深度学习在皮肤病变图像分割中的研究综述

doi:10.3778/j.issn.1673-9418.2504019

摘要/Abstract

摘要： 皮肤病变种类繁多，临床表现复杂，涵盖从良性病变到恶性黑色素瘤等多种类型。这些病变的早期检测和准确分割对于皮肤癌的诊断和治疗至关重要，尤其是在恶性黑色素瘤等高风险病变的早期识别和定位中，能够显著提高患者的生存率。近年来，深度学习技术在皮肤病变图像分割领域取得了显著进展，极大地提高了分割的准确性和速度。对深度学习在皮肤病变图像分割中的研究展开综述。介绍了多种皮肤病变成像方式及常用的公开数据集，并对常用的评价指标进行了归纳。针对图像普遍存在的噪声和伪影问题，详细探讨了多种图像预处理和增强技术。深入阐述了基于深度学习的皮肤病变分割方法，涵盖了U-Net、Transformer、SAM、Mamba以及多网络融合模型。同时，综合对比了各网络模型的主要结构设计、优势、局限性及其分割性能。对该领域当前所面临的挑战和问题进行了剖析，并对未来的研究方向提出了展望，以期为皮肤病变图像分割领域的进一步发展提供参考。

关键词: 皮肤病变分割, 深度学习, 医学图像, 卷积神经网络

Abstract: Skin lesions exhibit a wide variety of types and complex clinical manifestations, ranging from benign conditions to malignant melanomas. Early detection and accurate segmentation of these lesions are critical for the diagnosis and treatment of skin cancer, particularly in the early identification and localization of high-risk lesions such as malignant melanoma, which can significantly improve patient survival rates. In recent years, deep learning techniques have achieved remarkable progress in skin lesion image segmentation, greatly enhancing both accuracy and efficiency. This paper presents a comprehensive review of deep learning research in the field of skin lesion image segmentation. First, various skin lesion imaging modalities and commonly used public datasets are introduced, along with a summary of standard evaluation metrics. Then, addressing the prevalent issues of noise and artifacts in images, a detailed discussion on various image preprocessing and augmentation techniques is provided. Subsequently, deep learning-based segmentation methods are elaborated, covering U-Net, Transformer, SAM (segment anything model), Mamba, and multi-network fusion models. The main architectural designs, advantages, limitations, and segmentation performance of these models are comparatively analyzed. Finally, the current challenges and issues in this field are examined, and future research directions are proposed, aiming to provide valuable insights for the continued development of skin lesion image segmentation.

Key words: skin lesions segmentation, deep learning, medical imaging, convolutional neural network

孟祥福, 李佳讯, 俞纯林, 鲁蕴萱. 深度学习在皮肤病变图像分割中的研究综述[J]. 计算机科学与探索, 2026, 20(1): 21-39.

MENG Xiangfu, LI Jiaxun, YU Chunlin, LU Yunxuan. Research Review of Deep Learning in Skin Lesions Image Segmentation[J]. Journal of Frontiers of Computer Science and Technology, 2026, 20(1): 21-39.

