Endoscopic Video Manifolds

Abstract

Abstract. Postprocedural analysis of gastrointestinal (GI) endoscopic videos is a difficult task because the videos often suffer from a large number of poor-quality frames due to the motion or out-of-focus blur, specular highlights and artefacts caused by turbid fluid inside the GI tract. Clinically, each frame of the video is examined individually by the endoscopic expert due to the lack of a suitable visualisation technique. In this work, we introduce a low dimensional representation of endoscopic videos based on a manifold learning approach. The introduced endoscopic video manifolds (EVMs) enable the clustering of poor-quality frames and grouping of different segments of the GI endoscopic video in an unsupervised manner to facilitate subsequent visual assessment. In this paper, we present two novel inter-frame similarity measures for manifold learning to create structured manifolds from complex endoscopic videos. Our experiments demonstrate that the proposed method yields high precision and recall values for uninformative frame detection (90.91% and 82.90%) and results in well-structured manifolds for scene clustering.

ManiSMC: A New Method Using Manifold Modeling and Sequential Monte Carlo Sampler for Boosting Navigated Bronchoscopy

“…First, sometimes uninformative images are wrongly detected, which results in incorrect embedding in manifolds; e.g., an image with bubbles can never find a correct correspondence in eigenspaces. In the future, we will improve uninformative frame detection by the work of Atasoy et al [7] or the methods presented in [8,9]. Next, intrabronchus images are wrongly classified.…”

Video retrieval in laparoscopic video recordings with dynamic content descriptors

“…These works include (i) pre-processing of images such as image enhancement [14,41] and content filtering [2,36], (ii) real-time support at procedure time such as diagnostic decision support and computer-integrated surgery [44,45], as well as (iii) post-procedural applications such as quality/skills assessment [31,51] and contentbased retrieval [47,48]. A broad overview of such works is provided in an extensive survey by Muenzer et al [35].…”

“…2 The entire dataset consists of 16 different classes (see Table 1), where each class is represented by exactly 10 examples. The 160 video segments were extracted from 59 different recordings and have a resolution of 427×240 pixels, are encoded with H.264/AVC, and are very short in terms of duration (min: 51 frames, max: 126 frames, avg: 119.8 frames).…”

Deep sparse feature selection for computer aided endoscopy diagnosis

“…Depending on the specific lesions, the diagnosis methods can be classified to handle bleeding [2], cancer [19,17], Celiac disease, Helicobacter pylori [7], polyps [20,14] and ulcers [4], motility assessment [21], tumors [6,7], Barrett's esophagus, Crohn's disease [9,18], and just classify the region into normal and abnormal [22]. Some other applications include detecting informative frames [3], WCE color video segmentation [23], summarization [24] and clustering [25]. In this paper, we intend to detect various esophagopathy and gastropathy abnormalities using traditional gastroscope.…”