AbstractAI image classification algorithms have shown promising results when applied to skin cancer detection. Most public skin cancer image datasets are comprised of dermoscopic photos and are limited by selection bias, lack of standardization, and lend themselves to development of algorithms that can only be used by skilled clinicians.

摘要当应用于皮肤癌检测时，图像分类算法已显示出有希望的结果。大多数公共皮肤癌图像数据集由皮肤镜照片组成，并且受到选择偏倚，缺乏标准化的限制，并且有助于开发只能由熟练临床医生使用的算法。

The SLICE-3D (“Skin Lesion Image Crops Extracted from 3D TBP”) dataset described here addresses those concerns and contains images of over 400,000 distinct skin lesions from seven dermatologic centers from around the world. De-identified images were systematically extracted from sensitive 3D Total Body Photographs and are comparable in optical resolution to smartphone images.

此处描述的SLICE-3D（“从3D TBP中提取的皮肤病变图像作物”）数据集解决了这些问题，并包含来自世界各地七个皮肤病中心的40多万个不同皮肤病变的图像。去识别的图像是从敏感的3D全身照片中系统地提取的，并且在光学分辨率上与智能手机图像相当。

Algorithms trained on lower quality images could improve clinical workflows and detect skin cancers earlier if deployed in primary care or non-clinical settings, where photos are captured by non-expert physicians or patients. Such a tool could prompt individuals to visit a specialized dermatologist.

如果部署在初级保健或非临床环境中，在低质量图像上训练的算法可以改进临床工作流程，并更早地检测皮肤癌，这些环境中的照片是由非专家医生或患者拍摄的。。

This dataset circumvents many inherent limitations of prior datasets and may be used to build upon previous applications of skin imaging for cancer detection..

该数据集规避了先前数据集的许多固有局限性，可用于构建先前用于癌症检测的皮肤成像应用。。

Background & SummaryAlgorithms that can distinguish benign from malignant skin lesions with sufficient accuracy could improve triage for skin cancer detection and greatly benefit populations without access to specialized dermatologic care1,2,3,4,5,6,7,8. Current algorithms typically use images captured with a handheld medical device called a dermatoscope9, which uses a magnifying lens and a lighting source to illuminate morphologic features not otherwise visible to the naked eye10,11.

背景与总结能够以足够的准确性区分良性和恶性皮肤病变的算法可以改善皮肤癌检测的分类，并大大有利于没有专门皮肤病护理的人群1,2,3,4,5,6,7,8。目前的算法通常使用称为皮肤镜9的手持医疗设备捕获的图像，该设备使用放大镜和光源来照亮肉眼无法看到的形态特征10,11。

Dermatoscopes are used commonly in dermatology clinics as an aid to evaluate skin lesions and diagnose skin cancers such as melanoma (MM)10,12,13, basal cell carcinoma (BCC)14, and squamous cell carcinoma (SCC)15. Dermoscopy has been integrated into the clinical practice worldwide, and a large number of images have been routinely collected for skin cancer diagnosis and monitoring.

皮肤镜通常用于皮肤科诊所，用于评估皮肤病变和诊断皮肤癌，如黑色素瘤（MM）10,12,13，基底细胞癌（BCC）14和鳞状细胞癌（SCC）15。皮肤镜检查已被纳入全球临床实践中，并且已经常规收集了大量图像用于皮肤癌的诊断和监测。

As a result, most state-of-the-art open-source skin lesion datasets for training AI models consist of dermoscopy images16,17,18. Over the past several years, researchers have explored how clinicians may benefit from utilizing dermoscopy-based AI algorithms19,20,21,22. However, determining which individuals should see a clinician in the first place has great potential impact23.

因此，用于训练AI模型的大多数最先进的开源皮肤病变数据集由皮肤镜图像组成16,17,18。在过去的几年中，研究人员探索了临床医生如何从利用基于皮肤镜的AI算法中受益19,20,21,22。然而，确定哪些人应该首先去看临床医生有很大的潜在影响23。

Triaging applications have a significant potential to benefit underserved populations24,25 and improve early skin cancer detection, the key factor in long-term patient outcomes26,27. Similarly, decreasing unnecessary referrals can decrease delays in treating patients in true need of care and reduce burden on health systems28,29.

分类应用具有显着的潜力，可以使服务不足的人群受益24,25，并改善早期皮肤癌的检测，这是长期患者预后的关键因素26,27。同样，减少不必要的转诊可以减少治疗真正需要护理的患者的延误，并减轻卫生系统的负担28,29。

With this work, we have published the SLICE-3D (“Skin Lesion Image Crops Extracted from 3D TBP”) dataset of 400,000+ standardized, de-identified, and diagnostically labeled skin images relevant to use-cases outside .

通过这项工作，我们发布了SLICE-3D（“从3D TBP中提取的皮肤病变图像作物”）数据集，该数据集包含与外部用例相关的400000多个标准化，去识别和诊断标记的皮肤图像。

Code availability

代码可用性

Custom generated code used by all sites for collating the raw data from the ISIC2024 Tile Export Tool, which is described in the Methods section, is available at https://github.com/ISIC-Research/2024-challenge-dataset. All code is written in Python 3.10 and utilizes commonly used open-source packages, all of which are available on pypi.org..

