Root CT Segmentation Using Incremental Learning Methodology on Improved Multiple Resolution Images

The real-time issue of reliability segmenting root structure while using X-Ray Computed Tomography (CT) images is addressed in this work. A deep learning approach is proposed using a novel framework, involving decoders and encoders. The encoders-decoders framework is useful to improve multiple resolution by means of upsampling and downsampling images. The methodology of the work is enhanced by incorporating network branches with individual tasks using low-resolution context information and high-resolution segmentation. In large volumetric images, it is possible to resolve small root details by implementing a memory efficient system, resulting in the formation of a complete network. The proposed work, recent image analysis tool developed for root CT segmented is compared with several other previously existing methodology and it is found that this methodology is more efficient. Quantitatively and qualitatively, it is found that a multiresolution approach provides high accuracy in a shallower network with a large receptive field or deep network in a small receptive field. An incremental learning approach is also embedded to enhance the performance of the system. Moreover, it is also capable of detecting fine and large root materials in the entire volume. The proposed work is fully automated and doesn’t require user interaction.

Download Full-text

Three Dimensional Root CT Segmentation using Multi-Resolution Encoder-Decoder Networks

10.1101/713859 ◽

2019 ◽

Cited By ~ 1

Author(s):

Mohammadreza Soltaninejad ◽

Craig J. Sturrock ◽

Marcus Griffiths ◽

Tony P. Pridmore ◽

Michael P. Pound

Keyword(s):

Receptive Field ◽

Contextual Information ◽

Three Dimensional ◽

User Interaction ◽

Root System Architecture ◽

Complex Problem ◽

Field Size ◽

Learning Approach ◽

Analysis Tool ◽

Ct Segmentation

AbstractWe address the complex problem of reliably segmenting root structure from soil in X-ray Computed Tomography (CT) images. We utilise a deep learning approach, and propose a state-of-the-art multi-resolution architecture based on encoder-decoders. While previous work in encoder-decoders implies the use of multiple resolutions simply by downsampling and upsampling images, we make this process explicit, with branches of the network tasked separately with obtaining local high-resolution segmentation, and wider low-resolution contextual information. The complete network is a memory efficient implementation that is still able to resolve small root detail in large volumetric images. We evaluate our approach by comparing against a number of different encoder-decoder based architectures from the literature, as well as a popular existing image analysis tool designed for root CT segmentation. We show qualitatively and quantitatively that a multi-resolution approach offers substantial accuracy improvements over a both a small receptive field size in a deep network, or a larger receptive field in a shallower network. We obtain a Dice score of 0.59 compared with 0.41 for the closest competing method. We then further improve performance using an incremental learning approach, in which failures in the original network are used to generate harder negative training examples. Results of this process raise the precision of the network, and improve the Dice score to 0.66. Our proposed method requires no user interaction, is fully automatic, and identifies large and fine root material throughout the whole volume. The 3D segmented output of our method is well-connected, allowing the recovery of structured representations of root system architecture, and so may be successfully utilised in root phenotyping.

Download Full-text