Related Info Links
More by Authors Links
News and Announcements
ORIGINAL RESEARCH ARTICLE
Real-time You Only Look Once-based colorectal polyp detection for cancer screening across independent colonoscopy datasets
Show Less
1 Department of Computer Engineering, Faculty of Engineering, Igdir University, Igdir,
Türkiye
2 Department of Computer Engineering, Faculty of Engineering and Natural Sciences, Fenerbahce University, Istanbul,
Türkiye
3 Department of Electronics and Information Technologies, Faculty of Architecture and Engineering, Nakhchivan State University, Nakhchivan,
Azerbaijan
EJMO, 026220238 https://doi.org/10.36922/EJMO026220238
Received: 26 May 2026 | Revised: 27 June 2026 | Accepted: 3 July 2026 | Published online: 16 July 2026
© 2026 by the Author(s). This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution -Noncommercial 4.0 International License (CC-by the license) ( https://creativecommons.org/licenses/by-nc/4.0/ )
Abstract
Introduction: Colorectal cancer remains a major cause of cancer-related mortality, although many cases are preventable when precursor polyps are detected and removed during colonoscopy. Real-time computer-aided detection may assist endoscopists, but reliable localization is challenging because polyps vary in size, shape, color, contrast, boundary clarity, and visibility across heterogeneous endoscopic conditions.
Objective: This study benchmarked recent You Only Look Once (YOLO)-based detectors for single-class colorectal polyp localization by comparing architectural families and model scales ranging from nano to x-large.
Methods: YOLO12, YOLOv13, and YOLO26 models were evaluated using PolypGen2021, Polyp Imaging Classification for Colonoscopy using Optical Learning Outcomes (PICCOLO), and ETIS-Larib. PolypGen2021 was split at the patient level for model development; the predefined patient-level PICCOLO split was preserved, and ETIS-Larib was reserved exclusively for external testing. Performance was assessed using precision, recall, mean average precision (mAP) 50, mAP50–95, parameter count, giga floating-point operations per second (GLOPs), and inference time.
Results: On ETIS-Larib, YOLO26x achieved the highest mAP50–95 (0.6475) and the highest recall (0.7736). On the PICCOLO test set, YOLOv13x achieved the highest mAP50–95 of 0.6630, whereas YOLO26x reached the highest precision of 0.9118. Across both test sets, YOLO26x achieved the highest average mAP50–95 (0.6462). YOLO26n provided the most efficient profile, with 2.3750 million parameters, 5.1894 GFLOPs, and inference times below 3 ms per image.
Conclusion: YOLO26x was the strongest accuracy-oriented detector, while YOLO26n offered the most practical lightweight alternative for real-time colonoscopy support.
Keywords
Colorectal cancer
Colonoscopy
Polyp detection
You Only Look Once
Deep learning
Computer-aided detection
Funding
This study was supported by the Scientific and Technological Research Council of Türkiye (TÜBİTAK) under the 1507 SME R&D Start-up Support Program (project number 7250224, call period 1507-2025-1). The funder had no role in the study design, data collection, analysis, interpretation of results, manuscript preparation, or the decision to submit the article for publication.
Conflict of interest
The author declares that there is no conflict of interest regarding the publication of this manuscript.
