RootPainter3D: Interactive‐machine‐learning enables rapid and accurate contouring for radiotherapy

Abstract

Purpose: Organ-at-risk contouring is still a bottleneck in radiotherapy,with many deep learning methods falling short of promised results when evaluated on clinical data. We investigate the accuracy and time-savings resulting from the use of an interactive-machine-learning method for an organ-at-risk contouring task. Methods:We implement an open-source interactive-machine-learning software application that facilitates corrective-annotation for deep-learning generated contours on X-ray CT images. A trained-physician contoured 933 hearts using our software by delineating the first image, starting model training, and then correcting the model predictions for all subsequent images. These corrections were added into the training data, which was used for continuously training the assisting model. From the 933 hearts, the same physician also contoured the first 10 and last 10 in Eclipse (Varian) to enable comparison in terms of accuracy and duration. Results: We find strong agreement with manual delineations, with a dice score of 0.95. The annotations created using corrective-annotation also take less time to create as more images are annotated, resulting in substantial time savings compared to manual methods. After 923 images had been delineated, hearts took 2 min and 2 s to delineate on average, which includes time to evaluate the initial model prediction and assign the needed corrections, compared to 7 min and 1 s when delineating manually. Conclusions: Our experiment demonstrates that interactive-machine-learning with corrective-annotation provides a fast and accessible way for non computerscientists to train deep-learning models to segment their own structures of interest as part of routine clinical workflows.

On Acquisition Parameters and Processing Techniques for Interparticle Contact Detection in Granular Packings Using Synchrotron Computed Tomography

“…U-Net binarisation was carried out using RootPainter [ 48 , 49 ], which has been shown to deliver highly accurate segmentations of XCT data, including images of granular materials, and is straightforward to implement [ 50 , 51 ]. RootPainter is a client-server application for binary segmentation in which the user labels 2D images by manually annotating (‘painting’) foreground (feature of interest) and background (everything else) regions using the client’s graphical user interface.…”

Optimisation of root traits to provide enhanced ecosystem services in agricultural systems: A focus on cover crops

“…Common to all root imaging techniques described, image analysis is often the limiting factor. Deep learning approaches are now allowing faster and more accurate plant image analysis (Han et al, 2021 ; Smith et al, 2021 ; Soltaninejad et al, 2020 ). Promising applications that can be scaled up in the field include electrical resistance tomography, electromagnetic inductance and ground penetrating radar; however, these methods require species‐dependent optimisation as many factors affect root biomass estimations including soil texture, soil water content, and organic matter (X. Liu et al, 2018 ; Weigand & Kemna, 2017 ).…”

Towards interactive deep-learning for tumour segmentation in head and neck cancer radiotherapy

“…These are then used to retrain the CNN parameters, to improve the segmentation output for the case at hand. Scribble-based iDL has been successfully demonstrated in pancreas segmentation on CT [16] , organs at risk and tumour segmentation on MRI [17] , and also as a tool to annotate data in the training process [18] . While interactions are easy and fast to set, physicians are always first presented with an auto-segmentation for annotation, which could bias the delineation process.…”