所有站点都使用自定义生成的代码来整理来自ISIC024磁贴导出工具的原始数据，该工具在“方法”部分中有描述，可在https://github.com/ISIC-Research/2024-challenge-dataset.所有代码都是用Python 3.10编写的，并使用常用的开源软件包，所有这些都可以在pypi.org上找到。。

ReferencesJames, O. T. et al. Artificial intelligence and machine learning algorithms for early detection of skin cancer in community and primary care settings: a systematic review. Lancet Digit. Health 4, e466–e476 (2022).Article

参考文献James，O.T.等人，《社区和初级保健环境中皮肤癌早期检测的人工智能和机器学习算法：系统综述》。柳叶刀数字。健康4，e466–e476（2022）。

Google Scholar

谷歌学者

Beltrami, E. J. et al. Artificial intelligence in the detection of skin cancer. J. Am. Acad. Dermatol. 87, 1336–1342 (2022).Article

Beltrami，E.J.等人，《人工智能在皮肤癌检测中的应用》。J、 美国科学院。。871336-1342（2022）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Vaidya, T. et al. Socioeconomic and geographic barriers to dermatology care in urban and rural US populations. J. Am. Acad. Dermatol. 78, 406–408 (2017).Article

Vaidya，T.等人。美国城乡人群皮肤病护理的社会经济和地理障碍。J、 美国科学院。。78406-408（2017）。文章

Google Scholar

谷歌学者

Glazer, A. M. & Rigel, D. S. Analysis of trends in geographic distribution of US dermatology workforce density. JAMA Dermatol. 153, 472 (2017).Article

Glazer，A.M。＆Rigel，D.S。美国皮肤科劳动力密度地理分布趋势分析。JAMA皮肤病。153472（2017）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Leavitt, E. R. et al. Teledermatology as a tool to improve access to care for medically underserved populations: A retrospective descriptive study. J. Am. Acad. Dermatol. 75, 1259–1261 (2016).Article

Leavitt，E.R.等人，《远程皮肤病学作为改善医疗服务不足人群获得护理的工具：一项回顾性描述性研究》。J、 美国科学院。。751259-1261（2016）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Fludiona, N. et al. Impact of dermatology eConsults on access to care and skin cancer screening in underserved populations: A model for teledermatology services in community health centers. J. Am. Acad. Dermatol. 78, 293–302 (2018).Article

Fludiona，N.等人，《皮肤病学经济结果对服务不足人群获得护理和皮肤癌筛查的影响：社区卫生中心远程皮肤病学服务的模型》。J、 美国科学院。。78293-302（2018）。文章

Google Scholar

谷歌学者

Peracca, S. B. et al. Implementing teledermatology for rural veterans: an evaluation using the RE-AIM framework. Telemed J E Health 27, 218–226 (2021).Article

Peracca，S.B.等人，《为农村退伍军人实施远程皮肤病学：使用RE-AIM框架的评估》。Telemed J E Health 27218-226（2021）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Udrea, A. et al. Accuracy of a smartphone application for triage of skin lesions based on machine learning algorithms. J Eur Acad Dermatol Venereol 34, 648–655 (2020).Article

Udrea，A.等人。基于机器学习算法的皮肤损伤分类智能手机应用程序的准确性。J Eur Acad Dermatol Venereol 34648-655（2020）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Zafar, M. et al. Skin lesion analysis and cancer detection based on machine/deep learning techniques: a comprehensive survey. Life. 13, 146 (2023).Article

基于机器/深度学习技术的皮肤病变分析和癌症检测：综合调查。生活。13146（2023）。文章

ADS

广告

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Marghoob, A. A., Usatine, R. P. & Jaimes, N. Dermoscopy for the family physician. Am Fam Physician 88, 441–450 (2013).PubMed

Marghoob，A.A.，Usatine，R.P。和Jaimes，N。家庭医生的皮肤镜检查。Am Fam医师88441-450（2013）。PubMed出版社

Google Scholar

谷歌学者

Marghoob, A. A. et al. Instruments and new technologies for the in vivo diagnosis of melanoma. J Am Acad Dermatol 49, 777–799 (2003).Article

Marghoob，A.A.等人。用于黑色素瘤体内诊断的仪器和新技术。J Am Acad Dermatol 49777-799（2003）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Menzies, S. W., Ingvar, C., Crotty, K. A. & McCarthy, W. H. Frequency and morphologic characteristics of invasive melanomas lacking specific surface microscopic features. Arch Dermatol 132, 1178–1182 (1996).Article

Menzies，S.W.，Ingvar，C.，Crotty，K.A。＆McCarthy，W.H。缺乏特定表面微观特征的侵袭性黑色素瘤的频率和形态学特征。Arch Dermatol 1321178-1182（1996）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Bafounta, M. L., Beauchet, A., Aegerter, P. & Saiag, P. Is dermoscopy (epiluminescence microscopy) useful for the diagnosis of melanoma? Results of a meta-analysis using techniques adapted to the evaluation of diagnostic tests. Arch Dermatol 137, 1343–1350 (2001).Article

Bafounta，M.L.，Beauchet，A.，Aegerter，P。＆Saiag，P。皮肤镜检查（落射发光显微镜）对黑色素瘤的诊断有用吗？使用适用于诊断测试评估的技术进行荟萃分析的结果。Arch Dermatol 1371343-1350（2001）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Menzies, S. W. et al. Surface microscopy of pigmented basal cell carcinoma. Arch Dermatol 136, 1012–1016 (2000).Article

Menzies，S.W.等人。色素性基底细胞癌的表面显微镜检查。Arch Dermatol 1361012-1016（2000）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Wolner, Z. J. et al. Enhancing skin cancer diagnosis with dermoscopy. Dermatol Clin 35, 417–437 (2017).Article

Wolner，Z.J.等人。用皮肤镜检查增强皮肤癌的诊断。皮肤病临床35417-437（2017）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Tschandl, P., Rosendahl, C. & Kittler, H. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci Data 5, 180161 (2018).Article

Tschandl，P.，Rosendahl，C。＆Kittler，H。HAM1000数据集，一系列常见色素性皮肤病变的多源皮肤镜图像。Sci数据5180161（2018）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Ricci Lara, M. A. et al. A dataset of skin lesion images collected in Argentina for the evaluation of AI tools in this population. Sci Data 10, 712 (2023).Article

Ricci Lara，M.A。等人。在阿根廷收集的皮肤病变图像数据集，用于评估该人群的AI工具。Sci数据10712（2023）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Rotemberg, V., et al. A patient-centric dataset of images and metadata for identifying melanomas using clinical context. Sci Data 8 2021.Marchetti, M.A. et al. Prospective validation of dermoscopy-based open-source artificial intelligence for melanoma diagnosis (PROVE-AI study). Npj Digit Med 6 (2023).Tschandl, P.

