Model Dermatology Project

Model 12 Skin Tumorous Disorders

Model 12Dx ( is trained with 19,398 manually cropped images and additional 159,477 images (approximately 260 classes).

Paper – Journal of Investigative of Dermatology (Feb. 2018)
– Classification of the clinical images for benign and malignant cutaneous tumors using a deep learning algorithm

Letter Paper – Journal of Investigative of Dermatology (June. 2018)
– In here, we explained the difference between AUC and Top-accuracy and between multi-class classification and binary classification. If the results were calculated without considering threshold  of AUC and multi-class classification, the sensitivity appeared low inevitably.
– Interpretation of the Outputs of Deep Learning Model trained with Skin Cancer Dataset


Model Dermatology and Model Melanoma  are using the same AI model which was trained with 220,680 images (174 disease classes).

– Model Dermatology (
– Model Melanoma (

Paper – Journal of Investigative of Dermatology (March. 2020)
Augmented Intelligence Dermatology : Deep Neural Networks Empower Medical Professionals in Diagnosing Skin Cancer and Predicting Treatment Options for 134 Skin Disorders.

Interview –
AI improved diagnosis of skin disorders, especially distinguishing benign from malignant tumors

Media – EurekAlert
New artificial intelligence system can empower medical professionals in diagnosing skin diseases



The Model Dermatology with RCNN ( was developed for the use of screening skin cancer. Region-based CNN technology was used to train a blob detector and used CNNs to train a fine image selector and a disease classifier. We collected and annotated approximately 1100k images by extracting all possible lesional areas from the entire training photographs.

Paper – JAMA Dermatology (Dec. 2019)
Keratinocytic Skin Cancer Detection on the Face Using Region-Based Convolutional Neural Network

We have done a large scale retrospective study (patient N=10,426, image N=40,331). The sensitivity and specificity of the algorithm was 79.1% and 76.9%, respectively, while those of the attending physicians in a tertiary hospital was 88.1%, and 83.8%, respectively.

Paper – PLOS Medicine (Nov. 2020)
Assessment of deep neural networks for the diagnosis of benign and malignant skin neoplasms in comparison with dermatologists: A retrospective validation study

Paper – (Dec. 2019)
Retrospective Assessment of Deep Neural Networks for Skin Tumor Diagnosis

A New improved DEMO is available at  In determining malignancy, the sensitivity for the white population was improved using the ISIC dataset from 52.0% to 69.0%.



Model Onychomycosis ( is trained with 49,567 images generated by region-based CNN (R-CNN). In order to create a deep learning model that demonstrates diagnostic capabilities beyond the specialists, we generated a huge nail dataset by using faster R-CNN.

Android Apps
– Android (Model Onychomycosis)
Original article – PLoS One (Jan. 2018)
– Deep neural networks show an equivalent and often superior performance to dermatologists in onychomycosis diagnosis: Automatic construction of onychomycosis datasets by region-based convolutional deep neural network
Magazine – IEEE Spectrum (Feb. 2018)
– AI Beats Dermatologists in Diagnosing Nail Fungus



In order to obtain results similar to the specialist with current deep learning models and a small number of data (500 images per class), we should analyze the lesion of interest after cropping the part.

Original article – Acta Orthopaedica (Feb. 2018)
– Automated detection and classification of the proximal humerus fracture by using deep learning algorithm



MedicalPhoto( is a non-commercial medical image management program. This program was developed and maintained by Dr. Han Seung Seog. The core parts were written by standard C++ with boost asio library with Unicode support (both UTF-8 and UTF-16LE), and SQLite was utilized as a main database engine. The source codes and binaries of this project were released in 2007.