This collection contains the 15 images uploaded for "Dermoscopic Features of Infundibulocystic Basal Cell Carcinoma (IBCC): An Observational Study."

A small study evaluated the accuracy of smartphone and web-based dermatology apps offering AI diagnostics using an independent test set of clinical images. Sun MD, Kentley J, Mehta P, Dusza S, Halpern AC, Rotemberg V. Accuracy of commercially available smartphone applications for the detection of melanoma. Br J Dermatol. 2022;186(4):744-746. doi:10.1111/bjd.20903

Digital camera photographs of the posterior trunk of patients at risk for melanoma, taken at UPMC Hillman Cancer Center as part of the 96-099 image/tissue banking protocol. Images from "Development and narrow validation of computer vision approach to facilitate assessment of change in pigmented cutaneous lesions," corresponding author John M Kirkwood.

Images captured with an RCM device.

Moles and melanomas. Biopsy-confirmed melanocytic lesions. Both malignant and benign lesions are included.

Validation set from the ISIC 2018 Challenge. When using the ISIC 2018 datasets in your research, please cite the following works: > [1] Noel Codella, Veronica Rotemberg, Philipp Tschandl, M. Emre Celebi, Stephen Dusza, David Gutman, Brian Helba, Aadi Kalloo, Konstantinos Liopyris, Michael Marchetti, Harald Kittler, Allan Halpern: "Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)", 2018; arxiv.org/abs/1902.03368 > > [2] 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 doi:10.1038/sdata.2018.161 (2018).

Seborrheic keratoses obtained from patients during a clinical visit. These lesions were not biopsied and were determined to be seborrheic keratoses by agreement of three experts.

127 dermoscopic and clinical images matched to already published longitudinal images in the Archive

Validation set from the ISIC 2017 Challenge.

Contributed to the ISIC Archive by Dr. Cristián Naverrete et al.

A collection of dermoscopic images of biopsied melanocytic lesions. This was used to test for performance degradation of an AI melanoma classifier in discriminating melanomas from nevi among newly-acquired melanocytic lesions versus longer-existing acquired melanocytic lesions.

Validation set from the ISIC 2018 Challenge. When using the ISIC 2018 datasets in your research, please cite the following works: > [1] Noel Codella, Veronica Rotemberg, Philipp Tschandl, M. Emre Celebi, Stephen Dusza, David Gutman, Brian Helba, Aadi Kalloo, Konstantinos Liopyris, Michael Marchetti, Harald Kittler, Allan Halpern: "Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)", 2018; arxiv.org/abs/1902.03368 > > [2] 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 doi:10.1038/sdata.2018.161 (2018).

A collection of 248 melanocytic lesions that were submitted by experts as exemplars for 1 out of 31 dermoscopic features (8 images per feature), and used for evaluating agreement among (unrelated) experts on (1) malignancy, (2) feature presence, and (3) feature localization within a lesion. The repository of image masks and superpixel annotations is here: https://github.com/ISIC-Research/expert-annotation-agreement-data

248 dermoscopic images of melanocytic lesions (nevi and melanomas). The images were selected for exemplars of specific features, were contributed by 21 dermoscopy experts from around the world, and are comprised of 113 nevi and 133 melanomas (plus 1 AIMP and 1 dermatofibroma).

150 Seborrheic Keratoses contributed to the ISIC Archive by Dr. Cristián Naverrete et al. for the purpose of annotating dermoscopic features, matched with 150 prior contributed images.

Test set from the ISIC 2016 Challenge. The "Skin Lesion Analysis Towards Melanoma Detection" challenge leverages a dataset of annotated skin lesion images from the ISIC Archive, The dataset contains a representative mix of images of both malignant and benign skin lesions.

Assorted images and lesions, mostly nevi and basal cell carcinomas. These images were found based on a search not filtered for any particular pathology. All diagnoses confirmed by histopathology.

Moles and melanomas. Biopsy-confirmed melanocytic lesions. Both malignant and benign lesions are included.

Dataset from a prospective, observational clinical cohort study to assess the consistency of two commercially available convolutional neural networks (CNNs) in classifying melanoma risk of five sequentially acquired dermoscopic images of melanocytic lesions on the torso. 117 repeat image series of 116 melanocytic lesions from 66 patients were included. Biopsies were performed in cases of suspected melanoma or two consecutive elevated CNN risk scores. Expert consensus including 1-year follow-up images (where available) confirmed benign dignity of lesions without histological assessment. Goessinger EV, Cerminara SE, Mueller AM, et al. Consistency of convolutional neural networks in dermoscopic melanoma recognition: A prospective real-world study about the pitfalls of augmented intelligence. J Eur Acad Dermatol Venereol. 2024;38(5):945-953. doi:10.1111/jdv.19777

Test set from the ISIC 2017 Challenge.

