Colorectal cancer is a significant public health problem worldwide, and early detection is very necessary. However, the miss rate during routine colonoscopy examinations is very high, leading to undiagnosed polyps that can develop into colorectal cancer. Therefore, we proposed a novel architecture called Attention-based Dilated Network (DANet) for automatic polyp segmentation using convolutional neural networks (CNN). DANet uses a pre-trained ResNet50 proposed by He, Kaiming, et al [8] as an encoder and a Dilated Attention Convolution (DAC) block in between the encoder and decoder to learn a more robust feature representation. We evaluated DANet’s performance on four datasets namely KvasirSEG , CVC-ClinicDB , ETIS-Larib PolypDB and KvasirInstrument datasets and found that it outperformed state-of-the-art methods in terms of standard segmentation metrics, such as Jaccard score, F1 score, recall, accuracy, and F2 score. The superiority of DANet’s performance can be attributed to the effective combination of the pre-trained ResNet50 proposed by He, Kaiming, et al., [8] and the DAC block, which enables the network to learn long-range dependencies and focus on informative regions in the input image. This feature enables the network to segment the polyps accurately. In conclusion, the proposed DANet architecture is a promising solution for automatic polyp segmentation in the medical domain. Automated polyp segmentation methods such as DANet have the potential to improve detection rates and reduce miss rates, facilitating early detection and prevention of colorectal cancer, which can have a significant impact on public health.

The paper proposes a new architecture called Attention-based Dilated Network (DANet) that combines the strengths of pretrained ResNet50 [8] and a novel Dilated Attention Convolution (DAC) block. The DAC block employs multiple dilated convolution layers to expand the field of view, which allows the network to learn more global feature representations. The experiments conducted in the paper demonstrate that the proposed architecture achieves state-of-the-art performance on all four datasets used in the study. The high performance achieved on all three polyp segmentation datasets suggests that the proposed architecture can be adapted for clinical applications, particularly in computer-aided diagnosis (CADx). CADx is an area of research that aims to develop automated systems to aid medical professionals in making diagnostic decisions. The ability of the proposed architecture to accurately segment polyps indicates that it could be a useful tool for assisting in the detection and diagnosis of polyps in medical images. In the future, the authors suggest investigating unsupervised and semi-supervised learning approaches to better utilize the hidden capacity of unlabelled medical images. Unsupervised learning refers to the use of algorithms that can learn patterns in data without being explicitly trained on labelled data. Semi-supervised learning involves training a model using a combination of labelled and unlabelled data. By exploring these approaches, we will further improve the performance of the proposed architecture and expand its potential applications in clinical settings.

[1] Ronneberger, Olaf et al. ”U-net: Convolutional networks for biomedical image segmentation.” International Conference on Medical image computing and computer-assisted intervention. Springer, Cham, 2015. [2] Zhang, Zhengxin, et al. ”Road extraction by deep residual u-net.” IEEE Geoscience and Remote Sensing Letters 15.5 ,2018: 749-753. [3] Wu, H., Zhao et al.” A Lightweight Context-Aware Network for Real-Time Polyp Segmentation”. IEEE Transactions on Cybernetics. 2022. [4] Tomar, N. K., Jha, et al.”A feedback attention network for improved biomedical image segmentation”. IEEE Transactions on Neural Networks and Learning Systems. 