本校學位論文庫
CITYU Theses & Dissertations
論文詳情
刘雪
吳庚申
數據科學學院
數據科學碩士學位課程(中文學制)
碩士
2023
基於深度學習的皮膚癌診斷研究
Research on Skin Cancer Diagnosis Based on Deep Learning
深度學習 ; transformer ; 醫學圖像分析
Deep learning ; Transformer ; Medical image analysis
公開日期：29/5/2027
皮膚癌是嚴重威脅人類健康的常見疾病之一，而早期診斷並及時治療可以極大的提高患者的存活率，在臨床醫學上某些種類的皮膚癌具有極大的相似性，增添了醫生診斷的困難，傳統的檢測方法需要醫生依靠皮膚鏡，通過觀察病灶的特徵從而判斷，但醫生專業能力的高低，會影響診斷結果，會有誤診的現象。隨著計算機輔助診斷技術的快速發展，計算機輔助技術能夠輔助醫生進行專業診斷，提升早期皮膚癌的診斷準確率，給予患者更大的生存機率，極具有研究價值和現實意義。
目前使用計算機進行皮膚癌圖像的診斷仍然存在著分類準確率不高和泛化性不足的問題。因此，本文在前人工作的基礎上，提出了一種基於卷積神經網絡和Transformer的皮膚癌診斷模型。首先進行圖像的預處理，使用數據增強的方法處理數據集不平衡的問題。模型以殘差網絡和交叉注意力多尺度視覺Transformer（CrossViT）為基本骨架，構建特徵學習模塊和多尺度交叉注意力模塊，既延續了殘差網絡在圖像分類上的良好性能，又加強了提取全局特徵的能力，使用反卷積層連接兩個模塊，增強了特徵的表達能力，針對皮膚癌圖像分類任務在CrossViT模型中添加全連接層（Dense層）來保證網絡層之間的梯度傳播暢通無阻，從而獲得更好的診斷準確性。在訓練時使用交叉熵損失函數，實現皮膚癌圖像的診斷。
將本文所提出的混合深度模型在HAM10000數據集和Melanoma Skin Cancer Dataset of 10000 Images數據集上進行驗證。在HAM10000數據集上，分類準確率達到了86.03%，精確率達到了84.75%，召回率達到了86.03%，F1值達到了84.89%，在Melanoma Skin Cancer Dataset of 10000 Images數據集上，分類準確率達到了91.90%，AUC達到0.9696，相比於其他方法，本文模型獲得了更高的準確率，診斷效果更好，優於當前的先進方法，對於臨床皮膚癌診斷具有一定的參考價值。
目前使用計算機進行皮膚癌圖像的診斷仍然存在著分類準確率不高和泛化性不足的問題。因此，本文在前人工作的基礎上，提出了一種基於卷積神經網絡和Transformer的皮膚癌診斷模型。首先進行圖像的預處理，使用數據增強的方法處理數據集不平衡的問題。模型以殘差網絡和交叉注意力多尺度視覺Transformer（CrossViT）為基本骨架，構建特徵學習模塊和多尺度交叉注意力模塊，既延續了殘差網絡在圖像分類上的良好性能，又加強了提取全局特徵的能力，使用反卷積層連接兩個模塊，增強了特徵的表達能力，針對皮膚癌圖像分類任務在CrossViT模型中添加全連接層（Dense層）來保證網絡層之間的梯度傳播暢通無阻，從而獲得更好的診斷準確性。在訓練時使用交叉熵損失函數，實現皮膚癌圖像的診斷。
將本文所提出的混合深度模型在HAM10000數據集和Melanoma Skin Cancer Dataset of 10000 Images數據集上進行驗證。在HAM10000數據集上，分類準確率達到了86.03%，精確率達到了84.75%，召回率達到了86.03%，F1值達到了84.89%，在Melanoma Skin Cancer Dataset of 10000 Images數據集上，分類準確率達到了91.90%，AUC達到0.9696，相比於其他方法，本文模型獲得了更高的準確率，診斷效果更好，優於當前的先進方法，對於臨床皮膚癌診斷具有一定的參考價值。
Skin cancer, as one of the commonly occurring diseases, poses a significant risk to human health. Detecting it early and commencing prompt treatment can significantly improve the survival rate of patients. In clinical medicine, certain types of skin cancer have great similarities, which increases the difficulty of diagnosis by doctors. Traditional detection methods require doctors to rely on dermatoscopy to observe the characteristics of the lesion and make judgments. However, the professional ability of doctors can affect the diagnosis results and may lead to misdiagnosis. The rapid progress of computer-aided diagnostic technology has empowered doctors in their professional diagnosis, improving the accuracy of early skin cancer detection, ultimately increasing patients' chances of survival. It has great research value and practical significance.
