PH2 - A dermoscopic image database for research and benchmarking
The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Abstract
The increasing incidence of melanoma has recently promoted the development of computer-aided diagnosis systems for the classification of dermoscopic images. Unfortunately, the performance of such systems cannot be compared since they are evaluated in different sets of images by their authors and there are no public databases available to perform a fair evaluation of multiple systems. In this paper, a dermoscopic image database, called PH², is presented. The PH² database includes the manual segmentation, the clinical diagnosis, and the identification of several dermoscopic structures, performed by expert dermatologists, in a set of 200 dermoscopic images. The PH² database will be made freely available for research and benchmarking purposes.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Diagnostic accuracy of dermoscopy
Kittler, H., Pehamberger, H., Wolff, K., & Binder, M. (2002) · The Lancet Oncology · doi:10.1016/s1470-2045(02)00679-4 · Cited by 1,349 · cited 1×
“[3], the diagnosis accuracy of dermoscopy significantly depends on the experience of the dermatologists.”
BackgroundA methodological approach to the classification of dermoscopy images
Celebi, M. E., Kingravi, H. A., Uddin, B., Iyatomi, H., Aslandogan, Y. A., Stoecker, W. V., & Moss, R. H. (2007) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2007.01.003 · Cited by 693 · cited 2×
“system proposed in [12] uses a set of shape, color, and texture related features and a support vector machine (SVM)”
BackgroundMethodAutomated melanoma recognition
Ganster, H., Pinz, P., Rohrer, R., Wildling, E., Binder, M., & Kittler, H. (2001) · IEEE Transactions on Medical Imaging · doi:10.1109/42.918473 · Cited by 631
Computerized analysis of pigmented skin lesions: A review
Korotkov, K., & Garcia, R. (2012) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2012.08.002 · Cited by 355 · cited 1×
“They can also be used as an additional tool by non-experienced clinicians to perform a preliminary evaluation and to improve the patient follow-up procedure [6].”
MethodFitzpatrick skin typing: applications in dermatology
Sachdeva, S. (2009) · Indian Journal of Dermatology, Venereology and Leprology · doi:10.4103/0378-6323.45238 · Cited by 311 · cited 1×
“All dermoscopic images are either from the skin type II or III, according to the Fitzpatrick skin type classification scale [14].”
MethodIyatomi, H., Oka, H., Celebi, M. E., Hashimoto, M., Hagiwara, M., Tanaka, M., & Ogawa, K. (2008) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2008.06.005 · Cited by 230 · cited 2×
“[13] propose a melanoma diagnosis system that is already available in the internet for public use.”
BackgroundCampos‐do‐Carmo, G., & Ramos‐e‐Silva, M. (2008) · International Journal of Dermatology · doi:10.1111/j.1365-4632.2008.03556.x · Cited by 145 · cited 2×
“Therefore, dermoscopic images provide a more detailed view of the morphological structures and patterns as compared to the normally magnified images of the skin lesions [1], [2].”
BackgroundA possible new tool for clinical diagnosis of melanoma: The computer
Cascinelli, N., Ferrario, M., Tonelli, T., & Leo, E. (1987) · Journal of the American Academy of Dermatology · doi:10.1016/s0190-9622(87)70050-4 · Cited by 143 · cited 1×
“Computer-aided diagnosis systems of dermoscopic images have been developed since 1987 [5], in order to support the clinical decision of dermatologists and easily trigger the detection of the highly suspicious cases.”
Maglogiannis, I. G., Pavlopoulos, S. A., & Koutsouris, D. (2005) · IEEE Transactions on Information Technology in Biomedicine · doi:10.1109/titb.2004.837859 · Cited by 95 · cited 1×
“chine learning methodology has been explored to a much larger extent [10], [11], [12], [13].”
BackgroundA software tool for the diagnosis of melanomas
Di Leo, G., Paolillo, A., Sommella, P., Fabbrocini, G., & Rescigno, O. (2010) · 2010 IEEE Instrumentation & Measurement Technology Conference Proceedings · doi:10.1109/imtc.2010.5488165 · Cited by 35 · cited 1×
“An example of a diagnosis system inspired on clinical features can be found in [7].”
Background
Research works printed but not linked: 2
- 0, Dermoscopy Tutorial
- 0, Addi Project
Cited by
Items 201–300 of 1,000
Generative adversarial networks based skin lesion segmentation
Innani, S., Dutande, P. V., Baid, U., Pokuri, V., Bakas, S., Talbar, S. N., Baheti, B., & Guntuku, S. C. (2023) · Scientific Reports · doi:10.1038/s41598-023-39648-8 · Cited by 50
“While segmentation masks were available for the PH2 dataset 46 , we could not access the dataset.”
