Abstract：Polycystic ovary syndrome (PCOS) is a disease that seriously endangers women′s health. Aiming to solve the problem of low contrast in the targeted area and high background noise in PCOS ultrasound images, a segmentation method of polycystic ovary images based on improved U-Net network was proposed in this paper. Firstly, the PCOS images were preprocessed to reduce the influence of speckle noise and shadows; then, redundant low-frequency feature maps were reduced by octave convolution module and feature fusion is performed; then, the hierarchical residual skip connection module was used to compensate for U-Net semantic gap between encoder and decoder; secondly, experiments were performed using PCOS ultrasound image dataset; finally, validation experiments were performed using ISIC2018, a public dataset containing 2 594 skin lesion images. The proposed method achieved a segmentation accuracy of 88.42% on the PCOS ultrasound image dataset, which was 4.24% higher than that of U-Net; and achieved a segmentation accuracy of 97.5% on the ISIC2018 dataset. The experimental results showed that the proposed method not only improved the segmentation of polycystic ovarian vesicles, but also had better performance in terms of robustness, which could also be referred to other medical image segmentation fields.
[1] Saravanan A, Sathiamoorthy S. Detection of polycystic ovarian syndrome: a literature Survey[J]. Asian Journal of Engineering and Applied Technology, 2018, 7(2): 46-51. [2] Lujan ME, Jarrett BY, Brooks ED, et al. Updated ultrasound criteria for polycystic ovary syndrome: reliable thresholds for elevated follicle population and ovarian volume[J]. Human Reproduction, 2013, 28(5): 1361-1368. [3] Potocnik B, Zazula D. Improved prediction-based ovarian follicle detection from a sequence of ultrasound images[J]. Computer Methods and Programs in Biomedicine, 2003, 70(3): 199-213. [4] Saranya R, Maheswari SU. A literature review on computer assisted detection of follicles in ultrasound images of ovary[J]. International Journal of Computer Applications, 2012, 48(12): 39-40. [5] Niu Qiang, Huang Xinjian. An improved fuzzy C-means clustering algorithm based on PSO[J]. J Softw, 2011, 6(5): 873-879. [6] Purnama B, Wisesti UN, Nhita F, et al. A classification of polycystic ovary Syndrome based on follicle detection of ultrasound images[C]//2015 3rd International Conference on Information and Communication Technology (ICoICT). Nusa Dua:IEEE, 2015: 396-401. [7] Isah OR, Usman AD, Tekanyi AM. A review on computer assisted follicle detection techniques and polycystic ovarian syndrome (PCOS) diagnostic systems[J]. International Journal of Computer Trends and Technology, 2015, 28(1):41-45. [8] 邓寅晖, 汪源源, 陈萍. 超声图像多囊卵巢分割及其在自动检测中的应用[J]. 中国生物医学工程学报, 2009, 28(2): 199-204. [9] 田萱, 王亮, 丁琪. 基于深度学习的图像语义分割方法综述[J]. 软件学报, 2019, 30(2): 440-468. [10] Badrinarayanan V, Kendall A, Cipolla R. Segnet: a deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12): 2481-2495. [11] Shelhamer E, Long J, Darrell T. Fully Convolutional Networks for Semantic Segmentation [J]. IEEE Trans Pattern Anal Mach Intell, 2017,39(4):640-651. [12] Thufailah IF, Adiwijaya K, Wisesty UN, et al. An implementation of Elman neural network for polycystic ovary classification based on ultrasound images [J]. Journal of Physics Conference, 2018, 971(1): 012016. [13] Cahyono B, Mubarok MS, Wisesty UN. An implementation of convolutional neural network on PCO classification based on ultrasound image[C]//2017 5th International Conference on Information and Communication Technology (ICoIC7). Melaka: IEEE, 2017: 1-4. [14] Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation [C]//International Conference on Medical Image Computing and Computer-assisted Intervention. Munich: Springer, 2015: 234-241. [15] Wu J, Chen EZ, Rong R, et al. Skin lesion segmentation with C-UNet [C]//2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Berlin: IEEE, 2019: 2785-2788. [16] Liu Wei, Deng Xiaojie, Shi Heng. Research on algorithm of PSO in image segmentation of cement-based[C]//2016 7th International Conference on Cloud Computing and Big Data (CCBD). Macau: IEEE, 2016: 380-384. [17] Chen Y, Fan H, Xu B, et al. Drop an octave: reducing spatial redundancy in convolutional neural networks with octave convolution[C]// 2019 IEEE/CVF International Conference on Computer Vision (ICCV). Seoul: IEEE, 2019:3434-3443. [18] Lindeberg T. Scale-space theory: a basic tool for analyzing structures at different scales[J]. Journal of Applied Statistics, 1994, 21(1-2): 225-270. [19] Ibtehaz N, Rahman MS. MultiResUNet: rethinking the U-Net architecture for multimodal biomedical image segmentation[J]. Neural Networks, 2020, 121: 74-87. [20] Zhou Zongwei, Rahman Siddiquee MM, Tajbakhsh N, et al. Unet++: a nested u-net architecture for medical image segmentation[M]//Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Cham: Springer, 2018: 3-11. [21] Li Yuexiang, Shen Linlin. Skin lesion analysis towards melanoma detection using deep learning network[J]. Sensors, 2018, 18(2): 556. [22] Yuan Yading, Lo YC. Improving dermoscopic image segmentation with enhanced convolutional-deconvolutional networks[J]. IEEE Journal of Biomedical and Health Informatics, 2017, 23(2): 519-526. [23] 齐永锋, 侯璐璐, 段友放. 基于DenseNet-BC网络的皮肤镜下皮肤损伤分割[J]. 计算机工程与科学, 2020, 306(6):113-120. [24] Huang Gao, Liu Zhuang, Van Der Maaten L, et al. Densely connected convolutional networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 2261-2269.