Rotemberg，V。等人。一个以患者为中心的图像和元数据数据集，用于使用临床背景识别黑色素瘤。。Npj数字医学6（2023）。Tschandl，P。

et al. Human–computer collaboration for skin cancer recognition. Nat Med 26, 1229–1234 (2020).Article .

等人。皮肤癌识别的人机合作。《国家医学杂志》261229–1234（2020）。文章。

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Cerminara, S.E. et al. Diagnostic performance of augmented intelligence with 2D and 3D total body photography and convolutional neural networks in a high-risk population for melanoma under real-world conditions: A new era of skin cancer screening? Eur J Cancer 190 (2023).Barata, C. et al.

Cerminara，S.E.等人。在现实世界条件下，在黑色素瘤高危人群中，2D和3D全身摄影和卷积神经网络增强智能的诊断性能：皮肤癌筛查的新时代？Eur J Cancer 190（2023）。Barata，C。等人。

A reinforcement learning model for AI-based decision support in skin cancer. Nat Med 29, 1941–1946 (2023).Article .

基于AI的皮肤癌决策支持的强化学习模型。。文章。

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Gabel, C. K. et al. Use of teledermatology by dermatology hospitalists is effective in the diagnosis and management of inpatient disease. J. Am. Acad. Dermatol. 84, 1547–1553 (2021).Article

Gabel，C.K.等人。皮肤病住院医生使用远程皮肤病学在住院疾病的诊断和管理中是有效的。J、 美国科学院。。841547-1553（2021）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Pearlman, R. L., Brodell, R. T. & Byrd, A. C. Enhancing access to rural dermatological care; the time to start is now. JAMA Dermatol. 158, 725–726 (2022).Article

Pearlman，R.L.，Brodell，R.T。＆Byrd，A.C。增加农村皮肤病护理的机会；现在是开始的时候了。JAMA皮肤病。158725-726（2022）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Stitzenberg, K. B. et al. Distance to diagnosing provider as a measure of access for patients with melanoma. Arch Dermatol 143, 991–998 (2007).Article

Stitzenberg，K.B.等人，《诊断提供者的距离作为黑色素瘤患者进入的衡量标准》。Arch Dermatol 143991-998（2007）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Pennie, M. L. et al. Melanoma outcomes for Medicare patients: Association of stage and survival with detection by a dermatologist vs a nondermatologist. Arch Dermatol 143, 488–494 (2007).Article

Pennie，M.L.等人，《医疗保险患者的黑色素瘤结局：阶段和生存与皮肤科医生与非皮肤科医生检测的关系》。Arch Dermatol 143488-494（2007）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Jerant, A. F., Johnson, J. T., Sheridan, C. D. & Caffrey, T. J. Early detection and treatment of skin cancer. Am Fam Physician 62, 357–385 (2000).CAS

。Am Fam医师62357-385（2000）。中科院

PubMed

PubMed

Google Scholar

谷歌学者

Cantisani, C. et al. Melanoma detection by non-specialists: an untapped potential for triage? Diagnostics. 12, 2821 (2022).Article

Cantisani，C.等人。非专家检测黑色素瘤：尚未开发的分流潜力？诊断。122821（2022）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Yadav, G. et al. A cross sectional survey of population-wide wait times for patients seeking medical vs. cosmetic dermatologic care. PLOS ONE 11, e0162767 (2016).Article

Yadav，G.等人。对寻求医疗与美容皮肤科护理的患者的全人群等待时间的横断面调查。PLOS ONE 11，e0162767（2016）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Marchetti, M. A. et al. Results of the 2016 International Skin Imaging Collaboration International Symposium on Biomedical Imaging challenge: Comparison of the accuracy of computer algorithms to dermatologists for the diagnosis of melanoma from dermoscopic images. J Am Acad Dermatol 78, 270–277.e1 (2018).Article .

Marchetti，M.A.等人，2016年国际皮肤成像合作国际生物医学成像挑战研讨会的结果：计算机算法与皮肤科医生从皮肤镜图像诊断黑色素瘤的准确性比较。J Am Acad Dermatol 78270–277.e1（2018）。文章。

PubMed

PubMed

Google Scholar

谷歌学者

Marchetti, M. A. et al. Computer algorithms show potential for improving dermatologists’ accuracy to diagnose cutaneous melanoma: Results of the International Skin Imaging Collaboration 2017. J Am Acad Dermatol 82, 622–627 (2020).Article

Marchetti，M.A.等人，《计算机算法显示出提高皮肤科医生诊断皮肤黑色素瘤准确性的潜力：2017年国际皮肤成像合作的结果》。J Am Acad Dermatol 82622–627（2020）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Codella, N. et al. Skin lesion analysis toward melanoma detection 2018: a challenge hosted by the International Skin Imaging Collaboration (ISIC). arXiv. https://doi.org/10.48550/arXiv.1902.03368 (2019).Article

Codella，N.等人，《2018年黑色素瘤检测的皮肤病变分析：国际皮肤成像合作组织（ISIC）主办的挑战》。arXiv。https://doi.org/10.48550/arXiv.1902.03368。文章

