Developers and users of artificial-intelligence-based tools for automatic contouring and treatment planning in radiotherapy are expected to assess clinical acceptability of these tools. However, what is ‘clinical acceptability’? Quantitative and qualitative approaches have been used to assess this ill-defined concept, all of which have advantages and disadvantages or limitations. The approach chosen may depend on the goal of the study as well as on available resources. In this paper, we discuss various aspects of ‘clinical acceptability’ and how they can move us toward a standard for defining clinical acceptability of new autocontouring and planning tools.
A new approach is described for the rigorous global optimization of dynamic systems subject to inequality path constraints (IPCs). This method employs the sequential (control parameterization) approach and is based on techniques developed for the verified solution of parametric systems of ordinary differential equations. These techniques provide rigorous interval bounds on the state variables, and thus on the path constraints and objective function in the dynamic optimization problem. These techniques also provide explicit analytic representations (Taylor models) of these bounds in terms of the decision variables in the optimization problem. This facilitates the use of constraint propagation techniques that can greatly reduce the domain to be searched for the global optimum. Since IPCs are often related to safety concerns, we adopt a conservative, innerapproximation approach to constraint satisfaction. Through this approach, the search for the global optimum is restricted to a space in which continuous satisfaction of the IPCs is rigorously guaranteed, and an ǫ-global optimum within this space is determined. Examples are presented that demonstrate the potential and computational performance of this approach.
To enable generation of high-quality deep learning segmentation models from severely limited contoured cases (e.g.,~10 cases). Methods: Thirty head and neck computed tomography (CT) scans with well-defined contours were deformably registered to 200 CT scans of the same anatomic site without contours. Acquired deformation vector fields were used to train a principal component analysis (PCA) model for each of the 30 contoured CT scans by capturing the mean deformation and most prominent variations. Each PCA model can produce an infinite number of synthetic CT scans and corresponding contours by applying random deformations. We used 300, 600, 1000, and 2000 synthetic CT scans and contours generated from one PCA model to train V-Net, a 3D convolutional neural network architecture, to segment parotid and submandibular glands. We repeated the training using same numbers of training cases generated from 7, 10, 20, and 30 PCA models, with the data distributed evenly between each PCA model. Performance of the segmentation models was evaluated with Dice similarity coefficients between auto-generated contours and physician-drawn contours on 162 test CT scans for parotid glands and another 21 test CT scans for submandibular glands.Results: Dice values varied with the number of synthetic CT scans and the number of PCA models used to train the network. By using 2000 synthetic CT scans generated from 10 PCA models, we achieved Dice values of 82.8% AE 6.8% for right parotid, 82.0% AE 6.9% for left parotid, and 74.2% AE 6.8% for submandibular glands. These results are comparable with those obtained from state-of-the-art auto-contouring approaches, including a deep learning network trained from more than 1000 contoured patients and a multi-atlas algorithm from 12 well-contoured atlases. Improvement was marginal when >10 PCA models or >2000 synthetic CT scans were used. Conclusions: We demonstrated an effective data augmentation approach to train high-quality deep learning segmentation models from a limited number of well-contoured patient cases.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.