At present, there are still problems with low classification accuracy and insufficient generalization in the diagnosis of skin cancer images using computers. Therefore, based on previous work, this article proposes a skin cancer diagnosis model based on convolutional neural networks and Transformer. Firstly, perform image preprocessing and use data augmentation methods to address the issue of imbalanced datasets. The model takes residual networks and Cross-Attention Multi-Scale Vision Transformer (CrossViT) as the basic skeleton, constructs feature learning modules and multi-scale cross attention modules, which not only continue the good performance of residual networks in image classification but also strengthen the ability to extract global features. The deconvolution layer is used to connect the two modules, enhancing the expression ability of features. For skin cancer image classification tasks, a fully connected layer (Dense layer) is added to the CrossViT model to ensure smooth gradient propagation between network layers, thereby achieving better diagnostic accuracy. Use cross entropy loss function during training to achieve diagnosis of skin cancer images.
Verify the hybrid classification model proposed in this article on the HAM10000 dataset and the Melanoma Skin Cancer Dataset of 10000 Images dataset. On the HAM10000 dataset, the classification accuracy attained a figure of 86.03%, while the overall precision stood at 84.75%, the recall rate also achieved 86.03%, and the F1 score reached a notable level of 84.89%. On the Melanoma Skin Cancer Dataset of 10000 Images dataset, the classification accuracy reached 91.90%, and the AUC reached 0.9696. Compared with other methods, the model in this paper achieved higher accuracy, better diagnostic performance, and better than current advanced methods. It has certain reference value for clinical skin cancer diagnosis.
At present, there are still problems with low classification accuracy and insufficient generalization in the diagnosis of skin cancer images using computers. Therefore, based on previous work, this article proposes a skin cancer diagnosis model based on convolutional neural networks and Transformer. Firstly, perform image preprocessing and use data augmentation methods to address the issue of imbalanced datasets. The model takes residual networks and Cross-Attention Multi-Scale Vision Transformer (CrossViT) as the basic skeleton, constructs feature learning modules and multi-scale cross attention modules, which not only continue the good performance of residual networks in image classification but also strengthen the ability to extract global features. The deconvolution layer is used to connect the two modules, enhancing the expression ability of features. For skin cancer image classification tasks, a fully connected layer (Dense layer) is added to the CrossViT model to ensure smooth gradient propagation between network layers, thereby achieving better diagnostic accuracy. Use cross entropy loss function during training to achieve diagnosis of skin cancer images.
Verify the hybrid classification model proposed in this article on the HAM10000 dataset and the Melanoma Skin Cancer Dataset of 10000 Images dataset. On the HAM10000 dataset, the classification accuracy attained a figure of 86.03%, while the overall precision stood at 84.75%, the recall rate also achieved 86.03%, and the F1 score reached a notable level of 84.89%. On the Melanoma Skin Cancer Dataset of 10000 Images dataset, the classification accuracy reached 91.90%, and the AUC reached 0.9696. Compared with other methods, the model in this paper achieved higher accuracy, better diagnostic performance, and better than current advanced methods. It has certain reference value for clinical skin cancer diagnosis.