Google Scholar

谷歌学者

Combalia, M. et al. Validation of artificial intelligence prediction models for skin cancer diagnosis using dermoscopy images: the 2019 International Skin Imaging Collaboration Grand Challenge. Lancet Digit Health 4, e330–e339 (2022).Article

Combalia，M.等人。使用皮肤镜图像验证用于皮肤癌诊断的人工智能预测模型：2019年国际皮肤成像合作大挑战。。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Tschandl, P. et al. Comparison of the accuracy of human readers versus machine-learning algorithms for pigmented skin lesion classification: an open, web-based, international, diagnostic study. Lancet Oncol 20, 938–947 (2019).Article

Tschandl，P。等人。人类读者与机器学习算法对色素性皮肤病变分类的准确性比较：一项开放的，基于网络的，国际性的诊断研究。柳叶刀Oncol 20938-947（2019）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Esteva, A. et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 115–118 (2017).Article

Esteva，A。等人。皮肤科医生用深度神经网络对皮肤癌进行分类。。文章

ADS

广告

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Megna, M. et al. Teledermatology: a useful tool also after COVID-19 era? J Cosmet Dermatol 21, 2309–2310 (2022).Article

Megna，M.等人，《远程皮肤病学：COVID-19时代之后的有用工具？J Cosmet Dermatol 212309-2310（2022）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Trinidad, J., Kroshinsky, D., Kaffenberger, B. H. & Rojek, N. W. Telemedicine for inpatient dermatology consultations in response to the COVID-19 pandemic. J Am Acad Dermatol 83, e69–e71 (2020).Article

Trinidad，J.，Kroshinsky，D.，Kaffenberger，B.H。＆Rojek，N.W。针对新型冠状病毒大流行的住院皮肤病咨询远程医疗。J Am Acad Dermatol 83，e69–e71（2020）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Kennedy, J. et al. Dermatologist perceptions of teledermatology implementation and future use after COVID-19: demographics, barriers, and insights. JAMA Dermatol 157, 595–597 (2021).Article

皮肤科医生对新型冠状病毒肺炎后远程皮肤病学实施和未来使用的看法：人口统计学，障碍和见解。JAMA Dermatol 157595-597（2021）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Gordon, A. et al. Use of asynchronous interprofessional e-consults in cancer patients during the COVID-19 pandemic: current and future role. Telemed J E Health 29, 304–309.Young, A. T., Xiong, M., Pfau, J., Keiser, M. J. & Wei, M. L. Artificial intelligence in dermatology: a primer. J.

Gordon，A.等人，《新型冠状病毒肺炎大流行期间癌症患者使用异步跨专业电子咨询：当前和未来的作用》。Telemed J E Health 29304–309.Young，A.T.，Xiong，M.，Pfau，J.，Keiser，M.J。＆Wei，M.L。皮肤病学中的人工智能：入门。J。

Invest. Dermatol. 140, 1504–1512 (2020).Article .

投资。。1401504-1512（2020）。文章。

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Sangers, T. E. et al. Position statement of the EADV Artificial Intelligence (AI) Task Force on AI-assisted smartphone apps and web-based services for skin disease. J Eur Acad Dermatol Venereol 38, 22–30 (2024).Article

Sangers，T.E.等人，《EADV人工智能（AI）工作组关于人工智能辅助智能手机应用程序和基于网络的皮肤病服务的立场声明》。《欧洲皮肤性病杂志》38,22-30（2024）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Ji-Xu, A., Dinnes, J. & Matin, R. N. Total body photography for the diagnosis of cutaneous melanoma in adults: a systematic review and meta-analysis. Br. J. Dermatol. 185, 302–312 (2021).Article

Ji Xu，A.，Dinnes，J。＆Matin，R.N。全身摄影诊断成人皮肤黑色素瘤：系统评价和荟萃分析。Br.J.皮肤病。185302-312（2021）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Betz-Stablein, B. et al. Reproducible naevus counts using 3D total body photography and convolutional neural networks. Dermatology. 238, 4–11 (2021).Article

Betz Stablein，B。等人。使用3D全身摄影和卷积神经网络可再现痣计数。皮肤病学。238，4-11（2021）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Young, A. T. et al. The role of technology in melanoma screening and diagnosis. Pigment Cell Melanoma Res. 34, 288–300 (2020).Article

Young，A.T.等人，《技术在黑色素瘤筛查和诊断中的作用》。色素细胞黑色素瘤第34288-300号决议（2020年）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Primiero, C. A. et al. Evaluation of the efficacy of 3D total-body photography with sequential digital dermoscopy in a high-risk melanoma cohort: protocol for a randomised controlled trial. BMJ Open 9, e032969 (2019).Article

Primiero，C.A。等人。在高风险黑色素瘤队列中使用顺序数字皮肤镜检查评估3D全身摄影的疗效：随机对照试验的方案。BMJ Open 9，e032969（2019）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Marchetti, M. A. et al. 3D Whole-body skin imaging for automated melanoma detection. J Eur Acad Dermatol Venereol 37, 945–950 (2023).Article

Marchetti，M.A。等人。用于自动黑色素瘤检测的3D全身皮肤成像。J Eur Acad Dermatol Venereol 37945-950（2023）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Wen, D. et al. Characteristics of publicly available skin cancer image datasets: a systematic review. Lancet Digit Health 4, e64–e74 (2022).Article

Wen，D.等人。公开可用的皮肤癌图像数据集的特征：系统综述。柳叶刀数字健康4，e64-e74（2022）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Scope, A. et al. The ‘ugly duckling’ sign: agreement between observers. Arch Dermatol 144, 58–64 (2008).Article

