Correlation between tumor budding and the long-term follow-up outcomes after endoscopic submucosal dissection for superficial esophageal squamous cell carcinoma.

BACKGROUND: The effect of tumor budding (TB) on the prognosis of patients with esophageal squamous cell carcinoma (ESCC) after endoscopic submucosal dissection (ESD) remains unclear. We evaluated the long-term outcomes of patients with superficial ESCC after ESD and the risk factors of TB for the long-term prognosis. METHODS: We conducted a retrospective study in a Chinese hospital. All patients with ESCC treated by ESD and reported TB were included consecutively. Comparative analyses were conducted in three parts: specimen analysis, follow-up analyses of unmatched patients, and propensity score-matched (PSM) patients. Cox proportional hazard regression models were constructed to identify risk factors for overall survival and recurrence-free survival (RFS). RESULTS: A total of 437 patients were enrolled [154 TB and 283 no tumor budding (NTB)], and 258 patients (52 TB and 206 NTB) were included in the follow-up analysis. Results showed that the invasion depth, differentiation type, and positive vascular invasion (all p < 0.001) of the TB group were significantly different from the NTB group. The all-cause mortality and the median RFS time between the two groups were comparable. RFS rate at 5 years were 84.6% and 80.6%, respectively (p = 0.43). Cox analyses identified that having other cancers but not TB, as a risk factor independently associated with overall survival and RFS after ESD. CONCLUSION: TB tends to be associated with invasion depth, differentiation type, and positive vascular invasion. However, it might not affect the long-term outcomes of patients with superficial ESCC after ESD when other high-risk factors are negative.

Artificial intelligence for detecting and delineating the extent of superficial esophageal squamous cell carcinoma and precancerous lesions under narrow-band imaging (with video).

BACKGROUND AND AIMS: Although narrow-band imaging (NBI) is a useful modality for detecting and delineating esophageal squamous cell carcinoma (ESCC), there is a risk of incorrectly determining the margins of some lesions even with NBI. This study aimed to develop an artificial intelligence (AI) system for detecting superficial ESCC and precancerous lesions and delineating the extent of lesions under NBI. METHODS: Nonmagnified NBI images from 4 hospitals were collected and annotated. Internal and external image test datasets were used to evaluate the detection and delineation performance of the system. The delineation performance of the system was compared with that of endoscopists. Furthermore, the system was directly integrated into the endoscopy equipment, and its real-time diagnostic capability was prospectively estimated. RESULTS: The system was trained and tested using 10,047 still images and 140 videos from 1112 patients and 1183 lesions. In the image testing, the accuracy of the system in detecting lesions in internal and external tests was 92.4% and 89.9%, respectively. The accuracy of the system in delineating extents in internal and external tests was 88.9% and 87.0%, respectively. The delineation performance of the system was superior to that of junior endoscopists and similar to that of senior endoscopists. In the prospective clinical evaluation, the system exhibited satisfactory performance, with an accuracy of 91.4% in detecting lesions and an accuracy of 85.9% in delineating extents. CONCLUSIONS: The proposed AI system could accurately detect superficial ESCC and precancerous lesions and delineate the extent of lesions under NBI.

Artificial intelligence-based assessments of colonoscopic withdrawal technique: a new method for measuring and enhancing the quality of fold examination.

