Publications by authors named "Diego Herrera Egea"

Article Synopsis
  • Developing an automatic acne grading system using machine learning requires extensive data and labeling, but the authors created a model that performs well on low-resolution images from fewer patients with uneven acne severity distribution.
  • The study utilized 1,374 paired images from 391 patients, expertly labeled, to train a deep learning model which achieved 66.67% accuracy on the test set.
  • The results suggest that this model can be a viable tool for medical practitioners and provide standardized assessments for patients, highlighting its potential despite limited data.
View Article and Find Full Text PDF