2022. [5] Codella, Noel CF, et al. ”Skin lesion analysis toward melanoma detection: A challenge at the 2017 international symposium on biomedical imaging (isbi), hosted by the international skin imaging collaboration (isic).” IEEE 15th international symposium on biomedical imaging (ISBI 2018). IEEE, 2018. [6] Staal, Joes, et al. ”Ridge-based vessel segmentation in color images of the retina.” IEEE transactions on medical imaging 23.4 ,2004: 501-509. [7] Leufkens, A. M., et al. ”Factors influencing the miss rate of polyps in a back to back colonoscopy study.” Endoscopy 44.05 ,2012: 470-475. [8] He, Kaiming, et al. ”Deep residual learning for image recognition.” Proceedings of the IEEE conference on computer vision and pattern recognition. 2016. [8] Chen, Liang-Chieh, et al. ”Encoder-decoder with atrous separable convolution for semantic image segmentation.” Proceedings of the European conference on computer vision (ECCV). 2018. [9] Jha, Debesh, et al. ”Resunet++: An advanced architecture for medical image segmentation.” 2019 IEEE International Symposium on Multimedia (ISM). IEEE. [10] Hu, Jie, Li Shen, and Gang Sun. ”Squeeze-and-excitation networks.” Proceedings of the IEEE conference on computer vision and pattern recognition. 2018. [11] Zhou, Zongwei, et al. ”Unet++: A nested u-net architecture for medical image segmentation.” Deep learning in medical image analysis and multimodal learning for clinical decision support. Springer, Cham, 2018. 3-11. [12] .Fan, Deng-Ping, et al. ”Pranet: Parallel reverse attention network for polyp segmentation.” International conference on medical image computing and computer-assisted intervention. Springer, Cham, 2020. [13] Gao, Shang-Hua, et al. ”Res2net: A new multi-scale backbone architecture.” IEEE transactions on pattern analysis and machine intelligence 43.2 ,2019: 652-662. [14] .Bernal, Jorge, et al. ”WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians.” Computerized medical imaging and graphics 43 ,2015: 99-111. [15] Jha, Debesh, et al. ”Kvasir-seg: A segmented polyp dataset.” International Conference on Multimedia Modeling. Springer, Cham, 2020. [16] Silva, Juan, et al. ”Toward embedded detection of polyps in wce images for early diagnosis of colorectal cancer.” International journal of computer assisted radiology and surgery 9.2 ,2014: 283293. [17] Jha, Debesh, et al. ”Kvasir-instrument: Diagnostic and therapeutic tool segmentation dataset in gastrointestinal endoscopy.” International Conference on Multimedia Modeling. Springer, Cham, 2021. [18] Chen, Liang-Chieh, et al. ”Rethinking atrous convolution for semantic image segmentation.” arXiv preprint arXiv:1706.05587 ,2017. [19] Jie Hu, Li Shen, et al. “ Squeeze-and-Excitation Networks “ IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 7132-7141 [20] Debesh Jha, et al. “A Comprehensive Study on Colorectal Polyp Segmentation With ResUNet++, Conditional Random Field and Test-Time Augmentation”, IEEE Journal of Biomedical and Health Informatics, 2021 [21] Debesh Jha, Pia H. Smedsrud, et al. ,”ResUNet++: An Advanced Architecture for Medical Image Segmentation”, 2019 IEEE International Symposium on Multimedia (ISM), 2019 [22] Ayokunle O. Ige, Nikhil Kumar Tomar, Felix O. Aranuwa, Oluwafemi Oriola et al. “ConvSegNet: Automated Polyp Segmentation from Colonoscopy using Context Feature Refinement with Multiple Convolutional Kernel Sizes”, IEEE Access, 2023 [23] Nikhil Kumar Tomar, et al., “Automatic Polyp Segmentation with Multiple Kernel Dilated Convolution Network”, 2022 IEEE 35th International Symposium on Computer-Based Medical Systems (CBMS), 2022 [24] Zaka-Ud-Din Muhammad, Zhangjin Huang, Naijie Gu, Usman Muhammad. “DCANet: deep context attention network for automatic polyp segmentation”, The Visual Computer, 2022 [25] Yan Jin, Yibiao Hu, Zhiwei Jiang, Qiufu Zheng. “Polyp segmentation with convolutional MLP”, The Visual Computer, 2022 [26] Debesh Jha, Pia H. Smedsrud, Michael A. Riegler, Dag Johansen, Thomas De Lange, Pal Halvorsen, Havard D. Johansen. “ResUNet++: An Advanced Architecture for Medical Image Segmentation”, 2019 IEEE International Symposium on Multimedia (ISM), 2019