参考文献

[1] CELEBI M E, CODELLA N, HALPERN A. Dermoscopy image analysis: overview and future directions[J]. IEEE Journal of Biomedical and Health Informatics, 2019, 23(2): 474-478.
[2] ADEGUN A, VIRIRI S. Deep learning techniques for skin lesion analysis and melanoma cancer detection: a survey of state-of-the-art[J]. Artificial Intelligence Review, 2021, 54(2): 811-841.
[3] LI Y X, SHEN L L. Skin lesion analysis towards melanoma detection using deep learning network[J]. Sensors, 2018, 18(2): 556.
[4] JAIN S, JAGTAP V, PISE N. Computer aided melanoma skin cancer detection using image processing[J]. Procedia Computer Science, 2015, 48: 735-740.
[5] KHATTAR S, KAUR R. Computer assisted diagnosis of skin cancer: a survey and future recommendations[J]. Computers and Electrical Engineering, 2022, 104: 108431.
[6] ZAFAR M, SHARIF M I, SHARIF M I, et al. Skin lesion analysis and cancer detection based on machine/deep learning techniques: a comprehensive survey[J]. Life, 2023, 13(1): 146.
[7] KASSEM M A, HOSNY K M, DAMA?EVI?IUS R, et al. Machine learning and deep learning methods for skin lesion classification and diagnosis: a systematic review[J]. Diagnostics, 2021, 11(8): 1390.
[8] MA Z, TAVARES J M R S, JORGE R M N. A review on the current segmentation algorithms for medical images[C]//Proceedings of the 1st International Conference on Computer Imaging Theory and Applications, 2009: 135-140.
[9] RAJAB M I, WOOLFSON M S, MORGAN S P. Application of region-based segmentation and neural network edge detection to skin lesions[J]. Computerized Medical Imaging and Graphics, 2004, 28(1/2): 61-68.
[10] UL HUDA N, AMIN R, GILLANI S I, et al. Skin cancer malignancy classification and segmentation using machine learning algorithms[J]. JOM, 2023, 75(8): 3121-3135.
[11] LI Z W, LIU F, YANG W J, et al. A survey of convolutional neural networks: analysis, applications, and prospects[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(12): 6999-7019.
[12] RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C]//Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2015: 234-241.
[13] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Advances in Neural Information Processing Systems 30, 2017: 5998-6008.
[14] GU A, DAO T. Mamba: linear-time sequence modeling with selective state spaces[EB/OL]. [2025-01-15]. https://arxiv.org/abs/2312.00752.
[15] STOFA M M, ZULKIFLEY M A, ZAINURI M A A M. Skin lesions classification and segmentation: a review[J]. International Journal of Advanced Computer Science and Applications, 2021, 12(10).
[16] MINAEE S, BOYKOV Y, PORIKLI F, et al. Image segmentation using deep learning: a survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(7): 3523-3542.
[17] WANG R S, LEI T, CUI R X, et al. Medical image segmentation using deep learning: a survey[J]. IET Image Processing, 2022, 16(5): 1243-1267.
[18] HASAN M K, AHAMAD M A, YAP C H, et al. A survey, review, and future trends of skin lesion segmentation and classification[J]. Computers in Biology and Medicine, 2023, 155: 106624.
[19] HOSNY K M, ELSHOURA D, MOHAMED E R, et al. Deep learning and optimization-based methods for skin lesions segmentation: a review[J]. IEEE Access, 2023, 11: 85467-85488.
[20] MIRIKHARAJI Z, ABHISHEK K, BISSOTO A, et al. A survey on deep learning for skin lesion segmentation[J]. Medical Image Analysis, 2023, 88: 102863.
[21] SMITH L, MACNEIL S. State of the art in non-invasive imaging of cutaneous melanoma[J]. Skin Research and Technology, 2011, 17(3): 257-269.
[22] WANG S Q, RABINOVITZ H, KOPF A W, et al. Current technologies for the in vivo diagnosis of cutaneous melanomas[J]. Clinics in Dermatology, 2004, 22(3): 217-222.
[23] NIRMAL B. Dermatoscopy image characteristics and differences among commonly used standard dermatoscopes[J]. Indian Dermatology Online Journal, 2017, 8(3): 233-234.
[24] CAVALCANTI P G, SCHARCANSKI J. Macroscopic pigmented skin lesion segmentation and its influence on lesion classification and diagnosis[M]//Color medical image analysis. Dordrecht: Springer Netherlands, 2013: 15-39.
[25] WEN D, KHAN S M, XU A J, et al. Characteristics of publicly available skin cancer image datasets: a systematic review[J]. The Lancet Digital Health, 2022, 4(1): e64-e74.
