Abstract
Polyp detection in its early stages can reduce the risk of colorectal cancer. Utilizing colonoscopy image segmentation enables expedited polyp diagnosis, further enhancing the effectiveness of detection. However, achieving accurate polyp image segmentation is a challenging task due to the variability in size, shape, and location of polyps. Expert experience directly affects this process, playing a pivotal role in determining its effectiveness. In this paper, we propose a novel method for automatic segmentation of polyp areas from colonoscopy images. Initially, we modified the UNet architecture using different backbones based on the transfer learning technique. In order to achieve better separation and localization of polyp regions, we adopt a hybrid LGB color space. The proposed color space merges the primary hues of green and blue with the Lightness component derived from CIE-L × a × b, resulting in a hybrid color representation. Furthermore, we propose a modified ResUNet architecture called Xcep-MResUNet, which uses the Xception backbone for feature extraction with an additional middle decoder to determine polyp areas. The middle decoder utilizes middle features to retrieve spatial information, while the ResUNet decoder utilizes high-level features. The proposed Xcep-MResUNet architecture combines the proposed middle decoder features with the ResUNet decoder features to refine the polyp area. Evaluation of the proposed method using the Kvasir-SEG database shows that our proposed method achieves more accurate results compared to other ResUNet-based models. Finally, using the Ensemble learning technique, we integrated the output of the proposed Xcep-MResUNet architecture with two of the best architectures based on modified UNet. The segmentation results of the proposed method were evaluated using the Dice similarity coefficient, IOU, sensitivity, and positive predictive value criteria. The corresponding values for these criteria were 0.8890, 0.8249, 0.9108, and 0.8992, respectively. Furthermore, we have performed additional experiments to check the generalizability capability of the proposed architecture on the CVC-ClinicDB dataset. The results show a good performance of the proposed Ensemble models with respect to conventional methods.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-024-19703-w/MediaObjects/11042_2024_19703_Fig1_HTML.jpg)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-024-19703-w/MediaObjects/11042_2024_19703_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-024-19703-w/MediaObjects/11042_2024_19703_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-024-19703-w/MediaObjects/11042_2024_19703_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-024-19703-w/MediaObjects/11042_2024_19703_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-024-19703-w/MediaObjects/11042_2024_19703_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-024-19703-w/MediaObjects/11042_2024_19703_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-024-19703-w/MediaObjects/11042_2024_19703_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-024-19703-w/MediaObjects/11042_2024_19703_Fig9_HTML.png)
References
Asplund J, Kauppila JH, Mattsson F, Lagergren J (2018) Survival trends in gastric adenocarcinoma: a population-based study in Sweden. Ann Surg Oncol 25:2693–2702
Siegel RL, Miller KD, Goding Sauer A, Fedewa SA, Butterly LF, Anderson JC et al (2020) Colorectal cancer statistics, 2020. CA Cancer J Clin 70(3):145–164
Franz M, Scholz M, Henze I, Röckl S, Gomez LI (2013) Detection of colon polyps by a novel, polymer pattern-based full blood test. J Transl Med 11(1):1–9
Yang K, Chang S, Tian Z, Gao C, Du Y, Zhang X et al (2022) Automatic polyp detection and segmentation using shuffle efficient channel attention network. Alexandria Eng J 61(1):917–926
Stoitsis J, Valavanis I, Mougiakakou SG, Golemati S, Nikita A, Nikita KS (2006) Computer aided diagnosis based on medical image processing and artificial intelligence methods. Nuclear Instr Methods Phys Res Sec A: Accelerators, Spectrometers, Detectors and Associated Equipment 569(2):591–595