References
- Siegel RL, Giaquinto AN, Jemal A. Cancer statistics, 2024. CA Cancer J Clin. 2024;74(1):12-49. doi: 10.3322/caac.21820
- Morgan E, Arnold M, Gini A, et al. Global burden of colorectal cancer in 2020 and 2040: incidence and mortality estimates from GLOBOCAN. Gut. 2023;72(2):338-344. doi: 10.1136/gutjnl-2022-327736
- Winawer SJ, Zauber AG, Ho MN, et al. Prevention of colorectal cancer by colonoscopic polypectomy. N Engl J Med. 1993;329(27):1977-1981. doi: 10.1056/NEJM199312303292701
- Zauber AG, Winawer SJ, O’Brien MJ, et al. Colonoscopic polypectomy and long-term prevention of colorectal-cancer deaths. N Engl J Med. 2012;366(8):687-696. doi: 10.1056/NEJMoa1100370
- Corley DA, Jensen CD, Marks AR, et al. Adenoma detection rate and risk of colorectal cancer and death. N Engl J Med. 2014;370(14):1298-1306. doi: 10.1056/NEJMoa1309086
- Rex DK, Schoenfeld PS, Cohen J, et al. Quality indicators for colonoscopy. Gastrointest Endosc. 2015;81(1):31-53. doi: 10.1016/j.gie.2014.07.058
- van Rijn JC, Reitsma JB, Stoker J, Bossuyt PM, van Deventer SJ, Dekker E. Polyp miss rate determined by tandem colonoscopy: a systematic review. Am J Gastroenterol. 2006;101(2):343-350. doi: 10.1111/j.1572-0241.2006.00390.x
- Soetikno RM, Kaltenbach T, Rouse RV, et al. Prevalence of nonpolypoid colorectal neoplasms in asymptomatic and symptomatic adults. JAMA. 2008;299(9):1027-1035. doi: 10.1001/jama.299.9.1027
- Leggett B, Whitehall V. Role of the serrated pathway in colorectal cancer pathogenesis. Gastroenterology. 2010;138(6):2088-2100. doi: 10.1053/j.gastro.2009.12.066
- Wang P, Liu P, Glissen Brown JR, et al. Lower adenoma miss rate of computer-aided detection-assisted colonoscopy vs routine white-light colonoscopy in a prospective tandem study. Gastroenterology. 2020;159(4):1252-1261.e5. doi: 10.1053/j.gastro.2020.06.023
- Schauer C, van Rijnsoever M, Jafer A, Walmsley R, Wang MTM, Atkinson N. Man plus machine: a randomized control trial of artificial intelligence including the impact of adjunctive polyp detection techniques. J Gastroenterol Hepatol. 2026;41(1):117-127. doi: 10.1111/jgh.70145
- Silva J, Histace A, Romain O, Dray X, Granado B. Toward embedded detection of polyps in WCE images for early diagnosis of colorectal cancer. Int J Comput Assist Radiol Surg. 2014;9(2):283-293. doi: 10.1007/s11548-013-0926-3
- Tajbakhsh N, Gurudu SR, Liang J. Automated polyp detection in colonoscopy videos using shape and context information. IEEE Trans Med Imaging. 2016;35(2):630-644. doi: 10.1109/TMI.2015.2487997
- Pacal I, Karaboga D, Basturk A, Akay B, Nalbantoglu U. A comprehensive review of deep learning in colon cancer. Comput Biol Med. 2020;126:104003. doi: 10.1016/j.compbiomed.2020.104003
- Amirmohammadi E, Shalbaf A, Esteki A, et al. Application of artificial intelligence in colonoscopy imaging for polyp analysis: a systematic review. Comput Methods Programs Biomed. 2026;277:109239. doi: 10.1016/j.cmpb.2026.109239
- Bernal J, Sánchez FJ, Fernández-Esparrach G, Gil D, Rodríguez C, Vilariño F. WM-DOVA maps for accurate polyp highlighting in colonoscopy: validation vs. saliency maps from physicians. Comput Med Imaging Graph. 2015;43:99-111. doi: 10.1016/j.compmedimag.2015.02.007
- Jha D, Smedsrud PH, Riegler MA, et al. Kvasir-SEG: a segmented polyp dataset. In: MultiMedia Modeling. Heidelberg, Germany: Springer; 2020:451-462. doi: 10.1007/978-3-030-37734-2_37
- Sánchez-Peralta LF, Pagador JB, Picón A, et al. PICCOLO white-light and narrow-band imaging colonoscopic dataset: a performance comparative of models and datasets. Appl Sci. 2020;10(23):8501. doi: 10.3390/app10238501
- Ali S, Jha D, Ghatwary N, et al. A multi-centre polyp detection and segmentation dataset for generalisability assessment. Sci Data. 2023;10(1):75. doi: 10.1038/s41597-023-01981-y
- Redmon J, Divvala S, Girshick R, Farhadi A. You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NY, USA: IEEE; 2016:779-788. doi: 10.1109/CVPR.2016.91
- Bochkovskiy A, Wang CY, Liao HYM. YOLOv4: optimal speed and accuracy of object detection. arXiv. Preprint posted online 2020. doi: 10.48550/arXiv.2004.10934