[26] GUTMAN D, CODELLA N C F, CELEBI E, et al. Skin lesion analysis toward melanoma detection: a challenge at the international symposium on biomedical imaging (ISBI) 2016, hosted by the international skin imaging collaboration (ISIC)[EB/OL]. [2025-01-15]. https://arxiv.org/abs/1605. 01397.
[27] CODELLA N C F, GUTMAN D, CELEBI M E, 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)[C]//Proceedings of the 2018 IEEE 15th International Symposium on Biomedical Imaging. Piscataway: IEEE, 2018: 168-172.
[28] CODELLA N, ROTEMBERG V, TSCHANDL P, et al. Skin lesion analysis toward melanoma detection 2018: a challenge hosted by the international skin imaging collaboration (ISIC)[EB/OL]. [2025-01-15]. https://arxiv.org/abs/1902. 03368.
[29] TSCHANDL P, ROSENDAHL C, KITTLER H. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions[J]. Scientific Data, 2018, 5: 180161.
[30] COMBALIA M, CODELLA N C F, ROTEMBERG V, et al. BCN20000: dermoscopic lesions in the wild[EB/OL]. [2025-01-15]. https://arxiv.org/abs/1908.02288.
[31] ROTEMBERG V, KURTANSKY N, BETZ-STABLEIN B, et al. A patient-centric dataset of images and metadata for identifying melanomas using clinical context[J]. Scientific Data, 2021, 8: 34.
[32] MENDON?A T, FERREIRA P M, MARQUES J S, et al. PH2-a dermoscopic image database for research and benchmarking[C]//Proceedings of the 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Piscataway: IEEE, 2013: 5437-5440.
[33] BALLERINI L, FISHER R B, ALDRIDGE B, et al. A color and texture based hierarchical K-NN approach to the classification of non-melanoma skin lesions[M]//Color medical image analysis. Dordrecht: Springer Netherlands, 2013: 63-86.
[34] DANESHJOU R, YUKSEKGONUL M, CAI Z R, et al. SkinCon: a skin disease dataset densely annotated by domain experts for fine-grained model debugging and analysis[EB/OL]. [2025-01-16]. https://arxiv.org/abs/2302.00785.
[35] JOSEPH S, OLUGBARA O O. Preprocessing effects on performance of skin lesion saliency segmentation[J]. Diagnostics, 2022, 12(2): 344.
[36] KHATTAR S, KAUR R, GUPTA G. A review on preprocessing, segmentation and classification techniques for detection of skin cancer[C]//Proceedings of the 2023 2nd Edition of IEEE Delhi Section Flagship Conference. Piscataway: IEEE, 2023: 1-6.
[37] VOCATURO E, ZUMPANO E, VELTRI P. Image pre-processing in computer vision systems for melanoma detection[C]//Proceedings of the 2018 IEEE International Conference on Bioinformatics and Biomedicine. Piscataway: IEEE, 2018: 2117-2124.
[38] LI W, JOSEPH RAJ A N, TJAHJADI T, et al. Digital hair removal by deep learning for skin lesion segmentation[J]. Pattern Recognition, 2021, 117: 107994.
[39] GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial networks[J]. Communications of the ACM, 2020, 63(11): 139-144.
[40] CROITORU F A, HONDRU V, IONESCU R T, et al. Diffusion models in vision: a survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(9): 10850-10869.
[41] SILVEIRA M, NASCIMENTO J C, MARQUES J S, et al. Comparison of segmentation methods for melanoma diagnosis in dermoscopy images[J]. IEEE Journal of Selected Topics in Signal Processing, 2009, 3(1): 35-45.
[42] KOROTKOV K, GARCIA R. Computerized analysis of pigmented skin lesions: a review[J]. Artificial Intelligence in Medicine, 2012, 56(2): 69-90.
[43] LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2015: 3431-3440.
[44] AZAD R, AGHDAM E K, RAULAND A, et al. Medical image segmentation review: the success of U-net[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(12): 10076-10095.
[45] SIDDIQUE N, PAHEDING S, ELKIN C P, et al. U-Net and its variants for medical image segmentation: a review of theory and applications[J]. IEEE Access, 2021, 9: 82031-82057.
[46] ARORA R, RAMAN B, NAYYAR K, et al. Automated skin lesion segmentation using attention-based deep convolutional neural network[J]. Biomedical Signal Processing and Control, 2021, 65: 102358.
[47] OKTAY O, SCHLEMPER J, LE FOLGOC L, et al. Attention U-Net: learning where to look for the pancreas[EB/OL]. [2025-01-16]. https://arxiv.org/abs/1804.03999.
[48] CHENG D P, GAI J L, MAO Y Y, et al. EA-Net: research on skin lesion segmentation method based on U-Net[J]. Heliyon, 2023, 9(12): e22663.
