoscopic submucosal dissection (ESD), but it is not easily performed. We proposed a strategy combining EHS with clips (EHS-Clips) and explored its effectiveness in closing rectal defects after ESD or ESD with myectomy (ESD-ME). METHODS: In this observational study, data from patients with rectal defects closed using EHS-Clips were reviewed. EHS-Clips refers to a strategy where defects are sutured as much as possible by EHS first, with clips being used to close the remaining parts of defects that cannot be completely sutured. The primary endpoints included complete closure rate, delayed bleeding (DB) rate, and sustained closure rate. Logistic regression analyses were performed to identify risk factors for the sustained closure. RESULTS: All 49 (100%) defects (42 ESD defects and 7 ESD-ME defects) were completely closed through the strategy of EHS-Clips, with 35 (71.4%) through EHS alone and 14 (28.6%) through EHS and additional clips. No patients experienced DB. Thirty-six (73.5%) defects remained sustained closure on postoperative days 3 to 5 (73.8% for ESD defects vs 71.4% for ESD-ME defects). The multivariate analyses identified a stitch margin of ≥5 mm (hazard ratio, 0.313; 95% confidence interval, 0.023-0.781; P = .009) as the only independent advantage factor for the sustained closure. CONCLUSIONS: EHS-Clips can be used to effectively close the rectal defects after ESD or ESD-ME and prevent DB. Complete suture with a stitch margin of ≥5 mm may achieve more reliable sustained closure.

The Detection of Nasopharyngeal Carcinomas Using a Neural Network Based on Nasopharyngoscopic Images.

OBJECTIVE: To construct and validate a deep convolutional neural network (DCNN)-based artificial intelligence (AI) system for the detection of nasopharyngeal carcinoma (NPC) using archived nasopharyngoscopic images. METHODS: We retrospectively collected 14107 nasopharyngoscopic images (7108 NPCs and 6999 noncancers) to construct a DCNN model and prepared a validation dataset containing 3501 images (1744 NPCs and 1757 noncancers) from a single center between January 2009 and December 2020. The DCNN model was established using the You Only Look Once (YOLOv5) architecture. Four otolaryngologists were asked to review the images of the validation set to benchmark the DCNN model performance. RESULTS: The DCNN model analyzed the 3501 images in 69.35 s. For the validation dataset, the precision, recall, accuracy, and F1 score of the DCNN model in the detection of NPCs on white light imaging (WLI) and narrow band imaging (NBI) were 0.845 ± 0.038, 0.942 ± 0.021, 0.920 ± 0.024, and 0.890 ± 0.045, and 0.895 ± 0.045, 0.941 ± 0.018, and 0.975 ± 0.013, 0.918 ± 0.036, respectively. The diagnostic outcome of the DCNN model on WLI and NBI images was significantly higher than that of two junior otolaryngologists (p < 0.05). CONCLUSION: The DCNN model showed better diagnostic outcomes for NPCs than those of junior otolaryngologists. Therefore, it could assist them in improving their diagnostic level and reducing missed diagnoses. LEVEL OF EVIDENCE: 3 Laryngoscope, 134:127-135, 2024.

Laryngoscopy-based scoring system for the diagnosis of vocal fold leukoplakia.

OBJECTIVE: To propose a scoring system based on laryngoscopic characteristics for the differential diagnosis of benign and malignant vocal fold leukoplakia. METHODS: Laryngoscopic images from 200 vocal fold leukoplakia cases were retrospectively analysed. The laryngoscopic signs of benign and malignant vocal fold leukoplakia were compared, and statistically significant features were assigned and accumulated to establish the leukoplakia finding score. RESULTS: A total of five indicators associated with malignant vocal fold leukoplakia were included to construct the leukoplakia finding score, with a possible range of 0-10 points. A score of 6 points or more was indicative of a diagnosis of malignant vocal fold leukoplakia. The sensitivity, specificity and accuracy values of the leukoplakia finding score were 93.8 per cent, 83.6 per cent and 86.0 per cent, respectively. The consistency in the leukoplakia finding score obtained by different laryngologists was strong (kappa = 0.809). CONCLUSION: This scoring system based on laryngoscopic characteristics has high diagnostic value for distinguishing benign and malignant vocal fold leukoplakia.

Bariatric surgery reduces colorectal cancer incidence in obese individuals: Systematic review and meta-analysis.

