Computer-assisted segmentation of videocapsule images using alpha-divergence-based active contour in the framework of intestinal pathologies detection.

Visualization of the entire length of the gastrointestinal tract through natural orifices is a challenge for endoscopists. Videoendoscopy is currently the "gold standard" technique for diagnosis of different pathologies of the intestinal tract. Wireless capsule endoscopy (WCE) has been developed in the 1990s as an alternative to videoendoscopy to allow direct examination of the gastrointestinal tract without any need for sedation. Nevertheless, the systematic postexamination by the specialist of the 50,000 (for the small bowel) to 150,000 images (for the colon) of a complete acquisition using WCE remains time-consuming and challenging due to the poor quality of WCE images. In this paper, a semiautomatic segmentation for analysis of WCE images is proposed. Based on active contour segmentation, the proposed method introduces alpha-divergences, a flexible statistical similarity measure that gives a real flexibility to different types of gastrointestinal pathologies. Results of segmentation using the proposed approach are shown on different types of real-case examinations, from (multi)polyp(s) segmentation, to radiation enteritis delineation.

Towards real-time in situ polyp detection in WCE images using a boosting-based approach.

This paper presents a new embeddable method for polyp detections in Wireless Capsule Endoscopic - WCE images. this approach consists first of extracting candidate polyps within the image using geometric considerations about related shape, and second, in classifying (polyp/non-polyp) obtained candidates by a boosting-based method using texture features. The proposed approach has been designed in accordance with the hardware constraints related to FPGA implementation for integration within WCE imaging device. The classification performance of the method have been evaluated on a large dataset of 300 polyps, and 1200 non-polyps images. Experiments show interesting and promising performance: the boosting-based classification is characterized by a sensitivity of 91%, a specificity of 95% and a false detection rate of 4.8%, the detection rate of the overall processing chain being of 68%. The performance of the boosting-based classification are in accordance with the most recent reference on this particular topic using the same dataset. Building of a dedicated WCE image database should permit the improvement of the global detection rate.

SVM based colon polyps classifier in a wireless active stereo endoscope.

This work focuses on the recognition of three-dimensional colon polyps captured by an active stereo vision sensor. The detection algorithm consists of SVM classifier trained on robust feature descriptors. The study is related to Cyclope, this prototype sensor allows real time 3D object reconstruction and continues to be optimized technically to improve its classification task by differentiation between hyperplastic and adenomatous polyps. Experimental results were encouraging and show correct classification rate of approximately 97%. The work contains detailed statistics about the detection rate and the computing complexity. Inspired by intensity histogram, the work shows a new approach that extracts a set of features based on depth histogram and combines stereo measurement with SVM classifiers to correctly classify benign and malignant polyps.

Fast triggering in high-energy physics experiments using hardware neural networks.

High-energy physics experiments require high-speed triggering systems capable of performing complex pattern recognition at rates of Megahertz to Gigahertz. Neural networks implemented in hardware have been the solution of choice for certain experiments. The neural triggering problem is presented here via a detailed look at the H1 level 2 trigger at the HERA accelerator, Hamburg, Germany, followed by a section on the importance of hardware preprocessing for such systems, and finally some new architectural ideas for using field programmable gate arrays in very high-speed neural-network triggers at upcoming experiments.