Expert Endoscopists Research Articles

Multicentre study to assess the performance of an artificial intelligence instrument to support qualitative diagnosis of colorectal polyps

ObjectiveComputer-aided diagnosis (CAD) using artificial intelligence (AI) is expected to support the characterisation of colorectal lesions, which is clinically relevant for efficient colorectal cancer prevention. We conducted this study to...

Outcomes of lumen apposing metal stent placement in patients with surgically altered anatomy: Multicenter international experience.

Background and study aims Although outcomes of lumen-apposing metal stents (LAMS) placement in native anatomy have been reported, data on LAMS placement in surgically altered anatomy (SAA) are sparse. We aimed to assess outcomes of LAMS placement in patients with SAA for different indications. Patients and methods This was an international, multicenter, retrospective, observational study at 25 tertiary care centers through November 2023. Consecutive patients with SAA who underwent LAMS placement were included. The primary outcome was technical success defined as correct placement of LAMS. Secondary outcomes were clinical success and safety. Results Two hundred and seventy patients (125 males; average age 61 ± 15 years) underwent LAMS placement with SAA. Procedures included EUS-directed transgastric ERCP (EDGE) and EUS-directed transenteric ERCP (EDEE) (n = 82), EUS-guided entero-enterostomy (n = 81), EUS-guided biliary drainage (n = 57), EUS-guided drainage of peri-pancreatic fluid collections (n = 48), and EUS-guided pancreaticogastrostomy (n = 2). Most cases utilized AXIOS stents (n = 255) compared with SPAXUS stents (n = 15). Overall, technical success was 98%, clinical success was 97%, and the adverse event (AE) rate was 12%. Using AGREE classification, five events were rated as Grade II, 21 events as Grade IIIa, and six events as IIIb. No difference in AEs were noted among stent types ( P = 0.52). Conclusions This study shows that placement of LAMS is associated with high technical and clinical success rates in patients with SAA. However, the rate of AEs is noteworthy, and thus, these procedures should be performed by expert endoscopists at tertiary centers.

When the vermiform appendix resembles a polyp: Be cautious of an intussuscepted appendix polypectomy.

This article discusses a recently published case report on a rare instance of type IV appendiceal intussusception with a concurrent mucinous adenocarcinoma of the cecum in a young individual. The report highlights challenges in diagnosing appendiceal intussusception, emphasizing the importance of endoscopic expertise in preventing impulsive decisions such as inappropriate polypectomies. The rarity of the concurrent intussuscepted appendix and mucinous cecal cancer is underscored, prompting consideration of malignancy in appendiceal intussusception cases. Additionally, the report addresses the increasing incidence of early-onset colorectal cancer and the need for a revaluation of diagnostic paradigms in the context of evolving epidemiological trends. The awareness of potential misinterpretations and the imperative for further investigation into this rare condition are emphasized.

The Gastroscopy RAte of Cleanliness Evaluation (GRACE) Scale: an international reliability and validation study.

mucosal visualization during upper gastrointestinal (UGI) endoscopy can be impaired by the presence of foam, bubbles, and mucus. Some UGI endoscopy visibility scales were proposed but without a multicenter validation. This study aimed to develop and validate the Gastroscopy RAte of Cleanliness Evaluation (GRACE) scale. a multicenter international cross-sectional study was conducted. The GRACE scale is based on a score from 0-worst to 3-excellent of esophagus, stomach, and duodenum, for a total ranging from 0 to 9. In the first phase, four expert endoscopists evaluated 60 selected images twice with a two-week interval; in the second phase, the same 60 images were scored twice by one expert and one non-expert endoscopist from 27 different Endoscopy Departments worldwide. For reproducibility assessment and clinical validation, a real-time scale application was performed on consecutive patients undergoing gastroscopy in each center. in the internal validation, the interobserver agreement was 0.81 (95%CI[0.73-0.87]) and 0.80 (95%CI[0.72-0.86]), with a reliability of 0.73 (95%CI[0.63-0.82]) and 0.72 (95%CI[0.63-0.81]), in the two rounds, respectively. In the external validation, the overall interobserver agreement was 0.85 (95%CI[0.82-0.88]) with a reliability of 0.79 (95%CI[0.73-0.84]). In the real-time evaluation phase, the overall percentage of correct classifications was 0.80 (95%CI[0.77-0.82]). the GRACE scale showed good interobserver agreement and reliability and good validity. The spread of this scale could enhance the quality and standardize the cleanliness of the mucosa assessment during UGI endoscopy, pushing endoscopists to obtain excellent visibility and reducing the risk of missing lesions.