MethodMDViT: Multi-domain Vision Transformer for Small Medical Image Segmentation Datasets
Du, S., Bayasi, N., Hamarneh, G., & Garbi, R. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43901-8_43 · Cited by 53
FedIIC: Towards Robust Federated Learning for Class-Imbalanced Medical Image Classification
Wu, N., Yu, L., Yang, X. Y., Cheng, K.-T. T., & Yan, Z. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43895-0_65 · Cited by 82
“Real Multi-Source Dermoscopic Image Datasets (denoted as Real ) consisting of five data sources from three datasets, including PH 2 [29], Atlas [1], and HAM10000 [38] where each source is treated as an individual client.”
MethodGenerative AI enables medical image segmentation in ultra low-data regimes
Zhang, L., Jindal, B., Alaa, A. M., Weinreb, R. N., Wilson, D. O., Segal, E., Zou, J., & Xie, P. (2025) · Nature Communications · doi:10.1038/s41467-025-61754-6 · Cited by 79
Skin Hair Removal in Dermoscopic Images Using Soft Color Morphology
Bibiloni, P., González-Hidalgo, M., & Massanet, S. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-59758-4_37 · Cited by 43
“[11] (center right) and our algorithm (right) of sample IMD047 (top) and a detail of sample IMD101 (bottom) of the PH(2) dataset [9].”
BackgroundGenetic programming for skin cancer detection in dermoscopic images
Ain, Q. U., Xue, B., Al-Sahaf, H., & Zhang, M. (2017) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.1109/cec.2017.7969598 · Cited by 43
“A dataset of dermoscopic images namely PH 2 [1] acquired from Pedro Hispano Hospital Portugal, is used in the experiments.”
BackgroundMethodD-LEMA: Deep Learning Ensembles from Multiple Annotations - Application to Skin Lesion Segmentation
Mirikharaji, Z., Abhishek, K., Izadi, S., & Hamarneh, G. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00203 · Cited by 60
“• PH(2): The PH(2) (Pedro Hispano Hospital) dataset contains 200 8-bit RGB color dermoscopic images [26].”
BackgroundMethodSkin Lesion Segmentation by U-Net with Adaptive Skip Connection and Structural Awareness
Phan, T.-D.-T., Kim, S.-H., Yang, H.-J., & Lee, G.-S. (2021) · Applied Sciences · doi:10.3390/app11104528 · Cited by 44
Melanoma recognition using extended set of descriptors and classifiers
Kruk, M., Świderski, B., Osowski, S., Kurek, J., Słowińska, M., & Walecka, I. (2015) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-015-0099-9 · Cited by 46
“The additional experiments have been performed using the data set PH2 available in the Internet [23].”
MethodResultInfluentialIllumination-based Transformations Improve Skin Lesion Segmentation in Dermoscopic Images
Abhishek, K., Hamarneh, G., & Drew, M. S. (2020) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00372 · Cited by 42
Lucius, M., De All, J., De All, J. A., Belvisi, M., Radizza, L., Lanfranconi, M., Lorenzatti, V., & Galmarini, C. M. (2020) · Diagnostics · doi:10.3390/diagnostics10110969 · Cited by 40
“Other open skin lesions datasets containing clinical and dermoscopic images from non-Caucasian human skin types are available, however, these are not as large as the HAM10000 or are not publicly available [51].”
BackgroundMethodA hybrid deep learning approach for skin cancer diagnosis using subband fusion of 3D wavelets
Maniraj, S. P., & Maran, P. S. (2022) · The Journal of Supercomputing · doi:10.1007/s11227-022-04371-0 · Cited by 42
“The proposed HDL approach is analyzed using the PH2 database [25].”