2024
中文
54
致 謝 I
摘 要 II
Abstract III
圖目錄 VII
表目錄 VIII
第一章 緒 論 1
1.1 研究背景及意義 1
1.1.1 選題背景 1
1.1.2 選題意義 2
1.2 國內外研究現狀 2
1.2.1 傳統機器學習在皮膚癌診斷中的研究現狀 2
1.2.2 深度學習在皮膚癌診斷中的研究現狀 4
1.3 論文研究內容 7
1.4 論文組織結構 8
1.5 本章小結 9
第二章 相關理論基礎 10
2.1 數據增強方法 10
2.2 卷積神經網絡理論 11
2.2.1 卷積神經網絡的結構 12
2.2.2 卷積層 12
2.2.3 池化層 13
2.2.4 激活函數 14
2.2.5 全連接層 15
2.2.6 批歸一化層 15
2.2.7 經典網絡介紹 15
2.3 Transformer網絡理論 18
2.3.1 自注意力機制 19
2.3.2 多頭注意力機制 20
2.3.3 前饋神經網絡 20
2.3.4 位置編碼 21
2.3.5 視覺Transformer 21
2.3.6 交叉注意力多尺度視覺Transformer 22
2.4 本章小結 23
第三章 研究方法及設計 24
3.1 混合深度模型 24
3.1.1 模型整體框架 24
3.1.2 模型基本骨架 25
3.2 特徵學習模塊 29
3.3 多尺度交叉注意力融合模塊 30
3.4 損失函數 33
3.5 本章小結 33
第四章 實驗結果與分析 35
4.1 數據集與預處理 35
4.1.1 HAM10000數據集 35
4.1.2 Melanoma Skin Cancer Dataset of 10000 Images數據集 37
4.2 實驗設置 37
4.3 評價指標 38
4.4 實驗分析 40
4.4.1 對比實驗 40
4.4.2 消融實驗 44
4.5 本章小結 45
第五章 總結與建議 46
5.1 總結 46
5.2 建議 47
參考文獻 49
作者簡歷 54
摘 要 II
Abstract III
圖目錄 VII
表目錄 VIII
第一章 緒 論 1
1.1 研究背景及意義 1
1.1.1 選題背景 1
1.1.2 選題意義 2
1.2 國內外研究現狀 2
1.2.1 傳統機器學習在皮膚癌診斷中的研究現狀 2
1.2.2 深度學習在皮膚癌診斷中的研究現狀 4
1.3 論文研究內容 7
1.4 論文組織結構 8
1.5 本章小結 9
第二章 相關理論基礎 10
2.1 數據增強方法 10
2.2 卷積神經網絡理論 11
2.2.1 卷積神經網絡的結構 12
2.2.2 卷積層 12
2.2.3 池化層 13
2.2.4 激活函數 14
2.2.5 全連接層 15
2.2.6 批歸一化層 15
2.2.7 經典網絡介紹 15
2.3 Transformer網絡理論 18
2.3.1 自注意力機制 19
2.3.2 多頭注意力機制 20
2.3.3 前饋神經網絡 20
2.3.4 位置編碼 21
2.3.5 視覺Transformer 21
2.3.6 交叉注意力多尺度視覺Transformer 22
2.4 本章小結 23
第三章 研究方法及設計 24
3.1 混合深度模型 24
3.1.1 模型整體框架 24
3.1.2 模型基本骨架 25
3.2 特徵學習模塊 29
3.3 多尺度交叉注意力融合模塊 30
3.4 損失函數 33
3.5 本章小結 33
第四章 實驗結果與分析 35
4.1 數據集與預處理 35
4.1.1 HAM10000數據集 35
4.1.2 Melanoma Skin Cancer Dataset of 10000 Images數據集 37
4.2 實驗設置 37
4.3 評價指標 38
4.4 實驗分析 40
4.4.1 對比實驗 40
4.4.2 消融實驗 44
4.5 本章小結 45
第五章 總結與建議 46
5.1 總結 46
5.2 建議 47
參考文獻 49
作者簡歷 54
[1] Das K, Cockerell C J, Patil A, et al. Machine learning and its application in skin cancer[J]. International Journal of Environmental Research and Public Health, 2021, 18(24): 13409.
[2] Kumar M, Alshehri M, AlGhamdi R, et al. A de-ann inspired skin cancer detection approach using fuzzy c-means clustering[J]. Mobile Networks and Applications, 2020, 25: 1319-1329.
[3] Iqbal I, Younus M, Walayat K, et al. Automated multi-class classification of skin lesions through deep convolutional neural network with dermoscopic images[J]. Computerized medical imaging and graphics, 2021, 88: 101843.
[4] Baumann B C, MacArthur K M, Brewer J D, et al. Management of primary skin cancer during a pandemic: multidisciplinary recommendations[J]. Cancer, 2020, 126(17): 3900-3906.
[5] Parkin D M, Mesher D, Sasieni P. 13. Cancers attributable to solar (ultraviolet) radiation exposure in the UK in 2010[J]. British journal of cancer, 2011, 105(2): S66-S69.
[6] Kasmi R, Mokrani K. Classification of malignant melanoma and benign skin lesions: implementation of automatic ABCD rule[J]. IET Image Processing, 2016, 10(6): 448-455.
[7] Dildar M, Akram S, Irfan M, et al. Skin cancer detection: a review using deep learning techniques[J]. International journal of environmental research and public health, 2021, 18(10): 5479.
[8] Siegel R L, Miller K D, Jemal A. Cancer statistics, 2017[J]. CA: a cancer journal for clinicians, 2017, 67(1): 7-30.
[9] Gloster Jr H M, Neal K. Skin cancer in skin of color[J]. Journal of the American Academy of Dermatology, 2006, 55(5): 741-760.
[10] 楊淩舸, 王春萌. 惡性黑色素瘤免疫治療現狀與進展[J]. 中國腫瘤, 2018, 27(1): 54-60.
[11] Jerant A F, Johnson J T, Sheridan C D, et al. Early detection and treatment of skin cancer[J]. American family physician, 2000, 62(2): 357-368.