Micro-bacterial assessment of disposable gowns with a focus on green endoscopy in gastrointestinal endoscopy procedures: A Japanese pilot study for healthcare waste reduction.

This study aimed to implement green endoscopy through the microbiological assessment of gowning techniques during endoscopy to reduce carbon emissions and separate medical waste. Twenty-five patients who performed esophagogastroduodenoscopy from March to May 2024 were included in this study. Four sections of the isolation gowns (anterior, posterior, right, and left) were cut into 2 cm2 after endoscopy, and the rate of microbial contamination was examined using the stamp method. The endoscopic examination time was 8 min (6-12), and endoscopy was performed by 10 expert endoscopists, six endoscopists, and nine residents. The overall isolation gown contamination rate was 56%, with 25%, 20.8%, 20.8%, and 33.3% in the front, back, as well as right and left arms, respectively. The rates of isolation gown contamination rates in the expert endoscopists, endoscopists, and residents groups were 30%, 50%, and 77.8%, respectively, with a higher rate in the residents group. Regardless of the physician's performance, bacterial detection was consistently higher in the left arm (42.9% vs. 40% vs. 25%; p = 0.093). The detected bacteria comprised 58% Gram-positive and 42% Gram-negative organisms, including those from tap water used for endoscopy bacteria and obtained from the participant's skin or mouth. No pathogenic organisms were detected. The bacteria detected in disposable gowns after gastrointestinal endoscopy were non-pathogenic. Thus, our findings suggest that changing all personal protective equipment of respective endoscopes might not be essential. We advocate for green endoscopy to achieve sustainable development goals and reduce medical waste.

Chicken swarm algorithm with deep convolutional neural network based tongue image analysis for gastric cancer classification

Tongue images (the size, shape, and colour of tongue and the thickness, colour, and moisture content of tongue coating), reflecting the medical condition of entire body based on the model of traditional Chinese medicine (TCM) are extremely utilized in China for millions of years. Gastric cancer (GC) is great lethal kind of cancer in countries and societies. The screening and analysis of GC yet depend on gastroscopy, however its application was significantly restricted due to its invasive, maximum rate and the requirement for expert endoscopists. Early recognition in GC patients and direct treatment contribute significantly to safety for health. Consequently, this study introduces a Chicken Swarm Algorithm with Deep learningbased Tongue Image Analysis for Gastric Cancer Classification (CSADL-TIAGCC) system. The projected CSADL-TIAGCC approach studies the input tongue images for the identification and classification of GC. To accomplish this, the CSADL-TIAGCC system uses improved U-Net segmentation approach. Besides, residual network (ResNet-34) model-based feature extractor is used. Furthermore, long short term memory (LSTM) approach was exploited for GC classification and its hyperparameters are selected by the CSA. The simulation outcome of the CSADL-TIAGCC algorithm was examined under tongue image database. The experimental outcomes illustrate the enhanced results of the CSADL-TIAGCC technique with respect of different evaluation measures.

789. EFFICACY AND SAFETY OF CRYOBALLOON-180 ABLATION FOR THE TREATMENT OF DYSPLASTIC BARRETT ESOPHAGUS: PRELIMINARY RESULTS FROM A PROSPECTIVE MULTICENTER STUDY