Scope，A。等人，“丑小鸭”标志：观察者之间的协议。Arch Dermatol 144,58-64（2008）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Gaudy-Marqueste, C. et al. Ugly duckling sign as a major factor of efficiency in melanoma detection. JAMA Dermatol 153, 279–284 (2017).Article

丑小鸭征是黑色素瘤检测效率的主要因素。JAMA Dermatol 153279-284（2017）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Grob, J. J. & Bonerandi, J. J. The “ugly duckling” sign: identification of the common characteristics of nevi in an individual as a basis for melanoma screening. Arch Dermatol 134, 103–104 (1998).Article

。Arch Dermatol 134103-104（1998）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Primiero, C. A. et al. A narrative review: opportunities and challenges in artificial intelligence skin image analyses using total body photography. J Invest Dermatol https://doi.org/10.1016/j.jid.2023.11.007 (2024).Article

Primiero，C.A.等人，《叙述性评论：使用全身摄影进行人工智能皮肤图像分析的机遇和挑战》。J投资皮肤病https://doi.org/10.1016/j.jid.2023.11.007。文章

PubMed

PubMed

Google Scholar

谷歌学者

D’Alessandro, B. Methods and apparatus for identifying skin features of interest. (2021).Horsham, C., Janda, M., Kerr, M., Soyer, H. P. & Caffery, L. J. Consumer perceptions on privacy and confidentiality in dermatology for 3D total-body imaging. Australas J Dermatol 64, 118–121 (2023).Article .

D'Alessandro，B。用于识别感兴趣的皮肤特征的方法和装置。（2021年）。Horsham，C.，Janda，M.，Kerr，M.，Soyer，H.P。＆Caffery，L.J。消费者对3D全身成像皮肤病学隐私和保密性的看法。澳大利亚皮肤病杂志64118-121（2023）。文章。

PubMed

PubMed

Google Scholar

谷歌学者

Oh, Y. et al. Dermatology patient perspectives regarding consent, privacy, security, and identifiability of clinical photography at a tertiary cancer center: A qualitative study. JAAD Int 12, 121–123.Ghafur, S., Van Dael, J., Leis, M., Darzi, A., Sheikh, A. Public perceptions on data sharing: key insights from the UK and the USA.

Oh，Y.等人。皮肤病患者对三级癌症中心临床摄影的同意，隐私，安全性和可识别性的看法：定性研究。JAAD Int 12121-123.Ghafur，S.，Van Dael，J.，Leis，M.，Darzi，A.，Sheikh，A.公众对数据共享的看法：来自英国和美国的关键见解。

Lancet Digit Health 2, e444–e446.Kim, C. et al. Transparent medical image AI via an image-text foundation model grounded in medical literature. Nat. Med. 30, 1154–1165 (2024).Article .

《柳叶刀数字健康2》，e444–e446.Kim，C。等人。通过基于医学文献的图像文本基础模型的透明医学图像AI。《自然医学》301154-1165（2024）。文章。

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

https://www.isic-archive.com/terms-conditions (2024).Koh, U. et al. ‘Mind your Moles’ study: protocol of a prospective cohort study of melanocytic naevi. BMJ Open 8, e025857 (2018).Article

https://www.isic-archive.com/terms-conditions。Koh，U.等人的“小心你的痣”研究：黑素细胞痣前瞻性队列研究的方案。BMJ Open 8，e025857（2018）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Kurtansky, N. et al. SLICE-3D 2024 Challenge Dataset. International Skin Imaging Collaboration https://doi.org/10.34970/2024-slice-3d (2024).Kurtansky, N. et al. SLICE-3D 2024 Permissive Challenge Dataset. International Skin Imaging Collaboration https://doi.org/10.34970/2024-slice-3d-permissive (2024).Scope, A.

。国际皮肤成像合作https://doi.org/10.34970/2024-slice-3d。Kurtansky，N.等人，《SLICE-3D 2024许可挑战数据集》。国际皮肤成像合作https://doi.org/10.34970/2024-slice-3d-permissive。范围，A。

et al. International Skin Imaging Collaboration-Designated Diagnoses (ISIC-DX): consensus terminology for lesion diagnostic labeling. J Eur Acad Dermatol Venereol https://doi.org/10.1111/jdv.20055 (2024).Ferry, A. M., Sarrami, S. M., Hollier, P. C., Gerich, C. F. & Thornton, J. F. Treatment of non-melanoma skin cancers in the absence of mohs micrographic surgery.

等。国际皮肤成像合作指定诊断（ISIC-DX）：病变诊断标记的共识术语。欧洲皮肤性病杂志https://doi.org/10.1111/jdv.20055。Ferry，A.M.，Sarrami，S.M.，Hollier，P.C.，Gerich，C.F。和Thornton，J.F。在没有mohs显微手术的情况下治疗非黑色素瘤皮肤癌。

Plast Reconstr Surg Glob Open 8, e3300 (2022).Article .

Plast Reconstr Surg Glob Open 8，e3300（2022）。文章。

Google Scholar

谷歌学者

Ciuciulete, A. R., Stepan, A. E., Andreiana, B. C. & Simionescu, C. E. Non-melanoma skin cancer: statistical associations between clinical parameters. Curr Health Sci J 48, 110–115 (2022).PubMed

Ciuciulete，A.R.，Stepan，A.E.，Andreiana，B.C。和Simionescu，C.E。非黑色素瘤皮肤癌：临床参数之间的统计关联。Curr Health Sci J 48110–115（2022）。PubMed出版社

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Tsao, H., Bevona, C., Goggins, W. & Quinn, T. The transformation rate of moles (melanocytic nevi) into cutaneous melanoma: a population-based estimate. Arch Dermatol 139, 282–288 (2003).Article

Tsao，H.，Bevona，C.，Goggins，W。＆Quinn，T。痣（黑素细胞痣）向皮肤黑色素瘤的转化率：基于人群的估计。Arch Dermatol 139282-288（2003）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Ghiasvand, R. et al. Association of phenotypic characteristics and UV radiation exposure with risk of melanoma on different body sites. JAMA Dermatol 155, 39–49 (2019).Article

Ghiasvand，R.等人。表型特征和紫外线辐射暴露与不同身体部位黑色素瘤风险的关联。JAMA Dermatol 155,39-49（2019）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Download referencesAcknowledgementsDoug Canfield and Lisong Sun of Canfield Scientific, Inc. have provided resources and expertise during development of the ISIC2024 Tile Export Tool. Brian Helba and Dan LaManna of Kitware are the main developers and maintainers of the ISIC Archive, which hosts the data and serves as the sharing platform for each contributor.