MethodJiji, G. W., & Raj, P. J. D. (2015) · Applied Soft Computing · doi:10.1016/j.asoc.2015.01.058 · Cited by 41
Accurate and Scalable System for Automatic Detection of Malignant Melanoma
Celebi, M. E., Mendonca, T., & Marques, J. S. (2015) · CRC Press eBooks · doi:10.1201/b19107-14 · Cited by 45
Self-citationSkin cancer identification utilizing deep learning: A survey
Meedeniya, D., Silva, S. D., Gamage, L., & Isuranga, U. (2024) · IET Image Processing · doi:10.1049/ipr2.13219 · Cited by 41
Chatterjee, S., Dey, D., Munshi, S., & Gorai, S. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.114204 · Cited by 43
DE-Net: A deep edge network with boundary information for automatic skin lesion segmentation
Gu, R. C., Wang, L., & Zhang, L. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.10.017 · Cited by 41
Melanoma skin cancer detection based on deep learning methods and binary Harris Hawk optimization
Jaber, N. J. F., & Akbaş, A. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-19864-8 · Cited by 46
“The proposed method utilizes the ISIC 2016, ISIC 2017, and ISIC 2019 databases [27], which are sourced from a hospital in Portugal and accessible for download from the ISIC archive website at (https://challenge.isic-archive.com/data/).”
Principal Axes-Based Asymmetry Assessment Methodology for Skin Lesion Image Analysis
Vasconcelos, M. J. M., Rosado, L., & Ferreira, M. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-14364-4_3 · Cited by 39
“The second is the PH database with images collected in the Dermatology Service of Hospital Pedro Hispano (Matosinhos, Portugal) under the scope of the ADDI project [6].”
BackgroundChatterjee, S., Dey, D., & Munshi, S. (2017) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2017.09.028 · Cited by 40
Melanoma recognition in dermoscopy images using lesion's peripheral region information
Tajeddin, N. Z., & Asl, B. M. (2018) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2018.05.005 · Cited by 40
Hajabdollahi, M., Esfandiarpoor, R., Sabeti, E., Karimi, N., Soroushmehr, S. M. R., & Samavi, S. (2019) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2019.101792 · Cited by 40
Pigment network-based skin cancer detection
Alfed, N., Khelifi, F., Bouridane, A., & Şeker, H. (2015) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2015.7320056 · Cited by 39
“The proposed system has been assessed on a dataset of 200 dermoscopic images of the ‘Hospital Pedro Hispano’ [1] and the results of cross-validation have shown high detection accuracy.”
Ali, S., Li, J., Pei, Y., Khurram, R., Rehman, K. U., & Rasool, A. B. (2021) · Cancers · doi:10.3390/cancers13215546 · Cited by 49
“Suspicious areas and relevant pixel-level ground truth information annotated by the radiologist (normal, benign, and malignant image) are included in images [27] [30].”
BackgroundFogelberg, K., Chamarthi, S., Maron, R. C., Niebling, J., & Brinker, T. J. (2023) · New Biotechnology · doi:10.1016/j.nbt.2023.04.006 · Cited by 49
Segmentation of dermoscopy image using adversarial networks
Peng, Y., Wang, N., Wang, Y., & Wang, M. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-6523-2 · Cited by 38
Detection of Malignant Melanoma Using Deep Learning
Gulati, S., & Bhogal, R. K. (2019) · Communications in computer and information science · doi:10.1007/978-981-13-9939-8_28 · Cited by 38
Segmentation of skin lesion images using discrete wavelet transform
Ramya, J., VijayLakshmi, H. C., & Saifuddin, H. M. (2021) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.102839 · Cited by 40
Mabrouk, A., Dahou, A., Elaziz, M. A., Redondo, R. P. D., & Kayed, M. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/9112634 · Cited by 42
“The three datasets investigated were ISIC-2016 [44], PH2 [45] (Both for melanoma detection) and Blood-Cell classification [46].”
MethodBissoto, A. E., Perez, F., Ribeiro, V., Fornaciali, M. S., Avila, S., & Junior, E. A. D. V. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.08480 · Cited by 45
“PH2 Dataset [11] with 200 dermoscopic images.”
ABCD rule and pre-trained CNNs for melanoma diagnosis
Moura, N., Veras, R. D. M. S., Aires, K. R. T., Machado, V. P., Silva, R., Araújo, F. H. D., & Claro, M. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-6404-8 · Cited by 41
“The PH2 database consists of 200 images: 80 common nevi, 80 atypical nevi and 40 melanomas.”
MethodInfluentialMelanoma detection using color and texture features in computer vision systems
Fuduli, A., Veltri, P., Vocaturo, E., & Zumpano, E. (2019) · Advances in Science Technology and Engineering Systems Journal · doi:10.25046/aj040502 · Cited by 37
“In particular, this study was inspired by the good results obtained in [7], where the authors applied Multiple Instance Learning techniques for classifying some medical dermoscopic images drawn from the Ph2 database [8], by using only color features.”