Abstract Background Cryoballoon-ablation is a relatively novel method for the eradication of dysplastic Barrett esophagus (BE). While the focal cryoballoon-ablation system has shown to be efficacious for BE of limited extent, the cryoballoon180-ablation system (CBAS180) is developed to treat longer BE segments by semi-circumferential ablation over 3cm, in a single step. A first-in-human study demonstrated the feasibility of CBAS180 treatment, yet the optimal dose needs to be determined. The current prospective, multicenter study, investigates CBAS180 at lower dosages for patients with dysplastic BE. Methods A total of 62 patients with ablation naïve BE (C≤3 and M≥1) will be enrolled in six Dutch Barrett expert centers. Treatment consists of a full circumferential ablation over 3 cm of length, using two semi-circumferential ablations at a dose of 1.2 mm/sec. Follow-up consisted of phone calls at days 1, 7 and 30, a symptom diary during 14 days, and an endoscopy after 3 months. Outcomes included (1) technical success rate; (2) BE regression percentage at follow-up scored by an independent adjudication committee; (3) incidence of adverse events; (4) post-procedural pain (scored on a scale of 0-10); and (5) post-procedural dysphagia (scored on a validated scale of 0-4). Follow-up treatment consisted of focal cryoballoon-ablation until complete eradication of visible BE was achieved, confirmed by biopsies from the neo-Z-line. Results So far, 25 patients (80% male; mean age 67) with a median BE length of C0M2 (p25-p75 C0-1M2-4) were included. Technical success rate was 92% (23/25; 95% CI 74-99%). In two patients, treatment was technically unsuccessful due to unstable positioning of the balloon (n=1) or a device malfunction (n=1). Median procedure time was 14 (p25-p75 11-16) 4) minutes and median ablation time was 5 (p25-p75 3-5) minutes. All 23 successfully treated patients completed follow-up endoscopy at 3 months. Median BE regression was 90% (p25-p75 75%-100%) evaluated by the independent adjudication committee. Overall, CBAS180 adverse event rate was 8% (2/23); one patient developed esophageal stricture (1/23; 4% [95% CI 1-16%]) resolved after a single endoscopic dilation. Another patient (1/23; 4% [95% CI 1-16%]) experienced post-procedural bleeding, with re-endoscopy without intervention. The CBAS180 procedure was well tolerated with low post-procedural pain (median 2 [p25-p75 1-4] at day 1 and 0 [p25-p75 0-1] at day 7) and dysphagia (56% and 70% of patients with score 0 at days 1 and 7, respectively) scores. So far, 22/23 (95%) patients were additionally treated with focal cryoballoon-ablation and 18/22 (82%) achieved a complete endoscopis and histologic eradication of BE after median 1 (p25-p75 1-3) treatment, the other 4 are still under treatment. After focal cryoballoon-ablation, 2/22 patients developed strictures, resolved after 1 and 2 endoscopic dilatations. Conclusion Based on these preliminary results, circumferential ablation with CBAS180 at 1.2 mm/sec, followed by focal cryoballoon-ablation, emerges as an effective and safe procedure for dysplastic BE eradication in the hands of expert endoscopists. Further avenues for exploration should encompass the assessment of multiple CBAS180 ablations stacked on top of each other in larger segments and the validation of outcomes in a larger patient cohort.

Validation and efficacy of the Varix Trainer model as a Training device for esophagogastroduodenoscopy.

Background and study aims The Varix Trainer model 1 (VTM1) was created for trainees to safely practice basic endoscope manipulation skills. The VTM1 was tested to see if it could distinguish levels of endoscope manipulation skills (construct validity) and whether training with it could improve these skills faster (content validity). Patients and methods We enrolled 23 novice endoscopists, 18 second-year trainees, and 13 expert endoscopists. They were asked to point with the endoscope tip to 20 numbers in the model as quickly as possible using torque, single-hand small/large wheel manipulation (SHSW), and retroflexion techniques. Their mean times (t20) were compared to determine if the model could distinguish different levels of expertise. Subsequently, 14 novices trained for eight short sessions, and the pre-training and post-training t20 were compared. Nine novice endoscopists received no training and were retested after 4 to 6 weeks (controls). Results Experts had faster t20 than second-year trainees, who were faster than novices, for all three techniques ( P < 0.001). After eight sessions, the mean t20 for novices improved from 112 to 66 seconds for torque, 144 to 72 seconds for SHSW, and 108 to 63 seconds for retroflexion, (all P < 0.001). Their t20 were equivalent to second-year trainees. Improvement in t20 was also seen with the control group, but total reduction was less than for the training group. Conclusions The VTM1 distinguished varying levels of expertise for all techniques, suggesting that it is a valid tool for assessing endoscope manipulation skill. A short curriculum improved novices' manipulation skills faster than traditional practice.

