Introduction

Advances in transanal resection techniques have led to the increased use of surgical and endoscopic local excision (LE) as a diagnostic and potentially organ-sparing approach for early-stage (cT1-2N0) rectal cancer (RC). Current international guidelines recommend completion total mesorectal excision (TME) following LE for surgically fit patients with pT2 RC due to the 20-30% overall risk of lymph node metastasis (LNM). However, the risk of LNM is known to vary according to the presence of histological risk factors. Therefore, omitting completion TME in selected patients with pT2 RC may constitute an oncologically safe alternative, provided there are no additional high-risk histological features other than muscularis propria invasion. The aim of this study was to determine the rate of LNM in patients with pT2 RC without additional histological risk factors.

Aims & Methods

Data from two large Dutch multicentre registries were analysed to evaluate the rate of LNM in patients with pT2 RC who underwent surgery between 2012 and 2020. In accordance with the clinical selection criteria for LE, only patients without suspected LNM on baseline imaging (cN0) were included in the study. Patients who received (neo)adjuvant (chemo)radiotherapy were excluded. Treatment strategies included primary TME, surgical LE followed by completion TME, or surgical LE followed by active surveillance with MRI for at least 24 months. Histological risk factors available in both registries were lymphovascular invasion (LVI) and poor tumour differentiation (PD). Definitive LNM status was determined by histology after TME. Patients on active surveillance after LE were classified as LNM-negative if there was no evidence of LNM (cN0) on MRI during a minimum surveillance period of 24 months. The primary study outcome was the rate of LNM in pT2 RC patients without LVI and PD. Secondary outcomes included the association between the two histological risk factors and the rate of LNM using univariable and multivariable analyses adjusted for age and sex.

Results

A total of 334 patients with pT2 RC met the inclusion criteria (mean age 69 years, 64% male). The majority of patients (262/334, 78%) underwent primary TME, while initial surgical LE was performed in 72/334 (22%). Within the LE group, subsequent TME surgery was performed in 59/72 (82%) patients, either as completion surgery (n=51) or as salvage surgery during the follow-up period (n=8). The remaining 13/72 (18%) patients underwent active surveillance for at least 24 months without suspicion of LNM on MRI during a median follow-up of 42 months (IQR 32-55). The overall rate of LNM in the cohort was 17% (55/334). In the 266/334 (80%) patients without LVI and PD, the rate of LNM was 13% (34/266). The presence of either LVI alone or PD alone resulted in LNM rates of 31% (18/58) and 14% (1/7), respectively. When both LVI and PD were present, LNM occurred in 2 out of 3 cases. In our study, only LVI was identified as an independent predictor of LNM in multivariable analysis (p<0.001; OR = 3.1, 95% CI 1.6-5.9).

Conclusion

In this large retrospective surgical cohort of patients with pT2 RC, the absence of LVI and PD was associated with a 13% risk of LNM. However, more detailed histological reassessment including risk factors such as tumour budding and perineural invasion may identify a subgroup of pT2 RC with an even lower risk of LNM. This may allow the omission of completion TME.

Introduction

Third-space endoscopy (TSE) is standard for treating neoplastic and motility disorders but is limited by intra-procedural bleeding. Vessel pre-sealing using electrocautery in an underwater setting may mitigate this, improving procedural safety and efficiency.

Aims & Methods

We conducted a randomized controlled trial (NCT05804266) comparing underwater (saline immersion) vs conventional CO₂-based coagulation during TSE procedures (ESD and POEM). Patients were randomized 1:1. The same electrosurgical settings (SWIFT COAG E3, 89 W for POEM and SWIFT COAG E4, 124 W for ESD) and instruments (VIO 3 and HybridKnife T-type, Erbe Elektromedizin GmbH, Tübingen, Germany) were used across arms. In the underwater group, vessels ≥1.2 mm were coagulated under saline immersion to enable pre-sealing; smaller vessels were treated conventionally. In the control group, all vessels were treated under CO₂, with vessel isolation when needed. Primary endpoint was the rate of intra-procedural bleeding requiring further hemostatic treatment (knife tip, coagulation forceps) of pre-sealed vessels. Secondary outcomes included other adverse events (ie delayed bleeding).