[49] 魏坤, 沈记全, 赵艳梅. MAUNet: 用于皮肤病变分割的轻量级模型[J]. 中国医学物理学杂志, 2023, 40(5): 555-561.
WEI K, SHEN J Q, ZHAO Y M. MAUNet: a lightweight model for skin lesion segmentation[J]. Chinese Journal of Medical Physics, 2023, 40(5): 555-561.
[50] RUAN J C, XIANG S C, XIE M Y, et al. MALUNet: a multi-attention and light-weight UNet for skin lesion segmentation[C]//Proceedings of the 2022 IEEE International Conference on Bioinformatics and Biomedicine. Piscataway: IEEE, 2022: 1150-1156.
[51] RUAN J C, XIE M Y, GAO J S, et al. EGE-UNet: an efficient group enhanced UNet for skin lesion segmentation[C]//Proceedings of the 2023 International Conference on Medical Image Computing and Computer Assisted Intervention. Cham: Springer, 2023: 481-490.
[52] ZENG N Y, WU P S, WANG Z D, et al. A small-sized object detection oriented multi-scale feature fusion approach with application to defect detection[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 3507014.
[53] REN S J, PENG Y J. MFF-Net: multiscale feature fusion network for skin lesion segmentation[C]//Proceedings of the 2023 IEEE International Conference on Bioinformatics and Biomedicine. Piscataway: IEEE, 2023: 3473-3479.
[54] 王国凯, 张翔, 王顺芳. 多尺度和边界融合的皮肤病变区域分割网络[J]. 计算机科学与探索, 2024, 18(7): 1826-1837.
WANG G K, ZHANG X, WANG S F. Multi-scale and boundary fusion network for skin lesion regions segmentation[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(7): 1826-1837.
[55] SU R, ZHANG D Y, LIU J H, et al. MSU-Net: multi-scale U-Net for 2D medical image segmentation[J]. Frontiers in Genetics, 2021, 12: 639930.
[56] XU J H, TONG L Y. LB-UNet: a lightweight boundary-assisted UNet for skin lesion segmentation[C]//Proceedings of the 2024 International Conference on Medical Image Computing and Computer Assisted Intervention. Cham: Springer, 2024: 361-371.
[57] 白雪飞, 靳智超, 王文剑, 等. 融合边缘增强与多尺度注意力的皮肤病变分割[J]. 计算机科学, 2023, 50(4): 96-102.
BAI X F, JIN Z C, WANG W J, et al. Skin lesion segmentation combining boundary enhancement and multi-scale attention[J]. Computer Science, 2023, 50(4): 96-102.
[58] GU R, WANG L T, ZHANG L. DE-Net: a deep edge network with boundary information for automatic skin lesion segmentation[J]. Neurocomputing, 2022, 468: 71-84.
[59] KHAN S, NASEER M, HAYAT M, et al. Transformers in vision: a survey[J]. ACM Computing Surveys, 2022, 54(10s): 1-41.
[60] XIAO H G, LI L, LIU Q Y, et al. Transformers in medical image segmentation: a review[J]. Biomedical Signal Processing and Control, 2023, 84: 104791.
[61] KHAN R F, LEE B D, LEE M S. Transformers in medical image segmentation: a narrative review[J]. Quantitative Imaging in Medicine and Surgery, 2023, 13(12): 8747-8767.
[62] XIN C, LIU Z F, MA Y Z, et al. Transformer guided self-adaptive network for multi-scale skin lesion image segmentation[J]. Computers in Biology and Medicine, 2024, 169: 107846.
[63] HE X Z, TAN E L, BI H W, et al. Fully transformer network for skin lesion analysis[J]. Medical Image Analysis, 2022, 77: 102357.
[64] WANG J C, WEI L, WANG L S, et al. Boundary-aware transformers for skin lesion segmentation[C]//Proceedings of the 24th International Conference on Medical Image Computing and Computer Assisted Intervention. Cham: Springer, 2021: 206-216.
[65] LIU Z, LIN Y T, CAO Y, et al. Swin Transformer: hierarchical vision transformer using shifted windows[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 9992-10002.
[66] CAO H, WANG Y Y, CHEN J, et al. Swin-Unet: Unet-like pure transformer for medical image segmentation[C]//Proceedings of the 17th European Conference on Computer Vision. Cham: Springer, 2022: 205-218.
[67] AGHDAM E K, AZAD R, ZARVANI M, et al. Attention Swin U-Net: cross-contextual attention mechanism for skin lesion segmentation[C]//Proceedings of the 2023 IEEE 20th International Symposium on Biomedical Imaging. Piscataway: IEEE, 2023: 1-5.
[68] DU H, WANG J Z, LIU M, et al. SwinPA-Net: swin transformer-based multiscale feature pyramid aggregation network for medical image segmentation[J]. IEEE Transactions on Neural Networks and Learning Systems, 2024, 35(4): 5355-5366.
[69] WU H S, CHEN S H, CHEN G L, et al. FAT-Net: feature adaptive transformers for automated skin lesion segmentation[J]. Medical Image Analysis, 2022, 76: 102327.