Quantitative Evaluation of Noncontrast Magnetic Resonance Enterography for Active Inflammation in Crohn Disease Using Native T1 and T2 Mapping.

The aim of this study was to investigate the utility of native T1 and T2 mapping in the bowel to evaluate disease activity in Crohn disease (CD) using endoscopy as the reference standard. This was a prospective study. Magnetic resonance imaging was performed by using a 1.5-T Philips scanner. We used a modified look-locker inversion recovery and a multiecho gradient-spin-echo sequences for single breath-hold native T1 and T2 maps, respectively, for the short-axis image of the intestine, and the measurement at the most severe site was compared with partial Simple Endoscopic Score for Crohn's Disease (pSES-CD, assessed by an expert endoscopist). A pSES-CD ≥ 4 indicated active disease. Statistical analyses were performed using the Student t test, Spearman correlation, and receiver operating characteristic curve analysis. A total of 27 patients (mean age ± standard deviation, 37 ± 18 years; 20 men, 7 women) were included in this study. The native T1 value of active disease was significantly higher than that of inactive disease (1170.8 ± 100.5 milliseconds vs 924.5 ± 95.3 milliseconds; P = 0.018), but the T2 value was not significantly different between active and inactive disease (76.1 ± 7.8 milliseconds vs 69.3 ± 10.9 milliseconds; P = 0.424). A good correlation was found between native T1 value and pSES-CD (ρ = 0.71; P < 0.001) but not between T2 value and pSES-CD (ρ = 0.06; P = 0.790). The area under the receiver operating characteristic curve for differentiating the disease activity was 0.96 (95% confidence interval [CI]: 0.90-1.00) for T1 values and 0.68 (95% confidence interval: 0.41-0.96) for T2 values. Native T1 mapping could be potentially used as a noninvasive method to differentiate disease activity in patients with CD and may be superior to T2 mapping for this purpose.

Linked Color Imaging with Artificial Intelligence Improves the Detection of Early Gastric Cancer.

Esophagogastroduodenoscopy is the most important tool to detect gastric cancer (GC). In this study, we developed a computer-aided detection (CADe) system to detect GC with white light imaging (WLI) and linked color imaging (LCI) modes and aimed to compare the performance of CADe with that of endoscopists. The system was developed based on the deep learning framework from 9,021 images in 385 patients between 2017 and 2020. A total of 116 LCI and WLI videos from 110 patients between 2017 and 2023 were used to evaluate per-case sensitivity and per-frame specificity. The per-case sensitivity and per-frame specificity of CADe with a confidence level of 0.5 in detecting GC were 78.6% and 93.4% for WLI and 94.0% and 93.3% for LCI, respectively (p &lt; 0.001). The per-case sensitivities of nonexpert endoscopists for WLI and LCI were 45.8% and 80.4%, whereas those of expert endoscopists were 66.7% and 90.6%, respectively. Regarding detectability between CADe and endoscopists, the per-case sensitivities for WLI and LCI were 78.6% and 94.0% in CADe, respectively, which were significantly higher than those for LCI in experts (90.6%, p = 0.004) and those for WLI and LCI in nonexperts (45.8% and 80.4%, respectively, p &lt; 0.001); however, no significant difference for WLI was observed between CADe and experts (p = 0.134). Our CADe system showed significantly better sensitivity in detecting GC when used in LCI compared with WLI mode. Moreover, the sensitivity of CADe using LCI is significantly higher than those of expert endoscopists using LCI to detect GC.

Endoscopic Artificial Intelligence for Image Analysis in Gastrointestinal Neoplasms.