BackgroundMethodGiavina-Bianchi, M., de Sousa, R. M., Paciello, V. Z. D. A., Vitor, W. G., Okita, A. L., Prôa, R., Severino, G. L. D. S., Schinaid, A. A., Espírito Santo, R., & Machado, B. S. (2021) · PLOS ONE · doi:10.1371/journal.pone.0257006 · Cited by 36
Improving Automatic Melanoma Diagnosis Using Deep Learning-Based Segmentation of Irregular Networks
Nambisan, A. K., Maurya, A., Lama, N., Phan, T., Patel, G., Miller, K., Lama, B., Hagerty, J. R., Stanley, R. J., & Stoecker, W. V. (2023) · Cancers · doi:10.3390/cancers15041259 · Cited by 42
“Other datasets have also been used in CAD research, including PH2 [10], which has 200 dermoscopic images with three diagnosis classes, and the Interactive Atlas of Dermoscopy [11], which has over 1000 clinical cases with clinical and dermoscopy images, annotations of specific features,…”
MethodCheng, Z., Guo, J., Zhang, J., Qi, L., Zhou, L., Shi, Y., & Gao, Y. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2025.3564765 · Cited by 68
“This comprehensive dataset comprises 3 , 694 training images [68], [69] and 200 testing images [70], providing a robust platform for assessing Mamba’s performance in large-scale medical image segmentation tasks.”
Bakheet, S. S., & Al-Hamadi, A. K. (2020) · Diagnostics · doi:10.3390/diagnostics10100822 · Cited by 38
“The performance of the proposed system is tested on the PH2 benchmark dataset [49] that consists of a total number of 200 8-bit RGB dermoscopic images of melanocytic lesions with a resolution of 768× 560 pixels.”
MethodBarhoumi, W., & Khelifa, A. (2021) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2021.104825 · Cited by 37
Roy, A., Pal, A., & Garain, U. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2016.12.016 · Cited by 36
“For this purpose, we use the publicly available PH2 [44] dermoscopic image data set.”
MethodDERM12345: A Large, Multisource Dermatoscopic Skin Lesion Dataset with 40 Subclasses
Yılmaz, A., Yaşar, Ş. P., Gençoğlan, G., & Temelkuran, B. (2024) · Scientific Data · doi:10.1038/s41597-024-04104-3 · Cited by 56
“PH 2 dataset was published for benchmarking dermatoscopic images including with three lesion classes (common nevus, atypical nevus and melanoma (mel)) [24].”
Hair detection and lesion segmentation in dermoscopic images using domain knowledge
Pathan, S., Prabhu, K. G., & Siddalingaswamy, P. C. (2018) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-018-1837-9 · Cited by 35
Oukil, S., Kasmi, R., Mokrani, K., & García-Zapirain, B. (2021) · Skin Research and Technology · doi:10.1111/srt.13111 · Cited by 35
“Alfed et al. 15 combine texture (histogram of gradients, histogram of lines) with color vector angles and Zernike moments as features to classify melanoma from benign lesions of PH2 dataset, 16,17 using three classifiers SVM, Adaboost, and artificial neural network (ANN).”
BackgroundMethodInfluentialRezaee, K., & Zadeh, H. G. (2024) · Discover Applied Sciences · doi:10.1007/s42452-024-05655-1 · Cited by 41
“Scholars in this field hold the aforementioned characteristics in high regard and have successfully incorporated them into several research studies [41].”
Liu, Z., Hu, J., Gong, X., & Li, F. (2025) · Scientific Reports · doi:10.1038/s41598-025-92447-1 · Cited by 44
SkinSight: advancing deep learning for skin cancer diagnosis and classification
Ashfaq, N., Suhail, Z., Khalid, A., Sarwar, N., Irshad, A., Yaman, O., Alubaidi, A., Ahmed, F. M., & Almalki, F. A. (2025) · Discover Computing · doi:10.1007/s10791-025-09541-1 · Cited by 36
“The ISBI 2016 Skin Lesion Challenge and the PH2 datasets [47] were used to test their methodology.”
Query Expansion Based on Top-Ranked Images for Content-Based Medical Image Retrieval
Ahmed, A., & Malebary, S. J. (2020) · IEEE Access · doi:10.1109/access.2020.3033504 · Cited by 43
Pathan, S., Prabhu, K. G., & Siddalingaswamy, P. C. (2018) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2018.03.017 · Cited by 34
Skin Lesion Area Segmentation Using Attention Squeeze U-Net for Embedded Devices
Pennisi, A., Bloisi, D. D., Suriani, V., Nardi, D., Facchiano, A., & Giampetruzzi, A. R. (2022) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-022-00634-7 · Cited by 36
“The PH2 dataset [31] has been realized by the Universidade do Porto, Tecnico Lisboa in collaboration with the Hospital Pedro Hispano in Matosinhos, Portugal.”