BACKGROUND: This study aimed to develop an artificial intelligence (AI)-based system for measuring fold examination quality (FEQ) of colonoscopic withdrawal technique. We also examined the relationship between the system's evaluation of FEQ and FEQ scores from experts, and adenoma detection rate (ADR) and withdrawal time of colonoscopists, and evaluated the system's ability to improve FEQ during colonoscopy. METHODS: First, we developed an AI-based system for measuring FEQ. Next, 103 consecutive colonoscopies performed by 11 colonoscopists were collected for evaluation. Three experts graded FEQ of each colonoscopy, after which the recorded colonoscopies were evaluated by the system. We further assessed the system by correlating its evaluation of FEQ against expert scoring, historical ADR, and withdrawal time of each colonoscopist. We also conducted a prospective observational study to evaluate the system's performance in enhancing fold examination. RESULTS: The system's evaluations of FEQ of each endoscopist were significantly correlated with experts' scores (r = 0.871, P < 0.001), historical ADR (r = 0.852, P = 0.001), and withdrawal time (r = 0.727, P = 0.01). For colonoscopies performed by colonoscopists with previously low ADRs (< 25 %), AI assistance significantly improved the FEQ, evaluated by both the AI system (0.29 [interquartile range (IQR) 0.27-0.30] vs. 0.23 [0.17-0.26]) and experts (14.00 [14.00-15.00] vs. 11.67 [10.00-13.33]) (both P < 0.001). CONCLUSION: The system's evaluation of FEQ was strongly correlated with FEQ scores from experts, historical ADR, and withdrawal time of each colonoscopist. The system has the potential to enhance FEQ.

Artificial intelligence for detecting superficial esophageal squamous cell carcinoma under multiple endoscopic imaging modalities: A multicenter study.

BACKGROUND AND AIM: Diagnosis of esophageal squamous cell carcinoma (ESCC) is complicated and requires substantial expertise and experience. This study aimed to develop an artificial intelligence (AI) system for detecting superficial ESCC under multiple endoscopic imaging modalities. METHODS: Endoscopic images were retrospectively collected from West China Hospital, Sichuan University as a training dataset and an independent internal validation dataset. Images from other four hospitals were used as an external validation dataset. The AI system was compared with 11 experienced endoscopists. Furthermore, videos were collected to assess the performance of the AI system. RESULTS: A total of 53 933 images from 2621 patients and 142 videos from 19 patients were used to develop and validate the AI system. In the internal and external validation datasets, the performance of the AI system under all or different endoscopic imaging modalities was satisfactory, with sensitivity of 92.5-99.7%, specificity of 78.5-89.0%, and area under the receiver operating characteristic curves of 0.906-0.989. The AI system achieved comparable performance with experienced endoscopists. Regarding superficial ESCC confined to the epithelium, the AI system was more sensitive than experienced endoscopists on white-light imaging (90.8% vs 82.5%, P = 0.022). Moreover, the AI system exhibited good performance in videos, with sensitivity of 89.5-100% and specificity of 73.7-89.5%. CONCLUSIONS: We developed an AI system that showed comparable performance with experienced endoscopists in detecting superficial ESCC under multiple endoscopic imaging modalities and might provide valuable support for inexperienced endoscopists, despite requiring further evaluation.

Comparison of effectiveness and safety between endoscopic and surgical resection for 2-5 cm gastric stromal tumors.

BACKGROUND: As endoscopic resection remains controversial, this study aims to compare the effectiveness and safety between endoscopic and surgical resection for 2-5 cm gastric stromal tumors (GSTs). METHODS: Patients with 2-5 cm GST resected at West China Hospital from March 2008 to April 2019 were enrolled. Propensity score matching (PSM) (1:1) was performed to achieve baseline data consistency. RESULTS: 112 patients were matched between the endoscopic resection group (ER) and the open surgery group. There were no significant differences in the complete resection rate (94.6% vs. 100%), the incidence of complications (25.0% vs. 14.3%), the recurrence rate (0% vs. 1.8%) and the 5-year relapse-free survival (100% vs. 97.9%) (P > 0.05). The ER had a shorter fasting time (3.5 days vs. 5 days), a shorter postoperative hospital stay (7 days vs. 8 days) and a lower hospitalization cost (3,589.16 USD vs. 5,931.24 USD) (P < 0.05). 54 cases were matched between the ER and the laparoscopic surgery group (LS). There were no significant differences in the complete resection rate (92.6% vs. 96.3%), the incidence of complications (22.2% vs. 11.1%), the fasting time (4 days vs. 3 days), the recurrence rate (0% vs. 3.7%) and the 5-year relapse-free survival (100% vs. 96.3%) (P > 0.05). The hospitalization cost (3,589.25 USD vs. 4,715.16 USD) was lower in the ER, and the postoperative hospital stay was shorter in the LS (6 days vs. 7 days) (P < 0.05). CONCLUSIONS: Although slightly higher incidences of incomplete resection and perforation were shown in the endoscopic resection group, there was insignificant difference between groups (P > 0.05). Endoscopic resection might be an alternative surgical method for 2-5 cm GSTs.