Results

Among 70 patients (37 underwater, 33 CO₂, no significant demographic difference including history of antiplatelet/anticoagulant therapy, discontinued in all patients on therapy), intra-procedural bleeding requiring hemostasis of pre-sealed vessels occurred in 12/37 (32.4%) underwater group vs 25/33 (75.8%) control (RR 0.43(0.26-0.71); NNT 2.3; P<0.01). In the underwater group, no patient required coagulation forceps; all bleedings were managed with the knife. In contrast, 9/33 (27.3%) control patients required forceps (RR: 0.05 (0.00-0.78); NNT 3.76 P<0.01). One intra-procedural perforation and two post-procedural adverse events (delayed bleeding and fever) occurred in the control group; none in the underwater arm (n.s). No mortality occurred.

Conclusion

Underwater (saline immersion) vessel pre-sealing significantly reduces the risk of intraprocedural bleeding and consequently the need of hemostatic devices, suggesting a safer, cost-effective alternative to conventional coagulation in TSE.

Introduction

Any computer-assisted characterization (CADx) system relies on Artificial Intelligence algorithms to provide a probability score to the endoscopist, characterizing the polyp as an adenoma or a hyperplastic polyp.^1-3 However, the clinical utility of these AI-generated outputs is dependent on the endoscopist’s ability to interpret and integrate them into their final diagnostic decision-making process. This requires not only recognizing and accepting a true positive AI diagnosis, but also accurately identifying and rejecting false positives. This requires a higher level of endoscopist expertise to discern whether an AI-generated classification is accurate and should be incorporated into the final diagnosis or requires correction. The primary challenge in CADx implementation lies in this inherent complexity of human-AI interactions, which can lead to misinterpretation, resulting in the endoscopist either rejecting correct CADx outputs or accepting incorrect classifications, compromising diagnostic accuracy.

Aims & Methods

We conducted a secondary analysis from a prospective study. Endoscopists were first presented with the CADx classification for each polyp, which they could accept or reject and provide an alternative. A total of 1143 patients aged at least 45 underwent colonoscopy between June 2022 and January 2025 at the CHUM Hospital, yielding 753 polyps from 367 patients after exclusion criteria. The primary aim was to assess the agreement/rejection patterns of the CADx diagnosis by the endoscopists, stratified by categorization. Secondary outcomes included the rate at which clinicians correctly rejected inaccurate CADx outputs, as well as trends in post-rejection reclassification.

Results

A total of 89.1% (408/458, 95% CI: (85.8,91.7)) of accepted CADx neoplastic diagnoses were correct, and 68.7% (68/99, 95% CI: (58.5,77.4)) of accepted CADx hyperplastic diagnoses were accurate. However, endoscopists accepted incorrect diagnoses significantly more often when CADx predicted hyperplastic than neoplastic (%, 95% CI: 31.3% (22.6,41.5) vs 10.9% (8.3,14.2)). Regarding the post-rejection patterns, when endoscopists rejected adenoma classifications (N=47), they falsely classified 25 cases (53.2%, 95% CI: (38.2,67.6)) as a sessile serrated lesion/polyp (SSL/P). Similarly, although 43.6% of the rejected hyperplastic CADx predictions were correctly re-assigned an adenoma (31.5%, 95% CI: (24.3,39.7)) or SSL/P diagnosis (12.1%, 95% CI: (7.5,18.7)), there were 41.6% (95% CI: (33.7,50.0)) that were incorrectly re-classified as SSL/Ps.

Conclusion

Endoscopists generally accept accurate adenoma predictions provided by CADx systems but frequently misclassify hyperplastic polyps as SSLs, demonstrating a diagnostic bias toward neoplasia. Although beneficial from a safety perspective, this bias may result in unnecessary early follow-up colonoscopies, increasing associated costs.^4,5 Developing and integrating CADx systems with robust SSL recognition capabilities seems essential to overcome these diagnostic challenges and enhance clinical decision-making when using CADx assisted optical polyp diagnosis. Such advanced CADx systems are likely crucial for successful CADx integration into routine clinical practice.

