Polyp Segmentation in Colonoscopy Images using YOLOv8

• Sandro Luis de Araujo Junior UTFPR
• Michel Hanzen Scheeren UTFPR
• Rubens Miguel Gomes Aguiar CEIA
• Eduardo Mendes UTFPR
• Ricardo Augusto Pereira Franco UFG
• Pedro Luiz de Paula Filho UTFPR

DOI: https://doi.org/10.5753/sbcas.2024.2180

Abstract

Polyp segmentation in colonoscopy images is an important computeraided diagnostic task, as it can assist doctors in identifying and consequently removing polyps, thus contributing to the reduction of cases of colorectal cancer, one of the most common and lethal types of cancer. In this work, the capacity of different variants of the YOLOv8 algorithm was evaluated in the task of polyp segmentation, using three public databases of colonoscopy images. Among the different versions, YOLOv8n proved to be the most effective alternative, despite being the simplest version. The results achieved reached 0.919 dice and 0.877 IoU, thus demonstrating the effectiveness of the model.

References

Bernal, J., Sánchez, F. J., Fernández-Esparrach, G., Gil, D., Rodríguez, C., and Vilariño, F. (2015). Wm-dova maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians. Computerized Medical Imaging and Graphics, 43:99–111.

Fan, D.-P., Ji, G.-P., Zhou, T., Chen, G., Fu, H., Shen, J., and Shao, L. (2020). Pranet: Parallel reverse attention network for polyp segmentation. In Martel, A. L., Abolmaesumi, P., Stoyanov, D., Mateus, D., Zuluaga, M. A., Zhou, S. K., Racoceanu, D., and Joskowicz, L., editors, Medical Image Computing and Computer Assisted Intervention – MICCAI 2020, pages 263–273, Cham. Springer International Publishing.

Haque, I. R. I. and Neubert, J. (2020). Deep learning approaches to biomedical image segmentation. Informatics in Medicine Unlocked, 18:100297.

Heresbach, D., Barrioz, T., Lapalus, M.-G., Coumaros, D., Bauret, P., Potier, P., Sautereau, D., Boustière, C., Grimaud, J.-C., Barthélémy, C., Sée, J., Serraj, I., D’Halluin, P. N., Branger, B., and Ponchon, T. (2008). Miss rate for colorectal neoplastic polyps: a prospective multicenter study of back-to-back video colonoscopies. Endoscopy, 40(4):284–290.

Inui, A., Mifune, Y., Nishimoto, H., Mukohara, S., Fukuda, S., Kato, T., Furukawa, T., Tanaka, S., Kusunose, M., Takigami, S., Ehara, Y., and Kuroda, R. (2023). Detection of elbow ocd in the ultrasound image by artificial intelligence using yolov8. Applied Sciences, 13(13).

Jha, D., Smedsrud, P. H., Riegler, M. A., Halvorsen, P., de Lange, T., Johansen, D., and Johansen, H. D. (2020). Kvasir-seg: A segmented polyp dataset. In Ro, Y. M., Cheng, W.-H., Kim, J., Chu, W.-T., Cui, P., Choi, J.-W., Hu, M.-C., and De Neve, W., editors, MultiMedia Modeling, pages 451–462, Cham. Springer International Publishing.

Jocher, G., Chaurasia, A., and Qiu, J. (2023). Ultralytics yolov8.

Keum, N. and Giovannucci, E. (2019). Global burden of colorectal cancer: emerging trends, risk factors and prevention strategies. Nat Rev Gastroenterol Hepatol, 16(12):713–732.

Lalinia, M. and Sahafi, A. (2023). Colorectal polyp detection in colonoscopy images using yolo-v8 network. Signal, Image and Video Processing.

Lee, S.-H., Park, Y.-K., Lee, D.-J., and Kim, K.-M. (2014). Colonoscopy procedural skills and training for new beginners. World J Gastroenterol, 20(45):16984–95.

Liu, X., Song, L., Liu, S., and Zhang, Y. (2021). A review of deep-learning-based medical image segmentation methods. Sustainability, 13(3).

Mei, J., Zhou, T., Huang, K., Zhang, Y., Zhou, Y., Wu, Y., and Fu, H. (2023). A survey on deep learning for polyp segmentation: Techniques, challenges and future trends. ArXiv, abs/2311.18373.

Minaee, S., Boykov, Y., Porikli, F., Plaza, A., Kehtarnavaz, N., and Terzopoulos, D. (2022). Image segmentation using deep learning: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(7):3523–3542.

Osama, M., Kumar, R., and Shahid, M. (2023). Empowering cardiologists with deep learning yolov8 model for accurate coronary artery stenosis detection in angiography images. In 2023 International Conference on IoT, Communication and Automation Technology (ICICAT), pages 1–6.

Pacal, I., Karaboga, D., Basturk, A., Akay, B., and Nalbantoglu, U. (2020). A comprehensive review of deep learning in colon cancer. Computers in Biology and Medicine, 126:104003.

Pandey, S., Chen, K.-F., and Dam, E. B. (2023). Comprehensive multimodal segmentation in medical imaging: Combining yolov8 with sam and hq-sam models. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, pages 2592–2598.

Rex, D. K., Cutler, C. S., Lemmel, G. T., Rahmani, E. Y., Clark, D. W., Helper, D. J., Lehman, G. A., and Mark, D. G. (1997). Colonoscopic miss rates of adenomas determined by back-to-back colonoscopies. Gastroenterology, 112(1):24–8.

Silva, J., Histace, A., Romain, O., Dray, X., and Granado, B. (2014). Toward embedded detection of polyps in wce images for early diagnosis of colorectal cancer. International Journal of Computer Assisted Radiology and Surgery, 9(2):283–293.

Sung, H., Ferlay, J., Siegel, R. L., Laversanne, M., Soerjomataram, I., Jemal, A., and Bray, F. (2021). Global cancer statistics 2020: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: A Cancer Journal for Clinicians, 71(3):209–249.

Terven, J. and Cordova-Esparza, D. (2023). A comprehensive review of yolo: From yolov1 and beyond.

Zhou, Z., Rahman Siddiquee, M. M., Tajbakhsh, N., and Liang, J. (2018). Unet++: A nested u-net architecture for medical image segmentation. In Stoyanov, D., Taylor, Z., Carneiro, G., Syeda-Mahmood, T., Martel, A., Maier-Hein, L., Tavares, J. M. R., Bradley, A., Papa, J. P., Belagiannis, V., Nascimento, J. C., Lu, Z., Conjeti, S., Moradi, M., Greenspan, H., and Madabhushi, A., editors, Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, pages 3–11, Cham. Springer International Publishing.