Diabetic retinopathy classification and interpretation using deep learning techniques

• Autores: Jordi de la Torre
• Directores de la Tesis: Domènec Puig Valls (dir. tes.) , Aïda Valls Mateu (dir. tes.)
• Lectura: En la Universitat Rovira i Virgili ( España ) en 2019
• Idioma: español
• Tribunal Calificador de la Tesis: Miguel Cazorla Quevedo (presid.) , Hatem Abd El-Latif Fatahallah Ibrahim Mahmoud Rashwan (secret.) , Roberto Hornero Sánchez (voc.)
• Enlaces
  • Tesis en acceso abierto en: TDX
• Resumen

  • Diabetic Retinopathy (DR) is a leading disabling chronic disease and one of the main causes of blindness and visual impairment in developed countries for diabetic patients. Studies reported that 90\% of the cases can be prevented through early detection and treatment. Eye screening through retinal images is used by physicians to detect the lesions related with thisdisease. Due to the increasing number of diabetic people, the amount of images to be manually analyzed is becoming unaffordable. Moreover, training new personnel for this type of image-based diagnosis is long, because it requires to acquire expertise by daily practice.

    In this thesis, we explore different novel methods for the automatic diabetic retinopathy disease grade classification using retina fundus images. For this purpose, we explore methods based in automatic feature extraction and classification, based on deep neural networks.

    Furthermore, as results reported by these models are difficult to interpret, we design a new method for results interpretation. The model is designed in a modular manner in order to generalize its possible application to other networks and classification domains. We experimentally demonstrate that our interpretation model is able to detect retina lesions in the image solely from the classification information.

    Additionally, we propose a method for compressing model feature-space information. The method is based on a independent component analysis over the disentangled feature space information generated by the model for each image and serves also for identifying the mathematically independent elements causing the disease. Using our previously mentioned interpretation method is also possible to visualize such components on the image.

    Finally, we present an experimental application of our best model for classifying retina images of a different population, concretely from the Hospital de Reus. We study the possible presence of co-variate shift and present the results obtained from such a new population.

    The methods proposed, achieve ophthalmologist performance level and are able to identify with great detail lesions present on images, inferred only from image classification information.