Introduction

Initial reports have described rectal endoscopic knife-assisted full-thickness resection (kFTR) as a novel technique for achieving R0 resection in deeply invasive or technically challenging rectal lesions, avoiding the significant morbidity and mortality of rectal surgery.^1,2​​​​ We aimed to evaluate the feasibility, safety, and technical outcomes of rectal kFTR.

Aims & Methods

In this retrospective international study, we included consecutive patients who underwent rectal kFTR at 15 centres across 4 continents between April 2017 and April 2025. We included patients with adenocarcinoma suspected of deep submucosal invasion, severe fibrosis, or subepithelial lesions were included. Primary outcomes were technical success, en-bloc and R0 resection rates and adverse events. Secondary outcomes included rectal preservation, length of hospital stay, and recurrence. Risk factors for adverse events were evaluated using univariate and multivariate logistic regression.

Results

A total of 94 patients (mean age 65 years [IQR 58-73]; 56.4% male; 79.8% ASA I/II) underwent rectal kFTR. Median lesion size was 35 mm [IQR 25-50]. kFTR was performed for suspected deep invasion (57; 60.6%), severe fibrosis (31; 33%), and subepithelial lesions (6; 6.4%). Of lesions included, 59 (62.8%) were in the distal rectum, and 13 (13.8%) were anterior.

Technical success was achieved in 92 procedures (97.9%). Mean procedure time was 135 minutes (IQR 100-180). Antibiotics were administered in 83 procedures (88.3%) for a median of 5 days (IQR 5-5). Median hospital stay was 1 day (IQR 1 - 3). Overall, 19 adverse events occurred in 15/94 (16%) patients: 12 (63.1%) mild, 6 (31.6%) moderate, and 1 (5.3%) severe per ASGE lexicon. Delayed bleeding occurred in 4 (4.3%) patients, and post-procedural pain in 7 patients (7.4%). Surgery was required in one case for a recto-vaginal fistula. Increasing lesion size was the only risk factor independently associated with a higher risk of adverse events (OR 1.05, 95% CI 1.02–1.09, p = 0.003).

En-bloc and R0 resections were achieved in 91/94 (96.8%) and 74 (78.7%) procedures, respectively. Rectal preservation was achieved in 68 patients (72.3%) while, 25 (26.6%) underwent completion surgery for non-curative cancer resections, with no residual tumor in the surgical specimen in 11/25 cases (44%).

Among 59 patients with adenocarcinoma and available follow-up (median 12 months (IQR 6 - 23.5)), 3 (5.1%) experienced loco-regional recurrences, 1 (1.7%) had distant metastasis from a pT2 adenocarcinoma with surgery after kFTR, and 1 died of non-cancer-related causes.

Conclusion

kFTR appeared to be a feasible and safe technique for excising deeply invasive adenocarcinomas and complex fibrotic or subepithelial rectal lesions in expert centres. The high rate of R0 resections enabled accurate histopathological risk stratification, supporting individualised post-procedural management and rectal preservation in most patients. Rectal kFTR may serve as an alternative to device-assisted endoscopic full-thickness resection and local surgical excision, potentially avoiding radical surgery in highly selected patients. Further prospective research is needed to confirm these findings.

References

1. Argenziano ME*, Sorge A*, Poortmans PJ, Montori M, Balducci D, Hoorens A, Maroni L, Tate DJ, Knife-Assisted Full-Thickness Resection Guided by Pocket Detection Method for Detection and Complete Excision of Deeply Invasive Rectal Cancer, VideoGIE (2024), doi: https://doi.org/10.1016/j.vgie.2024.11.004.
2. Argenziano, M.E.*, Sorge, A.*, Hoorens, A., Montori, M., Poortmans, P.J., Smeets, S., Tornai, T., Debels, L.K., Desomer, L. and Tate, D.J. (2025), Knife-assisted full-thickness resection guided by the pocket-detection method for posterior deeply invasive rectal cancer: A novel endoscopic approach (with video). DEN Open, 5: e70116. https://doi.org/10.1002/deo2.70116

Introduction

For training deep learning algorithms in medical imaging, application-specific data is often scarce. Deep learning systems are therefore generally pretrained on large publicly available labeled data sets of general imagery, unrelated to the envisioned application, to have the algorithm learn basic features from these widely available data followed by refinement training on the generally scarce application-specific images. Pretraining might be more effective if the images for pretraining resemble the envisioned application, i.e., domain-specific pretraining.

Aims & Methods

We investigated if pretraining on general endoscopic imagery results in a better performance of five existing AI systems with an application in gastro-intestinal endoscopy, compared to current state-of-the art pretraining approaches (i.e., supervised pretraining with ImageNet and semi-weakly supervised pretraining with the Billion-scale data set). Our group has created an endoscopy-specific dataset called GastroNet for pretraining deep learning systems in endoscopy. GastroNet consists of 5,084,494 endoscopic images retrospectively collected between 2012 and 2020 in seven Dutch hospitals. We created four pretrained models: one using GastroNet and three using ImageNet and/or the Billion-scale data set. The pretraining method was either supervised, self-supervised, or semi-weakly supervised. The pretrained models were subsequently trained towards five independent, commonly used applications in GI endoscopy, using their original application-specific datasets. Outcome parameters were: 1) classification and/or localization performance of the five trained applications; 2) change in performance when the number of available application-specific training data was reduced, to investigate a possible difference in performance drop for the different pretrained models.

Results

Overall, the domain-specific pretrained model resulted in a statistically superior performance for the five different GI applications. More detailed results are presented in Table 1. The superiority was also reflected in a smaller drop in performance when the number of application-specific training data were reduced artificially.