Artificial intelligence for diagnosing gastric lesions under white-light endoscopy.

BACKGROUND: The ability of endoscopists to identify gastric lesions is uneven. Even experienced endoscopists may miss or misdiagnose lesions due to heavy workload or fatigue or subtle changes in lesions under white-light endoscopy (WLE). This study aimed to develop an artificial intelligence (AI) system that could diagnose six common gastric lesions under WLE and to explore its role in assisting endoscopists in diagnosis. METHODS: Images of early gastric cancer, advanced gastric cancer, submucosal tumor, polyp, peptic ulcer, erosion, and lesion-free gastric mucosa were retrospectively collected to train and test the system. The performance of the system was compared with that of 12 endoscopists. The performance of endoscopists with or without referring to the system was also evaluated. RESULTS: A total of 29,809 images from 8947 patients and 1579 images from 496 patients were used to train and test the system, respectively. For per-lesion analysis, the overall accuracy of the system was 85.7%, which was comparable to that of senior endoscopists (85.1%, P = 0.729) and significantly higher than that of junior endoscopists (78.8%, P < 0.001). With system assistance, the overall accuracies of senior and junior endoscopists increased to 89.3% (4.2%, P < 0.001) and 86.2% (7.4%, P < 0.001), respectively. Senior and junior endoscopists achieved varying degrees of improvement in the diagnostic performance of other types of lesions except for polyp. The diagnostic times of senior (3.8 vs 3.2 s per image, P = 0.500) and junior endoscopists (6.2 vs 4.6 s per image, P = 0.144) assisted by the system were both slightly shortened, despite no significant differences. CONCLUSIONS: The proposed AI system could be applied as an auxiliary tool to reduce the workload of endoscopists and improve the diagnostic accuracy of gastric lesions.

Artificial intelligence for diagnosing microvessels of precancerous lesions and superficial esophageal squamous cell carcinomas: a multicenter study.

BACKGROUND: Intrapapillary capillary loop (IPCL) is an important factor for predicting invasion depth of esophageal squamous cell carcinoma (ESCC). The invasion depth is closely related to the selection of treatment strategy. However, diagnosis of IPCLs is complicated and subject to interobserver variability. This study aimed to develop an artificial intelligence (AI) system to predict IPCLs subtypes of precancerous lesions and superficial ESCC. METHODS: Images of magnifying endoscopy with narrow band imaging from three hospitals were collected retrospectively. IPCLs subtypes were annotated on images by expert endoscopists according to Japanese Endoscopic Society classification. The performance of the AI system was evaluated using internal and external validation datasets (IVD and EVD) and compared with that of the 11 endoscopists. RESULTS: A total of 7094 images from 685 patients were used to train and validate the AI system. The combined accuracy of the AI system for diagnosing IPCLs subtypes in IVD and EVD was 91.3% and 89.8%, respectively. The AI system achieved better performance than endoscopists in predicting IPCLs subtypes and invasion depth. The ability of junior endoscopists to diagnose IPCLs subtypes (combined accuracy: 84.7% vs 78.2%, P < 0.0001) and invasion depth (combined accuracy: 74.4% vs 67.9%, P < 0.0001) were significantly improved with AI system assistance. Although there was no significant differences, the performance of senior endoscopists was slightly elevated. CONCLUSIONS: The proposed AI system could improve the diagnostic ability of endoscopists to predict IPCLs classification of precancerous lesions and superficial ESCC.

Value of the diving method for capsule endoscopy in the examination of small-intestinal disease: a prospective randomized controlled trial.

