In this randomized controlled pilot trial, we compared three-dimensional (3D)-printed made-to-measure splints to conventional custom-made thermoplastic splints. In a clinical setting, we evaluated their general applicability and possible benefits for immobilization in hand surgical patients. We included 20 patients with an indication for immobilization of at least 4 weeks, regardless of the splint design. Patient comfort and satisfaction were assessed with questionnaires at splint fitting, as well as 2 and 4–6 weeks later. The 3D splints were designed and printed in-house with polylactic acid from a 3D surface scan. Our data suggest that 3D-printed splinting is feasible, and patient satisfaction ratings were similar for 3D-printed and thermoplastic splints. The 3D splint production process needs to be optimized and other materials need to be tested before routine implementation is possible or more patients can be enrolled in further studies. Validated quality assessment tools for current splinting are lacking, and further investigation is necessary.
Convolutional neural networks (CNNs) have proven to be efficient tools for image segmentation when a large number of segmented images are available. However, when the number of segmented images is not so large, the CNN segmentations are less accurate. It is the case for nephroblastoma (kidney cancer) in particular. When a new patient arrives, the expert can only manually segment a sample of scanned images since manual segmentation is a time-consuming process. As a consequence, the question of how to compute accurate segmentations using both the trained CNN and such a sample is raised. A CBR approach based on proportional analogy is proposed in this paper. For a source image segmented by the expert, let a be the CNN segmentation of this image, b be its expert segmentation and c be the CNN segmentation of a target image close to the source image. The proposed approach aims at solving the analogical equation "a is to b as c is to d" with unknown d: the solution d of this equation is proposed as a segmentation of the target image. This approach and some of its improvements are evaluated and show an accuracy increase of the segmentation with respect to the CNN segmentation.
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.