S Machairas, V., Faessel, M., Cárdenas-Peña, D., Chabardes, T., Walter, T., Decencière, E.: Waterpixels. IEEE Trans. Image Process. 24(11), 3707–3716 (2015). https://doi.org/10.1109/TIP.2015.2451011

Wireless Capsule Endoscopy is a technique that allows for observation of the entire gastrointestinal tract in an easy and non-invasive way. However, its greatest limitation lies in the time required to analyze the large number of images generated in each examination for diagnosis, which is about 2 hours. This causes not only a high cost, but also a high probability of a wrong diagnosis due to the physician’s fatigue, while the variable appearance of abnormalities requires continuous concentration. In this work, we designed and developed a system capable of automatically detecting blood based on classification of extracted regions, following two different classification approaches. The first method consisted in extraction of hand-crafted features that were used to train machine learning algorithms, specifically Support Vector Machines and Random Forest, to create models for classifying images as healthy tissue or blood. The second method consisted in applying deep learning techniques, concretely convolutional neural networks, capable of extracting the relevant features of the image by themselves. The best results (95.7% sensitivity and 92.3% specificity) were obtained for a Random Forest model trained with features extracted from the histograms of the three HSV color space channels. For both methods we extracted square patches of several sizes using a sliding window, while for the first approach we also implemented the waterpixels technique in order to improve the classification results This work was funded by the European Unions H2020: MSCA: ITN program for the “Wireless In-body Environment Communication WiBEC” project under the grant agreement no. 675353. Additionally, we gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan V GPU used for this research. Pons Suñer, P.; Noorda, R.; Nevárez, A.; Colomer, A.; Pons Beltrán, V.; Naranjo, V. (2019). Design and Development of an Automatic Blood Detection System for Capsule Endoscopy Images. En Lecture Notes in Artificial Intelligence. Springer. 105-113. https://doi.org/10.1007/978-3-030-33617-2_12 Berens, J., Finlayson, G.D., Qiu, G.: Image indexing using compressed colour histograms. IEE Proc. Vis., Image Signal Process. 147(4), 349–355 (2000). https://doi.org/10.1049/ip-vis:20000630 Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001). https://doi.org/10.1023/A:1010933404324 Buscaglia, J.M., et al.: Performance characteristics of the suspected blood indicator feature in capsule endoscopy according to indication for study. Clin. Gastroenterol. Hepatol. 6(3), 298–301 (2008). https://doi.org/10.1016/j.cgh.2007.12.029 Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995). https://doi.org/10.1007/BF00994018 Li, B., Meng, M.Q.H.: Computer-aided detection of bleeding regions for capsule endoscopy images. IEEE Trans. Biomed. Eng. 56(4), 1032–1039 (2009). https://doi.org/10.1109/TBME.2008.2010526 Novozámskỳ, A., Flusser, J., Tachecí, I., Sulík, L., Bureš, J., Krejcar, O.: Automatic blood detection in capsule endoscopy video. J. Biomed. Opt. 21(12), 126007 (2016). https://doi.org/10.1117/1.JBO.21.12.126007 Signorelli, C., Villa, F., Rondonotti, E., Abbiati, C., Beccari, G., de Franchis, R.: Sensitivity and specificity of the suspected blood identification system in video capsule enteroscopy. Endoscopy 37(12), 1170–1173 (2005). https://doi.org/10.1055/s-2005-870410 Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014) Varma, S., Simon, R.: Bias in error estimation when using cross-validation for model selection. BMC Bioinform. 7(1), 91 (2006). https://doi.org/10.1186/1471-2105-7-91

Design and Development of an Automatic Blood Detection System for Capsule Endoscopy Images

Abstract