下载参考文献致谢Canfield Scientific，Inc.的Doug Canfield和Lisong Sun在开发ISIC024瓷砖导出工具期间提供了资源和专业知识。Kitware的BrianHelba和DanLamanna是ISIC Archive的主要开发人员和维护人员，ISIC Archive托管数据并作为每个贡献者的共享平台。

Rachel Stephenson and Leonid Zaytsev performed data extraction and subselection for University of Sydney and Melanoma Institute Australia. Dr. Noel Codella participated in the ISIC Challenge planning committee meetings that informed plans for the dataset. This work was funded in part by NIH/NCI U24-CA285296, NIH/NCI U24-CA264369, MSK Cancer Center Support Grant/Core Grant (P30 CA008748), and the European Union through project iToBoS (SC1-BHC-06-2020-965221).

瑞秋·斯蒂芬森（RachelStephenson）和莱昂尼德·扎伊采夫（LeonidZaytsev）为悉尼大学和澳大利亚黑色素瘤研究所进行了数据提取和亚选择。Noel Codella博士参加了ISIC挑战计划委员会会议，为数据集的计划提供了信息。这项工作部分由NIH/NCI U24-CA285296，NIH/NCI U24-CA264369，MSK癌症中心支持拨款/核心拨款（P30 CA008748）和欧盟通过iToBoS项目（SC1-BHC-06-2020-965221）资助。

The 2024 ISIC Grand Challenge is supported in part by Kaggle. Lastly, we are gracious for the clinical staff at each contributing center for their effort in photographing patients with the WB360 and for the patients who contributed images to the dataset.Author informationAuthors and AffiliationsDermatology Service, Department of Medicine, Memorial Sloan Kettering Cancer Center, New York, New York, USANicholas R.

2024年ISIC大挑战部分由卡格尔支持。最后，我们感谢每个贡献中心的临床工作人员为WB360拍摄患者以及为数据集贡献图像的患者所做的努力。。

Kurtansky, Maura C. Gillis, Allan C. Halpern, Kivanc Kose, Jochen Weber & Veronica RotembergCanfield Scientific, Inc., Parsippany, New Jersey, USABrian M. D’AlessandroFrazer Institute, The University of Queensland, Dermatology Research Centre, Brisbane, Queensland, AustraliaBrigid Betz-Stablein, Adam Mothershaw & H.

Kurtansky，Maura C.Gillis，Allan C.Halpern，Kivanc Kose，Jochen Weber＆Veronica RotembergCanfield Scientific，Inc.，新泽西州帕西帕尼，USABrian M.D'AlessandroFrazer Institute，昆士兰大学皮肤病研究中心，澳大利亚布里斯班Betz Stablein，Adam Mothershaw＆H。

Peter SoyerDepartment of Dermatology, University Hospital of Basel, Basel, SwitzerlandSara E. Cerminara, Elisabeth Victoria Goessinger, Philippe Gottfrois, Alina M. Mueller & Alexander A. NavariniComputer Vision and Robotics .

巴塞尔大学医院皮肤科彼得·索耶（PeterSoyerdepartment of Dermatology），巴塞尔，瑞士塞尔米纳拉（SwitzerlandSara E.Cerminara），伊丽莎白·维多利亚·戈辛格（ElisabethVictoria Goessinger），菲利普·戈特福利斯（Philippe Gottfrois），艾琳娜·M·米勒（Alina M.Mueller）和亚历山大·纳瓦里尼（Alexander A.Navar。

PubMed Google ScholarBrian M. D’AlessandroView author publicationsYou can also search for this author in

PubMed谷歌学者M.D'AlessandroView作者出版物您也可以在

PubMed Google ScholarMaura C. GillisView author publicationsYou can also search for this author in

PubMed Google ScholarMaura C.GillisView作者出版物您也可以在

PubMed Google ScholarBrigid Betz-StableinView author publicationsYou can also search for this author in

PubMed Google Scholarbriff Betz StableinView作者出版物您也可以在

PubMed Google ScholarSara E. CerminaraView author publicationsYou can also search for this author in

PubMed Google ScholarSara E.CerminaraView作者出版物您也可以在

PubMed Google ScholarRafael GarciaView author publicationsYou can also search for this author in

PubMed Google Scholarafael GarciaView作者出版物您也可以在

PubMed Google ScholarMarcela Alves GirundiView author publicationsYou can also search for this author in

PubMed Google ScholarMarcela Alves GirundiView作者出版物您也可以在

PubMed Google ScholarElisabeth Victoria GoessingerView author publicationsYou can also search for this author in

PubMed Google ScholarElisabeth Victoria GoessingerView作者出版物您也可以在

PubMed Google ScholarPhilippe GottfroisView author publicationsYou can also search for this author in

PubMed Google ScholarPhilippe GottfroisView作者出版物您也可以在

PubMed Google ScholarPascale GuiteraView author publicationsYou can also search for this author in