We conducted a prospective, observational clinical validation study to assess the diagnostic accuracy of the AI algorithm (ADAE) in predicting melanoma from dermoscopy skin lesion images. Patients who had consented for a skin biopsy to exclude melanoma were eligible. All lesions underwent biopsy.

The BRAAFF-Annotated Acral Lesions Dataset (BALD): A curated set of dermatoscopic images of acral melanoma and nevi from various sources. Müller C, Tschandl P, Rinner C, Kyrgidis A, Koga H, Moscarella E, Apalla Z, Di Stefani A, Kobayashi K, Lazaridou E, Longo C, Phan A, Saida T, Sotiriou E, Tanaka M, Thomas L, Zalaudek I, Argenziano G, Lallas A, Kittler H. The BRAAFF-Annotated Acral Lesions Dataset (BALD): A Curated Set of Dermatoscopic Images of Acral Melanoma and Nevi from Various Sources. J Invest Dermatol. 2025 Jan 17:S0022-202X(25)00021-1 [Additional metadata available here](https://github.com/kittler/BALD)

Training set from the ISIC 2016 Challenge. The "Skin Lesion Analysis Towards Melanoma Detection" challenge leverages a dataset of annotated skin lesion images from the ISIC Archive, The dataset contains a representative mix of images of both malignant and benign skin lesions.

*MILK10k Benchmark* consists of paired clinical close-up and dermatoscopic image for a set of lesions. The dataset’s metadata include age (in 5-year intervals), sex, anatomic site, and skin tone. Skin tone is categorized into six levels, ranging from very dark (0) to very light (5), intentionally distinct from the Fitzpatrick skin types to avoid confusion. Most patients had skin tones in the middle ranges. Diagnoses were mapped to a simplified classification based on the ISIC2018/2019 challenge and HAM10000 diagnostic categories. The dataset includes 11 broad diagnostic categories: 1. Basal cell carcinoma (bcc) 2. Melanocytic nevus (nv) 3. Benign keratinocytic lesion (bkl) 4. Squamous cell carcinoma/keratoacanthoma (sccka) 5. Melanoma (mel) 6. Actinic keratosis/intraepidermal carcinoma (akiec) 7. Dermatofibroma (df) 8. Inflammatory and infectious conditions (inf) 9. Vascular lesions and hemorrhage (vasc) 10. Other benign proliferations including collision tumors (ben_oth) 11. Other malignant proliferations including collision tumors (mal_oth) Although these broad diagnostic categories align with those in MILK10k, there can be different underlying granular diagnoses, primarily in the broad categories “other benign” and “other malignant proliferations”. Furthermore, all images have been annotated using the MONET framework, with probabilities for the following concept term groups included in the metadata: 1. Ulceration, crust 2. Hair 3. Vasculature, vessels 4. Erythema 5. Pigmentation 6. Gel, water drop, fluid, dermoscopy liquid 7. Skin markings, pen ink, purple pen *MILK10k Benchmark* is the accompanying test set to the *MILK10k* dataset and covers the same diagnostic categories. *MILK10k* is available on the ISIC Archive. Images were provided by the following institutions: - Department of Dermatology, Medical University of Vienna, Vienna, Austria - Medicine Faculty Department of Dermatology, Ankara University, Ankara, Turkey - Mayne Academy of General Practice, Medical School, The University of Queensland, Australia - Dermatology Service, Memorial Sloan Kettering Cancer Center, New York, USA - Independent Researcher, 1000 Skopje, North Macedonia

Test set from the ISIC 2018 Challenge. The lesion images come from the [HAM10000 Dataset](https://doi.org/10.7910/DVN/DBW86T), and were acquired with a variety of [dermatoscope types](https://dermoscopedia.org/Principles_of_dermoscopy), from all anatomic sites (excluding mucosa and nails), from a historical sample of patients presented for skin cancer screening, from several different institutions. Images were collected with approval of the Ethics Review Committee of University of Queensland (Protocol-No. 2017001223) and Medical University of Vienna (Protocol-No. 1804/2017). The distribution of disease states represent a modified "real world" setting whereby there are more benign lesions than malignant lesions, but an over-representation of malignancies. When using the ISIC 2018 datasets in your research, please cite the following works: > [1] Noel Codella, Veronica Rotemberg, Philipp Tschandl, M. Emre Celebi, Stephen Dusza, David Gutman, Brian Helba, Aadi Kalloo, Konstantinos Liopyris, Michael Marchetti, Harald Kittler, Allan Halpern: "Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)", 2018; arxiv.org/abs/1902.03368 > > [2] 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 doi:10.1038/sdata.2018.161 (2018).

