Abstract
Deep convolutional neural network (DCNN) models have been widely used to diagnose skin lesions, and some of them have achieved diagnostic results comparable to or even better than dermatologists. Most publicly available skin lesion datasets used to train DCNN were dermoscopic images. Expensive dermoscopic equipment is rarely available in rural clinics or small hospitals in remote areas. Therefore, it is of great significance to rely on clinical images for computer-aided diagnosis of skin lesions. This paper proposes an improved dual-branch fusion network called CR-Conformer. It integrates a DCNN branch that can effectively extract local features and a Transformer branch that can extract global features to capture more valuable features in clinical skin lesion images. In addition, we improved the DCNN branch to extract enhanced features in four directions through the convolutional rotation operation, further improving the classification performance of clinical skin lesion images. To verify the effectiveness of our proposed method, we conducted comprehensive tests on a private dataset named XJUSL, which contains ten types of clinical skin lesions. The test results indicate that our proposed method reduced the number of parameters by 11.17 M and improved the accuracy of clinical skin lesion image classification by 1.08%. It has the potential to realize automatic diagnosis of skin lesions in mobile devices.
Graphical Abstract
Similar content being viewed by others
References
Yue G, Wei P, Zhou T et al (2022) Toward multicenter skin lesion classification using deep neural network with adaptively weighted balance loss. IEEE Trans Med Imaging 42(1):119–131
Vestergaard M, Macaskill P, Holt P, Menzies S (2008) Dermoscopy compared with naked eye examination for the diagnosis of primary melanoma: a meta-analysis of studies performed in a clinical setting. Br J Dermatol 159(3):669–676
Feng H, Berk-Krauss J, Feng PW, Stein JA (2018) Comparison of dermatologist density between urban and rural counties in the United States. JAMA Dermatol 154(11):1265–1271
Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M et al (2017) A survey on deep learning in medical image analysis. Med Image Anal 42:60–88
Adegun A, Viriri S (2021) Deep learning techniques for skin lesion analysis and melanoma cancer detection: a survey of state-of-the-art. Artif Intell Rev 54(2):811–841
Yang J, Sun X, Liang J, and Rosin P L (2018) Clinical skin lesion diagnosis using representations inspired by dermatologist criteria[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1258–1266
Satheesha T, Satyanarayana F, Prasad MG, Dhruve KD (2017) Melanoma is skin deep: a 3D reconstruction technique for computerized dermoscopic skin lesion classification. IEEE J Transl Eng Health Med 5:1–17
Gessert N, Sentker T, Madesta F, Schmitz R, Kniep H, Baltruschat I et al (2019) Skin lesion classification using CNNs with patch-based attention and diagnosis-guided loss weighting. IEEE Trans Biomed Eng 67(2):495–503
Xie Y, Zhang J, Xia Y, Shen C (2020) A mutual bootstrapping model for automated skin lesion segmentation and classification. IEEE Trans Med Imaging 39(7):2482–2493
Yuan Y, Chao M, Lo YC (2017) Automatic skin lesion segmentation using deep fully convolutional networks with Jaccard distance. IEEE Trans Med Imaging 36(9):1876–1886
Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM et al (2017) Dermatologist-level classification of skin cancer with deep neural networks. Nature 542(7639):115–118
Liu Y, Jain A, Eng C, Way DH, Lee K, Bui P et al (2020) A deep learning system for differential diagnosis of skin diseases[J]. Nat Med 26(6):900–908
Pan SJ, Yang Q (2009) A survey on transfer learning[J]. IEEE Trans Knowl Data Eng 22(10):1345–1359
Kawahara J, Hamarneh G (2016) Multi-resolution-tract CNN with hybrid pretrained and skin-lesion trained layers[C]//International workshop on machine learning in medical imaging. Springer, Cham, pp 164–171
Simonyan K, and Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
He K, Zhang X, Ren S, and Sun J (2016) Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 770–778
Hu J, Shen L, and Sun G (2018) Squeeze-and-excitation networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 7132–7141
Zhang J, Xie Y, Xia Y, Shen C (2019) Attention residual learning for skin lesion classification. IEEE Trans Med Imaging 38(9):2092–2103
Wei Z, Li Q, Song H (2022) Dual attention based network for skin lesion classification with auxiliary learning. Biomed Signal Process Control 74:103549
Yap J, Yolland W, Tschandl P (2018) Multimodal skin lesion classification using deep learning. Exp Dermatol 27(11):1261–1267
Kawahara J, Daneshvar S, Argenziano G et al (2018) Seven-point checklist and skin lesion classification using multitask multimodal neural nets. IEEE J Biomed Health Inform 23(2):538–546
Bi L, Feng DD, Fulham M et al (2020) Multi-label classification of multi-modality skin lesion via hyper-connected convolutional neural network. Pattern Recogn 107:107502
Ge Z,Demyanov S, Chakravorty R, et al. (2017) Skin disease recognition using deep saliency features and multimodal learning of dermoscopy and clinical images[C]//Medical Image Computing and Computer Assisted Intervention− MICCAI 2017: 20th International Conference, Quebec City, QC, Canada, September 11-13, 2017, Proceedings, Part III 20. Springer International Publishing 250-258
Wang Y, Feng Y, Zhang L et al (2022) Adversarial multimodal fusion with attention mechanism for skin lesion classification using clinical and dermoscopic images. Med Image Anal 81:102535
Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, et al. (2020) An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929
Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, et al. (2021) Swin transformer: hierarchical vision transformer using shifted windows[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 10012–10022
Wang W, Xie E, Li X, Fan D P, Song K, Liang D, et al. Pyramid vision transformer: a versatile backbone for dense prediction without convolutions[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021: 568–578
Yue G, Han W, Jiang B et al (2022) Boundary constraint network with cross layer feature integration for polyp segmentation. IEEE J Biomed Health Inform 26(8):4090–4099
Yue G, Li S, Cong R et al (2023) Attention-guided pyramid context network for polyp segmentation in colonoscopy images. IEEE Trans Instrum Meas 72:1–13
Lei H, Liu W, Xie H et al (2021) Unsupervised domain adaptation based image synthesis and feature alignment for joint optic disc and cup segmentation. IEEE J Biomed Health Inform 26(1):90–102
Wang L, Zhang L, Shu X et al (2023) Intra-class consistency and inter-class discrimination feature learning for automatic skin lesion classification. Med Image Anal 85:102746
Nakai K, Chen YW, Han XH (2022) Enhanced deep bottleneck transformer model for skin lesion classification. Biomed Signal Process Control 78:103997
MMCV Contributors. MMCV: OpenMMLab computer vision foundation. https://github.com/open-mmlab/mmcv. Accessed Oct 14 2022
Selvaraju R R, Cogswell M, Das A, Vedantam R, Parikh D, and Batra D (2017) Grad-cam: visual explanations from deep networks via gradient-based localization[C]//Proceedings of the IEEE international conference on computer vision. 618–626
Funding
This work is partially supported by Xinjiang Uygur Autonomous Region Key R & D program under Grant 2021B03001-4 and National Natural Science Foundation of China 62362061.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Dezhi Zhang and Aolun Li have contributed equally to this work, should be regarded as co-first authorship.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhang, D., Li, A., Wu, W. et al. CR-Conformer: a fusion network for clinical skin lesion classification. Med Biol Eng Comput 62, 85–94 (2024). https://doi.org/10.1007/s11517-023-02904-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-023-02904-0