PubMed Google ScholarPascale GuiteraView作者出版物您也可以在

PubMed Google ScholarAllan C. HalpernView author publicationsYou can also search for this author in

PubMed Google ScholarAllan C.HalpernView作者出版物您也可以在

PubMed Google ScholarValerie JakrotView author publicationsYou can also search for this author in

PubMed谷歌学者Valerie JakrotView作者出版物您也可以在

PubMed Google ScholarHarald KittlerView author publicationsYou can also search for this author in

PubMed Google ScholarHarald KittlerView作者出版物您也可以在

PubMed Google ScholarKivanc KoseView author publicationsYou can also search for this author in

PubMed Google ScholarKivanc KoseView作者出版物您也可以在

PubMed Google ScholarKonstantinos LiopyrisView author publicationsYou can also search for this author in

PubMed Google ScholarKonstantinos LiopyrisView作者出版物您也可以在

PubMed Google ScholarJosep MalvehyView author publicationsYou can also search for this author in

PubMed Google ScholarJosep MalvehyView作者出版物您也可以在

PubMed Google ScholarVictoria J. MarView author publicationsYou can also search for this author in

PubMed Google ScholarVictoria J.MarView作者出版物您也可以在

PubMed Google ScholarLinda K. MartinView author publicationsYou can also search for this author in

PubMed Google ScholarLinda K.MartinView作者出版物您也可以在

PubMed Google ScholarThomas MathewView author publicationsYou can also search for this author in

PubMed Google ScholarThomas MathewView作者出版物您也可以在

PubMed Google ScholarLara Valeska MaulView author publicationsYou can also search for this author in

PubMed Google ScholarLara Valeska MaulView作者出版物您也可以在

PubMed Google ScholarAdam MothershawView author publicationsYou can also search for this author in

PubMed Google ScholarAdam MothershawView作者出版物您也可以在

PubMed Google ScholarAlina M. MuellerView author publicationsYou can also search for this author in

PubMed Google ScholarAlina M.MuellerView作者出版物您也可以在

PubMed Google ScholarChristoph MuellerView author publicationsYou can also search for this author in

PubMed Google ScholarChristoph MuellerView作者出版物您也可以在

PubMed Google ScholarAlexander A. NavariniView author publicationsYou can also search for this author in

PubMed Google ScholarAlexander A.NavariniView作者出版物您也可以在

PubMed Google ScholarTarlia RajeswaranView author publicationsYou can also search for this author in

PubMed Google ScholarTarlia RajeswaranView作者出版物您也可以在

PubMed Google ScholarVin RajeswaranView author publicationsYou can also search for this author in

PubMed Google ScholarVin RajeswaranView作者出版物您也可以在

PubMed Google ScholarAnup SahaView author publicationsYou can also search for this author in

PubMed Google ScholarAnup SahaView作者出版物您也可以在

PubMed Google ScholarMaithili SashindranathView author publicationsYou can also search for this author in

PubMed Google ScholarMaithili SashindranathView作者出版物您也可以在

PubMed Google ScholarLaura Serra-GarcíaView author publicationsYou can also search for this author in

PubMed Google ScholarLaura Serra GarcíaView作者出版物您也可以在

PubMed Google ScholarH. Peter SoyerView author publicationsYou can also search for this author in

PubMed Google ScholarH.PeterSoyerview作者出版物您也可以在

PubMed Google ScholarGeorgios TheocharisView author publicationsYou can also search for this author in

PubMed Google ScholarGeorgios TheocharisView作者出版物您也可以在

PubMed Google ScholarAyesha VosView author publicationsYou can also search for this author in

PubMed Google ScholarAyesha VosView作者出版物您也可以在

PubMed Google ScholarJochen WeberView author publicationsYou can also search for this author in

PubMed.；谷歌学术Jochen Weber查看作者出版物您也可以在

PubMed Google ScholarVeronica RotembergView author publicationsYou can also search for this author in

PubMed Google ScholarVeronica RotembergView作者出版物您也可以在

PubMed Google ScholarContributionsN. Kurtansky designed and collated the dataset, wrote the manuscript, and performed quality review. B. D’Alessandro developed the LV software that detects lesions from 3D TBP captures and the ISIC2024 Tile Export Tool. K. Kose and J. Weber assisted in drafting the manuscript and developed the programmatic assessments for duplicate image detection.

PubMed谷歌学术贡献。库坦斯基设计并整理了数据集，撰写了手稿，并进行了质量审查。B、 D'Alessandro开发了LV软件，可从3D TBP捕获和ISIC024瓷砖导出工具中检测病变。K、 Kose和J.Weber协助起草了手稿，并开发了重复图像检测的程序评估。

M. Gillis performed quality review steps. V. Rotemberg and A. Halpern collected data and provided executive leadership on the project. H. Kittler, K. Liopyris, J. Malvehy, V. Mar, L.V. Maul, A. Navarini, V. Rajeswaran, and H.P. Soyer collected and contributed data. B. Betz-Stablein, P. Gottfrois, A.

M、 吉利斯执行了质量审查步骤。五、 Rotemberg和A.Halpern收集了数据，并为项目提供了执行领导。H、 Kittler，K。Liopyris，J。Malvehy，V。Mar，L.V。Maul，A。Navarini，V。Rajeswaran和H.P。Soyer收集并贡献了数据。B、 。

Mothershaw, C. Mueller, T. Rajeswaran, M. Sashindranath, L. Serra-García, and G. Theocharis performed data extraction and collation. S. Cerminara, M.A. Girundi, E. Goessinger, T. Mathew, and A. Mueller recruited and imaged patients. A. Vos imaged patients and collated data. P. Guitera was involved in conceptualizing triage using 3D TBP.