BACKGROUND AND AIMS: Video capsule endoscopy (VCE) is limited by poor image quality and incomplete small-bowel transit. This study was designed to evaluate the diving method for VCE in the examination of small-intestinal disease. METHODS: From July 2017 to September 2017, eligible patients were randomly assigned to 2 groups, the diving group and the control group. For the diving group, 500 mL of water was administered every hour when the capsule reached the small bowel. The primary outcomes were image quality and positive findings. Secondary outcomes were the completion rate of examination, gastric transit time (GTT), small-bowel transit time (SBTT), lesion detection rate, adverse events, and patient satisfaction. RESULTS: One hundred forty patients were included. The scores of endoscopic images in the proximal third and middle third of the small bowel in the diving group were significantly higher than that in the control group (3.47 ± .60 vs 3.11 ± .63 [P = .007] and 3.24 ± .59 vs 2.78 ± .74 [P = .002], respectively). The positive findings in the distal third of the small bowel were significantly different between the 2 groups (P = .005). The completion rate in the diving group was significantly higher (92.19% vs 76.32%, respectively; P = .012). The GTT, SBTT, and lesion detection rate were similar in 2 groups (P = .282, .067, and .577, respectively). No discomfort or adverse events were reported except for a few cases of frequent urination. CONCLUSIONS: The diving method for VCE examination effectively improves the endoscopic view in the proximal and middle thirds of the small bowel and the positive findings in the distal small intestine and increases the completion rate. (Clinical trial registration number: ChiCTR-RDR-17011823.).

Aorto-esophageal fistula caused by fishbone ingestion: a case report on staged endovascular and endoscopic treatment.

BACKGROUND: Aorto-esophageal fistula (AEF) caused by foreign bodies ingestion is a rare but devastating disorder. Thoracic endovascular aortic repair (TEVAR) has become a widely accepted intervention for treating aorto-esophageal fistulas. As for post-TEVAR esophageal defect, secondary esophagectomy has been the recommended choice for most of the AEFs, but there is no general consensus with regard to the need of secondary surgeries for patients in the absence of clear signs of reinfection or bleeding. We herein presented a case of an AEF caused by fishbone ingestion, after successful TEVAR, the esophageal lesion was closed endoscopically. CASE PRESENTATION: A 38-year-old male presented with esophageal fistula for 4 months. He was diagnosed with AEF because of Chiari's triad after fishbone ingestion 4 months ago. Emergency thoracic aortic stent implantation was done, and given broad spectrum antibiotics and blood transfusion. His symptoms were improved, and discharged with an esophageal fistula left to heal itself. Nevertheless, after 4 months, re-examination of esophago-gastro-duodenoscopy revealed that the diameter of the fistula was changed from 3 to 6 mm. He was then admitted to our hospital for esophageal fistula repair. Laboratory examinations and chest computed tomography showed no signs of active infection, and endoscopic closure of the fistula was achieved with 4 clips. After that, he was discharged and gradually returned to normal diet. CONCLUSION: For AEFs in the absence of active infection with repaired aorta but persistent esophageal fistula, endoscopic closure by endoclips might be an effective treatment choice.

Peroral endoscopic myotomy for the treatment of esophageal diverticulum: an experience in China.

BACKGROUND: With the development of minimally invasive endoscopic approaches for the esophagus in recent years, peroral endoscopic myotomy (POEM) in the treatment of esophageal diverticulum has been described recently in some reports due to its successful outcomes. The aim of this study is to report our experience with the use of diverticular POEM (D-POEM) technique in the management of esophageal diverticulum. METHODS: This retrospective study included consecutive patients with symptomatic esophageal diverticulum who visited our endoscopy center between April 2014 and January 2019. D-POEM was performed based on the principles of submucosal endoscopy. A new symptomatic scoring system was introduced to evaluate the severity of diverticular symptoms. RESULTS: A total of 10 patients with esophageal diverticulum (Zenker's 2, mid-esophagus 5, and epiphrenic 3) were included. The overall technical success rate of D-POEM was 100%, with a mean procedure time of 38.9 ± 20.5 (range 16-70) min. No serious complications occurred. Clinical improvement was achieved in 90% (9/10) of patients. The symptomatic score was significantly decreased from 2.5 (IQR 2.00-3.25) to 1.0 (IQR 0-1.25) (P = 0.007) during a median follow-up period of 11.0 (IQR 10.25-17.25) months. CONCLUSION: These findings suggested complete septotomy by D-POEM. Our preliminary data and experience put forwarded D-POEM as a safe and effective technique for esophageal diverticulum.

