Objective We propose a new melanoma segmentation model, SG-UNet, to enhance the precision of melanoma segmentation in dermascopy images to facilitate early melanoma detection. Methods We utilized a U-shaped convolutional neural network, UNet, and made improvements to its backbone, skip connections, and downsampling pooling sections. In the backbone, with reference to the structure of VGG, we increased the number of convolutions from 10 to 13 in the downsampling part of UNet to achieve a deepened network hierarchy that allowed capture of more refined feature representations. To further enhance feature extraction and detail recognition, we replaced the traditional convolution the backbone section with self-calibrated convolution to enhance the model's ability to capture both spatial and channel dimensional features. In the pooling part, the original pooling layer was replaced by Haar wavelet downsampling to achieve more effective multi-scale feature fusion and reduce the spatial resolution of the feature map. The global attention mechanism was then incorporated into the skip connections at each layer to enhance the understanding of contextual information of the image. Results The experimental results showed that the SG-UNet model achieved significantly improved segmentation accuracy on ISIC 2017 and ISIC 2018 datasets as compared with other current state-of-the-art segmentation models, with Dice reached 92.41% and 86.62% and IoU reaching 92.31% and 86.48% on the two datasets, respectively. Conclusion The proposed model is capable of effective and accurate segmentation of melanoma from dermoscopy images.
MateenM, HayatS, ArshadF, et al. Hybrid deep learning framework for melanoma diagnosis using dermoscopic medical images[J]. Diagnostics, 2024, 14(19): 2242. doi:10.3390/diagnostics14192242
[2]
AliAR, LiJP, O'SheaSJ, et al. A deep learning based approach to skin lesion border extraction with a novel edge detector in dermoscopy images[C]//2019 International Joint Conference on Neural Networks (IJCNN). July 14-19, 2019, Budapest, Hungary. IEEE, 2019: 1-7. doi:10.1109/ijcnn.2019.8852134
[3]
AliAR, LiJP, YangG, et al. A machine learning approach to automatic detection of irregularity in skin lesion border using dermoscopic images[J]. PeerJ Comput Sci, 2020, 6: e268. doi:10.7717/peerj-cs.268
[4]
RonnebergerO, FischerP, BroxT. U-Net: convolutional networks for biomedical image segmentation[M]//Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015. Cham: Springer International Publishing, 2015: 234-41. doi:10.1007/978-3-319-24574-4_28
[5]
LongJ, ShelhamerE, DarrellT. Fully convolutional networks for semantic segmentation[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). June 7-12, 2015, Boston, MA, USA. IEEE, 2015: 3431-40. doi:10.1109/cvpr.2015.7298965
[6]
WangG, MaQS, LiYY, et al. A skin lesion segmentation network with edge and body fusion[J]. Appl Soft Comput, 2025, 170: 112683. doi:10.1016/j.asoc.2024.112683
[7]
WuHS, ChenSH, ChenGL, et al. FAT-Net: Feature adaptive transformers for automated skin lesion segmentation[J]. Med Image Anal, 2022, 76: 102327. doi:10.1016/j.media.2021.102327
LiuY, ShaoZ, HoffmannN. Global attention mechanism: Retain information to enhance channel-spatial interactions [J]. 2021, DOI:10.48550/arXiv.2112.05561 .
[10]
LiuJJ, HouQB, ChengMM, et al. Improving convolutional networks with self-calibrated convolutions[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 13-19, 2020, Seattle, WA, USA. IEEE, 2020: 10093-102. doi:10.1109/cvpr42600.2020.01011
[11]
XuGP, LiaoWT, ZhangX, et al. Haar wavelet downsampling: a simple but effective downsampling module for semantic segmentation[J]. Pattern Recognit, 2023, 143: 109819. doi:10.1016/j.patcog.2023.109819
[12]
NiuZY, ZhongGQ, YuH. A review on the attention mechanism of deep learning[J]. Neurocomputing, 2021, 452: 48-62. doi:10.1016/j.neucom.2021.03.091
[13]
UpadhyayAK, BhandariAK. Advances in deep learning models for resolving medical image segmentation data scarcity problem: a topical review[J]. Arch Comput Meth Eng, 2024, 31(3): 1701-19. doi:10.1007/s11831-023-10028-9
[14]
WooS, ParkJ, LeeJY, et al. CBAM: convolutional block attention module[M]//Computer Vision-ECCV 2018. Cham: Springer International Publishing, 2018: 3-19. doi:10.1007/978-3-030-01234-2_1
[15]
IoannouY, RobertsonD, CipollaR, et al. Deep roots: improving CNN efficiency with hierarchical filter groups[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). July 21-26, 2017, Honolulu, HI, USA. IEEE, 2017: 5977-86. doi:10.1109/cvpr.2017.633
[16]
PorwikP, LisowskaA. The haar–wavelet transform in digital image processing: its status and achievements[J]. Instit Comp Sci, 2004,13:79-98.