Consecutive biopsies of lesions with nevus, melanoma, lentigo, etc. in the clinical OR histologic diagnosis at Memorial Sloan Kettering Cancer Center between 1/1/2020 and 12/31/2020.

Consecutive biopsies of lesions with nevus, melanoma, lentigo, etc. in the clinical OR histologic diagnosis at MSKCC between 1/1/2020 and 12/31/2020.

Test set from the ISIC 2018 Challenge. When using the ISIC 2018 datasets in your research, please cite the following works: > [1] Noel Codella, Veronica Rotemberg, Philipp Tschandl, M. Emre Celebi, Stephen Dusza, David Gutman, Brian Helba, Aadi Kalloo, Konstantinos Liopyris, Michael Marchetti, Harald Kittler, Allan Halpern: "Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)", 2018; arxiv.org/abs/1902.03368 > > [2] 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 doi:10.1038/sdata.2018.161 (2018).

A dataset of clinical and dermoscopy images of skin lesions collected in Argentina as a reference for the evaluation of AI tools in this population. Supplementary data and an exploratory analysis of the data are publicly available at https://github.com/piashiba/HIBASkinLesionsDataset.

A dataset of clinical and dermoscopy images of skin lesions collected in Argentina as a reference for the evaluation of AI tools in this population

A dataset of clinical and dermoscopy images of skin lesions collected in Argentina as a reference for the evaluation of AI tools in this population

Both benign and malignant melanocytic lesions. Almost all diagnoses were confirmed by histopathology reports; the remainder consists of benign lesions confirmed by clinical follow-up. Images were not taken with modern digital cameras.

Training set from the ISIC 2017 Challenge.

Images found based on a search for patients with a personal history, clinical diagnosis, or differential diagnosis of melanoma. All diagnoses confirmed by histopathology.

Full name: PAD-UFES-20: a skin lesion dataset composed of patient data and clinical images collected from smartphones Full data descriptor published by Pacheco et al. at https://doi.org/10.1016/j.dib.2020.106221 Pacheco AGC, Lima GR, Salomão AS, et al. PAD-UFES-20: A skin lesion dataset composed of patient data and clinical images collected from smartphones. Data Brief. 2020;32:106221. Published 2020 Aug 25. doi:10.1016/j.dib.2020.106221 Summary description - The PAD-UFES-20 dataset was collected along with the Dermatological and Surgical Assistance Program (in Portuguese: Programa de Assistência Dermatológica e Cirurgica - PAD) at the Federal University of Espírito Santo (UFES-Brazil), which is a nonprofit program that provides free skin lesion treatment, in particular, to low-income people who cannot afford private treatment. - The dataset consists of 2,298 samples of six different types of skin lesions. Each sample consists of a clinical image and up to 22 clinical features including the patient's age, skin lesion location, Fitzpatrick skin type, and skin lesion diameter. - The skin lesions are: Basal Cell Carcinoma (BCC), Squamous Cell Carcinoma (SCC), Actinic Keratosis (ACK), Seborrheic Keratosis (SEK), Bowen’s disease (BOD), Melanoma (MEL), and Nevus (NEV). As the Bowen’s disease is considered SCC in situ, we clustered them together, which results in six skin lesions in the dataset, three skin cancers (BCC, MEL, and SCC) and three skin disease (ACK, NEV, and SEK) - All BCC, SCC, and MEL are biopsy-proven. The remaining ones may have clinical diagnosis according to a consensus of a group of dermatologists. In total, approximately 58% of the samples in this dataset are biopsy-proven. This information is described in the metadata. - The images present in the dataset have different sizes because they are collected using different smartphone devices. All images are available in .png format. - The metadata associated with each skin lesion is composed of up to 26 features. All features are available in a CSV document in which each line represents a skin lesion and each column a metadata feature. - In total, there are 1,373 patients and 2,298 images present in the dataset. Each image/sample has a reference to the patient and the skin lesion in the metadata. Ethics statement The dataset was collected along with the Dermatological and Surgical Assistance Program (PAD) of the Federal University of Espírito Santo. The program is managed by the Department of Specialized Medicine and was approved by the university ethics committee (nº 500002/478) and the Brazilian government through Plataforma Brasil (nº 4.007.097), the Brazilian agency responsible for research involving human beings. In addition, all data is collected under patient consent and the patient’s privacy is completely preserved. Data is also available on Mendeley at https://doi.org/10.17632/zr7vgbcyr2.1

Training set from the ISIC 2018 Challenge. When using the ISIC 2018 datasets in your research, please cite the following works: > [1] Noel Codella, Veronica Rotemberg, Philipp Tschandl, M. Emre Celebi, Stephen Dusza, David Gutman, Brian Helba, Aadi Kalloo, Konstantinos Liopyris, Michael Marchetti, Harald Kittler, Allan Halpern: "Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)", 2018; arxiv.org/abs/1902.03368 > > [2] 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 doi:10.1038/sdata.2018.161 (2018).

