Deep Sequential Segmentation of Organs in Volumetric Medical Scans
This addresses segmentation problems for clinical applications like diagnosis and treatment planning, but it is incremental as it builds on existing U-Net and LSTM methods.
The paper tackles the limitations of 3D convolutional neural networks in medical scan segmentation, such as memory constraints and resolution issues, by proposing a U-Net-like architecture with bidirectional convolutional LSTM and time-distributed wrappers, achieving performance demonstrated on vertebrae and liver segmentation in 3D CT scans.
Segmentation in 3D scans is playing an increasingly important role in current clinical practice supporting diagnosis, tissue quantification, or treatment planning. The current 3D approaches based on convolutional neural networks usually suffer from at least three main issues caused predominantly by implementation constraints - first, they require resizing the volume to the lower-resolutional reference dimensions, second, the capacity of such approaches is very limited due to memory restrictions, and third, all slices of volumes have to be available at any given training or testing time. We address these problems by a U-Net-like architecture consisting of bidirectional convolutional LSTM and convolutional, pooling, upsampling and concatenation layers enclosed into time-distributed wrappers. Our network can either process the full volumes in a sequential manner, or segment slabs of slices on demand. We demonstrate performance of our architecture on vertebrae and liver segmentation tasks in 3D CT scans.