Deep convolutional neural network-based segmentation and classification of difficult to define metastatic spinal lesions in 3D CT data

Computer Aided Detection (CAD) techniques play an important role in the process of assessing medical images used in a number of medical sectors ranging from oncology to neurology. The main contribution of CAD is a reduction in the duration of routine steps, thus resulting in fewer mistakes caused by fatigued medical staff and larger amounts of images being assessed. One of the most challenging aspects of the application of CAD is the detection and segmentation of metastases for subsequent time-development analysis and observing responses to treatment.

Source: Medical Image Analysis - August 2, 2018 Category: Radiology Authors: Jiri Chmelik, Roman Jakubicek, Petr Walek, Jiri Jan, Petr Ourednicek, Lukas Lambert, Elena Amadori, Giampaolo Gavelli Source Type: research