Fast Barcode Retrieval for Consensus Contouring
This work addresses the challenge of reducing observer variability in clinical practice for medical image segmentation, though it is incremental as it extends atlas-based methods with a faster retrieval technique.
The paper tackled the problem of building consensus contours in medical image segmentation by proposing a fast barcode retrieval method to access large atlases of expert delineations, achieving an average error of 8% ± 5% on synthetic data and a Jaccard overlap of 87% ± 9% on real prostate MRI images.
Marking tumors and organs is a challenging task suffering from both inter- and intra-observer variability. The literature quantifies observer variability by generating consensus among multiple experts when they mark the same image. Automatically building consensus contours to establish quality assurance for image segmentation is presently absent in the clinical practice. As the \emph{big data} becomes more and more available, techniques to access a large number of existing segments of multiple experts becomes possible. Fast algorithms are, hence, required to facilitate the search for similar cases. The present work puts forward a potential framework that tested with small datasets (both synthetic and real images) displays the reliability of finding similar images. In this paper, the idea of content-based barcodes is used to retrieve similar cases in order to build consensus contours in medical image segmentation. This approach may be regarded as an extension of the conventional atlas-based segmentation that generally works with rather small atlases due to required computational expenses. The fast segment-retrieval process via barcodes makes it possible to create and use large atlases, something that directly contributes to the quality of the consensus building. Because the accuracy of experts' contours must be measured, we first used 500 synthetic prostate images with their gold markers and delineations by 20 simulated users. The fast barcode-guided computed consensus delivered an average error of $8\%\!\pm\!5\%$ compared against the gold standard segments. Furthermore, we used magnetic resonance images of prostates from 15 patients delineated by 5 oncologists and selected the best delineations to serve as the gold-standard segments. The proposed barcode atlas achieved a Jaccard overlap of $87\%\!\pm\!9\%$ with the contours of the gold-standard segments.