[70] 陶惜婷, 叶青. 融合CNN和Transformer的并行双分支皮肤病灶图像分割[J]. 计算机应用研究, 2024, 41(8): 2554-2560.
TAO X T, YE Q. Parallel dual-branch image segmentation of skin lesions fusing CNN and Transformer[J]. Application Research of Computers, 2024, 41(8): 2554-2560.
[71] DING Y H, YI Z L, XIAO J T, et al. CTH-Net: a CNN and Transformer hybrid network for skin lesion segmentation[J]. iScience, 2024, 27(4): 109442.
[72] DONG Z W, LI J J, HUA Z. Transformer-based multi-attention hybrid networks for skin lesion segmentation[J]. Expert Systems with Applications, 2024, 244: 123016.
[73] ZHANG Y D, LIU H Y, HU Q. TransFuse: fusing transformers and CNNs for medical image segmentation[C]//Proceedings of the 24th International Conference on Medical Image Computing and Computer Assisted Intervention. Cham: Springer, 2021: 14-24.
[74] CHEN L F, LI J W, ZOU Y M, et al. ETU-Net: edge enhancement-guided U-Net with transformer for skin lesion segmentation[J]. Physics in Medicine and Biology, 2023, 69(1): 015001.
[75] CHEN B Z, LIU Y S, ZHANG Z, et al. TransAttUnet: multi-level attention-guided U-Net with transformer for medical image segmentation[J]. IEEE Transactions on Emerging Topics in Computational Intelligence, 2024, 8(1): 55-68.
[76] PAN S M, LIU X, XIE N D, et al. EG-TransUNet: a transformer-based U-Net with enhanced and guided models for biomedical image segmentation[J]. BMC Bioinformatics, 2023, 24(1): 85.
[77] KIRILLOV A, MINTUN E, RAVI N, et al. Segment anything[C]//Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2023: 3992-4003.
[78] ZHANG Y C, SHEN Z R, JIAO R S. Segment anything model for medical image segmentation: current applications and future directions[J]. Computers in Biology and Medicine, 2024, 171: 108238.
[79] ZHANG C H, LIU L, CUI Y W, et al. A comprehensive survey on segment anything model for vision and beyond[EB/OL]. [2025-01-17]. https://arxiv.org/abs/2305.08196.
[80] 孙兴, 蔡肖红, 李明, 等. 视觉大模型SAM在医学图像分割中的应用综述[J]. 计算机工程与应用, 2024, 60(17): 1-16.
SUN X, CAI X H, LI M, et al. Review of application of visual foundation model SAM in medical image segmentation[J]. Computer Engineering and Applications, 2024, 60(17): 1-16.
[81] HU M Z, LI Y H, YANG X F. SkinSAM: empowering skin cancer segmentation with segment anything model[EB/OL]. [2025-01-17]. https://arxiv.org/abs/2304.13973.
[82] JIANG Z K, CHENG D J, QIN Z Y, et al. TV-SAM: increasing zero-shot segmentation performance on multimodal medical images using GPT-4 generated descriptive prompts without human annotation[J]. Big Data Mining and Analytics, 2024, 7(4): 1199-1211.
[83] WU J D, JI W, LIU Y P, et al. Medical SAM adapter: adapting segment anything model for medical image segmentation[EB/OL]. [2025-01-17]. https://arxiv.org/abs/2304.12620.
[84] BANSAL S, MADISETTY S, REHMAN M Z U, et al. A comprehensive survey of mamba architectures for medical image analysis: classification, segmentation, restoration and beyond[EB/OL]. [2025-01-17]. https://arxiv.org/abs/2410. 02362.
[85] LIU Y, TIAN Y, ZHAO Y, et al. VMamba: visual state space model[C]//Advances in Neural Information Processing Systems 37, 2024: 103031-103063.
[86] ZOU S, ZHANG M Y, FAN B J, et al. SkinMamba: a precision skin lesion segmentation architecture with cross-scale global state modeling and frequency boundary guidance[EB/OL]. [2025-01-17]. https://arxiv.org/abs/2409.10890.
[87] RUAN J C, LI J C, XIANG S C. VM-UNet: vision mamba UNet for medical image segmentation[EB/OL]. [2025-01-17]. https://arxiv.org/abs/2402.02491.
[88] 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]. [2025-01-18]. https://arxiv.org/abs/2403.20035.
[89] WANG W, LUO Y W, WANG X. BEFNet: a hybrid CNN-mamba architecture for accurate skin lesion image segmentation[C]//Proceedings of the 2024 IEEE International Conference on Bioinformatics and Biomedicine. Piscataway: IEEE, 2024: 3795-3798.
[90] NGUYEN V T, PHAM V T, TRAN T T. AC-MambaSeg: an adaptive convolution and mamba-based architecture for enhanced skin lesion segmentation[C]//Computational Intelligence Methods for Green Technology and Sustainable Development. Cham: Springer, 2024: 13-26.
[91] YUAN C Y, ZHAO D F, AGAIAN S S. MUCM-Net: a mamba powered UCM-Net for skin lesion segmentation[EB/OL]. [2025-01-18]. https://arxiv.org/abs/2405.15925.