Deep Sequential Segmentation of Organs in Volumetric Medical Scans

TL;DR

This paper introduces a novel deep learning architecture for 3D medical scan segmentation that overcomes common limitations of existing CNN-based methods by processing full volumes sequentially or in slabs, improving accuracy and flexibility.

Contribution

The proposed U-Net-like model with bidirectional convolutional LSTM addresses memory and resolution constraints, enabling efficient 3D segmentation without resizing or requiring all slices simultaneously.

Findings

Effective segmentation of vertebrae and liver in 3D CT scans.

Outperforms traditional CNN approaches in accuracy and flexibility.

Capable of processing full volumes or slabs on demand.

Abstract

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.