[17]
MakandarA, HalalliB. Image enhancement techniques using highpass and lowpass filters[J]. Int J Comput Appl, 2015, 109(14): 21-7. doi:10.5120/19256-0999
[18]
ZaynidinovH. Digital image processing with two-dimensional haar wavelets[J]. Int J Adv Trends Comput Sci Eng, 2020, 9(3): 2729-34. doi:10.30534/ijatcse/2020/38932020
[19]
CodellaNCF, GutmanD, CelebiME, 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]//2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018). April 4-7, 2018, Washington, DC, USA. IEEE, 2018: 168-72. doi:10.1109/isbi.2018.8363547
[20]
CodellaN, RotembergV, TschandlP, et al. Skin lesion analysis toward melanoma detection 2018: a challenge hosted by the international skin imaging collaboration (ISIC)[EB/OL]. 2019: 1902.03368. doi:10.48550/arXiv.1902.03368
[21]
JiangHY, DiaoZS, ShiTY, et al. A review of deep learning-based multiple-lesion recognition from medical images: classification, detection and segmentation[J]. Comput Biol Med, 2023, 157: 106726. doi:10.1016/j.compbiomed.2023.106726
[22]
SoomroTA, AfifiAJ, GaoJB, et al. Strided U-Net model: retinal vessels segmentation using dice loss[C]//2018 Digital Image Computing: Techniques and Applications (DICTA). December 10-13, 2018, Canberra, ACT, Australia. IEEE, 2018: 1-8. doi:10.1109/dicta.2018.8615770
[23]
ChengBW, GirshickR, DollárP, et al. Boundary IoU: improving object-centric image segmentation evaluation[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 20-25, 2021, Nashville, TN, USA. IEEE, 2021: 15329-37. doi:10.1109/cvpr46437.2021.01508
[24]
ShamirRR, DuchinY, KimJ, et al. Continuous dice coefficient: a method for evaluating probabilistic segmentations [J]. 2018, DOI:10.1101/306977 .
[25]
ZhouZW, SiddiqueeMMR, TajbakhshN, et al. UNet++: redesigning skip connections to exploit multiscale features in image segmentation[J]. IEEE Trans Med Imaging, 2020, 39(6): 1856-67. doi:10.1109/tmi.2019.2959609
[26]
WangSH, LiL, ZhuangXH. AttU-NET: attention U-Net for brain tumor segmentation[M]//Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. Cham: Springer International Publishing, 2022: 302-11. doi:10.1007/978-3-031-09002-8_27
[27]
RahmanH, BukhtTFN, ImranA, et al. A deep learning approach for liver and tumor segmentation in CT images using ResUNet[J]. Bioengineering, 2022, 9(8): 368. doi:10.3390/bioengineering9080368
[28]
JhaD, SmedsrudPH, RieglerMA, et al. ResUNet: an advanced architecture for medical image segmentation[C]//2019 IEEE International Symposium on Multimedia (ISM). December 9-11, 2019, San Diego, CA, USA. IEEE, 2019: 225-2255. doi:10.1109/ism46123.2019.00049
[29]
GuR, WangGT, SongT, et al. CA-net: comprehensive attention convolutional neural networks for explainable medical image segmentation[J]. IEEE Trans Med Imaging, 2021, 40(2): 699-711. doi:10.1109/tmi.2020.3035253
[30]
JinQG, CuiH, SunCM, et al. Cascade knowledge diffusion network for skin lesion diagnosis and segmentation[J]. Appl Soft Comput, 2021, 99: 106881. doi:10.1016/j.asoc.2020.106881
[31]
FengSL, ZhaoHM, ShiF, et al. CPFNet: context pyramid fusion network for medical image segmentation[J]. IEEE Trans Med Imaging, 2020, 39(10): 3008-18. doi:10.1109/tmi.2020.2983721
[32]
XieYT, ZhangJP, XiaY, et al. A mutual bootstrapping model for automated skin lesion segmentation and classification[J]. IEEE Trans Med Imaging, 2020, 39(7): 2482-93. doi:10.1109/tmi.2020.2972964
[33]
YangG, YuSM, DongH, et al. DAGAN: deep de-aliasing generative adversarial networks for fast compressed sensing MRI reconstruction[J]. IEEE Trans Med Imaging, 2018, 37(6): 1310-21. doi:10.1109/tmi.2017.2785879
[34]
FanDP, JiGP, ZhouT, 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: 263-73. doi:10.1007/978-3-030-59725-2_26
[35]
XieYT, ZhangJP, LuH, et al. SESV: accurate medical image segmentation by predicting and correcting errors[J]. IEEE Trans Med Imag, 2021, 40(1): 286-96. doi:10.1109/tmi.2020.3025308
[36]
LiZ, ZhangL. Multi-scale context fusion network for melanoma segmentation[J]. KSII Trans Internet Inf Syst, 2024, 18(7): 1888-906. doi:10.3837/tiis.2024.07.009