Introduction

Accurate endoscopic diagnosis of colorectal polyps is essential for determining appropriate treatment strategies. The Japan NBI Expert Team (JNET) classification and pit pattern diagnosis are used for diagnosis, but their comparative diagnostic performance in real-world clinical settings remains unclear, particularly between experts and non-experts.

Aims & Methods

This post-hoc analysis aimed to evaluate the diagnostic accuracy of both classification across different levels of expertise using data from a prospective multicenter trial. We conducted a post-hoc analysis of the deTXIon trial¹ , a randomized controlled trial conducted at eight Japanese institutions between March and October 2023. From the per-protocol set, we analyzed colorectal lesions that had both JNET classification and pit pattern diagnosis with confirmed histopathology. JNET classification categorizes lesions into Type 1 (corresponding to hyperplastic polyps [HPs] and sessile serrated lesions [SSLs]), Type 2A (low-grade adenomas), Type 2B (high-grade adenomas or superficial submucosal invasive cancer), and Type 3 (deep submucosal invasive cancer). Pit pattern classification included Type II ( HPs/SSLs ), Type III_S/III_L/IV (low-grade adenomas), Type V_I low-grade (high-grade adenoma), and Type V_I high-grade/V_N (submucosal invasive cancer). We calculated sensitivity (Sen), specificity (Spe), positive predictive value (PPV), and negative predictive value (NPV) for each classification stratified by endoscopist expertise and lesion size.

Results

A total of 1,617 colorectal lesions with a median size (IQR) of 2(1-4) mm were included in this analysis. Histopathological examination revealed that 71.5% (1,156/1,617) were low-grade adenomas, 1.0% (16/1,617) were high-grade adenomas or cancer, 19.3% were HPs (312/1,617), and 8.2% (133/1,617) were SSLs. For JNET Type 1 lesions, diagnostic accuracy was comparable between experts (Sen: 82.8%, Spe: 95.9%, PPV: 88.3%, NPV: 93.7%) and non-experts (Sen: 81.7%, Spe: 93.4%, PPV: 83.1%, NPV: 92.8%). Similarly, for JNET Type 2A, both groups showed high diagnostic performance (experts: Sen 93.8%, Spe 81.0%, PPV: 92.6%, NPV: 83.8%; non-experts: Sen 91.5%, Spe 78.3%, PPV: 90.3%, NPV: 80.6%).
In contrast, pit pattern diagnosis experts showed higher performances, particularly for Type II (experts: Sen 80.9%, Spe 96.3%, PPV: 89.0%, NPV: 93.1%; non-experts: Sen 57.9%, Spe 92.8%, PPV: 76.0%, NPV: 84.8%). The diagnostic performance for small lesions (≤5mm) was consistently high with JNET classification (Type 1: Sen 79.5%, Spe 94.3%; Type 2A: Sen 93.7%, Spe 79.2%), while pit pattern diagnosis showed lower performance (Type II: Sen 70.8%, Spe 94.5%; Type III_S/III_L/IV: Sen 93.6%, Spe 79.5%), for these lesions among non-experts.

Conclusion

JNET classification demonstrates comparable diagnostic performance between expert and non-expert endoscopists, likely due to its standardized and intuitive visual criteria. Pit pattern diagnosis shows experience-dependent performance differences, suggesting that NBI-based assessment may be more suitable for routine clinical practice, especially for diminutive lesions.

References

1. Toyoshima N, Mizuguchi Y, Takamaru H,et al. The Efficacy of Texture and Color Enhancement Imaging Observation in the Detection of Colorectal Lesions: A Multicenter, Randomized Controlled Trial (deTXIon Study). Gastroenterology. 2025 in press

Disclosure

These authors disclose the following: Yutaka Saito, Masashi Misawa, Shin-ei Kudo, and Toshio Uraoka have received lecture fees from Olympus
Corporation. The remaining authors disclose no conflicts.

Introduction

Inflammatory Bowel Disease (IBD)^1,2 requires close monitoring to detect flare ups early and guide treatment. While endoscopy is the gold standard, it is invasive, costly, and uncomfortable^1,2. Intestinal Ultrasound (IUS) is a non-invasive alternative with strong correlation to endoscopic findings—especially bowel wall thickness (BWT), a marker of disease activity³. Nevertheless, IUS remains limited due to operator dependence and a steep learning curve⁴.
AI has improved consistency in other domains, e.g. endoscopic evaluation, but its application to IUS in IBD remains underexplored. Prior models lack interpretability and require manual image cropping, or are trained on ideal, selected data, limiting clinical use^5,6.

