Training deep convolutional neural network for classification in medical tasks is often difficult due to the lack of annotated data sam-ples. Deep convolutional networks (CNN) has been successfully used as an automatic detection tool to support the grading of diabetic retinopa-thy and macular edema. Nevertheless, the manual annotation of exu-dates in eye fundus images used to classify the grade of the DR is very time consuming and repetitive for clinical personnel. Active learning al-gorithms seek to reduce the labeling effort in training machine learning models. This work presents a label-efficient CNN model using the ex-pected gradient length, an active learning algorithm to select the most informative patches and images, converging earlier and to a better local optimum than the usual SGD (Stochastic Gradient Descent) strategy. Our method also generates useful masks for prediction and segments regions of interest.