MethodDEU-Net: Dual-Encoder U-Net for Automated Skin Lesion Segmentation
Karimi, A., Faez, K., & Nazari, S. (2023) · IEEE Access · doi:10.1109/access.2023.3337528 · Cited by 38
“Finally, to assess the effectiveness of our proposed approach, we have conducted tests on four separate datasets: ISIC 2016 [33], ISIC 2017 [12], ISIC 2018 [34], [35], and PH2 [36].”
MethodCTH-Net: A CNN and Transformer hybrid network for skin lesion segmentation
Ding, Y., Yi, Z., Xiao, J., Hu, M., Guo, Y. F., Liao, Z., & Wang, Y. (2024) · iScience · doi:10.1016/j.isci.2024.109442 · Cited by 39
A Large Dataset to Enhance Skin Cancer Classification With Transformer-Based Deep Neural Networks
Gallazzi, M., Biavaschi, S., Bulgheroni, A., Gatti, T. M., Corchs, S., & Gallo, I. (2024) · IEEE Access · doi:10.1109/access.2024.3439365 · Cited by 38
“• MSK5 [37] , Hospital Italiano de Buenos Aires [41] , BCN20000 (BCN) [42] , UDA-2 [37] , PH2 [43]: No image removal was performed.”
Advanced skin lesion discrimination pipeline for early melanoma cancer diagnosis towards PoC devices
Sabrina Conoci, A., Rundo, F., Petralta, S., & Battiato, S. (2017) · European Conference on Circuit Theory and Design · doi:10.1109/ecctd.2017.8093310 · Cited by 33
Fuzzy c-means clustering based active contour model driven by edge scaled region information
Soomro, S., Munir, A., & Choi, K. N. (2018) · Expert Systems with Applications · doi:10.1016/j.eswa.2018.10.052 · Cited by 33
Hu, K., Niu, X., Liu, S., Zhang, Y., Cao, C., Xiao, F., Yang, W., & Gao, X. (2019) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2019.02.018 · Cited by 33
Skin Lesion Segmentation Using Stochastic Region-Merging and Pixel-Based Markov Random Field
Salih, O., & Viriri, S. (2020) · Symmetry · doi:10.3390/sym12081224 · Cited by 34
“The first is the dermatology image dataset, also known as the PH2 dataset, which was released by the dermatology service of the Hospital Pedro Hispano, Portugal [32].”
BackgroundPérez, E., & Ventura, S. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-06655-7 · Cited by 37
“PH2 4 [69] comprises dermoscopic images, clinical diagnosis and the identification of several dermoscopic structures.”
BackgroundMethodBarata, C., Marques, J. S., & Rozeira, J. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-41914-0_5 · Cited by 32
“We performed the experiments on the dataset PH2 of 176 dermoscopy images (25 melanomas) [17].”
MethodResultSelf-citationHu, K., Liu, S., Zhang, Y., Cao, C., Xiao, F., Huang, W., & Gao, X. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-7160-0 · Cited by 33
Maron, R. C., Hekler, A., Krieghoff‐Henning, E., Schmitt, M., Schlager, J. G., Utikal, J. S., & Brinker, T. J. (2021) · Journal of Medical Internet Research · doi:10.2196/21695 · Cited by 39
“The first data set is publicly available and contains dermoscopic images acquired at the Dermatology Service of Hospital Pedro Hispano (PH2), Matosinhos, Portugal [8].”