Riegler M, Lux M, Griwodz C, Spampinato C, de Lange T, Eskeland SL et al (2016) Multimedia and medicine: teammates for better disease detection and survival. In: Proceedings of the 24th ACM international conference on multimedia, pp 968–977
Pham DL, Xu C, Prince JL (2000) Current methods in medical image segmentation. Annu Rev Biomed Eng 2(1):315–337
Jha D, Smedsrud PH, Riegler MA, Halvorsen P, de Lange T, Johansen D, Johansen HD (2020) Kvasir-seg: a segmented polyp dataset. In: In MultiMedia modeling: 26th international conference, MMM 2020, Daejeon, South Korea, January 5–8, 2020, proceedings, part II 26. Springer international publishing, pp 451–462
Gupta N, Bhatele P, Khanna P (2019) Glioma detection on brain MRIs using texture and morphological features with ensemble learning. Biomed Signal Process Ctrl 47:115–125
Todd C, Kirillov M, Tarabichi M, Naghdy F, Naghdy G (2009) An analysis of medical image processing methods for segmentation of the inner ear. University of Wollongong
Rahima Z, Ahror B, Basel S, Douraied BS, Souhil T (2018) Segmentation of low-grade gliomas based on the growing region and level sets techniques. In: 2018 4th international conference on advanced Technologies for Signal and Image Processing (ATSIP). IEEE, pp 1–5
Li Q, Gao Z, Wang Q, **a J, Zhang H, Zhang, Het al. (2018) Glioma segmentation with a unified algorithm in multimodal MRI images. IEEE Access 6:9543–9553
Haque IRI, Neubert J (2020) Deep learning approaches to biomedical image segmentation. Inform Med Unlocked 18:100297
Rathod J, Waghmode V, Sodha A, Bhavathankar P (2018) Diagnosis of skin diseases using convolutional neural networks. In: 2018 second international conference on electronics, communication and aerospace technology (ICECA). IEEE, pp 1048–1051
Chen S, Urban G, Baldi P (2022) Weakly supervised polyp segmentation in colonoscopy images using deep neural networks. J Imaging 8(5):121
Ahsan, M. M., Luna, S. A., & Siddique, Z. (2022). Machine-learning-based disease diagnosis: a comprehensive review. In healthcare (Vol. 10, no. 3, p. 541). MDPI.
Shen H, Zhang J, Zheng W (2017) Efficient symmetry-driven fully convolutional network for multimodal brain tumor segmentation. In: 2017 IEEE international conference on image processing (ICIP). IEEE, pp 3864–3868
Li L, Chen Y, Shen Z, Zhang X, Sang J, Ding Y et al (2020) Convolutional neural network for the diagnosis of early gastric cancer based on magnifying narrow band imaging. Gastric Cancer 23:126–132
Pereira S, Pinto A, Alves V, Silva CA (2016) Brain tumor segmentation using convolutional neural networks in MRI images. IEEE Trans Med Imaging 35(5):1240–1251
Havaei M, Davy A, Warde-Farley D, Biard A, Courville A, Bengio Y et al (2017) Brain tumor segmentation with deep neural networks. Med Image Anal 35:18–31
Hussain S, Anwar SM, Majid M (2018) Segmentation of glioma tumors in brain using deep convolutional neural network. Neurocomputing 282:248–261
Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: In medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18. Springer international publishing, pp 234–241
Zhang K, Sun M, Han TX, Yuan X, Guo L, Liu T (2017) Residual networks of residual networks: multilevel residual networks. IEEE Transactions on Circuits and Systems for Video Technology 28(6):1303–1314
Jha D, Smedsrud PH, Riegler MA, Johansen D, De Lange T, Halvorsen P, Johansen HD (2019) Resunet++: an advanced architecture for medical image segmentation. In: 2019 IEEE international symposium on multimedia (ISM). IEEE, pp 225–2255
Jha D, Ali S, Tomar NK, Johansen HD, Johansen D, Rittscher J et al (2021) Real-time polyp detection, localization and segmentation in colonoscopy using deep learning. IEEE Access 9:40496–40510
Mahmud T, Paul B, Fattah SA (2021) PolypSegNet: a modified encoder-decoder architecture for automated polyp segmentation from colonoscopy images. Comput Biol Med 128:104119
Huang, C. H., Wu, H. Y., & Lin, Y. L. (2021). Hardnet-mseg: a simple encoder-decoder polyp segmentation neural network that achieves over 0.9 mean dice and 86 fps. https://arxiv.org/abs/2101.07172.
