DermAI: Clinical dermatology acquisition through quality-driven image collection for AI classification in mobile
By: Thales Bezerra , Emanoel Thyago , Kelvin Cunha and more
Potential Business Impact:
Helps doctors find skin problems faster on phones.
AI-based dermatology adoption remains limited by biased datasets, variable image quality, and limited validation. We introduce DermAI, a lightweight, smartphone-based application that enables real-time capture, annotation, and classification of skin lesions during routine consultations. Unlike prior dermoscopy-focused tools, DermAI performs on-device quality checks, and local model adaptation. The DermAI clinical dataset, encompasses a wide range of skin tones, ethinicity and source devices. In preliminary experiments, models trained on public datasets failed to generalize to our samples, while fine-tuning with local data improved performance. These results highlight the importance of standardized, diverse data collection aligned with healthcare needs and oriented to machine learning development.
Similar Papers
Toward Accessible Dermatology: Skin Lesion Classification Using Deep Learning Models on Mobile-Acquired Images
CV and Pattern Recognition
Helps phones spot skin problems to help doctors.
DermINO: Hybrid Pretraining for a Versatile Dermatology Foundation Model
Image and Video Processing
Helps doctors diagnose skin problems better.
Prompting Medical Vision-Language Models to Mitigate Diagnosis Bias by Generating Realistic Dermoscopic Images
CV and Pattern Recognition
Helps AI see skin diseases on all skin colors.