Aims & Methods

We aim to develop a deep-learning model that automatically identifies and paints the bowel wall and measures BWT directly from raw clinical IUS images.
A training dataset of 570 images from 144 IUS videos and a testing dataset of 55 images from 55 separate exams were created. All images were extracted from previously performed IUS examinations reflecting real-world variation, including e.g. unclear boundaries and artefacts.
All images were annotated by International Bowel Ultrasound Group (IBUS) certified experts, including outline-paintings of the inner and outer bowel wall and two BWT measurements.
The AI consists of a combination of Convolutional neural networks and other image processing algorithms.
Evaluation included BWT error against the expert mean, classification accuracy using the standard IBUS 3 mm threshold³, and a leave-one-out comparison with individual doctors.

Results

The model produced predictions on 54 of 55 test images.
The model deviated from the gold standard mean by 0.98 mm (SD 1.1 mm) per image on the regression task. The average distance to expert-defined bounds was 0.44 mm (SD 0.89 mm), with 59% of predictions inside this range.
For classification (using a 3 mm threshold), the model reached an accuracy of 0.77, sensitivity of 0.69, specificity of 0.94, and Cohen’s Kappa of 0.56.
In the leave-one-out analysis, expert performance ranged from 0.89–0.93 accuracy and 0.79–0.83 Kappa. Depending on which expert was excluded from the gold standard, the model achieved 0.74–0.80 accuracy and 0.49–0.60 Kappa. Experts stayed within expert-defined bounds in 72–81% of cases, while the model did so in 46–55%.

Conclusion

Clinically, the model performed well. An error of 0.5–1 mm is negligible in practice and matches typical variation in manual measurements. Many real-world test images had BWT values near the 3 mm threshold, so small deviations led to misclassifications. In practice, a 2.5 mm reading could still raise concerns based on symptoms³.
While the system alone cannot provide expert-level BWT measurements, it could provide assistance to experts as well as non-expert and junior doctors, especially in locating the bowel, which is an essential part of IUS.
The model works on unprocessed clinical data, with the only selection criteria being that there is an identifiable bowel segment, measurable by an IBUS-certified doctor. Allowing the images to reflect realistic conditions
In summary, we developed an AI model that identifies the bowel and measures BWT with acceptable accuracy. We have already started the processes of collecting video data, to extend the AI’s functionality to a fully clinical setting.

References

1. Torres J, Mehandru S, Colombel JF, Peyrin-Biroulet L. Crohn’s disease. The Lancet. 2017;389(10080):1741-1755. doi:10.1016/S0140-6736(16)31711-1
2. Ungaro R, Mehandru S, Allen PB, Peyrin-Biroulet L, Colombel JF. Ulcerative colitis. Lancet. 2017;389(10080):1756-1770. doi:10.1016/S0140-6736(16)32126-2
3. Novak KL, Group I, Nylund K, et al. Expert Consensus on Optimal Acquisition and Development of the International Bowel Ultrasound Segmental Activity Score [IBUS-SAS]: A Reliability and Inter-rater Variability Study on Intestinal Ultrasonography in Crohn’s Disease. J Crohns Colitis. 2021;15(4):609-616. doi:10.1093/ECCO-JCC/JJAA216
4 Bove L, Meyer J, Collins M, Frampas E, Bourreille A, Le Berre C. Understanding the learning curve of intestinal ultrasound in inflammatory bowel disease: A comparative study between novice, regular, and expert. Clin Res Hepatol Gastroenterol. 2025;49(3):102548. doi:10.1016/J.CLINRE.2025.102548
5. Kumaralingam L, Le May K, Dang VB, Alavi J, Huynh HQ, Le LH. Artificial intelligence-assisted approach to assessing bowel wall thickness in pediatric inflammatory bowel disease using intestinal ultrasound images. J Crohns Colitis. 2025;19(4). doi:10.1093/ECCO-JCC/JJAF037
6. Carter D, Albshesh A, Shimon C, et al. Automatized Detection of Crohn’s Disease in Intestinal Ultrasound Using Convolutional Neural Network. Inflamm Bowel Dis. February 2023:1-6. doi:10.1093/IBD/IZAD014