Table 1. Overview of performance of the five different application-specific data sets using four different pretrained models. Cells highlighted in green represent the highest scoring pretrained model per application-specific data set.

Conclusion

Domain-specific pretraining, using unlabeled general endoscopic images, is superior to current state-of-the-art pretraining approaches for developing deep learning algorithms in GI endoscopy. It also allows more effective use of the generally scarce application-specific endoscopy images. These findings might cause a paradigm shift in the development of AI systems in endoscopy.

Introduction

Cardiac septal ocludder device is an off-label device for closure of gastrointestinal fistulas and should be considered for chronic refractory fistulas to conventional endoscopic treatments.

Aims & Methods

We describe the off-label use of a cardiac septal defect occluder (CSDO, Amplatzer™, Abbott) for endoscopic closure of a lower gastrointestinal tract fistula between the rectum and post-cystectomy surgical site.

Results

An 84-year-old male with medical history of T1 bladder cancer underwent radical cystectomy complicated with surgical site abscess. Abdominal CT revealed free gas in surgical site and a rectum wall defect suggestive of fistula. Despite conservative treatment, patient persisted with penial and anal discharge. Patient was referred for endoscopic closure. Colonoscopy showed a 6mm fistulous tract between the cystectomy surgical site and the rectum wall. Two initial closure attempts with 12/6 over-the-scope clips (OTSC) after margin epithelial ablation were tried (second attempt with combined placement of a detachable snare below the OTSC), each 3 months apart. Despite initial technical and clinical success, fistula recurred after spontaneous detachment of OTSCs. Endoscopic
internal drainage with a double pigtail stent was also tried, however, fistula persisted after distal spontaneous migration 2 months later. Considering fistula persistence, patient was proposed for closure with a CSDO. After fluoroscopic characterization of the defect (surgical site: 20x25mm, fistulous tract length: 4mm: fistula orifice diameter: 3mm), a 16/4/12mm Amplatzer™ CSDO was chosen. After placement of a 0.035’AmplatzerTM guidewire from the rectum into the surgical site, guided by a 5.4-Fr angiography catheter, a delivery sheath was then advanced into the surgical site over the guidewire. After mounting the CSDO on the loading device, it was advanced inside the delivery sheath, and correctly deployed with the proximal flange in the surgical site and distal flange in the rectum. Patient remains well, without clinical recurrence.

Conclusion

To date, only 4 cases of lower gastrointestinal fistulas closure with CSDO, all rectovaginal fistulas, have been reported. To the best of our knowledge, this is the first case of endoscopic closure of a fistula between rectum and surgical site.

Introduction

The PROTDILAT study (Loras et al. Lancet Gastroenterol Hepatol. 2022) at 1-year follow-up showed greater efficacy of EBD vs SEMS for the treatment of short strictures in CD. However, long term efficacy of endoscopic treatmetn is still debated, especially for EDB.

Aims & Methods

Aims: To assess the long-term evolution of patients included in PROTDILAT study. 1). Percentage of patients free of surgery; 2) Factors related to surgery; 3) Need for endoscopic retreatments; 4) Effectiveness related to the type of initial endoscopic treatment (EBD vs SEMS); 5) Complications related to endoscopic or surgical treatment.
Methods: Retrospective study based on PROTDILAT trial database (patients with CD, obstructive symptoms, with stenosis <10cm). Data on medical, endoscopic and surgical treatment and smoking habits were collected. The effectiveness of endoscopic treatment is defined by the percentage of patients free of surgery and endoscopic retreatment at the end of follow-up.

Results

Information available on 80/80 patients (39 SEMS, 41 EBD), 39 women, age (median): 45y (IQR: 38-55); median stricture length 3.4cm (IQR: 2-5.5), 42.5% being anastomotic. Thirty-one percent (25/80) of patients required surgical resection [(median time to surgery 30.61 months (6.35-55.24)). Factors associated to surgery: non-intensification of therapy (HR 0.26 (0.10-0.68)), treatment with EBD exclusively (HR 0.22 (0.08-0.58)) (with respect to treatment with EBD + SEMS) and number of stents (HR 2.31 (1.10-4.84)). Of the 55 patients free of surgery, during the entire follow-up (median 84 months (74.7-84.0)), a median of 2 endoscopic procedures (1-3) were performed: EBD in 45 cases (80.0%) and SEMS in 26 cases (46%). Thirty-eight-point seventy-five percent (31/80 patients) did not require neither surgery nor endoscopic retreatment during the follow-up. The long-term effectiveness of endoscopic treatment was 45% for SEMS and 57.6% for EBD (p=0.374). The complications related to endoscopic or surgical treatment were 8.75% (7/80) versus 36% (9/25) respectively (p=0.002). As for the severity of complications (AGREE/CLAVIEN-DINDO ≥ III), it was observed that surgical treatment presented more severe complications than endoscopic treatment (Endoscopic vs surgical treatment: 38% (3/8) vs 84% (10/12), p=0.011).

Conclusion

Endoscopic treatment (predominantly EBD) avoids surgery in most cases, requiring a low number of endoscopic treatments in the long-term. Patients at higher risk for surgery are those with a greater number of endoscopic treatments that include SEMS and EBD. On the contrary, protective factors are non-intensificationof therapy and having been treated exclusively with EBD. Although there are no significant differences in the long effectiveness between SEMS and EBD, a trend for a better outcome is observed for EBD. To highlight a significant higher rate of complications observed in surgicaltreatment compared to endoscopic treatment.

References

Loras et al. Lancet Gastroenterol Hepatol. 2022

Disclosure

No conflict of Interest