Per-oral endoscopic dual myotomy for the treatment of achalasia.

BACKGROUND: Repeat per-oral endoscopic myotomy is occasionally performed for persistent/recurrent symptoms in patients with achalasia, and yields favorable outcomes. We investigated a novel technique, per-oral endoscopic dual myotomy (dual-POEM), where a second myotomy was performed during a single session to augment the efficacy and avoid repeat interventions. The aim of this study was to evaluate its feasibility, safety and efficacy. METHODS: Consecutive patients diagnosed with achalasia who underwent dual-POEM (1/2018-5/2019) were prospectively collected and retrospectively analyzed. Patients with baseline Eckardt score ≥ 9, ≥ 10 years of symptoms, and/or having prior interventions other than myotomy received dual-POEM. The primary outcome was clinical success (Eckardt score ≤ 3). Secondary outcomes were procedure-related adverse events, change in lower esophageal sphincter (LES) pressure, and reflux complications. RESULTS: Seventeen patients received dual-POEM. Procedure-related adverse events were observed in 2 (11.8%) patients (mucosal injury and pneumonitis). Both were minor in severity. During a median follow-up of 33 months (interquartile range, IQR [31,35]; range, 19-36), clinical success was achieved in 16 (94.1%) patients. The median Eckardt score decreased from 9 (IQR [8, 11.5]; range 7-12) to 1 (IQR [1, 2]; range 0-4) (P < 0.001), and LES pressure decreased from 25.8 mmHg (IQR [21.7, 33.5]; range 17.7-46.3) to 7.4 mmHg (IQR [6.3, 10.4]; range 2.2-12.6) (P < 0.001). Seven (41.2%) patients developed postprocedural reflux either by gastroesophageal reflux disease questionnaire or esophagitis endoscopically, all successfully treated with proton pump inhibitors. CONCLUSION: Dual-POEM preliminarily demonstrated high efficacy with a favorable safety profile in patients with achalasia with predictors of treatment failure.

Endoscopic submucosal dissection with additional radiotherapy in the treatment of T1a esophageal squamous cell cancer: randomized controlled Trial.

BACKGROUND: Endoscopic submucosal dissection (ESD) is effective for treating T1a early esophageal squamous cell carcinoma (ESCC). However, occasional recurrences are inevitable. This trial was designed to clarify the efficacy of combining ESD with additional radiotherapy in the treatment of T1a ESCC. METHODS: Between January 2015 and September 2018, patients with early ESCC (T1aN0M0) following ESD were randomly assigned (1:1) to the radiotherapy group or non-radiotherapy group. Patients in the radiotherapy group received a median radiation dose of 59.4 Gy within 2 months after ESD. In the non-radiotherapy group, patients underwent regular follow-up only. Recurrence-free survival, cancer-specific survival, overall survival, and complications were evaluated. RESULTS: 70 patients completed the per-protocol treatment. Three patients in the non-radiotherapy group experienced intraluminal mucosal recurrence compared with none in the radiotherapy group. No local lymph node or distant metastases occurred in either group. The 3-year cumulative recurrence-free survival was 100 % in the radiotherapy group and 85.3 % in the non-radiotherapy group (P = 0.04; hazard ratio 0.08, 95 % confidence interval [CI] 0.01 - 0.86). However, there was no significant difference in RFS between the treatments within the T1a invasion subgroups (P > 0.05). No patient died in either group. Mucosal defects of more than three-quarters of the esophageal circumference were positively correlated with stenosis (P < 0.01; odds ratio 23.26, 95 %CI 4.04 - 133.86). No severe radiation toxicities were recorded. CONCLUSIONS: Radiotherapy after ESD might be a safe and effective optional therapeutic strategy to prevent recurrence of T1a ESCC.

Risk factors for distal migration of biliary plastic stents and related duodenal injury.