References

1. Djinbachian R, Taghiakbari M, Barkun A, et al. Optimized computer-assisted technique for increasing adenoma detection during colonoscopy: a randomized controlled trial. Surg Endosc 2025;39:1120-1127.
2. Byrne MF, Von Renteln D, Barkun AN. Artificial Intelligence-Aided Colonoscopy for Characterizing and Detecting Colorectal Polyps: Required, Nice to Have, or Overhyped? Gastroenterology 2023;164:332-333.
3. Taghiakbari M, Mori Y, von Renteln D. Artificial intelligence-assisted colonoscopy: A review of current state of practice and research. World J Gastroenterol 2021;27:8103-8122.à
4. Force AAT, Parasa S, Berzin T, et al. Consensus statements on the current landscape of artificial intelligence applications in endoscopy, addressing roadblocks, and advancing artificial intelligence in gastroenterology. Gastrointest Endosc 2025;101:2-9 e1.
5. Halvorsen N, Barua I, Kudo SE, et al. Leaving colorectal polyps in situ with endocytoscopy assisted by computer-aided diagnosis: a cost-effectiveness study. Endoscopy 2025.

Disclosure

Daniel von Renteln has received research funding from ERBE Elektromedizin GmbH, Ventage, Pendopharm, Fujifilm and Pentax, and has received consultant or speaker fees from Boston Scientific Inc., ERBE Elektromedizin GmbH, and Pendopharm. Roupen Djinbachian has received speaker fees from Fujifilm. The remaining authors declare that they have no conflict of interest.

Introduction

The metaverse consists of interconnected 3D virtual worlds that offer immersive experiences to users by stimulating a sense of presence, primarily through wearable headsets. Extended reality (XR), the core technology of the metaverse, combines virtual reality (VR), augmented reality (AR), and mixed reality (MR) to provide a shared online space where users can interact in both physical and virtual worlds.

Aims & Methods

We developed a holography-guided surgical navigation system based on the metaverse platform to improve spatial awareness in gastrointestinal (GI) and hepatobiliary-pancreatic (HPB) laparoscopic and robotic surgeries and investigated its usefulness.
We performed 40 endoscopic/laparoscopic GI and HPB surgeries using a metaverse-based holography-guided surgical navigation system. Over 20 Asian surgeons used a head-mounted display (HMD) during surgery. Holographic 3D guides of organs, lesions, and procedures were created based on individual patient CT/MRI images, providing a realistic 3D view in real space above the surgical field. Simultaneously, lifelike 3D avatars of surgeons were created, allowing for remote surgical planning and discussions in the metaverse.

Results

In all 40 surgeries, tumor lesions, surrounding organs, and blood vessels were accurately spatially reproduced as holographic images in a sterile space above the patient's abdomen, along with resection lines to guide surgical techniques. The system setup took less than 5 minutes on average, and no postoperative adverse events occurred in any patient. Positioning errors in superimposing the virtual models were within 2mm. Holographic avatars increased the efficiency and effectiveness of reviewing, brainstorming, and sharing virtual content. Holographic guidelines allowed surgeons to share their positions and hand movements, proving useful for hands-on training.

Conclusion

Our holography-guided surgical navigation system with the metaverse platform facilitated holographic telepresence through augmented reality, transforming the operating room into a 3D workspace. By allowing users to connect remotely and interact with lifelike avatars, our system reduced surgeon stress and unlocks new levels of computing beyond spatial limitations, regardless of any devices were used. We are currently evaluating its usefulness in gastroenterology by applying it to navigation guides for hepatic US-guided radiofrequency ablation (RFA) and endoscopic mucosal disection (ESD) of the gastrointestinal tract.