BackgroundAn automatic skin lesion segmentation system with hybrid FCN-ResAlexNet
Barın, S., & Güraksın, G. E. (2022) · Engineering Science and Technology an International Journal · doi:10.1016/j.jestch.2022.101174 · Cited by 47
Ain, Q. U., Xue, B., Al-Sahaf, H., & Zhang, M. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-97304-3_56 · Cited by 32
Ding, Z., Zhang, Y., Zhu, C., Zhang, G., Li, X., Jiang, N., Que, Y., Peng, Y., & Guan, X. (2024) · Information Sciences · doi:10.1016/j.ins.2024.120578 · Cited by 39
Owida, H. A., El‐Fattah, I. A., Abuowaida, S. F. A., Alshdaifat, N., Mashagba, H. A., Abd.Aziz, A. B., AlZoubi, A., Larguech, S., & Al‐Bawri, S. S. (2025) · Scientific Reports · doi:10.1038/s41598-025-21783-z · Cited by 46
Skin Lesions Identification Using Deep Convolutional Neural Network
Alkarakatly, T., Eidhah, S., Al-Sarawani, M., Al-Sobhi, A., & Bilal, M. (2020) · International Conference on Advances in the Emerging Computing Technologies (AECT) · doi:10.1109/aect47998.2020.9194205 · Cited by 31
Towards Accurate Diagnosis of Skin Lesions Using Feedforward Back Propagation Neural Networks
Moldovanu, S., Obreja, C.-D., Biswas, K. C., & Moraru, L. (2021) · Diagnostics · doi:10.3390/diagnostics11060936 · Cited by 34
“7-Point (B1) 439 3 4 68/297/74 Dermoscopic [39] PH2 (B2) 197 3 4 80/40/77 Dermoscopic [40] MED-NODE (B3) 170 2 4 100/70/0 Non-dermoscopic [41] PAD-UFES-20 (B4) 289 2 4 241/48/0 Dermoscopic [42]”
A Spatial Guided Self-supervised Clustering Network for Medical Image Segmentation
Ahn, E., Feng, D. D., & Kim, J. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87193-2_36 · Cited by 39
Rehman, H. U., Nida, N., Shah, S. A., Ahmad, W., Faizi, M. I., & Anwar, S. M. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12460-8 · Cited by 34
Skin Disease Analysis With Limited Data in Particular Rosacea: A Review and Recommended Framework
Mohanty, A., Sutherland, A., Bezbradica, M., & Javidnia, H. (2022) · IEEE Access · doi:10.1109/access.2022.3165574 · Cited by 43
Medical Image Classifications for 6G IoT-Enabled Smart Health Systems
Elaziz, M. A., Dahou, A., Mabrouk, A., Ibrahim, R. A., & Aseeri, A. O. (2023) · Diagnostics · doi:10.3390/diagnostics13050834 · Cited by 34
“From Figure 4a it can be noticed that the overall average accuracy on the PH2 dataset was nearly 96.11% and 95.68% for the SVM and KNN, respectively.”
InfluentialRobust Feature Spaces from Pre-Trained Deep Network Layers for Skin Lesion Classification
dos Santos, F. P., & Ponti, M. A. (2018) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi.2018.00031 · Cited by 32
“dataset [20] were extracted in three different CNNs pre-trained”
BackgroundMethodAutomated detection of melanocytes related pigmented skin lesions: A clinical framework
Pathan, S., Prabhu, K. G., & Siddalingaswamy, P. C. (2019) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2019.02.013 · Cited by 31
Andrade, C., Teixeira, L. F., Vasconcelos, M. J. M., & Rosado, L. (2020) · Journal of Imaging · doi:10.3390/jimaging7010002 · Cited by 33
“Dermoscopic Segmentation Databases In terms of dermoscopic databases, we used the three publicly available International Skin Imaging Collaboration (ISIC) challenges datasets (2016 [26], 2017 [27] and 2018 [28,29]) , as well as the PH2 database [30] .”
MethodAhmad, I., Amin, J., Lali, M. I. U., Abbas, F., & Sharif, M. I. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106084 · Cited by 32
Veeramani, N., & Premaladha, J. (2025) · Scientific Reports · doi:10.1038/s41598-025-89693-8 · Cited by 34
On the Usefulness of Pre-Processing Step in Melanoma Detection Using Multiple Instance Learning
Vocaturo, E., Zumpano, E., & Veltri, P. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-27629-4_34 · Cited by 33
Al‐Rasheed, A., Ksibi, A., Ayadi, M. F., Alzahrani, A. I. A., Zakariah, M., & Hakami, N. A. (2022) · Diagnostics · doi:10.3390/diagnostics12123145 · Cited by 31
“The ph2 dataset is used to train and test the proposed model [33].”
MethodULFAC-Net: Ultra-Lightweight Fully Asymmetric Convolutional Network for Skin Lesion Segmentation
Ma, Y., Li-ping, W., Gao, Y., Gao, F., Zhang, J., & Luo, Z. (2023) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2023.3259802 · Cited by 31
“The batch-size settings for the PH2, ISIC2016, ISBI2017, and ISIC2018 were 5, 10, 25, 16, respectively.”