BACKGROUND: Colorectal cancer ranks third in global cancer prevalence and stands as the second leading cause of cancer-related mortalities. With obesity recognized as a pivotal risk factor for colorectal cancer, the potential protective role of bariatric surgery, especially laparoscopic Roux-en-Y gastric bypass and laparoscopic sleeve gastrectomy, has garnered attention. AIM: To investigate the Roux-en-Y gastric bypass (RYGB) vs sleeve gastrectomy (SG) effect on colorectal cancer incidence in obese individuals. METHODS: A systematic review and meta-analysis of the literature was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses. Seventeen studies with a total of 12497322 patients were included. The primary outcome was the relative risk (RR) of developing colorectal cancer in obese patients who underwent weight loss surgery compared to those who did not. Secondary outcomes included determining the RR for colon and rectal cancer separately and subgroup analyses by gender and type of weight loss surgery. RESULTS: The meta-analysis revealed a 54% reduction in colorectal cancer risk in morbidly obese patients who underwent bariatric surgery compared to those who did not. A significant 46% reduction in colorectal cancer risk was observed among female patients. However, no significant differences were found in the meta-analysis for various types of bariatric surgery, such as SG and RYGB. CONCLUSION: This meta-analysis reveals weight loss surgery, regardless of type, reduces colorectal cancer risk, especially in women, as indicated by RR and hazard ratio assessments. Further validation is essential.

Target-site mutation and enhanced metabolism endow resistance to nicosulfuron in a Digitaria sanguinalis population.

Digitaria sanguinalis is a competitive and annual grass weed that commonly infests crops across the world. In recent years, the control of D. sanguinalis by nicosulfuron has declined in Hebei Province, China. To determine the resistance mechanisms of D. sanguinalis to nicosulfuron, a population of D. sanguinalis where nicosulfuron had failed was collected from a maize field of Hebei Province, China. Whole-plant dose-response experiments demonstrated that the resistant population (HBMT-15) displayed 6.9-fold resistance to nicosulfuron compared with the susceptible population (HBMT-5). Addition of the glutathione S-transferase (GSTs) inhibitor 4-chloro-7-nitrobenzoxadiazole (NBD-Cl) significantly reduced the resistance level of the HBMT-15 population to nicosulfuron, and the GSTs activity of the HBMT-15 population was higher than the HBMT-5 population after nicosulfuron treatment. In vitro acetolactate synthase (ALS) enzyme experiments revealed that the nicosulfuron I50 value for the HBMT-15 population was 41 times higher than that of the HBMT-5 population. An Asp376 to Glu substitution in the ALS gene was identified in the HBMT-15 population. The HBMT-15 population had a moderate (2- to 4-fold) level of cross-resistance to three other ALS inhibitors (imazethapyr, pyroxsulam, and flucarbazone­sodium), but was susceptible to pyrithiobac­sodium. This study demonstrated that both an Asp376 to Glu substitution in the ALS gene and GSTs-involved metabolic resistance to ALS inhibitors coexisted in a D. sanguinalis population.

Laparoscopic endoscopic cooperative surgery for the duodenal neuroendocrine tumor: a single-center case series (How I Do It).

BACKGROUND: Duodenal neuroendocrine tumors (D-NETs) are uncommon. The surgical treatment for D-NETs was in debate. Laparoscopic and endoscopic cooperative surgery (LECS) is a promising approach for treating gastrointestinal tumors. The study aimed to evaluate the feasibility and safety of LECS for D-NETs. Meanwhile, the authors described the details of the LECS technique. METHODS: All patients diagnosed with D-NETs underwent LECS between September 2018 and April 2022 were retrospectively reviewed. The endoscopic procedures were performed with endoscopic full-thickness resection. The defect was manually closed under the surveillance of the laparoscopy. RESULTS: A total of seven patients were enrolled, including three men and four women. The median age was 58 years (ranging from 39-65). Four tumors were located in the bulb and three in the second portion. All cases were diagnosed as NET with grade G1. The tumor depth was pT1 in two cases and pT2 in five cases. The median specimen size and the tumor size were 22 mm (ranging from 10-30) and 8.0 mm (ranging from 2.3-13.0), respectively. En-bloc resection and curative resection rates are 100 and 85.7%, respectively. There were no severe complications. Until 1 June 2022, there was no recurrence. The median follow-up was 9.5 months (range, 1.4-45.1). CONCLUSIONS: LECS with endoscopic full-thickness resection is a reliable surgical procedure. The minimally invasive advantages of LECS enable more individualized treatment options for a specific group. Limited by the length of observation, the long-term performance of LECS for D-NETs requires additional investigation.

