PH2 - A dermoscopic image database for research and benchmarking

By Teresa Mendonça, Pedro M. Ferreira, Jorge S. Marques, André R. S. Marçal, Jorge Rozeira. Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2013

1,219 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Epidemiology, Oncology

View Paper: https://www.semanticscholar.org/paper/24019050c30b7e5bf1be28e48b8cb5278c4286fd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Epidemiology

In Oncology

Citations in the corpus

Deep learning ensembles for melanoma recognition in dermoscopy images (2016, methodology): “A team from the Pedro Hispano Hospital of Portugal sought to evaluate the performance of several (e.g., SVM and kNN) machine learning classifiers based on color, edge, and texture descriptors [22,23].”
Towards Complementary Explanations Using Deep Neural Networks (2018, background): “The dataset [7] has 14 features from 200 patients describing the presence of certain colors on the nevus and abnormal patterns such as asymmetry, dots, streaks, among others.”
Dermoscopic Image Segmentation via Multistage Fully Convolutional Networks (2017, methodology): “2) The PH2 public dataset [52] was collaboratively collected by the Universidade do Porto, Técnico Lisboa, and the Dermatology service of Hospital Pedro Hispano in Matosinhos, Portugal.”
A Deep Learning Approach to Vascular Structure Segmentation in Dermoscopy Colour Images (2018, methodology): “Additionally, colour images have been used from the PH2 database [22], and images available in online libraries [23, 24].”
HiFormer: Hierarchical Multi-scale Representations Using Transformers for Medical Image Segmentation (2022, methodology): “Besides, the PH(2) dataset [37] is used, a dermoscopic image database introduced for both segmentation and classification tasks.”
Artificial Intelligence in XPRIZE DeepQ Tricorder (2017, methodology): “In our case, the training data available to us are 1) 1 , 195 OM images collected by seven otolaryngologists at Cathay General Hospital 4 , Taiwan [21] and 2) 200 melanoma images from the PH 2 dataset [15].”
Skin Cancer Detection: A Review Using Deep Learning Techniques (2021, methodology): “The dermoscopic images in the PH2 dataset were collected at the Dermatology Center of Pedro Hispano Hospital, Portugal [68].”
Progressive Transfer Learning and Adversarial Domain Adaptation for Cross-Domain Skin Disease Classification (2020, neutral): “Earlysystems weretrainedonrelativelysmallscaledatasets[3].”
A Mutual Bootstrapping Model for Automated Skin Lesion Segmentation and Classification (2019, methodology): “The PH2 public dataset [36] contains 200 dermoscopic images, including 160 nevus, and 40 melanomas.”
Skin Lesion Analysis toward Melanoma Detection: A Challenge at the International Symposium on Biomedical Imaging (ISBI) 2016, hosted by the International Skin Imaging Collaboration (ISIC) (2016, background): “While initial attempts have been made to create public archives of images to support research and development on automated algorithms for dermoscopic image assessment [35], a large-scale, centralized, coordinated, and comparative effort across institutions has yet to be implemented.”
Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization (2021, methodology): “Additionally, we perform segmentation on three out-of-domain datasets (PH2 [60], IS [25], Quest [25], details in supplemental material).”