Deep Facial Diagnosis: Deep Transfer Learning From Face Recognition to Facial Diagnosis

The relationship between face and disease has been discussed from thousands years ago, whichleads to the occurrence of facial diagnosis. The objective here is to explore the possibility of identifyingdiseases from uncontrolled 2D face images by deep learning techniques. In this paper, we propose usingdeep transfer learning from face recognition to perform the computer-aided facial diagnosis on variousdiseases. In the experiments, we perform the computer-aided facial diagnosis on single (beta-thalassemia)and multiple diseases (beta-thalassemia, hyperthyroidism, Down syndrome, and leprosy) with a relativelysmall dataset. The overall top-1 accuracy by deep transfer learning from face recognition can reach over90% which outperforms the performance of both traditional machine learning methods and clinicians in theexperiments. In practical, collecting disease-specific face images is complex, expensive and time consuming,and imposes ethical limitations due to personal data treatment. Therefore, the datasets of facial diagnosisrelated researches are private and generally small comparing with the ones of other machine learningapplication areas. The success of deep transfer learning applications in the facial diagnosis with a smalldataset could provide a low-cost and noninvasive way for disease screening and detection.