Fan DP, Ji GP, Zhou T, Chen G, Fu H, Shen J, Shao L (2020) Pranet: parallel reverse attention network for polyp segmentation. In: International conference on medical image computing and computer-assisted intervention. Springer International Publishing, Cham, pp 263–273
Tomar NK, Jha D, Ali S, Johansen HD, Johansen D, Riegler MA, Halvorsen P (2021) DDANet: dual decoder attention network for automatic polyp segmentation. In: In pattern recognition. ICPR international workshops and challenges: virtual event, January 10-15, 2021, proceedings, part VIII. Springer international publishing, pp 307–314
Rauniyar S, Jha VK, Jha RK, Jha D, Rauniyar A (2021) Improving polyp segmentation in colonoscopy using deep learning. Nordic Machine Intell 1(1):35–37
Elmeslimany EM, Kishk SS, Altantawy DA (2024) Ψnet: a parallel network with deeply coupled spatial and squeezed features for segmentation of medical images. Multimedia Tools Appl 83(8):24045–24082
Wu C, Long C, Li S, Yang J, Jiang F, Zhou R (2022) MSRAformer: multiscale spatial reverse attention network for polyp segmentation. Comput Biol Med 151:106274
Jain Y, Saxena V, Mittal S (2022) Ensembling deep learning and CIELAB color space model for fire detection from UAV images. In: Proceedings of the second international conference on AI-ML systems, pp 1–9
Niranjana KK, Devi MK (2015) RGB to lab transformation using image segmentation. Image 3(11)
Lakio S, Heinämäki J, Yliruusi J (2010) Colorful drying. Aaps Pharmscitech 11:46–53
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Proces Syst 25
Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition https://arxiv.org/abs/1409.1556.
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4700–4708
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., ... & Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. https://arxiv.org/abs/1704.04861.
Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC (2018) Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4510–4520
Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2818–2826
Tan M, Le Q (2019) Efficientnet: rethinking model scaling for convolutional neural networks. In: International conference on machine learning. PMLR, pp 6105–6114
Chollet F (2017) Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1251–1258
Zhang Z, Liu Q, Wang Y (2018) Road extraction by deep residual u-net. IEEE Geosci Remote Sens Lett 15(5):749–753
Salem MH, Li Y, Liu Z, AbdelTawab AM (2023) A transfer learning and optimized CNN based maritime vessel classification system. Appl Sci 13(3):1912
Large J, Lines J, Bagnall A (2019) A probabilistic classifier ensemble weighting scheme based on cross-validated accuracy estimates. Data Min Knowl Disc 33(6):1674–1709
Dubey SR, Singh SK, Chaudhuri BB (2022) Activation functions in deep learning: a comprehensive survey and benchmark. Neurocomputing 503:92–108
Bernal J, Sánchez FJ, Fernández-Esparrach G, Gil D, Rodríguez C, Vilariño F (2015) WM-DOVA maps for accurate polyp highlighting in colonoscopy: validation vs. saliency maps from physicians. Comput Med Imaging Graph 43:99–111
Dawod AY, Phaphuangwittayakul A (2021) Adaptive image segmentation for traumatic brain Haemorrhage. TEM J 10(3):1476
Funding
No organization funded this research.
Author information
Authors and Affiliations
Contributions
M. Aghalari designed the model, implemented the research, and wrote the original version of the draft. H. Khalghi Bezaki validated the methodology and reviewed the final version.
Corresponding author
Ethics declarations
Competing interests
The authors declare that they have no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Aghalari, M., Bizaki, H.K. Enhancing of polyp image segmentation in colonoscopy images: a comprehensive approach using modified UNet, hybrid color space, and ensemble learning. Multimed Tools Appl (2024). https://doi.org/10.1007/s11042-024-19703-w
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11042-024-19703-w