Artificial intelligence (AI) using deep learning systems has recently been utilized in various medical fields. In the field of gastroenterology, AI is primarily implemented in image recognition and utilized in the realm of gastrointestinal (GI) endoscopy. In GI endoscopy, computer-aided detection/diagnosis (CAD) systems assist endoscopists in GI neoplasm detection or differentiation of cancerous or noncancerous lesions. Several AI systems for colorectal polyps have already been applied in colonoscopy clinical practices. In esophagogastroduodenoscopy, a few CAD systems for upper GI neoplasms have been launched in Asian countries. The usefulness of these CAD systems in GI endoscopy has been gradually elucidated. In this review, we outline recent articles on several studies of endoscopic AI systems for GI neoplasms, focusing on esophageal squamous cell carcinoma (ESCC), esophageal adenocarcinoma (EAC), gastric cancer (GC), and colorectal polyps. In ESCC and EAC, computer-aided detection (CADe) systems were mainly developed, and a recent meta-analysis study showed sensitivities of 91.2% and 93.1% and specificities of 80% and 86.9%, respectively. In GC, a recent meta-analysis study on CADe systems demonstrated that their sensitivity and specificity were as high as 90%. A randomized controlled trial (RCT) also showed that the use of the CADe system reduced the miss rate. Regarding computer-aided diagnosis (CADx) systems for GC, although RCTs have not yet been conducted, most studies have demonstrated expert-level performance. In colorectal polyps, multiple RCTs have shown the usefulness of the CADe system for improving the polyp detection rate, and several CADx systems have been shown to have high accuracy in colorectal polyp differentiation. Most analyses of endoscopic AI systems suggested that their performance was better than that of nonexpert endoscopists and equivalent to that of expert endoscopists. Thus, endoscopic AI systems may be useful for reducing the risk of overlooking lesions and improving the diagnostic ability of endoscopists.

The Japanese Esophageal Society classification for prediction of superficial esophageal squamous cell neoplasia invasion depth: Validation in a Western population.

The Japan Esophageal Society proposed the JES microvessel classification to assess eligibility of early esophageal squamous cell neoplasia (ESCN) for endoscopic resection based on intrapapillary capillary loop assessment. We aimed to assess its diagnostic reproducibility and accuracy in Western ESCN patients. Intrapapillary capillary loops on endoscopic images of Western ESCN lesions (n=113) collected between 2010 and 2022 were assessed by nine endoscopists, including three Japanese expert endoscopists, three Western expert endoscopists, and three residents-in-training, and graded according to the JES microvessel classification where microvessel type A corresponds with normality or low-grade intraepithelial neoplasia, and microvessel types B1, B2, and B3 correspond with high-grade intraepithelial neoplasia or invasion into the lamina propria, muscularis mucosae or superficial submucosa, and deep submucosa, respectively. Outcomes included overall accuracy in predicting ESCN invasion depth and interobserver agreement. Good interobserver agreement was observed among expert endoscopists (Krippendorf's alpha 0.64, 95% CI 0.57-0.70), while agreement was moderate among residents-in-training (Krippendorf's alpha 0.58, 95% CI 0.52-0.72). Overall accuracy of the JES microvessel classification was 53% (95% CI 42-63), 52% (95% CI 41-62), and 44% (95% CI 34-55) for Japanese endoscopists, Western endoscopists, and residents-in-training, respectively. Sensitivity and specificity for vessel type A, B1, B2, and B3 across assessors were 0%-50% and 89%-100%, 55%-64% and 66%-77%, 42%-71% and 60%-76%, and 10%-24% and 92%-97%, respectively. Negative predictive value ranged between 80% and 85% for B3 vessels. Overall accuracy of the JES microvessel classification in Western ESCN patients is low, though absence of B3 vessels as assessed by experienced endoscopists may predict superficial ESCN amenable to endoscopic resection. www.trialregister.nl; NL8897 (6-9-2020).

Single stage laparoscopic cholecystectomy with intraoperative endoscopic retrograde cholangiopancreatography for cholecysto-choledocholithiasis. Lesson learnt from the COVID-19 pandemic.

