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

Abstract

We 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.

The interaction between wheat roots and soil pores in structured field soil

“…Developing automatic methods to extract root traits from soil cores is therefore urgently needed. The artificial intelligence-based image analysing methods have shown great potential and might be a possible solution ( Soltaninejad et al , 2020 ).…”

RootPainter: Deep Learning Segmentation of Biological Images with Corrective Annotation

“…All data are not created equal, with great variability in the utility of each annotated pixel for the model training process (20). It may be necessary to add harder examples after observing weaknesses in an initial trained model (21), or to correct for a class imbalance in the data where many examples exist of a majority class (22). Interactive segmentation methods using CNNs such as (23,24) provide ways to improve the annotation procedure by allowing user input to be used in the inference process and can be an effective way to create large high quality datasets in less time (25).…”

An improved method for the segmentation of roots from X-ray computed tomography 3D images: Rootine v.2

“…Methods relying on deep-learning algorithms and multi-scaled based approaches have also become common in X-ray CT and magnetic resonance imaging. promising applications of deep learning for the segmentation of roots from X-ray CT data were recently demonstrated by [ 13 ].…”