[12] Abbas Q, Garcia I F, Rashid M. Automatic skin tumour border detection for digital dermoscopy using a new digital image analysis scheme[J]. British journal of biomedical science, 2010, 67(4): 177-183.
[13] Stolz W. ABCD rule of dermatoscopy: a new practical method for early recognition of malignant melanoma[J]. Eur J Dermatol, 1994, 4: 521-527.
[14] Argenziano G, Fabbrocini G, Carli P, et al. Epiluminescence microscopy for the diagnosis of doubtful melanocytic skin lesions: comparison of the ABCD rule of dermatoscopy and a new 7-point checklist based on pattern analysis[J]. Archives of dermatology, 1998, 134(12): 1563-1570.
[15] Soyer H P, Argenziano G, Zalaudek I, et al. Three-Point Checklist of DermoscopyA New Screening Method for Early Detection of Melanoma[J]. Dermatology, 2004, 208(1): 27-31.
[16] Henning J S, Dusza S W, Wang S Q, et al. The CASH (color, architecture, symmetry, and homogeneity) algorithm for dermoscopy[J]. Journal of the American Academy of Dermatology, 2007, 56(1): 45-52.
[17] Pehamberger H, Steiner A, Wolff K. In vivo epiluminescence microscopy of pigmented skin lesions. I. Pattern analysis of pigmented skin lesions[J]. Journal of the American Academy of Dermatology, 1987, 17(4): 571-583.
[18] Menzies S W. A method for the diagnosis of primary cutaneous melanoma using surface microscopy[J]. Dermatologic clinics, 2001, 19(2): 299-305.
[19] Bi L, Kim J, Ahn E, et al. Automatic melanoma detection via multi-scale lesion-biased representation and joint reverse classification[C]//2016 IEEE 13th international symposium on biomedical imaging (ISBI). IEEE, 2016: 1055-1058.
[20] Barata C, Ruela M, Francisco M, et al. Two systems for the detection of melanomas in dermoscopy images using texture and color features[J]. IEEE systems Journal, 2013, 8(3): 965-979.
[21] Ganster H, Pinz P, Rohrer R, et al. Automated melanoma recognition[J]. IEEE transactions on medical imaging, 2001, 20(3): 233-239.
[22] Celebi M E, Kingravi H A, Uddin B, et al. A methodological approach to the classification of dermoscopy images[J]. Computerized Medical imaging and graphics, 2007, 31(6): 362-373.
[23] 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[J]. Color medical image analysis, 2013: 63-86.
[24] Mporas I, Perikos I, Paraskevas M. Color models for skin lesion classification from dermatoscopic images[C]//Advances in Integrations of Intelligent Methods: Post-workshop volume of the 8th International Workshop CIMA 2018, Volos, Greece, November 2018 (in conjunction with IEEE ICTAI 2018). Springer Singapore, 2020: 85-98.
[25] Wighton P, Sadeghi M, Lee T K, et al. A fully automatic random walker segmentation for skin lesions in a supervised setting[C]//Medical Image Computing and Computer-Assisted Intervention–MICCAI 2009: 12th International Conference, London, UK, September 20-24, 2009, Proceedings, Part II 12. Springer Berlin Heidelberg, 2009: 1108-1115.
[26] Emre Celebi M, Wen Q, Hwang S, et al. Lesion border detection in dermoscopy images using ensembles of thresholding methods[J]. Skin Research and Technology, 2013, 19(1): e252-e258.
[27] LeCun Y, Boser B, Denker J S, et al. Backpropagation applied to handwritten zip code recognition[J]. Neural computation, 1989, 1(4): 541-551.
[28] Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[J]. Advances in neural information processing systems, 2012, 25.
[29] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. arxiv preprint arxiv:1409.1556, 2014.
[30] Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 1-9.
[31] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778.
[32] Huang G, Liu Z, Van Der Maaten L, et al. Densely connected convolutional networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 4700-4708.
[33] Howard A G, Zhu M, Chen B, et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications[J]. arxiv preprint arxiv:1704.04861, 2017.
[34] Bhadula S, Sharma S, Juyal P, et al. Machine learning algorithms based skin disease detection[J]. International Journal of Innovative Technology and Exploring Engineering (IJITEE), 2019, 9(2): 4044-4049.
[35] Seeja R D, Suresh A. Deep learning based skin lesion segmentation and classification of melanoma using support vector machine (SVM)[J]. Asian Pacific journal of cancer prevention: APJCP, 2019, 20(5): 1555.
[36] Yu L, Chen H, Dou Q, et al. Automated melanoma recognition in dermoscopy images via very deep residual networks[J]. IEEE transactions on medical imaging, 2016, 36(4): 994-1004.