BACKGROUND: The risk factors of duodenal injury from distal migrated biliary plastic stents remain uncertain. The aim of this study was to determine the risk factors of distal migration and its related duodenal injury in patients who underwent placement of a single biliary plastic stent for biliary strictures. METHODS: We retrospectively reviewed all patients with biliary strictures who underwent endoscopic placement of a single biliary plastic stent from January 2006 to October 2017. RESULTS: Two hundred forty-eight patients with 402 endoscopic retrograde cholangiopancreatography procedures were included. The incidence of distal migration was 6.2%. The frequency of duodenal injury was 2.2% in all cases and 36% in cases with distal migration. Benign biliary strictures (BBS), length of the stent above the proximal end of the stricture (> 2 cm), and duration of stent retention (< 3 months) were independently associated with distal migration (p = 0.018, p = 0.009, and p = 0.016, respectively). Duodenal injury occurred more commonly in cases with larger angle (≥ 30°) between the distal end of the stent and the centerline of the patient's body (p = 0.018) or in cases with stent retention < 3 months (p = 0.031). CONCLUSIONS: The risk factors of distal migration are BBS and the length of the stent above the proximal end of the stricture. The risk factor of duodenal injury due to distal migration is large angle (≥ 30°) between the distal end of the stent and the centerline of the patient's body. Distal migration and related duodenal injury are more likely to present during the early period after biliary stenting.

An international study on the use of peroral endoscopic myotomy (POEM) in the management of esophageal diverticula: the first multicenter D-POEM experience.

BACKGROUND: The aim of this study is to report a novel, multicenter experience with the diverticular peroral endoscopic myotomy (D-POEM) technique in the management of esophageal diverticula. METHODS: This is a multicenter, international, retrospective study involving three centers. D-POEM was performed using the principles of submucosal endoscopy. RESULTS: A total of 11 patients with an esophageal diverticulum (Zenker's 7, mid-esophagus 1, epiphrenic 3) were included. The mean size of the esophageal diverticula was 34.5 mm. The overall technical success rate of D-POEM was 90.9 %, with a mean procedure time of 63.2 minutes. There were no adverse events. Clinical success was achieved in 100 % (10 /10), with a decrease in mean dysphagia score from 2.7 to 0.1 (P < 0.001) during a median follow-up of 145 days (interquartile range 126 - 273). CONCLUSION: Endoscopic management of esophageal diverticula using the novel technique of D-POEM appears promising. This first case series on D-POEM suggests that the procedure is feasible, safe, and effective in the management of esophageal diverticula. D-POEM offers the distinct advantage of ensuring a complete septotomy. Larger studies are needed to confirm these intriguing results.

Magnetic bead-assisted endoscopic submucosal dissection: a gravity-based traction method for treating large superficial colorectal tumors.

BACKGROUND: Colorectal endoscopic submucosal dissection (ESD) has always been challenging for endoscopists, but the procedure can be facilitated after adequate exposure of submucosal layer and cutting line. We developed a traction method based on gravity for facilitating colorectal ESD, referred as magnetic bead-assisted ESD (MBA-ESD). This study aimed to compare the safety and effectiveness of MBA-ESD and conventional ESD for treating large superficial colorectal tumors. METHODS: This retrospective study included consecutive patients with large (≥ 20 mm in their maximal diameter) superficial colorectal tumors who underwent MBA-ESD or conventional ESD at our endoscopy center between June 2017 to January 2018. Each patient in the MBA-ESD group was matched to a patient in the conventional ESD group using propensity scores. RESULTS: Thirteen patients in each group were matched for the analyses. The baseline characteristics were balanced after propensity matching. The incidence of overall complications was significantly lower in the matched MBA-ESD group (0% vs. 38.5%, P = 0.039), while similar rates of en bloc resection, R0 resection, curative resection, and tumor recurrence were noted. Although without statistic difference, dissection time and speed were improved when using MBA-ESD (33 min vs. 40 min, P = 0.111; and 21 mm2/min vs. 16 mm2/min, P = 0.143, respectively). CONCLUSIONS: MBA-ESD is a feasible, safe, and effective method for treating large superficial colorectal tumors. Further large, prospective and controlled studies are needed to fully assess this method.