%0 Generic %T Towards a computed-aided diagnosis system in colonoscopy: Automatic polyp segmentation using convolution neural networks %A Patrick Brandao %A O. Zisimopoulos %A E. Mazomenos %A G. Ciutib %A Jorge Bernal %A M. Visentini-Scarzanell %A A. Menciassi %A P. Dario %A A. Koulaouzidis %A A. Arezzo %A D.J. Hawkes %A D. Stoyanov %D 2018 %F Patrick Brandao2018 %O MV; no menciona %O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2976), last updated on Mon, 24 Jan 2022 15:38:00 +0100 %X Early diagnosis is essential for the successful treatment of bowel cancers including colorectal cancer (CRC) and capsule endoscopic imaging with robotic actuation can be a valuable diagnostic tool when combined with automated image analysis. We present a deep learning rooted detection and segmentation framework for recognizing lesions in colonoscopy and capsule endoscopy images. We restructure established convolution architectures, such as VGG and ResNets, by converting them into fully-connected convolution networks (FCNs), ne-tune them and study their capabilities for polyp segmentation and detection. We additionally use Shape-from-Shading (SfS) to recover depth and provide a richer representation of the tissue's structure in colonoscopy images. Depth isincorporated into our network models as an additional input channel to the RGB information and we demonstrate that the resulting network yields improved performance. Our networks are tested on publicly available datasets and the most accurate segmentation model achieved a mean segmentation IU of 47.78% and 56.95% on the ETIS-Larib and CVC-Colon datasets, respectively. For polypdetection, the top performing models we propose surpass the current state of the art with detection recalls superior to 90% for all datasets tested. To our knowledge, we present the rst work to use FCNs for polyp segmentation in addition to proposing a novel combination of SfS and RGB that boosts performance. %K convolutional neural networks %K colonoscopy %K computer aided diagnosis %U https://doi.org/10.1142/S2424905X18400020 %U http://refbase.cvc.uab.es/files/BZM2018.pdf %U http://dx.doi.org/10.1142/S2424905X18400020