Optimal starting age of endoscopic screening for esophageal cancer in China: A multicenter prospective cohort study.

BACKGROUND: Although endoscopic screening for esophageal cancer has been performed in high-risk areas in China for decades, there is limited and inconsistent evidence regarding the starting age for individuals participating in screening. The aim of this study is to investigate the optimal starting age of esophageal cancer screening. METHODS: This study is based on a multicenter prospective cohort consisting 338,017 permanent residents aged 40-69 years in six high-risk areas of esophageal cancer in China. The participation rate, detection rate, hazard ratios (HRs), cumulative incidence and mortality and number needed to screen (NNS) were calculated in each age group. Screening burden, benefit and risk were compared among screening strategies with different initiation ages to explore the optimal starting age for population-based screening in high-risk areas. RESULTS: Individuals aged 50-69 had a higher participation rate, a higher detection rate and improved screening effectiveness than those aged 40-49. The endoscopic screening had no significant effect on reducing the incidence of esophageal cancer in individuals under 55 and mortality in individuals under 45. Increasing the starting age to 50 years reduced the screening demand and NNS by 40% and 55%, and resulted in 12% of detectable positive cases, 16% of preventable incident cases, and 14% of preventable deaths being missed. CONCLUSIONS: Postponing the starting age of endoscopic screening to 50 years might yield a more-favorable balance between screening benefit and burden in high- risk areas with limited resources.

Identification and validation of IgG N-glycosylation biomarkers of esophageal carcinoma.

Introduction: Altered Immunoglobulin G (IgG) N-glycosylation is associated with aging, inflammation, and diseases status, while its effect on esophageal squamous cell carcinoma (ESCC) remains unknown. As far as we know, this is the first study to explore and validate the association of IgG N-glycosylation and the carcinogenesis progression of ESCC, providing innovative biomarkers for the predictive identification and targeted prevention of ESCC. Methods: In total, 496 individuals of ESCC (n=114), precancerosis (n=187) and controls (n=195) from the discovery population (n=348) and validation population (n=148) were recruited in the study. IgG N-glycosylation profile was analyzed and an ESCC-related glycan score was composed by a stepwise ordinal logistic model in the discovery population. The receiver operating characteristic (ROC) curve with the bootstrapping procedure was used to assess the performance of the glycan score. Results: In the discovery population, the adjusted OR of GP20 (digalactosylated monosialylated biantennary with core and antennary fucose), IGP33 (the ratio of all fucosylated monosyalilated and disialylated structures), IGP44 (the proportion of high mannose glycan structures in total neutral IgG glycans), IGP58 (the percentage of all fucosylated structures in total neutral IgG glycans), IGP75 (the incidence of bisecting GlcNAc in all fucosylated digalactosylated structures in total neutral IgG glycans), and the glycan score are 4.03 (95% CI: 3.03-5.36, P<0.001), 0.69 (95% CI: 0.55-0.87, P<0.001), 0.56 (95% CI: 0.45-0.69, P<0.001), 0.52 (95% CI: 0.41-0.65, P<0.001), 7.17 (95% CI: 4.77-10.79, P<0.001), and 2.86 (95% CI: 2.33-3.53, P<0.001), respectively. Individuals in the highest tertile of the glycan score own an increased risk (OR: 11.41), compared with those in the lowest. The average multi-class AUC are 0.822 (95% CI: 0.786-0.849). Findings are verified in the validation population, with an average AUC of 0.807 (95% CI: 0.758-0.864). Discussion: Our study demonstrated that IgG N-glycans and the proposed glycan score appear to be promising predictive markers for ESCC, contributing to the early prevention of esophageal cancer. From the perspective of biological mechanism, IgG fucosylation and mannosylation might involve in the carcinogenesis progression of ESCC, and provide potential therapeutic targets for personalized interventions of cancer progression.

Radiotherapy Improves Survival of Patients With Lymphovascular Invasion in pT1b Esophageal Squamous Cell Cancer After Endoscopic Submucosal Dissection.