MethodInfluentialSkin Diseases Detection Models using Image Processing: A Survey
Yadav, N., Kumar, V., & Shrivastava, U. (2016) · International Journal of Computer Applications · doi:10.5120/ijca2016909001 · Cited by 30
Evaluation of Melanoma Diagnosis using Deep Features
Maia, L. B., Lima, A. C. D. M., Pereira, R., Bráz, G., de Almeida, J. D. S., & de Paiva, A. C. (2018) · International Conference on Systems, Signals and Image Processing · doi:10.1109/iwssip.2018.8439373 · Cited by 36
“This technique is called Transfer Learning [18], where, because of the insufficient amount of data to create a new model, we try to transfer knowledge from a large amount of known data (source domain) to a set of data (target domain), as in the case of the PH2 dataset.”
MethodRA-Net: Region-Aware Attention Network for Skin Lesion Segmentation
Naveed, A., Naqvi, S. S., Iqbal, S., Razzak, I., Khan, H. A., & Khan, T. M. (2024) · Cognitive Computation · doi:10.1007/s12559-024-10304-1 · Cited by 37
“• DS-4: PH2 [52] is a data collection with just 200 dermoscopic images with ground truth masks.”
Recent Deep Learning Methods for Melanoma Detection: A Review
Sultana, N. N., & Puhan, N. B. (2018) · Communications in computer and information science · doi:10.1007/978-981-13-0023-3_12 · Cited by 31
Detection of Melanoma using Deep Learning Techniques: A Review
Venugopal, V., Nath, M. K., Sreejith, V., Giji, N. F., Ramesh, A., & Meera, M. (2021) · International Conference on Communication, Control and Information Sciences (ICCISc) · doi:10.1109/iccisc52257.2021.9484861 · Cited by 33
Deep Hybrid Convolutional Neural Network for Segmentation of Melanoma Skin Lesion
Yang, C., Ren, J.-H., Huang, H., Chuang, L., & Chang, P.-Y. (2021) · Computational Intelligence and Neuroscience · doi:10.1155/2021/9409508 · Cited by 34
“PH2 is dataset of skin images obtained from the Pediatric Department of Pedro HispanoHospital in Matosinhos, Portugal [53].”
BackgroundAMCC-Net: An asymmetric multi-cross convolution for skin lesion segmentation on dermoscopic images
Dayananda, C., Yamanakkanavar, N., Nguyen, T. Q., & Lee, B. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106154 · Cited by 34
Towards Automated Melanoma Screening: Proper Computer Vision & Reliable ResultsPreprint
Fornaciali, M. S., Carvalho, M. C., Bittencourt, F. V., Avila, S., & Junior, E. A. D. V. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1604.04024 · Cited by 37
“We are aware of only two efforts worth mentioning: the PH2 Dataset1 [53], and the ISIC Project2.”
BackgroundHassan, J., Saeed, S. M., Deka, L., Uddin, M. J., & Das, D. B. (2024) · Pharmaceutics · doi:10.3390/pharmaceutics16020260 · Cited by 34
“These are more accurate forecasts of cancer susceptibility, recurrence, and survival [287], which increase survival rates by effectively managing patients [288–290].”
BackgroundGarg, P., Sharma, M., & Kumar, P. (2025) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-024-09896-5 · Cited by 39
Abdulhamid, I. A. M., Şahiner, A., & Rahebi, J. (2020) · BioMed Research International · doi:10.1155/2020/5345923 · Cited by 28
“Every coe ffi cient was evaluated by a competent dermatologist for the numbering factors of analytic performance, the manual partition of lesion areas, and the dermoscopic norm [37].”
MethodAhmed, N. A., Tan, X., & Ma, L. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13618-0 · Cited by 34
“In context to further evaluate the distinguish generalization performance of the proposed method, we have conducted a segmentation test during inference time of the network on unseen images of PH2 dermoscopic dataset, as evaluation results are shown in Fig.”
MethodInfluentialAbbas, Q., Daadaa, Y., Rashid, U., & Ibrahim, M. E. A. (2023) · Diagnostics · doi:10.3390/diagnostics13152531 · Cited by 36
“Images Selected Images Number of Classes * HAM10000 [32,33] 10,015 10,015 7 (“AK, BCC, BKL, DF, NV, MEL, VASC”) ISIC 2019 [42] 25,331 25,331 8 (“MEL, NV, BCC, AKIEC, BKL, DF, VASC, SCC”) ISIC 2020 [43] 33,126 33,126 9 (“MEL, NV, BCC, AKIEC, BKL, DF, VASC, SCC, PBK”) Ph2 [44] 200 200 2(NV, and Mel) ISBI 2017 [45] 2750…”
Thanh, N. V., Pham, V.-T., & Tran, T.-T. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-76197-3_2 · Cited by 36
Classification of Skin Lesions in Dermatoscopic Images with Deep Convolution Network
Çevik, E., & Zengin, K. (2019) · European Journal of Science and Technology · doi:10.31590/ejosat.638247 · Cited by 33
Color identification in dermoscopy images using Gaussian mixture models
Barata, C., Figueiredo, M. A. T., Celebi, M. E., & Marques, J. S. (2014) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2014.6854274 · Cited by 27
“A total of 130 images selected from the PH(2) database [19] were used in this work.”