[37] Ge Z, Demyanov S, Chakravorty R, et al. 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, 2017: 250-258.
[38] Yang J, Xie F, Fan H, et al. Classification for dermoscopy images using convolutional neural networks based on region average pooling[J]. IEEE Access, 2018, 6: 65130-65138.
[39] Ray S. Disease classification within dermascopic images using features extracted by resnet50 and classification through deep forest[J]. arxiv preprint arxiv:1807.05711, 2018.
[40] Majtner T, Bajić B, Yildirim S, et al. Ensemble of convolutional neural networks for dermoscopic images classification[J]. arxiv preprint arxiv:1808.05071, 2018.
[41] Chaturvedi S S, Gupta K, Prasad P S. Skin lesion analyser: an efficient seven-way multi-class skin cancer classification using MobileNet[C]//Advanced Machine Learning Technologies and Applications: Proceedings of AMLTA 2020. Springer Singapore, 2021: 165-176.
[42] Milton M A A. Automated skin lesion classification using ensemble of deep neural networks in isic 2018: Skin lesion analysis towards melanoma detection challenge[J]. arxiv preprint arxiv:1901.10802, 2019.
[43] Mobiny A, Singh A, Van Nguyen H. Risk-aware machine learning classifier for skin lesion diagnosis[J]. Journal of clinical medicine, 2019, 8(8): 1241.
[44] Vasconcelos C N, Vasconcelos B N. Convolutional neural network committees for melanoma classification with classical and expert knowledge based image transforms data augmentation[J]. arxiv preprint arxiv:1702.07025, 2017.
[45] DeVries T, Ramachandram D. Skin lesion classification using deep multi-scale convolutional neural networks[J]. arxiv preprint arxiv:1703.01402, 2017.
[46] Kawahara J, BenTaieb A, Hamarneh G. Deep features to classify skin lesions[C]//2016 IEEE 13th international symposium on biomedical imaging (ISBI). IEEE, 2016: 1397-1400.
[47] Hosny K M, Kassem M A, Foaud M M. Skin cancer classification using deep learning and transfer learning[C]//2018 9th Cairo international biomedical engineering conference (CIBEC). IEEE, 2018: 90-93.
[48] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need in advances in neural information processing systems, 2017[J]. Search PubMed, 5998-6008.
[49] Zhang J, Xie Y, Xia Y, et al. Attention residual learning for skin lesion classification[J]. IEEE transactions on medical imaging, 2019, 38(9): 2092-2103.
[50] Cheng J, Tian S, Yu L, et al. ResGANet: Residual group attention network for medical image classification and segmentation[J]. Medical Image Analysis, 2022, 76: 102313.
[51] Fang L, Wang C, Li S, et al. Attention to lesion: Lesion-aware convolutional neural network for retinal optical coherence tomography image classification[J]. IEEE transactions on medical imaging, 2019, 38(8): 1959-1970.
[52] Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16x16 words: Transformers for image recognition at scale[J]. arxiv preprint arxiv:2010.11929, 2020.
[53] Touvron H, Cord M, Douze M, et al. Training data-efficient image transformers & distillation through attention[C]//International conference on machine learning. PMLR, 2021: 10347-10357.
[54] Wang W, Xie E, Li X, 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.
[55] Liu Z, Lin Y, Cao Y, et al. Swin transformer: Hierarchical vision transformer using shifted windows[C]//Proceedings of the IEEE/CVF international conference on computer vision. 2021: 10012-10022.
[56] Chen C F R, Fan Q, Panda R. Crossvit: Cross-attention multi-scale vision transformer for image classification[C]//Proceedings of the IEEE/CVF international conference on computer vision. 2021: 357-366.
[57] Dai Y, Gao Y, Liu F. Transmed: Transformers advance multi-modal medical image classification[J]. Diagnostics, 2021, 11(8): 1384.
[58] Wu X, Feng Y, Xu H, et al. CTransCNN: Combining transformer and CNN in multilabel medical image classification[J]. Knowledge-Based Systems, 2023, 281: 111030.
[59] Gheflati B, Rivaz H. Vision transformers for classification of breast ultrasound images[C]//2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). IEEE, 2022: 480-483.
[60] Sun R, Pang Y, Li W. Efficient lung cancer image classification and segmentation algorithm based on an improved swin transformer[J]. Electronics, 2023, 12(4): 1024.
[61] Wang T, Lan J, Han Z, et al. O-Net: a novel framework with deep fusion of CNN and transformer for simultaneous segmentation and classification[J]. Frontiers in neuroscience, 2022, 16: 876065.
