Introduction

Computer-aided polyp detection (CADe) systems based on artificial intelligence are increasingly used in routine endoscopic colorectal cancer screening. These systems are regularly updated and occasionally provide adjustable detection thresholds that impact their performance. However, little is known about the effect of these adjustments on the system’s performance.

Aims & Methods

The objective of this study is to evaluate the performance of various CADe systems on a common benchmark dataset, and to compare the performance of different versions and configurations of the same system. The study employed a total of 101 colonoscopy videos, and each video containing visible polyps was manually annotated with a bounding box, resulting in a total of 129 705 polyp images. The performance of three different CADe systems was assessed: two versions of GI Genius, two detection types of EndoAID, and the freely available CADe system EndoMind. The evaluation included a comprehensive analysis of sensitivity, false positive rate, and time to first polyp detection. In addition, the quality of the bounding boxes in delimiting the polyp was also evaluated by calculating the intersection over the union.

Results

EndoAID (type A), the earlier version of GI Genius, and EndoMind detected all 93 polyps in at least one image. Both the later version of GI Genius and EndoAID (type B) missed one polyp. The mean per-frame sensitivity for each system was 50.63 % for the earlier version of GI Genius, 67.85 % for the later version of GI Genius, 65.60 % for EndoAID (type A), 52.95 % for EndoAID (type B), and 60. 22 % for EndoMind. Regarding the mean first detection time, the earlier version of GI Genius required 1 510 ms, the later version of GI Genius required 607 ms, EndoAID (type A) required 659 ms, EndoAID (type B) required 1 316 ms, and EndoMind required 1 083 ms. The CADe system that presented the fewest number of false positive frames was EndoAID (Type B) with a ratio of only 0.63 %. Lastly, EndoMind was the best performing system in terms of bounding box quality with an intersection over union value of 68.32 %.

Conclusion

This study provides a direct comparison of the performance of different CADe systems, as well as different versions and configurations of the same system. The results show that the performance of CADe systems can vary significantly depending on the system used, the version of the system, and the configuration of the system. By providing an objective evaluation of the strengths and weaknesses of CADe systems, this study can help clinicians and researchers select the most appropriate system for their specific needs.

Introduction

Endoscopic stenting proved to be a valid surgery-sparing approach for upper gastrointestinal benign pathological conditions, mainly refractory benign strictures and post-surgical transmural defects. Niti-S™ Beta-2™ EKxxxxFNT2 esophageal covered stents were specifically designed to treat these conditions preventing stent migration and embedment.

Aims & Methods

We conducted a monocentric retrospective analysis on prospectively collected data regarding patients undergoing EKxxxxFNT2 placement for benign indication between January 2019 and December 2024, considering demographic, anthropometric, clinical and technical variables, and evaluating safety and efficacy profiles.

Results

A total of 32 patients were included (M 53.1%, median age 63 years), 25 (78.1%) post-surgical. Indication for stent placement was leakage in 16/32 cases (50%), and stricture/compression and fistula both in 8/32 (25%). Most frequently applied stent (16/32, 50%) was Niti-S™ Beta-2™ EKxxxxFNT2 esophageal covered stent 24 mm x 200 mm. Technical success was achieved in 100% of the cases. No periprocedural AEs were registered, 4 stents (12.5%) migrated. Median time to oral refeeding was 4 days [IQR 2-10]. Stents were removed after a median time of 34 days [IQR 17.3-41.5]. Three patients (9.4%) died before stent removal. Overall clinical success rate was 26/32 cases (81.3%); anastomotic leakage as indication proved to be significantly more frequent among the unsuccessful group [5/6 (83.3%) VS 7/26 (26.9%), p=0.0012]. Two cases (8%) of stenosis relapse were reported, all successfully endoscopically treated.

Conclusion

Double-bump antimigratory Niti-S™ Beta-2™ EKxxxxFNT2 esophageal covered stents proved to be a safe, effective, and rapid therapeutic option for patients with complex benign upper gastrointestinal conditions.

References

Binda C, Jung CFM, Fabbri S, Giuffrida P, Sbrancia M, Coluccio C, Gibiino G, Fabbri C (2023) Endoscopic Management of Postoperative Esophageal and Upper GI Defects-A Narrative Review. Med Kaunas Lith 59:136. https://doi.org/10.3390/medicina59010136
Medas R, Ferreira-Silva J, Girotra M, Barakat M, Tabibian JH, Rodrigues-Pinto E (2023) Best Practices in Esophageal, Gastroduodenal, and Colonic Stenting. GE Port J Gastroenterol 30:19–34. https://doi.org/10.1159/000527202
Fuccio L, Hassan C, Frazzoni L, Miglio R, Repici A (2016) Clinical outcomes following stent placement in refractory benign esophageal stricture: a systematic review and meta-analysis. Endoscopy 48:141–148. https://doi.org/10.1055/s-0034-1393331
Spaander MCW, van der Bogt RD, Baron TH, Albers D, Blero D, de Ceglie A, Conio M, Czakó L, Everett S, Garcia-Pagán J-C, Ginès A, Jovani M, Repici A, Rodrigues-Pinto E, Siersema PD, Fuccio L, van Hooft JE (2021) Esophageal stenting for benign and malignant disease: European Society of Gastrointestinal Endoscopy (ESGE) Guideline - Update 2021. Endoscopy 53:751–762. https://doi.org/10.1055/a-1475-0063
Boerlage TCC, Houben GPM, Groenen MJM, van der Linde K, van de Laar AWJM, Emous M, Fockens P, Voermans RP (2018) A novel fully covered double-bump stent for staple line leaks after bariatric surgery: a retrospective analysis. Surg Endosc 32:3174–3180. https://doi.org/10.1007/s00464-018-6034-2