DEEPBEAS3D: Deep Learning and B-Spline Explicit Active Surfaces
This work addresses the need for more robust and user-friendly segmentation tools in clinical settings, specifically for pelvic floor disorder analysis, though it is incremental as it extends an existing interactive framework to 3D.
The paper tackles the problem of domain shifts affecting deep learning-based automatic segmentation in clinical applications by proposing a 3D interactive segmentation framework that represents CNN outputs as B-spline explicit active surfaces, resulting in a 30% reduction in perceived workload and 70% less user time compared to a clinical tool.
Deep learning-based automatic segmentation methods have become state-of-the-art. However, they are often not robust enough for direct clinical application, as domain shifts between training and testing data affect their performance. Failure in automatic segmentation can cause sub-optimal results that require correction. To address these problems, we propose a novel 3D extension of an interactive segmentation framework that represents a segmentation from a convolutional neural network (CNN) as a B-spline explicit active surface (BEAS). BEAS ensures segmentations are smooth in 3D space, increasing anatomical plausibility, while allowing the user to precisely edit the 3D surface. We apply this framework to the task of 3D segmentation of the anal sphincter complex (AS) from transperineal ultrasound (TPUS) images, and compare it to the clinical tool used in the pelvic floor disorder clinic (4D View VOCAL, GE Healthcare; Zipf, Austria). Experimental results show that: 1) the proposed framework gives the user explicit control of the surface contour; 2) the perceived workload calculated via the NASA-TLX index was reduced by 30% compared to VOCAL; and 3) it required 7 0% (170 seconds) less user time than VOCAL (p< 0.00001)