[62] Xie J, Wu Z, Zhu R, et al. Melanoma detection based on swin transformer and SimAM[C]//2021 IEEE 5th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC). IEEE, 2021, 5: 1517-1521.
[63] Lungu-Stan V C, Cercel D C, Pop F. Skindistilvit: Lightweight vision transformer for skin lesion classification[C]//International Conference on Artificial Neural Networks. Cham: Springer Nature Switzerland, 2023: 268-280.
[64] Chen J, Chen J, Zhou Z, et al. MT-TransUNet: Mediating multi-task tokens in transformers for skin lesion segmentation and classification[J]. arxiv preprint arxiv:2112.01767, 2021.
[65] Sandler M, Howard A, Zhu M, et al. Mobilenetv2: Inverted residuals and linear bottlenecks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 4510-4520.
[66] 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)[J]. arxiv preprint arxiv:1902.03368, 2019.
[67] 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(1): 1-9.
[68] Korgialas C, Vision Transformer for Cancer Skin Classification TensorFlow[EB/OL].(2021)[2024-04-17].https://github.com/ckorgial/ViT-for-Cancer-Skin-Classification-TensorFlow.
[69] Javid M H, Melanoma Skin Cancer Dataset of 10000 Images[EB/OL]. (2022)[2024-04-17]. https://www.kaggle.com/datasets/hasnainjaved/melanoma-skin-cancer-dataset-of-10000-images.
[2] Kumar M, Alshehri M, AlGhamdi R, et al. A de-ann inspired skin cancer detection approach using fuzzy c-means clustering[J]. Mobile Networks and Applications, 2020, 25: 1319-1329.
[3] Iqbal I, Younus M, Walayat K, et al. Automated multi-class classification of skin lesions through deep convolutional neural network with dermoscopic images[J]. Computerized medical imaging and graphics, 2021, 88: 101843.
[4] Baumann B C, MacArthur K M, Brewer J D, et al. Management of primary skin cancer during a pandemic: multidisciplinary recommendations[J]. Cancer, 2020, 126(17): 3900-3906.
[5] Parkin D M, Mesher D, Sasieni P. 13. Cancers attributable to solar (ultraviolet) radiation exposure in the UK in 2010[J]. British journal of cancer, 2011, 105(2): S66-S69.
[6] Kasmi R, Mokrani K. Classification of malignant melanoma and benign skin lesions: implementation of automatic ABCD rule[J]. IET Image Processing, 2016, 10(6): 448-455.
[7] Dildar M, Akram S, Irfan M, et al. Skin cancer detection: a review using deep learning techniques[J]. International journal of environmental research and public health, 2021, 18(10): 5479.
[8] Siegel R L, Miller K D, Jemal A. Cancer statistics, 2017[J]. CA: a cancer journal for clinicians, 2017, 67(1): 7-30.
[9] Gloster Jr H M, Neal K. Skin cancer in skin of color[J]. Journal of the American Academy of Dermatology, 2006, 55(5): 741-760.
[10] 楊淩舸, 王春萌. 惡性黑色素瘤免疫治療現狀與進展[J]. 中國腫瘤, 2018, 27(1): 54-60.
[11] Jerant A F, Johnson J T, Sheridan C D, et al. Early detection and treatment of skin cancer[J]. American family physician, 2000, 62(2): 357-368.
[12] Abbas Q, Garcia I F, Rashid M. Automatic skin tumour border detection for digital dermoscopy using a new digital image analysis scheme[J]. British journal of biomedical science, 2010, 67(4): 177-183.
[13] Stolz W. ABCD rule of dermatoscopy: a new practical method for early recognition of malignant melanoma[J]. Eur J Dermatol, 1994, 4: 521-527.
[14] Argenziano G, Fabbrocini G, Carli P, et al. Epiluminescence microscopy for the diagnosis of doubtful melanocytic skin lesions: comparison of the ABCD rule of dermatoscopy and a new 7-point checklist based on pattern analysis[J]. Archives of dermatology, 1998, 134(12): 1563-1570.
[15] Soyer H P, Argenziano G, Zalaudek I, et al. Three-Point Checklist of DermoscopyA New Screening Method for Early Detection of Melanoma[J]. Dermatology, 2004, 208(1): 27-31.
[16] Henning J S, Dusza S W, Wang S Q, et al. The CASH (color, architecture, symmetry, and homogeneity) algorithm for dermoscopy[J]. Journal of the American Academy of Dermatology, 2007, 56(1): 45-52.
[17] Pehamberger H, Steiner A, Wolff K. In vivo epiluminescence microscopy of pigmented skin lesions. I. Pattern analysis of pigmented skin lesions[J]. Journal of the American Academy of Dermatology, 1987, 17(4): 571-583.