Choledocholithiasis, a common complication of gallstone disease, poses significant risks including cholangitis and pancreatitis. Various treatment approaches exist, including single-stage and two-stage techniques, with recent literature suggesting advantages of the single-stage approach in terms of outcomes and cost-effectiveness. This study evaluates the feasibility, efficacy, and safety of single-stage laparoscopic cholecystectomy combined with intraoperative endoscopic retrograde cholangiopancreatography (LC + iERCP) compared to the previously adopted two-stage approach. A retrospective analysis was conducted on patients undergoing single-stage LC + iERCP for cholecysto-choledocholithiasis during the COVID-19 pandemic (2020-2022). Data on demographics, preoperative assessments, intraoperative parameters, and postoperative outcomes were collected and compared with an historical control group undergoing the two-stage approach (LC + preopERCP). Hospitalization costs were also compared between the two groups. A total of 190 patients were included, with 105 undergoing single-stage LC + iERCP. The single-stage approach demonstrated successful completion without cystic duct cannulation, with no conversions to open surgery. Operative time was comparable to the two-stage approach, while hospital stay, and costs were significantly lower in the single-stage group. Complication rates were similar between the groups. Single-stage LC + iERCP appears to be a feasible, effective, and safe approach for treating cholecysto-choledocholithiasis, offering potential benefits in terms of reduced hospital stay, OR occupation time, and costs compared to the two-stage approach. Integration of this approach into clinical practice warrants consideration, unless there are logistical challenges that cannot be overcome or lack of endoscopic expertise also for treating challenging urgent cases.

New Method of Papillectomy May Decrease Recurrence: Anchoring Method versus Conventional Method.

Background/Objectives: Endoscopic papillectomy (EP) is the preferred treatment for ampullary tumors because it has fewer side effects than surgical removal. This study retrospectively compared a new anchoring EP method (A-EP) with the conventional (C-EP) approach. Methods: Ninety-nine patients who underwent EP at a single medical institution between 2009 and 2021 were retrospectively reviewed. In all patients, the indications for EP were pathological adenoma with <10 mm of biliary invasion and a tumor diameter <30 mm on endoscopic ultrasonography. The exclusion criteria were antiplatelet/anticoagulant use, previous upper GI surgery, or prior biliary/pancreatic endoscopic therapy. One expert endoscopist performed the two types of EPs, A-EP and C-EP. Results: Sixty-two patients underwent A-EP, and 37 underwent C-EP. There were no significant differences in baseline characteristics, such as sex, age, tumor size, and ductal invasion on endoscopic ultrasound. The A-EP group had higher en bloc resection rates (95.2% vs. 78.4%, p = 0.010). Although the difference was not statistically significant, it tended towards fewer incidences of pancreatitis (p = 0.081) and duct stricture (p = 0.081). The recurrence rate was lower in the A-EP group (8.1% vs. 37.8%, p = 0.000). There were no significant differences between the two groups regarding the follow-up period (A-EP vs. C-EP, 725 vs. 1045 days, p = 0.109) or the days of recurrence (A-EP vs. C-EP, 341 vs. 562 days, p = 0.551). Conclusions: A-EP showed better outcomes than C-EP in terms of en bloc resection and recurrence rates, providing evidence for the efficacy of this novel EP method.

Single Center Experience of Eus-Guided Cystogastrostomy and Lumen-Apposing Metal Stent (LAMS) Positioning in Children with Pancreatic Fluid Collections: A Case Series.

Pancreatic fluid collections (PFCs) are a well-known complication of pancreatitis. PFCs operative management includes percutaneous, endoscopic or surgical drainage. Even if in adult patients, endoscopic drainage is a well-established treatment, few data are available in pediatric setting. We report our single-center experience of EUS-guided cystogastrostomy and lumen-apposing metal stent (LAMS) positioning in children with PFCs; this, at the best of our knowledge, has never been reported before. All consecutive children with PFCs between April 2020 and November 2022 were enrolled in this retrospective study. PFCs were preoperatively evaluated with MRI or CT scan. All the procedures were performed under general anesthesia. A LAMS Hot-AxiosTM 10 × 15 mm was placed in all patients. We evaluated technical feasibility and clinical outcomes, including complications and recurrence rates. Follow-up included clinical observation, blood tests and US. EUS-guided cystogastrostomy was performed in 3 children (2 males; median age 13.2 years). Median maximum cyst diameter was 14.7 cm (range 10-22 cm). Technical and clinical success rates were 100%. No intra or post-operative complications occurred. Our experience suggests that this can be considered a safe and feasible treatment of PCFs even in the pediatric population, as long as the procedure is performed by an expert Endoscopist in a pediatric tertiary-level Center.