References

• Maki Sugimoto. Cloud XR (Extended Reality: Virtual Reality・Augmented Reality・Mixed Reality) and 5G networks for holographic medical image-guided surgery and telemedicine. Multidisciplinary Computational Anatomy - Principles and Clinical Application of MCA-based Medicine. pp 381-338, 2021. Editor: Hashizume M. Springer, Singapore. 2021. DOI https://doi.org/10.1007/978-981-16-4325-5_52
• Maki Sugimoto. Extended Reality (XR:VR/AR/MR), 3D Printing, Holography, A.I., Radiomics, and Online VR Tele-Medicine for Precision Surgery. Surgery and Operating Room Innovation. p65-70. Editor: Takenoshita S, Yasuhara H. Springer, Singapore. 2020. DOI https://doi.org/10.1007/978-981-15-8979-9_7
• Maki Sugimoto. Augmented Tangibility Surgical Navigation Using Spatial Interactive 3-D Hologram zSpace with OsiriX and Bio-Texture 3-D Organ Modeling. IEEE 2015 International Conference on Computer Application Technologies (CCATS 2015). 189-194, 2015. DOI:10.1109/CCATS.2015.53

Disclosure

Holoeyes Inc.; Board member

Introduction

Early diagnosis of pancreatic cancer remains difficult due to the lack of overt findings on imaging. Our prior analysis revealed that indirect signs such as pancreatic atrophy and ductal stenosis or dilation often precede tumor visibility. In collaboration with Fujifilm Corporation, we developed an AI-based system capable of detecting pancreatic masses, atrophy, and ductal abnormalities on contrast-enhanced CT(CE-CT) and non-contrast CT(NC-CT). This study evaluated its diagnostic performance.

Aims & Methods

The AI algorithm extracts the pancreatic parenchyma, ducts, and tumor regions from CT images and classifies the presence of four imaging findings (pancreatic mass, atrophy, ductal dilation, and ductal stenosis). The model was trained and validated using approximately 2,000 images. For testing, we used an external dataset comprising 90 pancreatic cancer cases (Tis/T1: T2: T3–T4 = 1:1:1) and 100 controls collected from affiliated institutions. Reference standard for each imaging findings was established by two expert radiologists. Diagnosis of pancreas cancer was also performed using the logistic regression model with the results of each imaging finding. Diagnostic performances were performed on CE-CT and NC-CT, and AI diagnostic accuracy and reading time were compared with those of four radiologists and two gastroenterologists.

Results

For the diagnosis of pancreas cancer, the AI showed a sensitivity of 98.9% and specificity of 93.0% on CE-CT, and sensitivity of 83.9% and specificity of 92.0% on NC-CT. The system successfully detected early-stage cancers, including Tis and T1, by identifying indirect imaging findings. Detection metrics for CE-CT vs. NC-CT were as follows: mass (sensitivity 97.2% vs. 87.5%; specificity 74.6% vs. 71.4%), atrophy (74.0% vs. 59.6%; 90.7% vs. 92.9%), ductal dilation (78.8% vs. 90.5%; 96.4% vs. 88.3%), and ductal stenosis (87.7% vs. 93.9%; 90.4% vs. 85.1%).
Physicians showed mean sensitivities/specificities of 88.9%/99.3% on CE-CT and 53.4%/99.5% on NC-CT. Mean reading time per case was 22 seconds (AI) vs. 63 seconds (physicians) for CE-CT and 20 seconds (AI) vs. 78 seconds (physicians) for NC-CT.

Conclusion

The AI system demonstrated diagnostic performance comparable to that of experienced radiologists and significantly reduced reading time. While its specificity was somewhat lower than that of physicians, the system effectively identified early-stage pancreatic cancers using secondary findings. At present, it may be best applied as a second-reader support tool in radiological interpretation. Further refinement may expand its role in early detection and possibly future screening.

Disclosure

N.H., A.O., and M.T. are employees of Fujifilm Corporation.
A.M., K.S., T.M., and Y.K. declare financial conflicts of interest with Fujifilm Corporation.