UOLO - automatic object detection and segmentation in biomedical images
This addresses the need for efficient analysis of medical images, though it appears incremental as it builds on existing detection and segmentation methods.
The paper tackled the problem of simultaneous object detection and segmentation in biomedical images by proposing UOLO, a framework that achieved state-of-the-art performance on tasks like optic disc detection, fovea detection, and optic disc segmentation from retinal images.
We propose UOLO, a novel framework for the simultaneous detection and segmentation of structures of interest in medical images. UOLO consists of an object segmentation module which intermediate abstract representations are processed and used as input for object detection. The resulting system is optimized simultaneously for detecting a class of objects and segmenting an optionally different class of structures. UOLO is trained on a set of bounding boxes enclosing the objects to detect, as well as pixel-wise segmentation information, when available. A new loss function is devised, taking into account whether a reference segmentation is accessible for each training image, in order to suitably backpropagate the error. We validate UOLO on the task of simultaneous optic disc (OD) detection, fovea detection, and OD segmentation from retinal images, achieving state-of-the-art performance on public datasets.