Optical diagnosis in still images of colorectal polyps: comparison between expert endoscopists and PolyDeep, a Computer-Aided Diagnosis system

BackgroundPolyDeep is a computer-aided detection and classification (CADe/x) system trained to detect and classify polyps. During colonoscopy, CADe/x systems help endoscopists to predict the histology of colonic lesions.ObjectiveTo compare the diagnostic performance of PolyDeep and expert endoscopists for the optical diagnosis of colorectal polyps on still images.MethodsPolyDeep Image Classification (PIC) is an in vitro diagnostic test study. The PIC database contains NBI images of 491 colorectal polyps with histological diagnosis. We evaluated the diagnostic performance of PolyDeep and four expert endoscopists for neoplasia (adenoma, sessile serrated lesion, traditional serrated adenoma) and adenoma characterization and compared them with the McNemar test. Receiver operating characteristic curves were constructed to assess the overall discriminatory ability, comparing the area under the curve of endoscopists and PolyDeep with the chi- square homogeneity areas test.ResultsThe diagnostic performance of the endoscopists and PolyDeep in the characterization of neoplasia is similar in terms of sensitivity (PolyDeep: 89.05%; E1: 91.23%, p=0.5; E2: 96.11%, p&amp;lt;0.001; E3: 86.65%, p=0.3; E4: 91.26% p=0.3) and specificity (PolyDeep: 35.53%; E1: 33.80%, p=0.8; E2: 34.72%, p=1; E3: 39.24%, p=0.8; E4: 46.84%, p=0.2). The overall discriminative ability also showed no statistically significant differences (PolyDeep: 0.623; E1: 0.625, p=0.8; E2: 0.654, p=0.2; E3: 0.629, p=0.9; E4: 0.690, p=0.09). In the optical diagnosis of adenomatous polyps, we found that PolyDeep had a significantly higher sensitivity and a significantly lower specificity. The overall discriminative ability of adenomatous lesions by expert endoscopists is significantly higher than PolyDeep (PolyDeep: 0.582; E1: 0.685, p &amp;lt; 0.001; E2: 0.677, p &amp;lt; 0.0001; E3: 0.658, p &amp;lt; 0.01; E4: 0.694, p &amp;lt; 0.0001).ConclusionPolyDeep and endoscopists have similar diagnostic performance in the optical diagnosis of neoplastic lesions. However, endoscopists have a better global discriminatory ability than PolyDeep in the optical diagnosis of adenomatous polyps.

Artificial Intelligence for Real-Time Prediction of the Histology of Colorectal Polyps by General Endoscopists.

Real-time prediction of histologic features of small colorectal polyps may prevent resection and/or pathologic evaluation and therefore decrease colonoscopy costs. Previous studies showed that computer-aided diagnosis (CADx) was highly accurate, though it did not outperform expert endoscopists. To assess the diagnostic performance of histologic predictions by general endoscopists before and after assistance from CADx in a real-life setting. Prospective, multicenter, single-group study. (ClinicalTrials.gov: NCT04437615). 6 centers across the United States. 1252 consecutive patients undergoing colonoscopy and 49 general endoscopists with variable experience in real-time prediction of polyp histologic features. Real-time use of CADx during routine colonoscopy. The primary end points were the sensitivity and specificity of CADx-unassisted and CADx-assisted histologic predictions for adenomas measuring 5 mm or less. For clinical purposes, additional estimates according to location and confidence level were provided. The CADx device made a diagnosis for 2695 polyps measuring 5 mm or less (96%) in 1252 patients. There was no difference in sensitivity between the unassisted and assisted groups (90.7% vs. 90.8%; P = 0.52). Specificity was higher in the CADx-assisted group (59.5% vs. 64.7%; P < 0.001). Among all 2695 polyps measuring 5 mm or less, 88.2% and 86.1% (P < 0.001) in the CADx-assisted and unassisted groups, respectively, could be resected and discarded without pathologic evaluation. Among 743 rectosigmoid polyps measuring 5 mm or less, 49.5% and 47.9% (P < 0.001) in the CADx-assisted and unassisted groups, respectively, could be left in situ without resection. Decision making based on CADx might differ outside a clinical trial. CADx assistance did not result in increased sensitivity of optical diagnosis. Despite a slight increase, the specificity of CADx-assisted diagnosis remained suboptimal. Olympus America Corporation served as the clinical study sponsor.