[18] Menzies S W. A method for the diagnosis of primary cutaneous melanoma using surface microscopy[J]. Dermatologic clinics, 2001, 19(2): 299-305.
[19] Bi L, Kim J, Ahn E, et al. Automatic melanoma detection via multi-scale lesion-biased representation and joint reverse classification[C]//2016 IEEE 13th international symposium on biomedical imaging (ISBI). IEEE, 2016: 1055-1058.
[20] Barata C, Ruela M, Francisco M, et al. Two systems for the detection of melanomas in dermoscopy images using texture and color features[J]. IEEE systems Journal, 2013, 8(3): 965-979.
[21] Ganster H, Pinz P, Rohrer R, et al. Automated melanoma recognition[J]. IEEE transactions on medical imaging, 2001, 20(3): 233-239.
[22] Celebi M E, Kingravi H A, Uddin B, et al. A methodological approach to the classification of dermoscopy images[J]. Computerized Medical imaging and graphics, 2007, 31(6): 362-373.
[23] 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[J]. Color medical image analysis, 2013: 63-86.
[24] Mporas I, Perikos I, Paraskevas M. Color models for skin lesion classification from dermatoscopic images[C]//Advances in Integrations of Intelligent Methods: Post-workshop volume of the 8th International Workshop CIMA 2018, Volos, Greece, November 2018 (in conjunction with IEEE ICTAI 2018). Springer Singapore, 2020: 85-98.
[25] Wighton P, Sadeghi M, Lee T K, et al. A fully automatic random walker segmentation for skin lesions in a supervised setting[C]//Medical Image Computing and Computer-Assisted Intervention–MICCAI 2009: 12th International Conference, London, UK, September 20-24, 2009, Proceedings, Part II 12. Springer Berlin Heidelberg, 2009: 1108-1115.
[26] Emre Celebi M, Wen Q, Hwang S, et al. Lesion border detection in dermoscopy images using ensembles of thresholding methods[J]. Skin Research and Technology, 2013, 19(1): e252-e258.
[27] LeCun Y, Boser B, Denker J S, et al. Backpropagation applied to handwritten zip code recognition[J]. Neural computation, 1989, 1(4): 541-551.
[28] Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[J]. Advances in neural information processing systems, 2012, 25.
[29] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. arxiv preprint arxiv:1409.1556, 2014.
[30] Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 1-9.
[31] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778.
[32] Huang G, Liu Z, Van Der Maaten L, et al. Densely connected convolutional networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 4700-4708.
[33] Howard A G, Zhu M, Chen B, et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications[J]. arxiv preprint arxiv:1704.04861, 2017.
[34] Bhadula S, Sharma S, Juyal P, et al. Machine learning algorithms based skin disease detection[J]. International Journal of Innovative Technology and Exploring Engineering (IJITEE), 2019, 9(2): 4044-4049.
[35] Seeja R D, Suresh A. Deep learning based skin lesion segmentation and classification of melanoma using support vector machine (SVM)[J]. Asian Pacific journal of cancer prevention: APJCP, 2019, 20(5): 1555.
[36] Yu L, Chen H, Dou Q, et al. Automated melanoma recognition in dermoscopy images via very deep residual networks[J]. IEEE transactions on medical imaging, 2016, 36(4): 994-1004.
[37] Ge Z, Demyanov S, Chakravorty R, et al. 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, 2017: 250-258.
[38] Yang J, Xie F, Fan H, et al. Classification for dermoscopy images using convolutional neural networks based on region average pooling[J]. IEEE Access, 2018, 6: 65130-65138.
[39] Ray S. Disease classification within dermascopic images using features extracted by resnet50 and classification through deep forest[J]. arxiv preprint arxiv:1807.05711, 2018.
[40] Majtner T, Bajić B, Yildirim S, et al. Ensemble of convolutional neural networks for dermoscopic images classification[J]. arxiv preprint arxiv:1808.05071, 2018.
[41] Chaturvedi S S, Gupta K, Prasad P S. Skin lesion analyser: an efficient seven-way multi-class skin cancer classification using MobileNet[C]//Advanced Machine Learning Technologies and Applications: Proceedings of AMLTA 2020. Springer Singapore, 2021: 165-176.
[42] Milton M A A. Automated skin lesion classification using ensemble of deep neural networks in isic 2018: Skin lesion analysis towards melanoma detection challenge[J]. arxiv preprint arxiv:1901.10802, 2019.
[43] Mobiny A, Singh A, Van Nguyen H. Risk-aware machine learning classifier for skin lesion diagnosis[J]. Journal of clinical medicine, 2019, 8(8): 1241.
