To address the challenge of balancing segmentation accuracy and complexity in existing segmentation methods, a novel lightweight colorectal polyp image segmentation network, MCANet(Mamba and convolutional attention network), is proposed. The core of this network lies in a multiscale convolutional attention module cascading spatial and channel attention by fusing multiscale features in order to reduce the gap between shallow and deep features. In addition, a parallel Mamba module is introduced to improve the computational efficiency by utilizing parallelized computation. Experimental results on three public datasets show that the proposed method outperforms other state-of-the-art methods in terms of effectiveness and generalization, enabling it to pinpoint the abnormal portions in the colorectum and provide clinicians with critical decision support, which reduces the risk of polyp cancer.
[1] WANG D C, CHEN S J, SUN X Z, et al. AFP-mask: anchor-free polyp instance segmentation in colonoscopy[J]. IEEE J Biomed Health Inform, 2022, 26(7): 2995-3006. DOI:10.1109/JBHI.2022.3147686.
[2] WANG M, AN X W, PEI Z C, et al. An efficient multi-task synergetic network for polyp segmentation and classification[J]. IEEE J Biomed Health Inform, 2024, 28(3): 1228-1239. DOI:10.1109/JBHI.2023.3273728.
[3] YUE G H, HAN W W, JIANG B, et al. Boundary constraint network with cross layer feature integration for polyp segmentation[J]. IEEE J Biomed Health Inform, 2022, 26(8): 4090-4099. DOI:10.1109/JBHI.2022.3173948.
[4] JIN Q C, HOU H Y, ZHANG G X, et al. FEGNet: a feedback enhancement gate network for automatic polyp segmentation[J]. IEEE J Biomed Health Inform, 2023, 27(7): 3420-3430. DOI:10.1109/JBHI.2023.3272168.
[5] 陆秋, 邵铧泽, 张云磊.动态平衡多尺度特征融合的结直肠息肉分割[J].图学学报, 2023, 44(2): 225-232. DOI:10.11996/JG.j.2095-302X.2023020225.
[6] LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C] //2015 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Boston, USA, IEEE, 2015: 3431-3440. DOI:10.1109/CVPR.2015.7298965.
[7] RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[M] //Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015, Cham: Springer International Publishing, 2015: 234-241. DOI:10.1007/978-3-319-24574-4_28.
[8] XIAO B, HU J W, LI W S, et al. CTNet: contrastive transformer network for polyp segmentation[J]. IEEE Trans Cybern, 2024, 54(9): 5040-5053. DOI:10.1109/TCYB.2024.3368154.
[9] XIANG S Y, WEI L S, HU K F. Lightweight colon polyp segmentation algorithm based on improved DeepLabV3[J]. J Cancer, 2024, 15(1): 41-53. DOI:10.7150/jca.88684.
[10] WU H S, ZHAO Z B, ZHONG J F, et al. PolypSeg: a lightweight context-aware network for real-time polyp segmentation[J]. IEEE Trans Cybern, 2023, 53(4): 2610-2621. DOI:10.1109/TCYB.2022.3162873.
[11] CUI R S, YANG R Z, LIU F, et al. HD2A-Net: a novel dual gated attention network using comprehensive hybrid dilated convolutions for medical image segmentation[J]. Comput Biol Med, 2023, 152: 106384. DOI:10.1016/j.compbiomed.2022.106384.
[12] SANDLER M, HOWARD A, ZHU M L, et al. MobileNetV2: inverted residuals and linear bottlenecks[C] //2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition,Salt Lake City, USA, IEEE, 2018: 4510-4520. DOI:10.1109/CVPR.2018.00474.
[13] VÁZQUEZ D, BERNAL J, JAVIER SÁNCHEZ F, et al. A benchmark for endoluminal scene segmentation of colonoscopy images[J]. J Healthc Eng, 2017, 2017: 4037190. DOI:10.1155/2017/4037190.
[14] POGORELOV K, RANDEL K R, GRIWODZ C, et al. KVASIR: a multi-class image dataset for computer aided gastrointestinal disease detection[C] //Proceedings of the 8th ACM on Multimedia Systems Conference,ACM, 2017: 164-169. DOI:10.1145/3083187.3083212.
[15] SÁNCHEZ-PERALTA L F, PAGADOR J B, PICÓN A, et al. PICCOLO white-light and narrow-band imaging colonoscopic dataset: a performance comparative of models and datasets[J]. Appl Sci, 2020, 10(23): 8501. DOI:10.3390/app10238501.
[16] FAN D P, JI G P, ZHOU T, et al. PraNet: parallel reverse attention network for polyp segmentation[M] //Medical Image Computing and Computer Assisted Intervention-MICCAI 2020, Cham: Springer International Publishing, 2020, 263-273. DOI:10.1007/978-3-030-59725-2_26.
[17] ZHANG R F, LI G B, LI Z, et al. Adaptive context selection for polyp segmentation[M] //Medical Image Computing and Computer Assisted Intervention-MICCAI 2020, Cham: Springer International Publishing, 2020: 253-262. DOI:10.1007/978-3-030-59725-2_25.
[18] WEI J, HU Y W, ZHANG R M, et al. Shallow attention network for polyp segmentation[M] //Medical Image Computing and Computer Assisted Intervention-MICCAI 2021, Cham: Springer International Publishing, 2021: 699-708. DOI:10.1007/978-3-030-87193-2_66.
[19] LOU A G, GUAN S Y, KO H, et al. CaraNet: context axial reverse attention network for segmentation of small medical objects[C] //Medical Imaging 2022: Image Processing,San Diego, USA, SPIE, 2022: 81-92. DOI:10.1117/12.2611802.
[20] WU C, LONG C, LI S J, et al. MSRAformer: Multiscale spatial reverse attention network for polyp segmentation[J]. Comput Biol Med, 2022, 151: 106274. DOI:10.1016/j.compbiomed.2022.106274.
[21] YIN Z J, WEI R P, LIANG K M, et al. Semantic memory guided image representation for polyp segmentation[C] //ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP), Rhodes Island, Greece, IEEE, 2023: 1-5. DOI:10.1109/ICASSP49357.2023.10094302.
[22] RUAN J C, XIANG S C, XIE M Y, et al. MALUNet: a multi-attention and light-weight UNet for skin lesion segmentation[C] //2022 IEEE International Conference on Bioinformatics and Biomedicine(BIBM), Las Vegas, USA, IEEE, 2022: 1150-1156. DOI:10.1109/BIBM55620.2022.9995040.
[23] WU R K, LIU Y H, LIANG P C, et al. UltraLight VM-UNet: parallel vision mamba significantly reduces parameters for skin lesion segmentation[EB/OL]. 2024: 2403.20035. https://arxiv.org/abs/2403.20035v3. (