Mothershaw，C。Mueller，T。Rajeswaran，M。Sashindranath，L。Serra García和G。Theocharis进行了数据提取和整理。S、 Cerminara，M.A.Girundi，E.Goessinger，T.Mathew和A.Mueller招募并成像了患者。A、 Vos对患者成像并整理数据。P、 Guitera使用3D TBP参与了分类的概念化。

V. Jakrot and L. Martin provided administrative support. R. Garcia and A. Saha provided technical support. All authors helped edit the final manuscript.Corresponding authorCorrespondence to.

五、 Jakrot和L.Martin提供了行政支持。R、 加西亚和A.萨哈提供了技术支持。。对应作者对应。

Nicholas R. Kurtansky.Ethics declarations

尼古拉斯·R·库坦斯基。道德宣言

Competing interests

相互竞争的利益

B. D’Alessandro is an employee of Canfield Scientific, Inc. B. Betz-Stablein is anticipating employment with Canfield Scientific, Inc. H. Halpern receives consultation fees from Canfield Scientific, Inc. H. Kittler has received speaker honoraria from Fotofinder, is an advisor of Fotofinder and AI Medical Technology, and has received license fees from Heine, Casio, MetaOptima, and Barco.

B、 D'Alessandro是Canfield Scientific，Inc.的员工。B.Betz Stablein期望受雇于Canfield Scientific，Inc.H.Halpern从Canfield Scientific，Inc.获得咨询费。H.Kittler从Fotofinder获得演讲者酬金，是Fotofinder和AI Medical Technology的顾问，并从Heine，Casio，MetaOptima和Barco获得许可费。

H. Kittler has received equipment from Heine, Casio, and DermaMedical. J. Malvehy is co-founder of Athena Tech, scientific advisor of Dermavision, and is chairman of the Task Force of Artificial Intelligence of the EADV. V. Mar has received speaker fees from Novartis, Bristol Myers Squibb, Merck and Janssen, and has participated in Advisory Boards for MSD, L’Oreal, and SkylineDx.

H、 基特勒从海涅（Heine）、卡西欧（Casio）和德玛医疗（DermaMedical）那里获得了设备。J、 马尔维是雅典娜科技公司的联合创始人，Dermavision的科学顾问，也是EADV人工智能工作组的主席。五、 。

L. Martin is funded by the Warwick L Morison Professorship in dermatology. A. Navarini and L.V. Maul received a grant from Canfield Scientific, Inc. for physician salary in a separate study that had no influence on this manuscript. H.P. Soyer is a shareholder of MoleMap N.Z. Limited and e-derm consult GmbH, and undertakes regular teledermatological reporting for both companies.

五十、 Martin由Warwick L Morison皮肤病学教授资助。A、 Navarini和L.V.Maul在另一项对本手稿没有影响的研究中获得了Canfield Scientific，Inc.的医生工资资助。H、 P.Soyer是MoleMap N.Z.Limited和e-derm consult GmbH的股东，并为两家公司定期进行远程皮肤病报告。

H.P. Soyer is a Medical Consultant for Canfield Scientific, Inc. and a Medical Advisor for First Derm. H.P. Soyer is involved in several committees of the Australiasian College of Dermatology. V. Rotemberg is a consultant for Inhabit Brands, Inc., and receives in kind support from Kaggle and AWS..

H、 P.Soyer是Canfield Scientific，Inc.的医学顾问和First Derm的医学顾问。H、 P.Soyer参与了澳大利亚皮肤病学院的几个委员会。五、 Rotemberg是Inbitin Brands，Inc.的顾问，并获得Kaggle和AWS的实物支持。。

Additional informationPublisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.Rights and permissions

Additional informationPublisher的注释Springer Nature在已发布的地图和机构隶属关系中的管辖权主张方面保持中立。权限和权限

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.

开放获取本文是根据知识共享署名4.0国际许可证授权的，该许可证允许以任何媒体或格式使用，共享，改编，分发和复制，只要您对原始作者和来源给予适当的信任，提供知识共享许可证的链接，并指出是否进行了更改。

The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.

本文中的图像或其他第三方材料包含在文章的知识共享许可中，除非在材料的信用额度中另有说明。如果材料未包含在文章的知识共享许可中，并且您的预期用途不受法律法规的许可或超出许可用途，则您需要直接获得版权所有者的许可。

To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/..

要查看此许可证的副本，请访问http://creativecommons.org/licenses/by/4.0/..

Reprints and permissionsAbout this articleCite this articleKurtansky, N.R., D’Alessandro, B.M., Gillis, M.C. et al. The SLICE-3D dataset: 400,000 skin lesion image crops extracted from 3D TBP for skin cancer detection.

转载和许可本文引用本文Kurtansky，N.R.，D'Alessandro，B.M.，Gillis，M.C.等人的SLICE-3D数据集：从3D TBP中提取400000个皮肤病变图像作物，用于皮肤癌检测。

Sci Data 11, 884 (2024). https://doi.org/10.1038/s41597-024-03743-wDownload citationReceived: 03 June 2024Accepted: 05 August 2024Published: 14 August 2024DOI: https://doi.org/10.1038/s41597-024-03743-wShare this articleAnyone you share the following link with will be able to read this content:Get shareable linkSorry, a shareable link is not currently available for this article.Copy to clipboard.

Sci数据11884（2024）。https://doi.org/10.1038/s41597-024-03743-wDownload引文接收日期：2024年6月3日接受日期：2024年8月5日发布日期：2024年8月14日OI：https://doi.org/10.1038/s41597-024-03743-wShare本文与您共享以下链接的任何人都可以阅读此内容：获取可共享链接对不起，本文目前没有可共享的链接。复制到剪贴板。

Provided by the Springer Nature SharedIt content-sharing initiative

由Springer Nature SharedIt内容共享计划提供