Computer-aided diagnosis system for optical diagnosis of colorectal polyps under white light imaging

ObjectivesThis study presents a novel computer-aided diagnosis (CADx) designed for optically diagnosing colorectal polyps using white light imaging (WLI).We aimed to evaluate the effectiveness of the CADx and its auxiliary role among endoscopists with different levels of expertise. MethodsWe collected 2,324 neoplastic and 3,735 nonneoplastic polyp WLI images for model training, and 838 colorectal polyp images from 740 patients for model validation. We compared the diagnostic accuracy of the CADx with that of 15 endoscopists under WLI and narrow band imaging (NBI). The auxiliary benefits of CADx for endoscopists of different experience levels and for identifying different types of colorectal polyps was also evaluated. ResultsThe CADx demonstrated an optical diagnostic accuracy of 84.49%, showing considerable superiority over all endoscopists, irrespective of whether WLI or NBI was used (P < 0.001). Assistance from the CADx significantly improved the diagnostic accuracy of the endoscopists from 68.84% to 77.49% (P = 0.001), with the most significant impact observed among novice endoscopists. Notably, novices using CADx-assisted WLI outperform junior and expert endoscopists without such assistance. ConclusionsThe CADx demonstrated a crucial role in substantially enhancing the precision of optical diagnosis for colorectal polyps under WLI and showed the greatest auxiliary benefits for novice endoscopists.

Using Computer-aided Optical Diagnosis and Expert Review to Evaluate Colorectal Polyps Diagnosed as Normal Mucosa in Pathology

Pathological assessment of colorectal polyps is considered the current reference standard for histologic diagnosis. About 10% of polyps sent to the pathology lab are returned with the diagnosis of mucosal folds, mucosal prolapse, or normal mucosa.1,2 Two recent publications have indicated that disagreements between endoscopic optical diagnosis and the subsequent pathological diagnoses might be due to misdiagnosis in pathology.3,4 We were therefore interested in re-evaluating pathology-based diagnosis of "mucosal polyps" using expert endoscopists and computer-assisted diagnosis (CADx) evaluation.

Pediatric Congenital Anterior Skull Base Encephaloceles and Surgical Management: A Comparative Review of 22 Patients Treated Transnasally, Transcranially, or Combined Approach With a Review of the Literature.

Anterior basal encephaloceles are considered a rare entity and are often associated with midline cerebral abnormalities. Those with a large skull base defect and herniation of brain parenchyma in the neonate or young infant present unique challenges for surgical management. We analyzed the neurosurgical administrative and operative databases between 1986 and 2022 to determine clinical presentation, operative approach, and outcome of basal encephaloceles. Over the 36-year period, 27 pediatric anterior basal encephaloceles were managed, of which 22 had full documentation and images allowing comprehensive review. Mean age at presentation was 5 years (SD 4.94). The majority were transethmoidal encephaloceles (59%), followed by the transsphenoidal-sphenoethmoidal type (32%). Overall, 91% were managed surgically by a transcranial, endoscopic, or combined approach. Four children required subsequent procedures, predominantly for persistent cerebrospinal fluid leak. No significant differences in proportion of patients requiring interval/revision surgery after initial conservative, endoscopic endonasal, or transcranial surgery was identified. Neither age at surgery nor size of the defect on computed tomography scan was associated with the need for revision surgery. Size of cranial defect was significantly smaller in the endoscopic group ( P = .01). There was a historic tendency for younger children with larger defects to have a transcranial approach. With the addition of endoscopic skull base expertise, smaller defects in older children were more recently treated endoscopically. Basal encephaloceles are rare and complex lesions and are optimally managed within a skull base multidisciplinary team able to provide multiple approaches. Large skull base defects with brain parenchymal involvement often require a transcranial or combined transcranial-endoscopic approach.