- Wang CY, Bochkovskiy A, Liao HYM. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York, NY, USA: IEEE; 2023:7464-7475. doi: 10.1109/CVPR52729.2023.00721
- Urban G, Tripathi P, Alkayali T, et al. Deep learning localizes and identifies polyps in real time with 96% accuracy in screening colonoscopy. Gastroenterology. 2018;155(4):1069- 1078.e8. doi: 10.1053/j.gastro.2018.06.037
- Lee JY, Jeong J, Song EM, et al. Real-time detection of colon polyps during colonoscopy using deep learning: systematic validation with four independent datasets. Sci Rep. 2020;10(1):8379. doi: 10.1038/s41598-020-65387-1
- Pacal I, Karaboga D. A robust real-time deep learning based automatic polyp detection system. Comput Biol Med. 2021;134:104519. doi: 10.1016/j.compbiomed.2021.104519
- Pacal I, Karaman A, Karaboga D, et al. An efficient real-time colonic polyp detection with YOLO algorithms trained by using negative samples and large datasets. Comput Biol Med. 2022;141:105031. doi: 10.1016/j.compbiomed.2021.105031
- Karaman A, Karaboga D, Pacal I, et al. Hyper-parameter optimization of deep learning architectures using artificial bee colony algorithm for high performance real-time automatic colorectal cancer polyp detection. Appl Intell. 2023;53(12):15660-15685. doi: 10.1007/s10489-022-04299-1
- Karaman A, Pacal I, Basturk A, et al. Robust real-time polyp detection system design based on YOLO algorithms by optimizing activation functions and hyper-parameters with artificial bee colony. Expert Syst Appl. 2023;221:119741. doi: 10.1016/j.eswa.2023.119741
- Zare O, Beigzadeh M, Bzuayene AA, et al. LightAttn- YOLO-V8: an efficient colorectal polyp detection with lightweight attention mechanism based on YOLO. Sci Rep. 2026;16(1):18100. doi: 10.1038/s41598-026-35390-z
- Sureban NB, Ajish AC, Abhinav Y, Prusty MR, Patra SR. A channel-efficient colorectal polyp detection using wavelet-enhanced reverse attention and custom neck YOLO architecture. Biomed Signal Process Control. 2026;119:109909. doi: 10.1016/j.bspc.2026.109909
- Du J, He Z, Zhang S, Wu G, Liang C. Gastrointestinal polyp detection method based on the improved RT-DETR. Sci Rep. 2026;16(1):7020. doi: 10.1038/s41598-026-38617-1
- Lin Y, Huang C, Tian H, Yang B, Deng T, Pan Y, Wang H, Li X. Improving generalization of polyp detection via conditional StyleGAN augmented training. npj Digit Med. 2026;9(1):113. doi: 10.1038/s41746-025-02293-8
- Liao H, Hu X, Zhang X, Tang T, Xu X. An efficient object detection network for early polyp detection. Biomed Signal Process Control. 2026;113:108860. doi: 10.1016/j.bspc.2025.108860
- Elkarazle K, Raman V, Chua C, Then P, Prabhavathy M. EfficientPolySeg: a fast and accurate network for complex polyp segmentation. Biomed Signal Process Control. 2026;112:108449. doi: 10.1016/j.bspc.2025.108449
- Tesema FB, Guerra-Manzanares A, Cui T, Zhang Q, Solomon MM, He X. LGPS: a lightweight GAN-based approach for polyp segmentation in colonoscopy images. Biomed Signal Process Control. 2026;118:109777. doi: 10.1016/j.bspc.2026.109777
- Li F, Xu L, Ma Z, Zhao Y, Li X. APU-Net: a U-Net enhanced network with dynamic feature fusion and pyramid cross-attention mechanism for polyp segmentation. Digit Signal Process. 2026;172:105879. doi: 10.1016/j.dsp.2025.105879
- Tian Y, Ye Q, Doermann D. YOLOv12: attention-centric real-time object detectors. arXiv. Preprint posteded online 2025. doi: 10.48550/arXiv.2502.12524
- Lei M, Li S, Wu Y, et al. YOLOv13: real-time object detection with hypergraph-enhanced adaptive visual perception. arXiv. Preprint posted online 2025. doi: 10.48550/arXiv.2506.17733
- Jocher G, Qiu J, Liu M, Lyu S, Akyon FC, Kalfaoglu ME. Ultralytics YOLO26: unified real-time end-to-end vision models. arXiv. Preprint posted online 2026. doi: 10.48550/arXiv.2606.03748
- Lin TY, Maire M, Belongie S, et al. Microsoft COCO: Common Objects in Context. In: Lecture Notes in Computer Science. Cham, Switzerland: Springer International Publishing; 2014:740-755. doi: 10.1007/978-3-319-10602-1_48