GIANA 2019 Abstracts

Full Papers
Full Papers
Paper Nr: 1
Title:

Active Contour Segmentation based on Histograms and Dictionary Learning for Videocapsule Image Analysis
Authors:

Gaetan Raynaud, Camille Simon-Chane, Pierre Jacob and Aymeric Histace
Abstract: This article deals with statistical region-based active contour segmentation using histograms and dictionary learning. Following previous publication, the active contour segmentation using optimization alpha-diver-gence family, leads to satisfying results. The method of the segmentation is based on histograms of the luminance of the pixels. To improve this method and to allow it to adapt to more types of images, we propose to replace luminance histograms with histograms of features using a bag of features model. This approach will be able to overcome the limitations of the luminance and give a better representation of the image. We will present the approach to create the new representation of the image, first with associated histograms to show its potential, using a local approach based on dictionary learning to compute the probability map of each pixel of the image to belong to the targeted object. In a second step using histograms based on bag of features for the representation of the image. We present experiments for the two methods on images extracted from small bowel videocapsule acquisitions and for two types of targeted objects (angiodysplasia and ulcer). We show that by replacing the luminance representation by a more complex one, we reach better performances for the segmentation of the targeted objects.
Download
Paper Nr: 2
Title:

Towards a Single Solution for Polyp Detection, Localization and Segmentation in Colonoscopy Images
Authors:

Willem Dijkstra, André Sobiecki, Jorge Bernal and Alexandru C. Telea
Abstract: Colorectal cancer is one of the main causes of cancer death worldwide. Early detection of its precursor lesion, the polyp, is key to ensure patient survival. Despite its gold standard status, colonoscopy presents some drawbacks such as polyp misses. While several computer-based solutions in this direction have been proposed, there is no available solution tackling lesion detection, localization and segmentation at once. We present in this paper a one-shot solution to characterize polyps in colonoscopy images. Our method uses a fully convolutional neural network model for semantic segmentation. Next, we apply transfer learning to provide detection and localization. We tested our method on several public datasets showing promising results, including compliance with technical and clinical requirements needed for an efficient deployment in the exploration room.
Download
Paper Nr: 3
Title:

Polyp Detection in Gastrointestinal Images using Faster Regional Convolutional Neural Network
Authors:

Lourdes Duran-Lopez, Francisco Luna-Perejon, Isabel Amaya-Rodriguez, Javier Civit-Masot, Anton Civit-Balcells, Saturnino Vicente-Diaz and Alejandro Linares-Barranco
Abstract: Colorectal cancer is the third most frequently diagnosed malignancy in the world. To prevent this disease, polyps, the principal precursor, are removed during a colonoscopy. Automatic detection of polyps in this technique could play an important role to assist doctors for achieving an accurate diagnosis. In this work, we apply a state-of-the-art Deep Learning algorithm called Faster Regional Convolutional Neural Network to each colonoscopy frame in order to detect the presence of polyps. The proposed detection system contains two main stages: (1) processing of the colonoscopy frames for training and testing datasets generation, where artifacts are extracted and the number of images in the dataset is augmented; and (2) the Neural Network model, which performs feature extraction over the frames in order to detect polyps within the frames. After training the algorithm under different conditions, our result shows that the proposed system detection has a precision of 80.31%, a recall of 75.37%, an accuracy of 71.99% and a specificity of 65.70%.
Download
Paper Nr: 4
Title:

GIANA Polyp Segmentation with Fully Convolutional Dilation Neural Networks
Authors:

Yun B. Guo and Bogdan J. Matuszewski
Abstract: Polyp detection and segmentation in colonoscopy images plays an important role in early detection of colorectal cancer. The paper describes methodology adopted for the EndoVisSub2017/2018 Gastrointestinal Image ANAlysis – (GIANA) polyp segmentation sub-challenges. The developed segmentation algorithms are based on the fully convolutional neural network (FCNN) model. Two novel variants of the FCNN have been investigated, implemented and evaluated. The first one, combines the deep residual network and the dilation kernel layers within the fully convolutional network framework. The second proposed architecture is based on the U-net network augmented by the dilation kernels and “squeeze and extraction” units. The proposed architectures have been evaluated against the well-known FCN8 model. The paper describes the adopted evaluation metrics and presents the results on the GIANA dataset. The proposed methods produced competitive results, securing the first place for the SD and HD image segmentation tasks at the 2017 GIANA challenge and the second place for the SD images at the 2018 GIANA challenge.
Download