Dermoscopic lesion images (close-up views of benign and malignant lesions) from the MEL-SELF trial (the Melanoma Self Surveillance trial).

This dataset contains detailed skin tone annotations collected from a prospective, single-center observational study performed at Memorial Sloan Kettering Cancer Center from 2023-2024. The cohort consists of 64 adult patients who underwent full-body skin examinations by board-certified dermatologists. To ensure diverse representation across the spectrum of skin tones, patients were recruited to achieve a balanced distribution across all six Fitzpatrick Skin Types. This dataset was developed to evaluate the reliability of different skin tone labeling methods and to support fairness research in dermatologic AI. The dataset comprises both patient-level and site-level metadata for skin tone classification using the Fitzpatrick Skin Type scale, Monk Skin Tone scale, Pantone SkinTone Guide, and colorimeter readings (SkinColorCatch, Delfin Technologies). A total of 4,879 dermoscopic images are included. Skin tone assessments were collected across both lesional and non-lesional (normal skin) sites, mapped to standardized anatomic locations. All skin lesions are assumed to be benign, as they were imaged immediately following dermatologic evaluation. All data were collected under an IRB-approved protocol with informed consent. The dataset has been fully de-identified in accordance with HIPAA regulations, and no protected health information (PHI) is included.

Biopsy-confirmed melanocytic and non-melanocytic skin lesions. This dataset includes over 500 melanomas. Many images have polarized and contact variants.

Test set from the ISIC 2019 Challenge.

Moles in children. Benign melanocytic lesions from a pediatric population. The benign nature of the lesions is based on clinical assessment and/or no change on serial imaging.

These are the images used in the paper: Analysis of the ISIC image datasets: Usage, benchmarks and recommendations Paper Link: https://www.sciencedirect.com/science/article/pii/S1361841521003509 They have also been used by newer versions such as: Skin Lesion Classification Using Dermoscopic Images and Clinical Metadata: Insights from Multimodal Models Paper Link: https://openaccess.thecvf.com/content/CVPR2025W/MULA2025/papers/Ahammed_Skin_Lesion_Classification_Using_Dermoscopic_Images_and_Clinical_Metadata_Insights_CVPRW_2025_paper.pdf https://api.isic-archive.com/collections/469/

Training set from the ISIC 2018 Challenge. When using the ISIC 2018 datasets in your research, please cite the following works: > [1] Noel Codella, Veronica Rotemberg, Philipp Tschandl, M. Emre Celebi, Stephen Dusza, David Gutman, Brian Helba, Aadi Kalloo, Konstantinos Liopyris, Michael Marchetti, Harald Kittler, Allan Halpern: "Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)", 2018; arxiv.org/abs/1902.03368 > > [2] 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 doi:10.1038/sdata.2018.161 (2018).