MethodSelf-citationSaliency-Driven Active Contour Model for Image Segmentation
Iqbal, E., Niaz, A., Memon, A. A., Asim, U., & Choi, K. N. (2020) · IEEE Access · doi:10.1109/access.2020.3038945 · Cited by 27
Bayasi, N., Hamarneh, G., & Garbi, R. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87234-2_16 · Cited by 35
“Datasets and Implementation Details: We use 6 public skin lesion datasets each representing a unique data domain: HAM10000 (HAM) [22], Dermofit (DMF) [3], Derm7pt (D7P) [13], MSK [9], PH2 [16], and UDA [9], each comprising skin lesion images collected using different equipment at different clinical sites.”
MethodTran, T.-T., & Pham, V.-T. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12413-1 · Cited by 28
“8 Segmentation comparison between the proposed approach with recent networks on the PH2 database of the network for the task of skin lesion segmentation.”
MethodResultInfluentialAbuzaghleh, O., Barkana, B. D., & Faezipour, M. (2014) · IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI) · doi:10.1109/ssiai.2014.6806035 · Cited by 27
Melanoma Skin Cancer Detection Based on ABCD Rule
Lattoofi, N. F., Al-sharuee, I. F., Kamil, M. Y., Obaid, A. H., Mahidi, A. A., Omar, A. A., & Saleh, A. K. (2019) · International Conference of Computer and Applied Sciences (CAS) · doi:10.1109/cas47993.2019.9075465 · Cited by 27
“The images have a resolution of 768×560 pixels in the RGB colour system [20].”
MethodDangerousness of dysplastic nevi: a Multiple Instance Learning Solution for Early Diagnosis
Vocaturo, E., & Zumpano, E. (2019) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm47256.2019.8983056 · Cited by 27
Skin lesion segmentation using convolutional neural networks with improved U-Net architecture
Iranpoor, R., Mahboob, A. S., Shahbandegan, S., & Baniasadi, N. (2020) · Iranian Conference on Signal Processing and Intelligent Systems (ICSPIS) · doi:10.1109/icspis51611.2020.9349577 · Cited by 26
“The histological diagnosis is only available for some of the images, since the histological test is just performed for those lesions considered highly suspicious by dermatologists [14].”
BackgroundMethodInfluentialA Prior-mask-guided Few-shot Learning for Skin Lesion Segmentation
Xiao, J., Xu, H., Zhao, W., Chen, C., & Gao, H. (2021) · Computing · doi:10.1007/s00607-021-00907-z · Cited by 31
“The three datasets are ISIC-2017 [49] (i.e., Skin Lesion Analysis Towards Melanoma Detection), ISIC-2019 [50] (i.e., Dermoscopic Lesions in the Wild), and PH2 [51].”
Background
Metadata
- Authors
- Mendonca, T., Ferreira, P. M., Marques, J. S., Marcal, A. R. S., & Rozeira, J.
- Affiliations
- Universidade do Porto (PT)
- Instituto Superior Técnico (PT)
- Hospital Pedro Hispano (PT)
- Venue
- 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
- Publisher
- IEEE
- Published
- 2013-07
- Volume
- 2013
- Pages
- 5437-5440
- ISSN
- 2375-7477 (ISSN-L)
- OpenAlex
- W2061253660
- Cited by
- 1,009
- References
- 13
- Citations by year
- 2026: 115 · 2025: 142 · 2024: 125 · 2023: 100 · 2022: 101 · 2021: 89 · 2020: 86 · 2019: 83 · 2018: 70 · 2017: 43 · 2016: 22 · 2015: 22 · 2014: 9 · 2013: 2
- FWCI
- 125.66
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Oncology › Cutaneous Melanoma Detection and Management
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Keywords
- dermoscopic images, melanoma, computer-aided diagnosis, image classification, benchmarking, image segmentation, diagnosis
- MeSH terms
- Diagnosis, Computer-Assisted, Humans, Image Processing, Computer-Assisted, Melanoma, Databases, Factual, Benchmarking, Dermoscopy
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.