INTRODUCTION: Adjuvant radiotherapy is recommended for pT1b esophageal squamous cell cancer (ESCC) after endoscopic submucosal dissection (ESD). However, it is unclear whether additional radiotherapy can improve patient survival. This study aimed to evaluate the efficacy of adjuvant radiotherapy after ESD for pT1b ESCC. METHODS: This was a multicenter, cross-sectional study involving 11 hospitals in China. Between January 2010 and December 2019, patients with T1bN0M0 ESCC treated with or without adjuvant radiotherapy after ESD were included. Survival between groups was compared. RESULTS: Overall, 774 patients were screened, and 161 patients were included. Forty-seven patients (29.2%) received adjuvant radiotherapy after ESD (RT group) and 114 (70.8%) underwent ESD alone (non-RT group). There were no significant differences in overall survival (OS) and disease-free survival (DFS) between the RT and non-RT groups. Lymphovascular invasion (LVI) was the only prognostic factor. In the LVI+ group, adjuvant radiotherapy significantly improved survival (5-year OS: 91.7% vs 59.5%, P = 0.050; 5-year DFS: 92.9% vs 42.6%, P = 0.010). In the LVI- group, adjuvant radiotherapy did not improve survival (5-year OS: 83.5% vs 93.9%, P = 0.148; 5-year DFS: 84.2% vs 84.7%, P = 0.907). The standardized mortality ratios were 1.52 (95% confidence interval 0.04-8.45) in the LVI+ group with radiotherapy and 0.55 (95% confidence interval 0.15-1.42) in the LVI- group without radiotherapy. DISCUSSION: Adjuvant radiotherapy could improve survival in pT1b ESCC with LVI+ other than LVI- after ESD. Selective adjuvant radiotherapy based on LVI status achieved survival rates similar to those of the general population.

[Automatic anatomical site recognition of laryngoscopic images using convolutional neural network].

Objective:To explore the automatic recognition and classification of 20 anatomical sites in laryngoscopy by an artificial intelligence（AI） quality control system using convolutional neural network（CNN）. Methods: Laryngoscopic image data archived from laryngoscopy examinations at the Department of Endoscopy, Cancer Hospital, Chinese Academy of Medical Sciences from January to December 2018 were collected retrospectively, and a CNN model was constructed using Inception-ResNet-V2+SENet. Using 14000 electronic laryngoscope images as the training set, these images were classified into 20 specific anatomical sites including the whole head and neck, and their performance was tested by 2000 laryngoscope images and 10 laryngoscope videos. Results:The average time of the trained CNN model for recognition of each laryngoscopic image was（20.59 ± 1.55） ms, and the overall accuracy of recognition of 20 anatomical sites in laryngoscopic images was 97.75%（1955/2000）, with average sensitivity, specificity, positive predictive value, and negative predictive value of 100%, 99.88%, 97.76%, and 99.88%, respectively. The model had an accuracy of ≥ 99% for the identification of 20 anatomical sites in laryngoscopic videos. Conclusion:This study confirms that the CNN-based AI system can perform accurate and fast classification and identification of anatomical sites in laryngoscopic pictures and videos, which can be used for quality control of photo documentation in laryngoscopy and shows potential application in monitoring the performance of laryngoscopy.

The Feasibility and Safety of Endoscopic Submucosal Dissection for Circumferential Superficial Esophageal Squamous Cell Neoplasms.

Background It remains controversial whether endoscopic submucosal dissection (ESD) is still appropriate for circumferential superficial esophageal squamous cell neoplasms (SESCN), and few studies compared the short-term and long-term outcomes of ESD with radical surgery. Methods A total of 140 patients with SESCN who underwent ESD or surgery between February 2014 and October 2021 were retrospectively reviewed. The characteristics of patients, operative time, postoperative complications, overall survival (OS), recurrence-free survival (RFS), and quality of life (QOL) were compared between the ESD and surgery groups. The effect of different methods to prevent esophageal stenosis after ESD were analysed. Results Drinking, family history of cancer, macroscopic type, and intrapapillary capillary loop (IPCL) type were independent risk factors for deep submucosal invasion (SM ≥ 200 µm). Smoking and IPCL type were independent predictive factors for angiolymphatic invasion. The average operative time of ESD was significantly shorter than that of surgery (174.5 ± 51.16 min vs. 255.9 ± 88.18 min, p < 0.001). The incidence of perioperative complications in ESD group was significantly lower than that in surgery group (5.5% vs. 19.4%, p = 0.015). The ESD group had significantly better functional scale scores for emotional functioning, cognitive functioning, and global health status, and lower rates of pain, dyspnoea, insomnia, appetite loss, diarrhoea, reflux, and trouble with taste than the surgery group. No significant difference in OS and RFS between ESD and surgery group. Conclusions ESD can significantly shorten the operative time and reduce perioperative complications. Additionally, on the premise of using appropriate measures to prevent postoperative stenosis, ESD can be the first choice for the treatment of SESCN, which could provide better QOL, and the long-term prognosis of ESD is no less than that of surgery.