*MILK10k* consists of 10480 images, each representing a paired clinical close-up and dermatoscopic image for 5240 lesions. The dataset’s metadata include age (in 5-year intervals), sex, anatomic site, skin tone, diagnosis, method of ground truth establishment (histopathology or other means), and, if a dermatoscopic image of the same lesion was previously included in ISIC, its corresponding ISIC identifier. Skin tone is categorized into six levels, ranging from very dark (0) to very light (5), intentionally distinct from the Fitzpatrick skin types to avoid confusion. Most patients had skin tones in the middle ranges. Of the 5240 lesions, 95.7% were biopsied or excised, with histopathology serving as the gold standard for diagnosis. Diagnoses were mapped to both the ISIC-Dx diagnostic scheme and a simplified classification based on the ISIC2018/2019 challenge and HAM10000 diagnostic categories. The dataset includes 11 broad diagnostic categories: 1. Basal cell carcinoma (bcc) 2. Melanocytic nevus (nv) 3. Benign keratinocytic lesion (bkl) 4. Squamous cell carcinoma/keratoacanthoma (sccka) 5. Melanoma (mel) 6. Actinic keratosis/intraepidermal carcinoma (akiec) 7. Dermatofibroma (df) 8. Inflammatory and infectious conditions (inf) 9. Vascular lesions and hemorrhage (vasc) 10. Other benign proliferations including collision tumors (ben_oth) 11. Other malignant proliferations including collision tumors (mal_oth) Additionally, we provide the most specific ISIC-Dx diagnosis and its parent branch in the ISIC-Dx diagnostic tree. In cases where a dermatoscopic image of the same lesion was already included in the ISIC archive, its ISIC identifier is reported in the metadata. Furthermore, all images have been annotated using the MONET framework, with probabilities for the following concept term groups included in the metadata: 1. Ulceration, crust 2. Hair 3. Vasculature, vessels 4. Erythema 5. Pigmentation 6. Gel, water drop, fluid, dermoscopy liquid 7. Skin markings, pen ink, purple pen In addition to *MILK10k*, we have curated a smaller benchmark dataset, called *MILK10k Benchmark* derived from the same sources and covering the same diagnostic categories. This dataset is available as part of a live challenge within the ISIC framework and can be accessed on ISIC. Images were provided by the following institutions: - Department of Dermatology, Medical University of Vienna, Vienna, Austria - Medicine Faculty Department of Dermatology, Ankara University, Ankara, Turkey - Mayne Academy of General Practice, Medical School, The University of Queensland, Australia - Dermatology Service, Memorial Sloan Kettering Cancer Center, New York, USA - Independent Researcher, 1000 Skopje, North Macedonia

Evaluation set from the ML challenge: [SIIM-ISIC Melanoma Classification](https://www.kaggle.com/c/siim-isic-melanoma-classification/leaderboard).

This dataset contains 11,720 segmentation masks created for the ISIC 2018 dataset. The masks were initially generated using a U-Net model trained on the IMA++ dataset, and then manually reviewed, with corrections made where necessary. When lesion boundaries were unknown, a similarity search was performed across the entire IMA++ dataset to find a reference. If the search failed to find a truly similar match, the manual segmentation focused on capturing outlier details in the center of the image, which may bias the data toward the middle of the frame. Easter egg image ISIC_0035068 is intentionally left completely black with no segmentation. Additionally, some minor artefacts are present: certain masks slightly overlap onto the surrounding skin, some edges appear sharp or spiky. If two skin lesions were very close together, they were marked as a single lesion. This is based on the assumption that the main lesion of interest is placed in the center of the image. As a result, smaller lesions near the edges of the image were not always segmented. You can read about duplicate data and other quirks of ISIC 2018 (named as DermaMNIST-E in article) https://www.nature.com/articles/s41597-025-04382-5

Dermatoscopic images of the most common classes of pigmented skin lesions: Pigmented Actinic Keratoses / Bowen's disease, Basal Cell Carcinoma, Benign Keratoses (Seborrheic Keratosis, Solar Lentigo and Lichen-Planus Like Keratosis), Dermatofibroma, Melanocytic Nevi, Melanoma and Vascular lesions. Images are made available in preparation for the "Human-Against-Machine with 10000 training images" study, and originate mainly from the ViDIR Group (Department of Dermatology, Medical University of Vienna) and a skin cancer office in Australia (School of Medicine, University of Queensland). Data is provided under the CC BY-NC 4.0 license, attribution should be made by referencing the data descriptor manuscript: 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 doi:10.1038/sdata.2018.161 (2018).

Skin lesion datasets provide essential information for understanding various skin conditions and developing effective diagnostic tools. They aid the artificial intelligence-based early detection of skin cancer, facilitate treatment planning, and contribute to medical education and research. Published large datasets have partially coverage the subclassifications of the skin lesions. This limitation highlights the need for more expansive and varied datasets to reduce false predictions and help improve the failure analysis for skin lesions. This study presents a diverse dataset comprising 12,345 dermatoscopic images with 40 subclasses of skin lesions, collected in Turkiye, which comprises different skin types in the transition zone between Europe and Asia. Each subgroup contains high-resolution images and expert annotations, providing a strong and reliable basis for future research. The detailed analysis of each subgroup provided in this study facilitates targeted research endeavors and enhances the depth of understanding regarding the skin lesions. This dataset distinguishes itself through a diverse structure with its 5 super classes, 15 main classes, 40 subclasses and 12,345 high-resolution dermatoscopic images. Yilmaz, A., Yasar, S.P., Gencoglan, G. et al. DERM12345: A Large, Multisource Dermatoscopic Skin Lesion Dataset with 40 Subclasses. Sci Data 11, 1302 (2024). [https://doi.org/10.1038/s41597-024-04104-3](https://doi.org/10.1038/s41597-024-04104-3)