Abstract Dermoscopy image recognition can distinguish skin lesions and it is helpful for the early diagnosis of skin cancer. To enhance the efficiency of dermoscopy image recognition, an involutional capsule network(InvCNet) is proposed. InvCNet combines an involutional operation and a global attention mechanism(GAM), while the reconstruction part is removed. The involution operation provides rich minutiae to enhance the dermoscopy image features by fusing information of feature maps across channels. Meanwhile, GAM is employed to mitigate the loss of spatial information induced by the convolution and pooling operations and amplify the cross-dimensional interactions. Experiments on four public datasets demonstrate that InvCNet significantly reduces the number of network parameters while achieving superior performance on most datasets.
[1] ROGERS H W, WEINSTOCK M A, FELDMAN S R, et al. Incidence Estimate of Nonmelanoma Skin Cancer(Keratinocyte Carcinomas) in the U.S. Population, 2012. JAMA Dermatology, 2015, 151(10): 1081-1086. [2] ESTEVA A, KUPREL B, NOVOA R A, et al. Dermatologist-Level Classification of Skin Cancer with Deep Neural Networks. Nature, 2017, 542: 115-118. [3] BISSOTO A, VALLE E, AVILA S. GAN-Based Data Augmentation and Anonymization for Skin-Lesion Analysis: A Critical Review // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Washington, USA: IEEE, 2021: 1847-1856. [4] ZHAO C, SHUAI R J, MA L, et al. Dermoscopy Image Classification Based on StyleGAN and DenseNet201. IEEE Access, 2021, 9: 8659-8679. [5] DATTA S K, SHAIKH M A, SRIHARI S N, et al. Soft Attention Improves Skin Cancer Classification Performance // Proc of the 4th International Workshop on Interpretability of Machine Intelligence in Medical Image Computing and 1st International Workshop on Topological Data Analysis and Its Applications for Medical Data. Berlin, Germany: Springer, 2021: 13-23. [6] XIE Y T, ZHANG J P, XIA Y. Semi-Supervised Adversarial Model for Benign-Malignant Lung Nodule Classification on Chest CT. Medi-cal Image Analysis, 2019, 57: 237-248. [7] ZHANG J P, XIE Y T, WU Q, et al. Medical Image Classification Using Synergic Deep Learning. Medical Image Analysis, 2019, 54: 10-19. [8] TANG P, LIANG Q K, YAN X T, et al. GP-CNN-DTEL: Global-Part CNN Model with Data-Transformed Ensemble Learning for Skin Lesion Classification. IEEE Journal of Biomedical and Health Informatics, 2020, 24(10): 2870-2882. [9] ZHANG J P, XIE Y T, XIA Y, et al. Attention Residual Learning for Skin Lesion Classification. IEEE Transactions on Medical Imaging, 2019, 38(9): 2092-2103. [10] WAN Y C, CHENG Y S, SHAO M W. MSLANet: Multi-scale Long Attention Network for Skin Lesion Classification. Applied Intelligence, 2022, 53(10): 12580-12598. [11] YU Z, MAR V, ERIKSSON A,et al. End-to-End Ugly Duckling Sign Detection for Melanoma Identification with Transformers // Proc of the 24th International Conference on Medical Image Computing and Computer Assisted Intervention. Berlin, Germany: Sprin-ger, 2021: 176-184. [12] WU W J, MEHTA S, NOFALLAH S, et al. Scale-Aware Transformers for Diagnosing Melanocytic Lesions. IEEE Access, 2021, 9: 163526-163541. [13] XIE J S, WU Z Z, ZHU R J, et al. Melanoma Detection Based on Swin Transformer and SimAM // Proc of the IEEE 5th Information Technology, Networking, Electronic and Automation Control Conference. Washington, USA: IEEE, 2021: 1517-1521. [14] LIU Z, LIN Y T, CAO Y, et al. Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows // Proc of the IEEE/CVF International Conference on Computer Vision. Washington, USA: IEEE, 2021: 9992-10002. [15] ZHANG Y L, XIE F Y, CHEN J Q. TFormer: A Throughout Fusion Transformer for Multi-modal Skin Lesion Diagnosis. Computers in Biology and Medicine, 2023, 157. DOI: 10.1016/j.compbiomed.2023.106712. [16] PEDRO R, OLIVEIRA A L. Assessing the Impact of Attention and Self-Attention Mechanisms on the Classification of Skin Lesions // Proc of the International Joint Conference on Neural Networks. Washington, USA: IEEE, 2022. DOI: 10.1109/IJCNN55064.2022.9892274. [17] SABOUR S, FROSST N, HINTON G E. Dynamic Routing between Capsules // Proc of the 31st International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2017: 3859-3869. [18] AFSHAR P, PLATANIOTIS K N, MOHAMMADI A. BoostCaps: A Boosted Capsule Network for Brain Tumor Classification // Proc of the 42nd Annual International Conference of the IEEE Enginee-ring in Medicine and Biology Society. Washington, USA: IEEE, 2020: 1075-1079. [19] KWABENA P K, WEYORI B A, MIGHTY A A. Gabor Capsule Network for Plant Disease Detection. International Journal of Advanced Computer Science and Applications, 2020, 11(10): 388-395. [20] LONG F, PENG J J, SONG W T, et al. BloodCaps: A Capsule Network Based Model for the Multi-classification of Human Peripheral Blood Cells. Computer Methods and Programs in Biomedicine, 2021, 202. DOI: 10.1016/j.cmpb.2021.105972. [21] XIANG C Q, ZHANG L, TANG Y, et al. MS-CapsNet: A Novel Multi-scale Capsule Network. IEEE Signal Processing Letters, 2018, 25(12): 1850-1854. [22] XIAO H, RASUL K, VOLLGRAF R. Fashion-MNIST: A Novel Image Dataset for Benchmarking Machine Learning Algorithms[C/OL]. [2024-06-12].https://arxiv.org/pdf/1708.07747.pdf. [23] KRIZHEVSKY A. Learning Multiple Layers of Features from Tiny Images[C/OL]. [2024-06-12]. https://www.cs.toronto.edu/~kriz/learning-features-2009-TR.pdf. [24] RAJASEGARAN J, JAYASUNDARA V, JAYASEKARA S, et al. DeepCaps: Going Deeper with Capsule Networks // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2019: 10717-10725. [25] SHARIFI R, SHIRI P, BANIASADI A. PrunedCaps: A Case for Primary Capsules Discrimination // Proc of the 20th IEEE International Conference on Machine Learning and Applications. Washington, USA: IEEE, 2021: 1437-1442. [26] LAN Z L, CAI S B, HE X, et al. FixCaps: An Improved Capsules Network for Diagnosis of Skin Cancer. IEEE Access. 2022, 10: 76261-76267. [27] GOCERI E. Classification of Skin Cancer Using Adjustable and Fully Convolutional Capsule Layers. Biomedical Signal Processing and Control, 2023, 85. DOI: 10.1016/j.bspc.2023.104949. [28] 李励泽,张晨洁,杨晓慧,等.基于改进CapsNet的色素性皮肤病识别的研究.电子技术应用, 2020, 46(11): 60-64. (LI L Z, ZHANG C J, YANG X H, et al. Pigmented Skin Lesion Recognition Based on Improved CapsNet. Application of Electronic Technique, 2020, 46(11): 60-64.) [29] 林凯迪,杜洪波,王鸿菲,等.基于矩阵胶囊网络的皮肤镜图像黑色素分类识别算法及研究.湖北民族学院学报(自然科学版), 2021, 39(2): 175-179, 240. (LIN K D, DU H B, WANG H F, et al. Research on Classification and Recognition Algorithm of Melanoma in Dermoscopy Image Based on Matrix Capsule Network. Journal of Hubei Minzu University(Natural Science Edition), 2021, 39(2): 175-179, 240.) [30] 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) // Proc of the IEEE 15th International Symposium on Biomedical Imaging. Wa-shington, USA: IEEE, 2018: 168-172. [31] TSCHANDL P, ROSENDAHL C, KITTLER H. The HAM10000 Dataset, A Large Collection of Multi-source Dermatoscopic Images of Common Pigmented Skin Lesions. Scientific Data, 2018, 5(1). DOI: 10.1038/sdata.2018.161. [32] CODELLA N, ROTEMBERG V, TSCHANDL P, et al. Skin Lesion Analysis toward Melanoma Detection Skin Lesion Analysis toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration[C/OL]. [2024-06-12]. https://arxiv.org/abs/1902.03368. [33] LI D, HU J, WANG C H, et al. Involution: Inverting the Inherence of Convolution for Visual Recognition // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2021: 12316-12325. [34] LIU Y C, SHAO Z R, HOFFMANN N. Global Attention Mechanism: Retain Information to Enhance Channel-Spatial Interactions[C/OL]. [2024-06-12]. https://arxiv.org/pdf/2112.05561. [35] HUANG G, LIU Z, VAN DER MAATEN L, et al. Densely Connected Convolutional Networks // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2017: 2261-2269 [36] SZEGEDY C, VANHOUCKE V, IOFFE S, et al. Rethinking the Inception Architecture for Computer Vision // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2016: 2818-2826. [37] HE K M, ZHANG X Y, REN S Q, et al. Deep Residual Learning for Image Recognition // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2016: 770-778. [38] HOWARD A, SANDLER M, CHEN B, et al. Searching for MobileNetV3 // Proc of the IEEE/CVF International Conference on Computer Vision. Washington, USA: IEEE, 2019: 1314-1324. [39] DENG X D, YIN Q, GUO P. Efficient Structural Pseudoinverse Learning-Based Hierarchical Representation Learning for Skin Lesion Classification. Complex and Intelligent Systems, 2022, 8(2): 1445-1457. [40] WEI M J, WU Q W, JI H Y, et al. A Skin Disease Classification Model Based on DenseNet and ConvNeXt Fusion. Electronics, 2023, 12(2). DOI: 10.3390/electronics12020438. [41] WANG S T, YIN Y Q, WANG D J, et al. Interpretability-Based Multimodal Convolutional Neural Networks for Skin Lesion Diagnosis. IEEE Transactions on Cybernetics, 2022, 52(12): 12623-12637. [42] BIBI S, KHAN M A, SHAH J H, et al. MSRNet: Multiclass Skin Lesion Recognition Using Additional Residual Block Based Fine-Tuned Deep Models Information Fusion and Best Feature Selection. Diagnostics, 2023, 13. DOI: 10.3390/diagnostics13193063. [43] TALAYEH TABIBI S, NIKRAVANSGALMANI A, SABOOHI H. An Ensemble Classifier Based on Diverse Convolutional Neural Networks for Skin Lesions Classification. IEEE Access, 2024. DOI: 10.1109/ACCESS.2024.3442827. [44] KASSEM M A, HOSNY K M, FOUAD M M. Skin Lesions Classification into Eight Classes for ISIC 2019 Using Deep Convolutional Neural Network and Transfer Learning. IEEE Access, 2020, 8: 114822-114832. [45] NAEEM A, ANEES T, FIZA M, et al. SCDNet: A Deep Lear-ning-Based Framework for the Multiclassification of Skin Cancer Using Dermoscopy Images. Sensors, 2022, 22(15). DOI: 10.3390/s22155652. [46] GILANI S Q, SYED T, UMAIR M, et al. Skin Cancer Classification Using Deep Spiking Neural Network. Journal of Digital Imaging, 2023, 36(3): 1137-1147. [47] HOANG L, LEE S H, LEE E J, et al. Multiclass Skin Lesion Classification Using a Novel Lightweight Deep Learning Framework for Smart Healthcare. Applied Sciences, 2022, 12(5). DOI: 10.3390/app12052677. [48] HU J, SHEN L, SUN G. Squeeze-and-Excitation Networks // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Re-cognition. Washington, USA: IEEE, 2018: 7132-7141. [49] WOO S, PARK J, LEE J Y, et al. CBAM: Convolutional Block Attention Module // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2018: 3-19. [50] PARK J, WOO S, LEE J Y, et al. BAM: Bottleneck Attention Module[C/OL].[2024-06-12]. https://arxiv.org/pdf/1807.06514. [51] MISRA D, NALAMADA T, ARASANIPALAI A U, et al. Rotate to Attend: Convolutional Triplet Attention Module // Proc of the IEEE Winter Conference on Applications of Computer Vision. Washington, USA: IEEE, 2021: 3138-3147.
2024, Vol. 37 
