Retinal Blood Vessel Segmentation Using a Fully Convolutional Network – Transfer Learning from Patch- to Image-Level

Fully convolutional networks (FCNs) are well known to provide state-of-the-art results in various medical image segmentation tasks. However, these models usually need a tremendous number of training samples to achieve good performances. Unfortunately, this requirement is often difficult to satisfy in the medical imaging field, due to the scarcity of labeled images. As a consequence, the common tricks for FCNs’ training go from data augmentation and transfer learning to patch-based segmentation. In the latter, the segmentation of an image involves patch extraction, patch segmentation, then patch aggregation. This paper presents a framework that takes advantage of all these tricks by starting with a patch-level segmentation which is then extended to the image level by transfer learning. The proposed framework follows two main steps. Given a image database \(\mathcal {D}\), a first network \(\mathcal {N}_P\) is designed and trained using patches extracted from \(\mathcal {D}\). Then, \(\mathcal {N}_P\) is used to pre-train a FCN \(\mathcal {N}_I\) to be trained on the full sized images of \(\mathcal {D}\). Experimental results are presented on the task of retinal blood vessel segmentation using the well known publicly available DRIVE database.