[44] Vasconcelos C N, Vasconcelos B N. Convolutional neural network committees for melanoma classification with classical and expert knowledge based image transforms data augmentation[J]. arxiv preprint arxiv:1702.07025, 2017.
[45] DeVries T, Ramachandram D. Skin lesion classification using deep multi-scale convolutional neural networks[J]. arxiv preprint arxiv:1703.01402, 2017.
[46] Kawahara J, BenTaieb A, Hamarneh G. Deep features to classify skin lesions[C]//2016 IEEE 13th international symposium on biomedical imaging (ISBI). IEEE, 2016: 1397-1400.
[47] Hosny K M, Kassem M A, Foaud M M. Skin cancer classification using deep learning and transfer learning[C]//2018 9th Cairo international biomedical engineering conference (CIBEC). IEEE, 2018: 90-93.
[48] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need in advances in neural information processing systems, 2017[J]. Search PubMed, 5998-6008.
[49] Zhang J, Xie Y, Xia Y, et al. Attention residual learning for skin lesion classification[J]. IEEE transactions on medical imaging, 2019, 38(9): 2092-2103.
[50] Cheng J, Tian S, Yu L, et al. ResGANet: Residual group attention network for medical image classification and segmentation[J]. Medical Image Analysis, 2022, 76: 102313.
[51] Fang L, Wang C, Li S, et al. Attention to lesion: Lesion-aware convolutional neural network for retinal optical coherence tomography image classification[J]. IEEE transactions on medical imaging, 2019, 38(8): 1959-1970.
[52] Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16x16 words: Transformers for image recognition at scale[J]. arxiv preprint arxiv:2010.11929, 2020.
[53] Touvron H, Cord M, Douze M, et al. Training data-efficient image transformers & distillation through attention[C]//International conference on machine learning. PMLR, 2021: 10347-10357.
[54] Wang W, Xie E, Li X, 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.
[55] Liu Z, Lin Y, Cao Y, et al. Swin transformer: Hierarchical vision transformer using shifted windows[C]//Proceedings of the IEEE/CVF international conference on computer vision. 2021: 10012-10022.
[56] Chen C F R, Fan Q, Panda R. Crossvit: Cross-attention multi-scale vision transformer for image classification[C]//Proceedings of the IEEE/CVF international conference on computer vision. 2021: 357-366.
[57] Dai Y, Gao Y, Liu F. Transmed: Transformers advance multi-modal medical image classification[J]. Diagnostics, 2021, 11(8): 1384.
[58] Wu X, Feng Y, Xu H, et al. CTransCNN: Combining transformer and CNN in multilabel medical image classification[J]. Knowledge-Based Systems, 2023, 281: 111030.
[59] Gheflati B, Rivaz H. Vision transformers for classification of breast ultrasound images[C]//2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). IEEE, 2022: 480-483.
[60] Sun R, Pang Y, Li W. Efficient lung cancer image classification and segmentation algorithm based on an improved swin transformer[J]. Electronics, 2023, 12(4): 1024.
[61] Wang T, Lan J, Han Z, et al. O-Net: a novel framework with deep fusion of CNN and transformer for simultaneous segmentation and classification[J]. Frontiers in neuroscience, 2022, 16: 876065.
[62] Xie J, Wu Z, Zhu R, et al. Melanoma detection based on swin transformer and SimAM[C]//2021 IEEE 5th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC). IEEE, 2021, 5: 1517-1521.
[63] Lungu-Stan V C, Cercel D C, Pop F. Skindistilvit: Lightweight vision transformer for skin lesion classification[C]//International Conference on Artificial Neural Networks. Cham: Springer Nature Switzerland, 2023: 268-280.
[64] Chen J, Chen J, Zhou Z, et al. MT-TransUNet: Mediating multi-task tokens in transformers for skin lesion segmentation and classification[J]. arxiv preprint arxiv:2112.01767, 2021.
[65] Sandler M, Howard A, Zhu M, et al. Mobilenetv2: Inverted residuals and linear bottlenecks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 4510-4520.
[66] 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)[J]. arxiv preprint arxiv:1902.03368, 2019.
[67] 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(1): 1-9.
[68] Korgialas C, Vision Transformer for Cancer Skin Classification TensorFlow[EB/OL].(2021)[2024-04-17].https://github.com/ckorgial/ViT-for-Cancer-Skin-Classification-TensorFlow.
[69] Javid M H, Melanoma Skin Cancer Dataset of 10000 Images[EB/OL]. (2022)[2024-04-17]. https://www.kaggle.com/datasets/hasnainjaved/melanoma-skin-cancer-dataset-of-10000-images.
